update release

Switched to using the utility function that works in both nodejs and browser environments

.api-extractor.json

@@ -1,8 +1,9 @@
 {
   "$schema": "https://developer.microsoft.com/json-schemas/api-extractor/v7/api-extractor.schema.json",
   "mainEntryPointFilePath": "types/lib/src/human.d.ts",
+  "bundledPackages": ["@tensorflow/tfjs-core", "@tensorflow/tfjs-converter", "@tensorflow/tfjs-data", "@tensorflow/tfjs-layers"],
   "compiler": {
-    "skipLibCheck": true
+    "skipLibCheck": false
   },
   "newlineKind": "lf",
   "dtsRollup": {

.build.json

@@ -12,10 +12,10 @@
     "clean": ["clean"]
   },
   "clean": {
-    "locations": ["dist/*", "types/*", "typedoc/*"]
+    "locations": ["dist/*", "types/lib/*", "typedoc/*"]
   },
   "lint": {
-    "locations": [ "**/*.json", "src/**/*.ts", "test/**/*.js", "demo/**/*.js", "**/*.md" ],
+    "locations": [ "*.json", "src/**/*.ts", "test/**/*.js", "demo/**/*.js" ],
     "rules": { }
   },
   "changelog": {
@@ -24,8 +24,8 @@
   "serve": {
     "sslKey": "node_modules/@vladmandic/build/cert/https.key",
     "sslCrt": "node_modules/@vladmandic/build/cert/https.crt",
-    "httpPort": 8000,
-    "httpsPort": 8001,
+    "httpPort": 10030,
+    "httpsPort": 10031,
     "documentRoot": ".",
     "defaultFolder": "demo",
     "defaultFile": "index.html"
@@ -39,13 +39,6 @@
       "banner": { "js": "/*\n  Human\n  homepage: <https://github.com/vladmandic/human>\n  author: <https://github.com/vladmandic>'\n*/\n" }
     },
     "targets": [
-      { 
-        "name": "tfjs/browser/version",
-        "platform": "browser",
-        "format": "esm",
-        "input": "tfjs/tf-version.ts",
-        "output": "dist/tfjs.version.js"
-      },
       {
         "name": "tfjs/nodejs/cpu",
         "platform": "node",
@@ -84,7 +77,6 @@
         "format": "cjs",
         "input": "tfjs/tf-node-wasm.ts",
         "output": "dist/tfjs.esm.js",
-        "minify": false,
         "external": ["@tensorflow"]
       },
       {
@@ -95,6 +87,13 @@
         "output": "dist/human.node-wasm.js",
         "external": ["@tensorflow"]
       },
+      { 
+        "name": "tfjs/browser/version",
+        "platform": "browser",
+        "format": "esm",
+        "input": "tfjs/tf-version.ts",
+        "output": "dist/tfjs.version.js"
+      },
       {
         "name": "tfjs/browser/esm/nobundle",
         "platform": "browser",
@@ -113,13 +112,13 @@
         "external": ["@tensorflow"]
       },
       {
-        "name": "tfjs/browser/esm/bundle",
+        "name": "tfjs/browser/esm/custom",
         "platform": "browser",
         "format": "esm",
-        "input": "tfjs/tf-browser.ts",
+        "input": "tfjs/tf-custom.ts",
         "output": "dist/tfjs.esm.js",
         "sourcemap": false,
-        "minify": true
+        "minify": false
       },
       {
         "name": "human/browser/iife/bundle",
@@ -160,15 +159,6 @@
         "output": "demo/faceid/index.js",
         "sourcemap": true,
         "external": ["*/human.esm.js"]
-      },
-      {
-        "name": "demo/tracker",
-        "platform": "browser",
-        "format": "esm",
-        "input": "demo/tracker/index.ts",
-        "output": "demo/tracker/index.js",
-        "sourcemap": true,
-        "external": ["*/human.esm.js"]
       }
     ]
   },

.eslintrc.json

@@ -1,28 +1,29 @@
 {
-  "globals": {
-  },
-  "rules": {
-    "@typescript-eslint/no-require-imports":"off"
-  },
+  "globals": {},
   "overrides": [
     {
       "files": ["**/*.ts"],
-      "parser": "@typescript-eslint/parser",
-      "parserOptions": { "ecmaVersion": "latest", "project": ["./tsconfig.json"] },
-      "plugins": ["@typescript-eslint"],
       "env": {
         "browser": true,
         "commonjs": false,
         "node": false,
         "es2021": true
       },
+      "parser": "@typescript-eslint/parser",
+      "parserOptions": {
+        "ecmaVersion": "latest",
+        "project": ["./tsconfig.json"]
+      },
+      "plugins": [
+        "@typescript-eslint"
+      ],
       "extends": [
         "airbnb-base",
         "eslint:recommended",
-        "plugin:@typescript-eslint/strict",
+        "plugin:@typescript-eslint/eslint-recommended",
         "plugin:@typescript-eslint/recommended",
         "plugin:@typescript-eslint/recommended-requiring-type-checking",
-        "plugin:@typescript-eslint/eslint-recommended",
+        "plugin:@typescript-eslint/strict",
         "plugin:import/recommended",
         "plugin:promise/recommended"
       ],
@@ -30,12 +31,9 @@
         "@typescript-eslint/ban-ts-comment":"off",
         "@typescript-eslint/dot-notation":"off",
         "@typescript-eslint/no-empty-interface":"off",
-        "@typescript-eslint/no-empty-object-type":"off",
         "@typescript-eslint/no-inferrable-types":"off",
         "@typescript-eslint/no-misused-promises":"off",
-        "@typescript-eslint/no-require-imports":"off",
         "@typescript-eslint/no-unnecessary-condition":"off",
-        "@typescript-eslint/no-unnecessary-type-assertion":"off",
         "@typescript-eslint/no-unsafe-argument":"off",
         "@typescript-eslint/no-unsafe-assignment":"off",
         "@typescript-eslint/no-unsafe-call":"off",
@@ -74,15 +72,20 @@
     },
     {
       "files": ["**/*.d.ts"],
-      "parser": "@typescript-eslint/parser",
-      "parserOptions": { "ecmaVersion": "latest", "project": ["./tsconfig.json"] },
-      "plugins": ["@typescript-eslint"],
       "env": {
         "browser": true,
         "commonjs": false,
         "node": false,
         "es2021": true
       },
+      "parser": "@typescript-eslint/parser",
+      "parserOptions": {
+        "ecmaVersion": "latest",
+        "project": ["./tsconfig.json"]
+      },
+      "plugins": [
+        "@typescript-eslint"
+      ],
       "extends": [
         "airbnb-base",
         "eslint:recommended",
@@ -117,14 +120,18 @@
     },
     {
       "files": ["**/*.js"],
-      "parserOptions": { "sourceType": "module", "ecmaVersion": "latest" },
-      "plugins": [],
       "env": {
         "browser": true,
         "commonjs": true,
         "node": true,
         "es2021": true
       },
+      "parserOptions": {
+        "sourceType": "module",
+        "ecmaVersion": "latest"
+      },
+      "plugins": [
+      ],
       "extends": [
         "airbnb-base",
         "eslint:recommended",
@@ -154,40 +161,42 @@
     },
     {
       "files": ["**/*.json"],
-      "parserOptions": { "ecmaVersion": "latest" },
-      "plugins": ["json"],
       "env": {
         "browser": false,
         "commonjs": false,
         "node": false,
         "es2021": false
       },
-      "extends": [] 
+      "parserOptions": {
+        "ecmaVersion": "latest"
+      },
+      "plugins": [
+        "json"
+      ],
+      "extends": [
+        "plugin:json/recommended"
+      ] 
     },
     {
-      "files": ["**/*.md"],
-      "plugins": ["markdown"],
-      "processor": "markdown/markdown",
-      "rules": {
-        "no-undef":"off"
-      }
+      "files": ["**/*.html"],
+      "env": {
+        "browser": true,
+        "commonjs": false,
+        "node": false,
+        "es2021": false
       },
-    {
-      "files": ["**/*.md/*.js"],
+      "parserOptions": {
+        "sourceType": "module",
+        "ecmaVersion": "latest"
+      },
+      "parser": "@html-eslint/parser",
+      "extends": ["plugin:@html-eslint/recommended"],
+      "plugins": [
+        "html", "@html-eslint"
+      ],
       "rules": {
-        "@typescript-eslint/no-unused-vars":"off",
-        "@typescript-eslint/triple-slash-reference":"off",
-        "import/newline-after-import":"off",
-        "import/no-unresolved":"off",
-        "no-console":"off",
-        "no-global-assign":"off",
-        "no-multi-spaces":"off",
-        "no-restricted-globals":"off",
-        "no-undef":"off",
-        "no-unused-vars":"off",
-        "node/no-missing-import":"off",
-        "node/no-missing-require":"off",
-        "promise/catch-or-return":"off"
+        "@html-eslint/element-newline":"off",
+        "@html-eslint/indent": ["error", 2]
       }
     }
   ],
@@ -198,7 +207,6 @@
     "demo/helpers/*.js",
     "demo/typescript/*.js",
     "demo/faceid/*.js",
-    "demo/tracker/*.js",
     "typedoc"
   ]
 }

.gitignore

@@ -1,9 +1,4 @@
 node_modules/
 types/lib
 pnpm-lock.yaml
-package-lock.json
 *.swp
-samples/**/*.mp4
-samples/**/*.webm
-temp
-tmp

.markdownlint.json

@@ -1,7 +1,6 @@
 {
   "MD012": false,
   "MD013": false,
-  "MD029": false,
   "MD033": false,
   "MD036": false,
   "MD041": false

.npmrc

@@ -1,5 +1,4 @@
 force=true
-omit=dev
+production=true
 legacy-peer-deps=true
 strict-peer-dependencies=false
-node-options='--no-deprecation'

CHANGELOG.md

@@ -1,6 +1,6 @@
 # @vladmandic/human  
 
-  Version: **3.3.6**  
+  Version: **2.11.1**  
   Description: **Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gesture Recognition**  
   
   Author: **Vladimir Mandic <mandic00@live.com>**  
@@ -9,132 +9,11 @@
   
 ## Changelog
   
-### **3.3.6** 2025/08/26 mandic00@live.com
+### **HEAD -> main** 2022/10/09 mandic00@live.com
 
 
-### **origin/main** 2025/02/05 mandic00@live.com
+### **origin/main** 2022/10/02 mandic00@live.com
 
-- full rebuild
-
-### **3.3.5** 2025/02/05 mandic00@live.com
-
-- rebuild
-- add human.draw.tensor method
-
-### **3.3.4** 2024/10/24 mandic00@live.com
-
-
-### **3.3.3** 2024/10/14 mandic00@live.com
-
-- add loaded property to model stats and mark models not loaded correctly.
-- release build
-
-### **3.3.2** 2024/09/11 mandic00@live.com
-
-- full rebuild
-
-### **3.3.1** 2024/09/11 mandic00@live.com
-
-- add config.face.detector.square option
-- human 3.3 alpha test run
-- human 3.3 alpha with new build environment
-- release rebuild
-- fix flazeface tensor scale and update build platform
-
-### **3.2.2** 2024/04/17 mandic00@live.com
-
-
-### **release: 3.2.1** 2024/02/15 mandic00@live.com
-
-
-### **3.2.1** 2024/02/15 mandic00@live.com
-
-
-### **3.2.0** 2023/12/06 mandic00@live.com
-
-- set browser false when navigator object is empty
-- https://github.com/vladmandic/human/issues/402
-
-### **release: 3.1.2** 2023/09/18 mandic00@live.com
-
-- full rebuild
-
-### **3.1.2** 2023/09/18 mandic00@live.com
-
-- major toolkit upgrade
-- full rebuild
-- major toolkit upgrade
-
-### **3.1.1** 2023/08/05 mandic00@live.com
-
-- fixes plus tfjs upgrade for new release
-
-### **3.0.7** 2023/06/12 mandic00@live.com
-
-- full rebuild
-- fix memory leak in histogramequalization
-- initial work on tracker
-
-### **3.0.6** 2023/03/21 mandic00@live.com
-
-- add optional crop to multiple models
-- fix movenet-multipose
-- add electron detection
-- fix gender-ssrnet-imdb
-- add movenet-multipose workaround
-- rebuild and publish
-- add face.detector.minsize configurable setting
-- add affectnet
-
-### **3.0.5** 2023/02/02 mandic00@live.com
-
-- add gear-e models
-- detect react-native
-- redo blazeface annotations
-
-### **3.0.4** 2023/01/29 mandic00@live.com
-
-- make naviator calls safe
-- fix facedetector-only configs
-
-### **3.0.3** 2023/01/07 mandic00@live.com
-
-- full rebuild
-
-### **3.0.2** 2023/01/06 mandic00@live.com
-
-- default face.rotation disabled
-
-### **release: 3.0.1** 2022/11/22 mandic00@live.com
-
-
-### **3.0.1** 2022/11/22 mandic00@live.com
-
-- support dynamic loads
-- polish demos
-- add facedetect demo and fix model async load
-- enforce markdown linting
-- cleanup git history
-- default empty result
-- refactor draw and models namespaces
-- refactor distance
-- add basic anthropometry
-- added webcam id specification
-- include external typedefs
-- prepare external typedefs
-- rebuild all
-- include project files for types
-- architectural improvements
-- refresh dependencies
-- add named exports
-- add draw label templates
-- reduce dev dependencies
-- tensor rank strong typechecks
-- rebuild dependencies
-
-### **2.11.1** 2022/10/09 mandic00@live.com
-
-- add rvm segmentation model
 - add human.webcam methods
 - create funding.yml
 - fix rotation interpolation
@@ -146,7 +25,9 @@
 ### **2.10.2** 2022/09/11 mandic00@live.com
 
 - add node.js esm compatibility (#292)
-- release
+
+### **release: 2.10.1** 2022/09/07 mandic00@live.com
+
 
 ### **2.10.1** 2022/09/07 mandic00@live.com
 
@@ -182,7 +63,9 @@
 
 ### **2.9.2** 2022/08/08 mandic00@live.com
 
-- release rebuild
+
+### **release: 2.9.1** 2022/07/25 mandic00@live.com
+
 
 ### **2.9.1** 2022/07/25 mandic00@live.com
 
@@ -229,6 +112,7 @@
 - enable precompile as part of warmup
 - prepare release beta
 - change default face crop
+- face attention model is available in human-models
 - beta release 2.7
 - refactor draw methods
 - implement face attention model
@@ -540,6 +424,7 @@
 - implemented human.next global interpolation method
 - finished draw buffering and smoothing and enabled by default
 - implemented service worker
+- quantized centernet
 - release candidate
 - added usage restrictions
 - quantize handdetect model

README.md

@@ -4,6 +4,7 @@
 ![Last Commit](https://img.shields.io/github/last-commit/vladmandic/human?style=flat-square&svg=true)
 ![License](https://img.shields.io/github/license/vladmandic/human?style=flat-square&svg=true)
 ![GitHub Status Checks](https://img.shields.io/github/checks-status/vladmandic/human/main?style=flat-square&svg=true)
+![Vulnerabilities](https://img.shields.io/snyk/vulnerabilities/github/vladmandic/human?style=flat-square&svg=true)
 
 # Human Library
 
@@ -11,8 +12,7 @@
 **Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis,**  
 **Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition, Body Segmentation**  
 
-<br>
-
+JavaScript module using TensorFlow/JS Machine Learning library  
 ## Highlights
 
 - Compatible with most server-side and client-side environments and frameworks  
@@ -24,26 +24,19 @@
 - Simple unified API  
 - Built-in Image, Video and WebCam handling
 
-[*Jump to Quick Start*](#quick-start)
-
 <br>
 
 ## Compatibility
 
-**Browser**:  
-  - Compatible with both desktop and mobile platforms  
-  - Compatible with *WebGPU*, *WebGL*, *WASM*, *CPU* backends  
-  - Compatible with *WebWorker* execution  
-  - Compatible with *WebView*  
-  - Primary platform: *Chromium*-based browsers  
-  - Secondary platform: *Firefox*, *Safari*
-
-**NodeJS**:  
-  - Compatibile with *WASM* backend for executions on architectures where *tensorflow* binaries are not available  
-  - Compatible with *tfjs-node* using software execution via *tensorflow* shared libraries  
-  - Compatible with *tfjs-node* using GPU-accelerated execution via *tensorflow* shared libraries and nVidia CUDA  
-  - Supported versions are from **14.x** to **22.x**  
-  - NodeJS version **23.x** is not supported due to breaking changes and issues with `@tensorflow/tfjs`  
+- **Browser**:  
+  Compatible with both desktop and mobile platforms  
+  Compatible with *CPU*, *WebGL*, *WASM* backends  
+  Compatible with *WebWorker* execution  
+  Compatible with *WebView*  
+- **NodeJS**:  
+  Compatibile with *WASM* backend for executions on architectures where *tensorflow* binaries are not available  
+  Compatible with *tfjs-node* using software execution via *tensorflow* shared libraries  
+  Compatible with *tfjs-node* using GPU-accelerated execution via *tensorflow* shared libraries and nVidia CUDA  
 
 <br>
 
@@ -73,9 +66,8 @@
 
 - **Full** [[*Live*]](https://vladmandic.github.io/human/demo/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/demo): Main browser demo app that showcases all Human capabilities
 - **Simple** [[*Live*]](https://vladmandic.github.io/human/demo/typescript/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/typescript): Simple demo in WebCam processing demo in TypeScript
-- **Embedded** [[*Live*]](https://vladmandic.github.io/human/demo/video/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/video/index.html): Even simpler demo with tiny code embedded in HTML file
-- **Face Detect** [[*Live*]](https://vladmandic.github.io/human/demo/facedetect/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/facedetect): Extract faces from images and processes details
-- **Face Match** [[*Live*]](https://vladmandic.github.io/human/demo/facematch/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/facematch): Extract faces from images, calculates face descriptors and similarities and matches them to known database
+- **Embedded** [[*Live*]](https://vladmandic.github.io/human/demo/video/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/video/index.html): Even simpler demo with tiny code embedded in HTML file
+- **Face Match** [[*Live*]](https://vladmandic.github.io/human/demo/facematch/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/facematch): Extract faces from images, calculates face descriptors and simmilarities and matches them to known database
 - **Face ID** [[*Live*]](https://vladmandic.github.io/human/demo/faceid/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/faceid): Runs multiple checks to validate webcam input before performing face match to faces in IndexDB
 - **Multi-thread** [[*Live*]](https://vladmandic.github.io/human/demo/multithread/index.html) [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/multithread): Runs each Human module in a separate web worker for highest possible performance  
 - **NextJS** [[*Live*]](https://vladmandic.github.io/human-next/out/index.html) [[*Details*]](https://github.com/vladmandic/human-next): Use Human with TypeScript, NextJS and ReactJS
@@ -89,15 +81,14 @@
 *NodeJS demos may require extra dependencies which are used to decode inputs*  
 *See header of each demo to see its dependencies as they are not automatically installed with `Human`*
 
-- **Main** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs/node.js): Process images from files, folders or URLs using native methods  
-- **Canvas** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs/node-canvas.js): Process image from file or URL and draw results to a new image file using `node-canvas`  
-- **Video** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs/node-video.js): Processing of video input using `ffmpeg`  
-- **WebCam** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs/node-webcam.js): Processing of webcam screenshots using `fswebcam`  
-- **Events** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs/node-event.js): Showcases usage of `Human` eventing to get notifications on processing
-- **Similarity** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs/node-similarity.js): Compares two input images for similarity of detected faces
-- **Face Match** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/facematch/node-match.js): Parallel processing of face **match** in multiple child worker threads
-- **Multiple Workers** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/multithread/node-multiprocess.js): Runs multiple parallel `human` by dispaching them to pool of pre-created worker processes  
-- **Dynamic Load** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs): Loads Human dynamically with multiple different desired backends  
+- **Main** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs): Process images from files, folders or URLs using native methods  
+- **Canvas** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs): Process image from file or URL and draw results to a new image file using `node-canvas`  
+- **Video** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs): Processing of video input using `ffmpeg`  
+- **WebCam** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs): Processing of webcam screenshots using `fswebcam`  
+- **Events** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs): Showcases usage of `Human` eventing to get notifications on processing
+- **Similarity** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs): Compares two input images for similarity of detected faces
+- **Face Match** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/facematch): Parallel processing of face **match** in multiple child worker threads
+- **Multiple Workers** [[*Details*]](https://github.com/vladmandic/human/tree/main/demo/nodejs): Runs multiple parallel `human` by dispaching them to pool of pre-created worker processes  
 
 ## Project pages
 
@@ -116,7 +107,6 @@
 - [**Usage & Functions**](https://github.com/vladmandic/human/wiki/Usage)
 - [**Configuration Details**](https://github.com/vladmandic/human/wiki/Config)
 - [**Result Details**](https://github.com/vladmandic/human/wiki/Result)
-- [**Customizing Draw Methods**](https://github.com/vladmandic/human/wiki/Draw)
 - [**Caching & Smoothing**](https://github.com/vladmandic/human/wiki/Caching)
 - [**Input Processing**](https://github.com/vladmandic/human/wiki/Image)
 - [**Face Recognition & Face Description**](https://github.com/vladmandic/human/wiki/Embedding)
@@ -151,21 +141,24 @@
 ## App Examples
 
 Visit [Examples gallery](https://vladmandic.github.io/human/samples/index.html) for more examples  
-[<img src="assets/samples.jpg" width="640"/>](assets/samples.jpg)
+<https://vladmandic.github.io/human/samples/index.html>
+
+![samples](assets/samples.jpg)
 
 <br>
 
 ## Options
 
 All options as presented in the demo application...  
-[demo/index.html](demo/index.html)  
-[<img src="assets/screenshot-menu.png"/>](assets/screenshot-menu.png)
+> [demo/index.html](demo/index.html)  
+
+![Options visible in demo](assets/screenshot-menu.png)
 
 <br>
 
 **Results Browser:**  
 [ *Demo -> Display -> Show Results* ]<br>
-[<img src="assets/screenshot-results.png"/>](assets/screenshot-results.png)
+![Results](assets/screenshot-results.png)
 
 <br>
 
@@ -177,39 +170,33 @@ sorts them by similarity to selected face
 and optionally matches detected face with database of known people to guess their names
 > [demo/facematch](demo/facematch/index.html)  
 
-[<img src="assets/screenshot-facematch.jpg" width="640"/>](assets/screenshot-facematch.jpg)
+![Face Matching](assets/screenshot-facematch.jpg)
 
-2. **Face Detect:**  
-Extracts all detect faces from loaded images on-demand and highlights face details on a selected face  
-> [demo/facedetect](demo/facedetect/index.html)  
-
-[<img src="assets/screenshot-facedetect.jpg" width="640"/>](assets/screenshot-facedetect.jpg)
-
-3. **Face ID:**  
+2. **Face ID:**  
 Performs validation check on a webcam input to detect a real face and matches it to known faces stored in database
 > [demo/faceid](demo/faceid/index.html)  
 
-[<img src="assets/screenshot-faceid.jpg" width="640"/>](assets/screenshot-faceid.jpg)
+![Face Matching](assets/screenshot-faceid.jpg)
 
 <br>
 
-4. **3D Rendering:**  
+3. **3D Rendering:**  
 > [human-motion](https://github.com/vladmandic/human-motion)
 
-[<img src="https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-face.jpg" width="640"/>](https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-face.jpg)
-[<img src="https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-body.jpg" width="640"/>](https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-body.jpg)
-[<img src="https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-hand.jpg" width="640"/>](https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-hand.jpg)
+![Face3D](https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-face.jpg)
+![Body3D](https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-body.jpg)
+![Hand3D](https://github.com/vladmandic/human-motion/raw/main/assets/screenshot-hand.jpg)
 
 <br>
 
-5. **VR Model Tracking:**  
+4. **VR Model Tracking:**  
 > [human-three-vrm](https://github.com/vladmandic/human-three-vrm)  
 > [human-bjs-vrm](https://github.com/vladmandic/human-bjs-vrm)  
 
-[<img src="https://github.com/vladmandic/human-three-vrm/raw/main/assets/human-vrm-screenshot.jpg" width="640"/>](https://github.com/vladmandic/human-three-vrm/raw/main/assets/human-vrm-screenshot.jpg)
+![ThreeVRM](https://github.com/vladmandic/human-three-vrm/raw/main/assets/human-vrm-screenshot.jpg)
 
 
-6. **Human as OS native application:**
+5. **Human as OS native application:**
 > [human-electron](https://github.com/vladmandic/human-electron)
 
 <br>
@@ -217,7 +204,7 @@ Performs validation check on a webcam input to detect a real face and matches it
 **468-Point Face Mesh Defails:**  
 (view in full resolution to see keypoints)  
 
-[<img src="assets/facemesh.png" width="400"/>](assets/facemesh.png)
+![FaceMesh](assets/facemesh.png)
 
 <br><hr><br>
 
@@ -227,16 +214,33 @@ Simply load `Human` (*IIFE version*) directly from a cloud CDN in your HTML file
 (pick one: `jsdelirv`, `unpkg` or `cdnjs`)
 
 ```html
-<!DOCTYPE HTML>
 <script src="https://cdn.jsdelivr.net/npm/@vladmandic/human/dist/human.js"></script>
 <script src="https://unpkg.dev/@vladmandic/human/dist/human.js"></script>
-<script src="https://cdnjs.cloudflare.com/ajax/libs/human/3.0.0/human.js"></script>
+<script src="https://cdnjs.cloudflare.com/ajax/libs/human/2.1.5/human.js"></script>
 ```
 
 For details, including how to use `Browser ESM` version or `NodeJS` version of `Human`, see [**Installation**](https://github.com/vladmandic/human/wiki/Install)
 
 <br>
 
+## Inputs
+
+`Human` library can process all known input types:  
+
+- `Image`, `ImageData`, `ImageBitmap`, `Canvas`, `OffscreenCanvas`, `Tensor`,  
+- `HTMLImageElement`, `HTMLCanvasElement`, `HTMLVideoElement`, `HTMLMediaElement`
+
+Additionally, `HTMLVideoElement`, `HTMLMediaElement` can be a standard `<video>` tag that links to:
+
+- WebCam on user's system
+- Any supported video type  
+  e.g. `.mp4`, `.avi`, etc.
+- Additional video types supported via *HTML5 Media Source Extensions*  
+  e.g.: **HLS** (*HTTP Live Streaming*) using `hls.js` or **DASH** (*Dynamic Adaptive Streaming over HTTP*) using `dash.js`
+- **WebRTC** media track using built-in support  
+
+<br>
+
 ## Code Examples
 
 Simple app that uses Human to process video input and  
@@ -245,7 +249,7 @@ draw output on screen using internal draw helper functions
 ```js
 // create instance of human with simple configuration using default values
 const config = { backend: 'webgl' };
-const human = new Human.Human(config);
+const human = new Human(config);
 // select input HTMLVideoElement and output HTMLCanvasElement from page
 const inputVideo = document.getElementById('video-id');
 const outputCanvas = document.getElementById('canvas-id');
@@ -264,7 +268,6 @@ function detectVideo() {
     human.draw.gesture(outputCanvas, result.gesture);
     // and loop immediate to the next frame
     requestAnimationFrame(detectVideo);
-    return result;
   });
 }
 
@@ -372,53 +375,6 @@ drawResults(); // start draw loop
 
 And for even better results, you can run detection in a separate web worker thread
 
-<br><hr><br>
-
-## Inputs
-
-`Human` library can process all known input types:  
-
-- `Image`, `ImageData`, `ImageBitmap`, `Canvas`, `OffscreenCanvas`, `Tensor`,  
-- `HTMLImageElement`, `HTMLCanvasElement`, `HTMLVideoElement`, `HTMLMediaElement`
-
-Additionally, `HTMLVideoElement`, `HTMLMediaElement` can be a standard `<video>` tag that links to:
-
-- WebCam on user's system
-- Any supported video type  
-  e.g. `.mp4`, `.avi`, etc.
-- Additional video types supported via *HTML5 Media Source Extensions*  
-  e.g.: **HLS** (*HTTP Live Streaming*) using `hls.js` or **DASH** (*Dynamic Adaptive Streaming over HTTP*) using `dash.js`
-- **WebRTC** media track using built-in support  
-
-<br><hr><br>
-
-## Detailed Usage
-
-- [**Wiki Home**](https://github.com/vladmandic/human/wiki)
-- [**List of all available methods, properies and namespaces**](https://github.com/vladmandic/human/wiki/Usage)
-- [**TypeDoc API Specification - Main class**](https://vladmandic.github.io/human/typedoc/classes/Human.html)
-- [**TypeDoc API Specification - Full**](https://vladmandic.github.io/human/typedoc/)
-
-    ![typedoc](assets/screenshot-typedoc.png)
-
-<br><hr><br>
-
-## TypeDefs
-
-`Human` is written using TypeScript strong typing and ships with full **TypeDefs** for all classes defined by the library bundled in `types/human.d.ts` and enabled by default  
-
-*Note*: This does not include embedded `tfjs`  
-If you want to use embedded `tfjs` inside `Human` (`human.tf` namespace) and still full **typedefs**, add this code:
-
-> import type * as tfjs from '@vladmandic/human/dist/tfjs.esm';  
-> const tf = human.tf as typeof tfjs;
-
-This is not enabled by default as `Human` does not ship with full **TFJS TypeDefs** due to size considerations  
-Enabling `tfjs` TypeDefs as above creates additional project (dev-only as only types are required) dependencies as defined in `@vladmandic/human/dist/tfjs.esm.d.ts`:
-
-> @tensorflow/tfjs-core, @tensorflow/tfjs-converter, @tensorflow/tfjs-backend-wasm, @tensorflow/tfjs-backend-webgl
-
-
 <br><hr><br>
 
 ## Default models
@@ -448,9 +404,9 @@ For more info, see [**Configuration Details**](https://github.com/vladmandic/hum
 
 <br><hr><br>
 
-`Human` library is written in [TypeScript](https://www.typescriptlang.org/docs/handbook/intro.html) **5.1** using [TensorFlow/JS](https://www.tensorflow.org/js/) **4.10** and conforming to latest `JavaScript` [ECMAScript version 2022](https://262.ecma-international.org/) standard  
-
-Build target for distributables is `JavaScript` [EMCAScript version 2018](https://262.ecma-international.org/9.0/)  
+`Human` library is written in `TypeScript` [4.8](https://www.typescriptlang.org/docs/handbook/intro.html)  
+Conforming to latest `JavaScript` [ECMAScript version 2022](https://262.ecma-international.org/) standard  
+Build target is `JavaScript` [EMCAScript version 2018](https://262.ecma-international.org/11.0/)  
 
 <br>
 

TODO.md

@@ -2,6 +2,21 @@
 
 ## Work-in-Progress
 
+
+<hr><br>
+
+## Exploring
+
+- **Optical flow** for intelligent temporal interpolation  
+  <https://docs.opencv.org/3.3.1/db/d7f/tutorial_js_lucas_kanade.html>
+- **CLAHE** advanced histogram equalization for optimization of badly lit scenes  
+- **TFLite** models  
+  <https://js.tensorflow.org/api_tflite/0.0.1-alpha.4/>
+- **Principal Components Analysis** for reduction of descriptor complexity  
+  <https://github.com/vladmandic/human-match/blob/main/src/pca.js>  
+- **Temporal guidance** for face/body segmentation  
+  <https://github.com/PeterL1n/RobustVideoMatting>
+
 <hr><br>
 
 ## Known Issues & Limitations
@@ -16,9 +31,10 @@ No issues with default model `FaceMesh`
 `NanoDet` model is not supported when using `WASM` backend due to missing kernel op in **TFJS**  
 No issues with default model `MB3-CenterNet`  
 
-## Body Detection using MoveNet-MultiPose
+### WebGPU
 
-Model does not return valid detection scores (all other functionality is not impacted)  
+Experimental support only until support is officially added in Chromium  
+Enable via <chrome://flags/#enable-unsafe-webgpu>  
 
 ### Firefox
 
@@ -31,8 +47,31 @@ Enable via `about:config` -> `gfx.offscreencanvas.enabled`
 No support for running in **web workers** as Safari still does not support `OffscreenCanvas`  
 [Details](https://developer.mozilla.org/en-US/docs/Web/API/OffscreenCanvas#browser_compatibility)  
 
-## React-Native
-
-`Human` support for **React-Native** is best-effort, but not part of the main development focus  
-
 <hr><br>
+
+## Pending Release Changes
+
+- New methods [`human.webcam.*`](https://vladmandic.github.io/human/typedoc/classes/WebCam.html)  
+  Enables built-in configuration and control of **WebCam** streams  
+- New method [`human.video()`](https://vladmandic.github.io/human/typedoc/classes/Human.html#video)  
+  Runs continous detection of an input **video**  
+  instead of processing each frame manually using `human.detect()`  
+- New demo for **webcam** and **video** methods [*Live*](https://vladmandic.github.io/human/demo/video/index.html) | [*Code*](https://github.com/vladmandic/human/blob/main/demo/video/index.html)  
+  *Full HTML and JavaScript code in less than a screen*  
+- Redesigned [`human.segmentation`](https://vladmandic.github.io/human/typedoc/classes/Human.html#segmentation)  
+  *Breaking changes*  
+- New model `rvm` for high-quality body segmentation in real-time  
+  *Not part of default deployment, download from [human-models](https://github.com/vladmandic/human-models/tree/main/models)*  
+- New demo for **segmentation** methods [*Live*](https://vladmandic.github.io/human/demo/segmentation/index.html) | [*Code*](https://github.com/vladmandic/human/blob/main/demo/segmentation/index.html)  
+  *Full HTML and JavaScript code in less than a screen*  
+- New advanced demo using **BabylonJS and VRM** [*Live*](https://vladmandic.github.io/human-bjs-vrm) | [*Code*](https://github.com/vladmandic/human-bjs-vrm)
+- Update **TypeDoc** generation [*Link*](https://vladmandic.github.io/human/typedoc)  
+- Update **TypeDefs** bundle generation [*Link*](https://github.com/vladmandic/human/blob/main/types/human.d.ts)  
+  No external dependencies  
+- Fix model caching when using web workers  
+- Fix `face.rotation` when using interpolation  
+- Improve NodeJS resolver when using ESM  
+- Update demo `demo/typescript`  
+- Update demo `demo/faceid`  
+- Update demo `demo/nodejs/process-folder.js`  
+  and re-process `/samples` [*Link*](https://vladmandic.github.io/human/samples)  

build.js

@@ -31,42 +31,25 @@ const apiExtractorIgnoreList = [ // eslint-disable-line no-unused-vars
   'tsdoc-unnecessary-backslash',
 ];
 
-const regEx = [
-  { search: 'types="@webgpu/types/dist"', replace: 'path="../src/types/webgpu.d.ts"' },
-  { search: 'types="offscreencanvas"', replace: 'path="../src/types/offscreencanvas.d.ts"' },
-];
-
-function copyFile(src, dst) {
-  if (!fs.existsSync(src)) {
-    log.warn('Copy:', { input: src, output: dst });
-    return;
-  }
-  log.state('Copy:', { input: src, output: dst });
+function copy(src, dst) {
+  if (!fs.existsSync(src)) return;
   const buffer = fs.readFileSync(src);
   fs.writeFileSync(dst, buffer);
 }
 
-function writeFile(str, dst) {
-  log.state('Write:', { output: dst });
+function write(str, dst) {
   fs.writeFileSync(dst, str);
 }
 
-function regExFile(src, entries) {
-  if (!fs.existsSync(src)) {
-    log.warn('Filter:', { src });
-    return;
-  }
-  log.state('Filter:', { input: src });
-  for (const entry of entries) {
+function filter(str, src) {
+  if (!fs.existsSync(src)) return;
   const buffer = fs.readFileSync(src, 'UTF-8');
   const lines = buffer.split(/\r?\n/);
   const out = [];
   for (const line of lines) {
-      if (line.includes(entry.search)) out.push(line.replace(entry.search, entry.replace));
-      else out.push(line);
+    if (!line.includes(str)) out.push(line);
   }
   fs.writeFileSync(src, out.join('\n'));
-  }
 }
 
 async function analyzeModels() {
@@ -106,22 +89,14 @@ async function analyzeModels() {
 async function main() {
   log.logFile(logFile);
   log.data('Build', { name: packageJSON.name, version: packageJSON.version });
-
   // run production build
   const build = new Build();
   await build.run('production');
-
   // patch tfjs typedefs
-  copyFile('node_modules/@vladmandic/tfjs/types/tfjs-core.d.ts', 'types/tfjs-core.d.ts');
-  copyFile('node_modules/@vladmandic/tfjs/types/tfjs.d.ts', 'types/tfjs.esm.d.ts');
-  copyFile('src/types/tsconfig.json', 'types/tsconfig.json');
-  copyFile('src/types/eslint.json', 'types/.eslintrc.json');
-  copyFile('src/types/tfjs.esm.d.ts', 'dist/tfjs.esm.d.ts');
-  regExFile('types/tfjs-core.d.ts', regEx);
-
+  log.state('Copy:', { input: 'tfjs/tfjs.esm.d.ts' });
+  copy('tfjs/tfjs.esm.d.ts', 'types/lib/dist/tfjs.esm.d.ts');
   // run api-extractor to create typedef rollup
   const extractorConfig = APIExtractor.ExtractorConfig.loadFileAndPrepare('.api-extractor.json');
-  try {
   const extractorResult = APIExtractor.Extractor.invoke(extractorConfig, {
     localBuild: true,
     showVerboseMessages: false,
@@ -134,16 +109,24 @@ async function main() {
     },
   });
   log.state('API-Extractor:', { succeeeded: extractorResult.succeeded, errors: extractorResult.errorCount, warnings: extractorResult.warningCount });
-  } catch (err) {
-    log.error('API-Extractor:', err);
-  }
-  regExFile('types/human.d.ts', regEx);
-  writeFile('export * from \'../types/human\';', 'dist/human.esm-nobundle.d.ts');
-  writeFile('export * from \'../types/human\';', 'dist/human.esm.d.ts');
-  writeFile('export * from \'../types/human\';', 'dist/human.d.ts');
-  writeFile('export * from \'../types/human\';', 'dist/human.node-gpu.d.ts');
-  writeFile('export * from \'../types/human\';', 'dist/human.node.d.ts');
-  writeFile('export * from \'../types/human\';', 'dist/human.node-wasm.d.ts');
+  // distribute typedefs
+  // log.state('Copy:', { input: 'types/human.d.ts' });
+  // copy('types/human.d.ts', 'dist/human.esm-nobundle.d.ts');
+  // copy('types/human.d.ts', 'dist/human.esm.d.ts');
+  // copy('types/human.d.ts', 'dist/human.d.ts');
+  // copy('types/human.d.ts', 'dist/human.node-gpu.d.ts');
+  // copy('types/human.d.ts', 'dist/human.node.d.ts');
+  // copy('types/human.d.ts', 'dist/human.node-wasm.d.ts');
+  log.state('Filter:', { input: 'types/human.d.ts' });
+  filter('reference types', 'types/human.d.ts');
+  log.state('Link:', { input: 'types/human.d.ts' });
+  write('export * from \'../types/human\';', 'dist/human.esm-nobundle.d.ts');
+  write('export * from \'../types/human\';', 'dist/human.esm.d.ts');
+  write('export * from \'../types/human\';', 'dist/human.d.ts');
+  write('export * from \'../types/human\';', 'dist/human.node-gpu.d.ts');
+  write('export * from \'../types/human\';', 'dist/human.node.d.ts');
+  write('export * from \'../types/human\';', 'dist/human.node-wasm.d.ts');
+  // export * from '../types/human';
 
   // generate model signature
   await analyzeModels();

demo/README.md

@@ -8,7 +8,6 @@ For details on other demos see Wiki: [**Demos**](https://github.com/vladmandic/h
 `index.html`: Full demo using `Human` ESM module running in Browsers,  
 
 Includes:
-
 - Selectable inputs:
   - Sample images
   - Image via drag & drop
@@ -38,14 +37,12 @@ Includes:
   in `index.js:ui`
 
 ```js
-const ui = {
   console: true,      // log messages to browser console
   useWorker: true,    // use web workers for processing
   buffered: true,     // should output be buffered between frames
   interpolated: true, // should output be interpolated for smoothness between frames
   results: false,     // show results tree
   useWebRTC: false,   // use webrtc as camera source instead of local webcam
-};
 ```
 
 Demo implements several ways to use `Human` library,  

demo/facedetect/facedetect.js

@@ -1,160 +0,0 @@
-/**
- * Human demo for browsers
- *
- * Demo for face detection
- */
-
-/** @type {Human} */
-import { Human } from '../../dist/human.esm.js';
-
-let loader;
-
-const humanConfig = { // user configuration for human, used to fine-tune behavior
-  cacheSensitivity: 0,
-  debug: true,
-  modelBasePath: 'https://vladmandic.github.io/human-models/models/',
-  filter: { enabled: true, equalization: false, flip: false },
-  face: {
-    enabled: true,
-    detector: { rotation: false, maxDetected: 100, minConfidence: 0.2, return: true, square: false },
-    iris: { enabled: true },
-    description: { enabled: true },
-    emotion: { enabled: true },
-    antispoof: { enabled: true },
-    liveness: { enabled: true },
-  },
-  body: { enabled: false },
-  hand: { enabled: false },
-  object: { enabled: false },
-  gesture: { enabled: false },
-  segmentation: { enabled: false },
-};
-
-const human = new Human(humanConfig); // new instance of human
-
-export const showLoader = (msg) => { loader.setAttribute('msg', msg); loader.style.display = 'block'; };
-export const hideLoader = () => loader.style.display = 'none';
-
-class ComponentLoader extends HTMLElement { // watch for attributes
-  message = document.createElement('div');
-
-  static get observedAttributes() { return ['msg']; }
-
-  attributeChangedCallback(_name, _prevVal, currVal) {
-    this.message.innerHTML = currVal;
-  }
-
-  connectedCallback() { // triggered on insert
-    this.attachShadow({ mode: 'open' });
-    const css = document.createElement('style');
-    css.innerHTML = `
-      .loader-container { top: 450px; justify-content: center; position: fixed; width: 100%; }
-      .loader-message { font-size: 1.5rem; padding: 1rem; }
-      .loader { width: 300px; height: 300px; border: 3px solid transparent; border-radius: 50%; border-top: 4px solid #f15e41; animation: spin 4s linear infinite; position: relative; }
-      .loader::before, .loader::after { content: ""; position: absolute; top: 6px; bottom: 6px; left: 6px; right: 6px; border-radius: 50%; border: 4px solid transparent; }
-      .loader::before { border-top-color: #bad375; animation: 3s spin linear infinite; }
-      .loader::after { border-top-color: #26a9e0; animation: spin 1.5s linear infinite; }
-      @keyframes spin { from { transform: rotate(0deg); } to { transform: rotate(360deg); } }
-    `;
-    const container = document.createElement('div');
-    container.id = 'loader-container';
-    container.className = 'loader-container';
-    loader = document.createElement('div');
-    loader.id = 'loader';
-    loader.className = 'loader';
-    this.message.id = 'loader-message';
-    this.message.className = 'loader-message';
-    this.message.innerHTML = '';
-    container.appendChild(this.message);
-    container.appendChild(loader);
-    this.shadowRoot?.append(css, container);
-    loader = this; // eslint-disable-line @typescript-eslint/no-this-alias
-  }
-}
-
-customElements.define('component-loader', ComponentLoader);
-
-function addFace(face, source) {
-  const deg = (rad) => Math.round((rad || 0) * 180 / Math.PI);
-  const canvas = document.createElement('canvas');
-  const emotion = face.emotion?.map((e) => `${Math.round(100 * e.score)}% ${e.emotion}`) || [];
-  const rotation = `pitch ${deg(face.rotation?.angle.pitch)}° | roll ${deg(face.rotation?.angle.roll)}°  | yaw ${deg(face.rotation?.angle.yaw)}°`;
-  const gaze = `direction ${deg(face.rotation?.gaze.bearing)}° strength ${Math.round(100 * (face.rotation.gaze.strength || 0))}%`;
-  canvas.title = `
-    source: ${source}
-    score: ${Math.round(100 * face.boxScore)}% detection ${Math.round(100 * face.faceScore)}% analysis
-    age: ${face.age} years | gender: ${face.gender} score ${Math.round(100 * face.genderScore)}%
-    emotion: ${emotion.join(' | ')}
-    head rotation: ${rotation}
-    eyes gaze: ${gaze}
-    camera distance: ${face.distance}m | ${Math.round(100 * face.distance / 2.54)}in
-    check: ${Math.round(100 * face.real)}% real ${Math.round(100 * face.live)}% live
-  `.replace(/  /g, ' ');
-  canvas.onclick = (e) => {
-    e.preventDefault();
-    document.getElementById('description').innerHTML = canvas.title;
-  };
-  human.draw.tensor(face.tensor, canvas);
-  human.tf.dispose(face.tensor);
-  return canvas;
-}
-
-async function addFaces(imgEl) {
-  showLoader('human: busy');
-  const faceEl = document.getElementById('faces');
-  faceEl.innerHTML = '';
-  const res = await human.detect(imgEl);
-  console.log(res); // eslint-disable-line no-console
-  document.getElementById('description').innerHTML = `detected ${res.face.length} faces`;
-  for (const face of res.face) {
-    const canvas = addFace(face, imgEl.src.substring(0, 64));
-    faceEl.appendChild(canvas);
-  }
-  hideLoader();
-}
-
-function addImage(imageUri) {
-  const imgEl = new Image(256, 256);
-  imgEl.onload = () => {
-    const images = document.getElementById('images');
-    images.appendChild(imgEl); // add image if loaded ok
-    images.scroll(images?.offsetWidth, 0);
-  };
-  imgEl.onerror = () => console.error('addImage', { imageUri }); // eslint-disable-line no-console
-  imgEl.onclick = () => addFaces(imgEl);
-  imgEl.title = imageUri.substring(0, 64);
-  imgEl.src = encodeURI(imageUri);
-}
-
-async function initDragAndDrop() {
-  const reader = new FileReader();
-  reader.onload = async (e) => {
-    if (e.target.result.startsWith('data:image')) await addImage(e.target.result);
-  };
-  document.body.addEventListener('dragenter', (evt) => evt.preventDefault());
-  document.body.addEventListener('dragleave', (evt) => evt.preventDefault());
-  document.body.addEventListener('dragover', (evt) => evt.preventDefault());
-  document.body.addEventListener('drop', async (evt) => {
-    evt.preventDefault();
-    evt.dataTransfer.dropEffect = 'copy';
-    for (const f of evt.dataTransfer.files) reader.readAsDataURL(f);
-  });
-  document.body.onclick = (e) => {
-    if (e.target.localName !== 'canvas') document.getElementById('description').innerHTML = '';
-  };
-}
-
-async function main() {
-  showLoader('loading models');
-  await human.load();
-  showLoader('compiling models');
-  await human.warmup();
-  showLoader('loading images');
-  const images = ['group-1.jpg', 'group-2.jpg', 'group-3.jpg', 'group-4.jpg', 'group-5.jpg', 'group-6.jpg', 'group-7.jpg', 'solvay1927.jpg', 'stock-group-1.jpg', 'stock-group-2.jpg', 'stock-models-6.jpg', 'stock-models-7.jpg'];
-  const imageUris = images.map((a) => `../../samples/in/${a}`);
-  for (let i = 0; i < imageUris.length; i++) addImage(imageUris[i]);
-  initDragAndDrop();
-  hideLoader();
-}
-
-window.onload = main;

demo/facedetect/index.html

@@ -1,43 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-  <head>
-    <meta charset="utf-8">
-    <title>Human</title>
-    <!-- <meta http-equiv="content-type" content="text/html; charset=utf-8"> -->
-    <meta name="viewport" content="width=device-width, shrink-to-fit=yes">
-    <meta name="keywords" content="Human">
-    <meta name="application-name" content="Human">
-    <meta name="description" content="Human: 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking, Age & Gender Prediction, Emotion Prediction & Gesture Recognition; Author: Vladimir Mandic <https://github.com/vladmandic>">
-    <meta name="msapplication-tooltip" content="Human: 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking, Age & Gender Prediction, Emotion Prediction & Gesture Recognition; Author: Vladimir Mandic <https://github.com/vladmandic>">
-    <meta name="theme-color" content="#000000">
-    <link rel="manifest" href="../manifest.webmanifest">
-    <link rel="shortcut icon" href="../../favicon.ico" type="image/x-icon">
-    <link rel="apple-touch-icon" href="../../assets/icon.png">
-    <script src="./facedetect.js" type="module"></script>
-    <style>
-      img { object-fit: contain; }
-      img:hover { filter: grayscale(1); transform: scale(1.08); transition : all 0.3s ease; }   
-      @font-face { font-family: 'Lato'; font-display: swap; font-style: normal; font-weight: 100; src: local('Lato'), url('../../assets/lato-light.woff2') }
-      html { font-family: 'Lato', 'Segoe UI'; font-size: 24px; font-variant: small-caps; }
-      body { margin: 24px; background: black; color: white; overflow: hidden; text-align: -webkit-center; width: 100vw; height: 100vh; }
-      ::-webkit-scrollbar { height: 8px; border: 0; border-radius: 0; }
-      ::-webkit-scrollbar-thumb { background: grey }
-      ::-webkit-scrollbar-track { margin: 3px; }
-      canvas { width: 192px; height: 192px; margin: 2px; padding: 2px; cursor: grab; transform: scale(1.00); transition : all 0.3s ease; }
-      canvas:hover { filter: grayscale(1); transform: scale(1.08); transition : all 0.3s ease; }   
-    </style>
-  </head>
-  <body>
-    <component-loader></component-loader>
-    <div style="display: flex">
-      <div>
-        <div style="margin: 24px">select image to show detected faces<br>drag & drop to add your images</div>
-        <div id="images" style="display: flex; width: 98vw; overflow-x: auto; overflow-y: hidden; scroll-behavior: smooth"></div>
-      </div>
-    </div>
-    <div id="list" style="height: 10px"></div>
-    <div style="margin: 24px">hover or click on face to show details</div>
-    <div id="faces" style="overflow-y: auto"></div>
-    <div id="description" style="white-space: pre;"></div>
-  </body>
-</html>

demo/faceid/index.ts

@@ -11,13 +11,12 @@ import * as H from '../../dist/human.esm.js'; // equivalent of @vladmandic/Human
 import * as indexDb from './indexdb'; // methods to deal with indexdb
 
 const humanConfig = { // user configuration for human, used to fine-tune behavior
-  cacheSensitivity: 0.01,
+  cacheSensitivity: 0,
   modelBasePath: '../../models',
-  filter: { enabled: true, equalization: true }, // lets run with histogram equilizer
-  debug: true,
+  filter: { equalization: true }, // lets run with histogram equilizer
   face: {
     enabled: true,
-    detector: { rotation: true, return: true, mask: false }, // return tensor is used to get detected face image
+    detector: { rotation: true, return: true, cropFactor: 1.6, mask: false }, // return tensor is used to get detected face image
     description: { enabled: true }, // default model for face descriptor extraction is faceres
     // mobilefacenet: { enabled: true, modelPath: 'https://vladmandic.github.io/human-models/models/mobilefacenet.json' }, // alternative model
     // insightface: { enabled: true, modelPath: 'https://vladmandic.github.io/insightface/models/insightface-mobilenet-swish.json' }, // alternative model
@@ -42,10 +41,9 @@ const options = {
   blinkMin: 10, // minimum duration of a valid blink
   blinkMax: 800, // maximum duration of a valid blink
   threshold: 0.5, // minimum similarity
-  distanceMin: 0.4, // closest that face is allowed to be to the cammera in cm
-  distanceMax: 1.0, // farthest that face is allowed to be to the cammera in cm
   mask: humanConfig.face.detector.mask,
   rotation: humanConfig.face.detector.rotation,
+  cropFactor: humanConfig.face.detector.cropFactor,
   ...matchOptions,
 };
 
@@ -58,7 +56,6 @@ const ok: Record<string, { status: boolean | undefined, val: number }> = { // mu
   faceSize: { status: false, val: 0 },
   antispoofCheck: { status: false, val: 0 },
   livenessCheck: { status: false, val: 0 },
-  distance: { status: false, val: 0 },
   age: { status: false, val: 0 },
   gender: { status: false, val: 0 },
   timeout: { status: true, val: 0 },
@@ -76,7 +73,6 @@ const allOk = () => ok.faceCount.status
   && ok.faceConfidence.status
   && ok.antispoofCheck.status
   && ok.livenessCheck.status
-  && ok.distance.status
   && ok.descriptor.status
   && ok.age.status
   && ok.gender.status;
@@ -191,8 +187,6 @@ async function validationLoop(): Promise<H.FaceResult> { // main screen refresh
     ok.livenessCheck.status = ok.livenessCheck.val >= options.minConfidence;
     ok.faceSize.val = Math.min(human.result.face[0].box[2], human.result.face[0].box[3]);
     ok.faceSize.status = ok.faceSize.val >= options.minSize;
-    ok.distance.val = human.result.face[0].distance || 0;
-    ok.distance.status = (ok.distance.val >= options.distanceMin) && (ok.distance.val <= options.distanceMax);
     ok.descriptor.val = human.result.face[0].embedding?.length || 0;
     ok.descriptor.status = ok.descriptor.val > 0;
     ok.age.val = human.result.face[0].age || 0;
@@ -239,8 +233,8 @@ async function detectFace() {
   dom.canvas.getContext('2d')?.clearRect(0, 0, options.minSize, options.minSize);
   if (!current?.face?.tensor || !current?.face?.embedding) return false;
   console.log('face record:', current.face); // eslint-disable-line no-console
-  log(`detected face: ${current.face.gender} ${current.face.age || 0}y distance ${100 * (current.face.distance || 0)}cm/${Math.round(100 * (current.face.distance || 0) / 2.54)}in`);
-  await human.draw.tensor(current.face.tensor, dom.canvas);
+  log(`detected face: ${current.face.gender} ${current.face.age || 0}y distance ${current.face.iris || 0}cm/${Math.round(100 * (current.face.iris || 0) / 2.54) / 100}in`);
+  human.tf.browser.toPixels(current.face.tensor as unknown as H.TensorLike, dom.canvas);
   if (await indexDb.count() === 0) {
     log('face database is empty: nothing to compare face with');
     document.body.style.background = 'black';
@@ -249,7 +243,7 @@ async function detectFace() {
   }
   const db = await indexDb.load();
   const descriptors = db.map((rec) => rec.descriptor).filter((desc) => desc.length > 0);
-  const res = human.match.find(current.face.embedding, descriptors, matchOptions);
+  const res = human.match(current.face.embedding, descriptors, matchOptions);
   current.record = db[res.index] || null;
   if (current.record) {
     log(`best match: ${current.record.name} | id: ${current.record.id} | similarity: ${Math.round(1000 * res.similarity) / 10}%`);
@@ -281,8 +275,8 @@ async function main() { // main entry point
   await detectionLoop(); // start detection loop
   startTime = human.now();
   current.face = await validationLoop(); // start validation loop
-  dom.canvas.width = current.face?.tensor?.shape[1] || options.minSize;
-  dom.canvas.height = current.face?.tensor?.shape[0] || options.minSize;
+  dom.canvas.width = current.face.tensor?.shape[1] || options.minSize;
+  dom.canvas.height = current.face.tensor?.shape[0] || options.minSize;
   dom.source.width = dom.canvas.width;
   dom.source.height = dom.canvas.height;
   dom.canvas.style.width = '';

demo/facematch/README.md

@@ -11,7 +11,7 @@
 ## Browser Face Recognition Demo
 
 - `demo/facematch`: Demo for Browsers that uses all face description and embedding features to  
-detect, extract and identify all faces plus calculate similarity between them
+detect, extract and identify all faces plus calculate simmilarity between them
 
 It highlights functionality such as:
 
@@ -72,13 +72,12 @@ Non-linear performance that increases with number of worker threads due to commu
 
 > node node-match
 
-<!-- eslint-skip -->
 ```js
-INFO:  options: { dbFile: './faces.json', dbMax: 10000, threadPoolSize: 6, workerSrc: './node-match-worker.js', debug: false, minThreshold: 0.9, descLength: 1024 }
-DATA:  created shared buffer: { maxDescriptors: 10000, totalBytes: 40960000, totalElements: 10240000 }
-DATA:  db loaded: { existingRecords: 0, newRecords: 5700 }
-INFO:  starting worker thread pool: { totalWorkers: 6, alreadyActive: 0 }
-STATE: submitted: { matchJobs: 100, poolSize: 6, activeWorkers: 6 }
-STATE: { matchJobsFinished: 100, totalTimeMs: 1769, averageTimeMs: 17.69 }
-INFO:  closing workers: { poolSize: 6, activeWorkers: 6 }
+2021-10-13 07:53:36 INFO:  options: { dbFile: './faces.json', dbMax: 10000, threadPoolSize: 6, workerSrc: './node-match-worker.js', debug: false, minThreshold: 0.9, descLength: 1024 }
+2021-10-13 07:53:36 DATA:  created shared buffer: { maxDescriptors: 10000, totalBytes: 40960000, totalElements: 10240000 }
+2021-10-13 07:53:36 DATA:  db loaded: { existingRecords: 0, newRecords: 5700 }
+2021-10-13 07:53:36 INFO:  starting worker thread pool: { totalWorkers: 6, alreadyActive: 0 }
+2021-10-13 07:53:36 STATE: submitted: { matchJobs: 100, poolSize: 6, activeWorkers: 6 }
+2021-10-13 07:53:38 STATE: { matchJobsFinished: 100, totalTimeMs: 1769, averageTimeMs: 17.69 }
+2021-10-13 07:53:38 INFO:  closing workers: { poolSize: 6, activeWorkers: 6 }
 ```

demo/facematch/facematch.js

@@ -1,7 +1,7 @@
 /**
  * Human demo for browsers
  *
- * Demo for face descriptor analysis and face similarity analysis
+ * Demo for face descriptor analysis and face simmilarity analysis
  */
 
 /** @type {Human} */
@@ -11,7 +11,7 @@ const userConfig = {
   backend: 'humangl',
   async: true,
   warmup: 'none',
-  cacheSensitivity: 0.01,
+  cacheSensitivity: 0,
   debug: true,
   modelBasePath: '../../models/',
   deallocate: true,
@@ -22,6 +22,7 @@ const userConfig = {
   },
   face: {
     enabled: true,
+    // detector: { rotation: false, return: true, maxDetected: 50, iouThreshold: 0.206, minConfidence: 0.122 },
     detector: { return: true, rotation: true, maxDetected: 50, iouThreshold: 0.01, minConfidence: 0.2 },
     mesh: { enabled: true },
     iris: { enabled: false },
@@ -63,16 +64,25 @@ async function loadFaceMatchDB() {
   }
 }
 
-async function selectFaceCanvas(face) {
+async function SelectFaceCanvas(face) {
   // if we have face image tensor, enhance it and display it
   let embedding;
   document.getElementById('orig').style.filter = 'blur(16px)';
   if (face.tensor) {
     title('Sorting Faces by Similarity');
+    const enhanced = human.enhance(face);
+    if (enhanced) {
       const c = document.getElementById('orig');
-    await human.draw.tensor(face.tensor, c);
+      const squeeze = human.tf.squeeze(enhanced);
+      const normalize = human.tf.div(squeeze, 255);
+      await human.tf.browser.toPixels(normalize, c);
+      human.tf.dispose([enhanced, squeeze, normalize]);
+      const ctx = c.getContext('2d');
+      ctx.font = 'small-caps 0.4rem "Lato"';
+      ctx.fillStyle = 'rgba(255, 255, 255, 1)';
+    }
     const arr = db.map((rec) => rec.embedding);
-    const res = await human.match.find(face.embedding, arr);
+    const res = await human.match(face.embedding, arr);
     log('Match:', db[res.index].name);
     const emotion = face.emotion[0] ? `${Math.round(100 * face.emotion[0].score)}% ${face.emotion[0].emotion}` : 'N/A';
     document.getElementById('desc').innerHTML = `
@@ -93,11 +103,11 @@ async function selectFaceCanvas(face) {
   for (const canvas of canvases) {
     // calculate similarity from selected face to current one in the loop
     const current = all[canvas.tag.sample][canvas.tag.face];
-    const similarity = human.match.similarity(face.embedding, current.embedding);
+    const similarity = human.similarity(face.embedding, current.embedding);
     canvas.tag.similarity = similarity;
     // get best match
     // draw the canvas
-    await human.draw.tensor(current.tensor, canvas);
+    await human.tf.browser.toPixels(current.tensor, canvas);
     const ctx = canvas.getContext('2d');
     ctx.font = 'small-caps 1rem "Lato"';
     ctx.fillStyle = 'rgba(0, 0, 0, 1)';
@@ -110,7 +120,7 @@ async function selectFaceCanvas(face) {
     ctx.font = 'small-caps 1rem "Lato"';
     const start = human.now();
     const arr = db.map((rec) => rec.embedding);
-    const res = await human.match.find(current.embedding, arr);
+    const res = await human.match(current.embedding, arr);
     time += (human.now() - start);
     if (res.similarity > minScore) ctx.fillText(`DB: ${(100 * res.similarity).toFixed(1)}% ${db[res.index].name}`, 4, canvas.height - 30);
   }
@@ -125,7 +135,7 @@ async function selectFaceCanvas(face) {
   title('Selected Face');
 }
 
-async function addFaceCanvas(index, res, fileName) {
+async function AddFaceCanvas(index, res, fileName) {
   all[index] = res.face;
   for (const i in res.face) {
     if (!res.face[i].tensor) continue; // did not get valid results
@@ -144,25 +154,25 @@ async function addFaceCanvas(index, res, fileName) {
       gender: ${Math.round(100 * res.face[i].genderScore)}% ${res.face[i].gender}
       emotion: ${emotion}
     `.replace(/  /g, ' ');
-    await human.draw.tensor(res.face[i].tensor, canvas);
+    await human.tf.browser.toPixels(res.face[i].tensor, canvas);
     const ctx = canvas.getContext('2d');
-    if (!ctx) return;
+    if (!ctx) return false;
     ctx.font = 'small-caps 0.8rem "Lato"';
     ctx.fillStyle = 'rgba(255, 255, 255, 1)';
     ctx.fillText(`${res.face[i].age}y ${(100 * (res.face[i].genderScore || 0)).toFixed(1)}% ${res.face[i].gender}`, 4, canvas.height - 6);
     const arr = db.map((rec) => rec.embedding);
-    const result = human.match.find(res.face[i].embedding, arr);
+    const result = human.match(res.face[i].embedding, arr);
     ctx.font = 'small-caps 1rem "Lato"';
     if (result.similarity && res.similarity > minScore) ctx.fillText(`${(100 * result.similarity).toFixed(1)}% ${db[result.index].name}`, 4, canvas.height - 30);
     document.getElementById('faces').appendChild(canvas);
     canvas.addEventListener('click', (evt) => {
       log('Select:', 'Image:', evt.target.tag.sample, 'Face:', evt.target.tag.face, 'Source:', evt.target.tag.source, all[evt.target.tag.sample][evt.target.tag.face]);
-      selectFaceCanvas(all[evt.target.tag.sample][evt.target.tag.face]);
+      SelectFaceCanvas(all[evt.target.tag.sample][evt.target.tag.face]);
     });
   }
 }
 
-async function addImageElement(index, image, length) {
+async function AddImageElement(index, image, length) {
   const faces = all.reduce((prev, curr) => prev += curr.length, 0);
   title(`Analyzing Input Images<br> ${Math.round(100 * index / length)}% [${index} / ${length}]<br>Found ${faces} Faces`);
   return new Promise((resolve) => {
@@ -171,7 +181,7 @@ async function addImageElement(index, image, length) {
       document.getElementById('images').appendChild(img); // and finally we can add it
       human.detect(img, userConfig)
         .then((res) => { // eslint-disable-line promise/always-return
-          addFaceCanvas(index, res, image); // then wait until image is analyzed
+          AddFaceCanvas(index, res, image); // then wait until image is analyzed
           resolve(true);
         })
         .catch(() => log('human detect error'));
@@ -212,23 +222,18 @@ async function main() {
   // could not dynamically enumerate images so using static list
   if (images.length === 0) {
     images = [
-      'ai-face.jpg', 'ai-upper.jpg', 'ai-body.jpg', 'solvay1927.jpg',
+      'ai-body.jpg', 'solvay1927.jpg', 'ai-upper.jpg',
+      'person-carolina.jpg', 'person-celeste.jpg', 'person-leila1.jpg', 'person-leila2.jpg', 'person-lexi.jpg', 'person-linda.jpg', 'person-nicole.jpg', 'person-tasia.jpg',
+      'person-tetiana.jpg', 'person-vlado1.jpg', 'person-vlado5.jpg', 'person-vlado.jpg', 'person-christina.jpg', 'person-lauren.jpg',
       'group-1.jpg', 'group-2.jpg', 'group-3.jpg', 'group-4.jpg', 'group-5.jpg', 'group-6.jpg', 'group-7.jpg',
-      'person-celeste.jpg', 'person-christina.jpg', 'person-lauren.jpg', 'person-lexi.jpg', 'person-linda.jpg', 'person-nicole.jpg', 'person-tasia.jpg', 'person-tetiana.jpg', 'person-vlado.jpg', 'person-vlado1.jpg', 'person-vlado5.jpg',
-      'stock-group-1.jpg', 'stock-group-2.jpg',
-      'stock-models-1.jpg', 'stock-models-2.jpg', 'stock-models-3.jpg', 'stock-models-4.jpg', 'stock-models-5.jpg', 'stock-models-6.jpg', 'stock-models-7.jpg', 'stock-models-8.jpg', 'stock-models-9.jpg',
-      'stock-teen-1.jpg', 'stock-teen-2.jpg', 'stock-teen-3.jpg', 'stock-teen-4.jpg', 'stock-teen-5.jpg', 'stock-teen-6.jpg', 'stock-teen-7.jpg', 'stock-teen-8.jpg',
-      'stock-models-10.jpg', 'stock-models-11.jpg', 'stock-models-12.jpg', 'stock-models-13.jpg', 'stock-models-14.jpg', 'stock-models-15.jpg', 'stock-models-16.jpg',
-      'cgi-model-1.jpg', 'cgi-model-2.jpg', 'cgi-model-3.jpg', 'cgi-model-4.jpg', 'cgi-model-5.jpg', 'cgi-model-6.jpg', 'cgi-model-7.jpg', 'cgi-model-8.jpg', 'cgi-model-9.jpg',
-      'cgi-model-10.jpg', 'cgi-model-11.jpg', 'cgi-model-12.jpg', 'cgi-model-13.jpg', 'cgi-model-14.jpg', 'cgi-model-15.jpg', 'cgi-model-18.jpg', 'cgi-model-19.jpg',
-      'cgi-model-20.jpg', 'cgi-model-21.jpg', 'cgi-model-22.jpg', 'cgi-model-23.jpg', 'cgi-model-24.jpg', 'cgi-model-25.jpg', 'cgi-model-26.jpg', 'cgi-model-27.jpg', 'cgi-model-28.jpg', 'cgi-model-29.jpg',
-      'cgi-model-30.jpg', 'cgi-model-31.jpg', 'cgi-model-33.jpg', 'cgi-model-34.jpg',
-      'cgi-multiangle-1.jpg', 'cgi-multiangle-2.jpg', 'cgi-multiangle-3.jpg', 'cgi-multiangle-4.jpg', 'cgi-multiangle-6.jpg', 'cgi-multiangle-7.jpg', 'cgi-multiangle-8.jpg', 'cgi-multiangle-9.jpg', 'cgi-multiangle-10.jpg', 'cgi-multiangle-11.jpg',
-      'stock-emotions-a-1.jpg', 'stock-emotions-a-2.jpg', 'stock-emotions-a-3.jpg', 'stock-emotions-a-4.jpg', 'stock-emotions-a-5.jpg', 'stock-emotions-a-6.jpg', 'stock-emotions-a-7.jpg', 'stock-emotions-a-8.jpg',
-      'stock-emotions-b-1.jpg', 'stock-emotions-b-2.jpg', 'stock-emotions-b-3.jpg', 'stock-emotions-b-4.jpg', 'stock-emotions-b-5.jpg', 'stock-emotions-b-6.jpg', 'stock-emotions-b-7.jpg', 'stock-emotions-b-8.jpg',
+      'daz3d-brianna.jpg', 'daz3d-chiyo.jpg', 'daz3d-cody.jpg', 'daz3d-drew-01.jpg', 'daz3d-drew-02.jpg', 'daz3d-ella-01.jpg', 'daz3d-ella-02.jpg', 'daz3d-gillian.jpg',
+      'daz3d-hye-01.jpg', 'daz3d-hye-02.jpg', 'daz3d-kaia.jpg', 'daz3d-karen.jpg', 'daz3d-kiaria-01.jpg', 'daz3d-kiaria-02.jpg', 'daz3d-lilah-01.jpg', 'daz3d-lilah-02.jpg',
+      'daz3d-lilah-03.jpg', 'daz3d-lila.jpg', 'daz3d-lindsey.jpg', 'daz3d-megah.jpg', 'daz3d-selina-01.jpg', 'daz3d-selina-02.jpg', 'daz3d-snow.jpg',
+      'daz3d-sunshine.jpg', 'daz3d-taia.jpg', 'daz3d-tuesday-01.jpg', 'daz3d-tuesday-02.jpg', 'daz3d-tuesday-03.jpg', 'daz3d-zoe.jpg', 'daz3d-ginnifer.jpg',
+      'daz3d-_emotions01.jpg', 'daz3d-_emotions02.jpg', 'daz3d-_emotions03.jpg', 'daz3d-_emotions04.jpg', 'daz3d-_emotions05.jpg',
     ];
     // add prefix for gitpages
-    images = images.map((a) => `../../samples/in/${a}`);
+    images = images.map((a) => `/human/samples/in/${a}`);
     log('Adding static image list:', images);
   } else {
     log('Discovered images:', images);
@@ -237,7 +242,7 @@ async function main() {
   // images = ['/samples/in/person-lexi.jpg', '/samples/in/person-carolina.jpg', '/samples/in/solvay1927.jpg'];
 
   const t0 = human.now();
-  for (let i = 0; i < images.length; i++) await addImageElement(i, images[i], images.length);
+  for (let i = 0; i < images.length; i++) await AddImageElement(i, images[i], images.length);
   const t1 = human.now();
 
   // print stats
@@ -251,7 +256,7 @@ async function main() {
   title('');
   log('Ready');
   human.validate(userConfig);
-  human.match.similarity([], []);
+  human.similarity([], []);
 }
 
 window.onload = main;

demo/facematch/node-match-worker.js

@@ -38,8 +38,7 @@ function match(descBuffer, options = { order: 2, multiplier: 20 }) {
     if (best < threshold || best === 0) break; // short circuit
   }
   best = (options.order === 2) ? Math.sqrt(best) : best ** (1 / options.order);
-  const similarity = Math.round(100 * Math.max(0, 100 - best) / 100.0) / 100;
-  return { index, distance: best, similarity };
+  return { index, distance: best, similarity: Math.max(0, 100 - best) / 100.0 };
 }
 
 threads.parentPort?.on('message', (msg) => {
@@ -61,11 +60,11 @@ threads.parentPort?.on('message', (msg) => {
   }
   if (typeof msg.debug !== 'undefined') { // set verbose logging
     debug = msg.debug;
-    // if (debug) threads.parentPort?.postMessage(`debug: ${debug}`);
+    if (debug) threads.parentPort?.postMessage(`debug: ${debug}`);
   }
   if (typeof msg.threshold !== 'undefined') { // set minimum similarity threshold
     threshold = msg.threshold;
-    // if (debug) threads.parentPort?.postMessage(`threshold: ${threshold}`);
+    if (debug) threads.parentPort?.postMessage(`threshold: ${threshold}`);
   }
   if (typeof msg.shutdown !== 'undefined') { // got message to close worker
     if (debug) threads.parentPort?.postMessage('shutting down');

demo/facematch/node-match.js

@@ -15,7 +15,7 @@ const options = {
   dbMax: 10000, // maximum number of records to hold in memory
   threadPoolSize: 12, // number of worker threads to create in thread pool
   workerSrc: './node-match-worker.js', // code that executes in the worker thread
-  debug: true, // verbose messages
+  debug: false, // verbose messages
   minThreshold: 0.5, // match returns first record that meets the similarity threshold, set to 0 to always scan all records
   descLength: 1024, // descriptor length
 };
@@ -176,7 +176,7 @@ async function main() {
     data.requestID++; // increase request id
     if (testOptions.fuzDescriptors) match(fuzDescriptor(descriptor)); // fuz descriptor for harder match
     else match(descriptor);
-    if (options.debug) log.debug('submited job', data.requestID); // we already know what we're searching for so we can compare results
+    if (options.debug) log.info('submited job', data.requestID); // we already know what we're searching for so we can compare results
   }
   log.state('submitted:', { matchJobs: testOptions.maxJobs, poolSize: data.workers.length, activeWorkers: data.workers.filter((worker) => !!worker).length });
 }

demo/index-pwa.js

@@ -28,10 +28,10 @@ async function updateCached(req) {
     .then((update) => {
       // update cache if request is ok
       if (update.ok) {
-        caches
+        caches // eslint-disable-line promise/no-nesting
           .open(cacheName)
           .then((cache) => cache.put(req, update))
-          .catch((err) => log('cache update error', err)); // eslint-disable-line promise/no-nesting
+          .catch((err) => log('cache update error', err));
       }
       return true;
     })
@@ -76,8 +76,8 @@ async function getCached(evt) {
 
 function cacheInit() {
   caches.open(cacheName)
-    .then((cache) => cache.addAll(cacheFiles)
-      .then( // eslint-disable-line promise/no-nesting
+    .then((cache) => cache.addAll(cacheFiles) // eslint-disable-line promise/no-nesting
+      .then(
         () => log('cache refresh:', cacheFiles.length, 'files'),
         (err) => log('cache error', err),
       ))

demo/index.js

@@ -18,10 +18,7 @@
  * ui={}: contains all variables exposed in the UI
  */
 
-// WARNING!!!
-// This demo is written using older code style and a lot of manual setup
-// Newer versions of Human have richer functionality allowing for much cleaner & easier usage
-// It is recommended to use other demos such as `demo/typescript` for usage examples
+// test url <https://human.local/?worker=false&async=false&bench=false&draw=true&warmup=full&backend=humangl>
 
 import { Human } from '../dist/human.esm.js'; // equivalent of @vladmandic/human
 import Menu from './helpers/menu.js';
@@ -86,7 +83,7 @@ const ui = {
   facing: true, // camera facing front or back
   baseBackground: 'rgba(50, 50, 50, 1)', // 'grey'
   columns: 2, // when processing sample images create this many columns
-  useWorker: false, // use web workers for processing
+  useWorker: true, // use web workers for processing
   worker: 'index-worker.js',
   maxFPSframes: 10, // keep fps history for how many frames
   modelsPreload: false, // preload human models on startup
@@ -185,7 +182,7 @@ function status(msg) {
     prevStatus = msg;
   } else {
     const video = document.getElementById('video');
-    const playing = isLive(video) && !video.paused; // eslint-disable-line no-use-before-define
+    const playing = (video.srcObject !== null) && !video.paused;
     document.getElementById('play').style.display = playing ? 'none' : 'block';
     document.getElementById('loader').style.display = 'none';
     div.innerText = '';
@@ -195,6 +192,7 @@ function status(msg) {
 async function videoPlay(videoElement = document.getElementById('video')) {
   document.getElementById('btnStartText').innerHTML = 'pause video';
   await videoElement.play();
+  // status();
 }
 
 async function videoPause() {
@@ -222,13 +220,21 @@ async function calcSimmilarity(result) {
     compare.original = result;
     log('setting face compare baseline:', result.face[0]);
     if (result.face[0].tensor) {
+      const enhanced = human.enhance(result.face[0]);
+      if (enhanced) {
         const c = document.getElementById('orig');
-      human.draw.tensor(result.face[0].tensor, c);
+        const squeeze = human.tf.squeeze(enhanced);
+        const norm = human.tf.div(squeeze, 255);
+        human.tf.browser.toPixels(norm, c);
+        human.tf.dispose(enhanced);
+        human.tf.dispose(squeeze);
+        human.tf.dispose(norm);
+      }
     } else {
       document.getElementById('compare-canvas').getContext('2d').drawImage(compare.original.canvas, 0, 0, 200, 200);
     }
   }
-  const similarity = human.match.similarity(compare.original.face[0].embedding, result.face[0].embedding);
+  const similarity = human.similarity(compare.original.face[0].embedding, result.face[0].embedding);
   document.getElementById('similarity').innerText = `similarity: ${Math.trunc(1000 * similarity) / 10}%`;
 }
 
@@ -513,6 +519,17 @@ function runHumanDetect(input, canvas, timestamp) {
     human.detect(input, userConfig)
       .then((result) => {
         status();
+        /*
+        setTimeout(async () => { // simulate gl context lost 2sec after initial detection
+          const ext = human.gl && human.gl.gl ? human.gl.gl.getExtension('WEBGL_lose_context') : {};
+          if (ext && ext.loseContext) {
+            log('simulate context lost:', human.env.webgl, human.gl, ext);
+            human.gl.gl.getExtension('WEBGL_lose_context').loseContext();
+            await videoPause();
+            status('Exception: WebGL');
+          }
+        }, 2000);
+        */
         if (result.performance && result.performance.total) ui.detectFPS.push(1000 / result.performance.total);
         if (ui.detectFPS.length > ui.maxFPSframes) ui.detectFPS.shift();
         if (ui.bench) {
@@ -606,15 +623,21 @@ async function processImage(input, title) {
 
 async function processVideo(input, title) {
   status(`processing video: ${title}`);
+  // const video = document.getElementById('video-file') || document.createElement('video');
   const video = document.getElementById('video');
   const canvas = document.getElementById('canvas');
+  // video.id = 'video-file';
+  // video.controls = true;
+  // video.loop = true;
+  // video.style.display = 'none';
+  // document.body.appendChild(video);
   video.addEventListener('error', () => status(`video loading error: ${video.error.message}`));
   video.addEventListener('canplay', async () => {
     for (const m of Object.values(menu)) m.hide();
     document.getElementById('samples-container').style.display = 'none';
     canvas.style.display = 'block';
     await videoPlay();
-    runHumanDetect(video, canvas);
+    if (!ui.detectThread) runHumanDetect(video, canvas);
   });
   video.srcObject = null;
   video.src = input;
@@ -627,8 +650,9 @@ async function detectVideo() {
   const canvas = document.getElementById('canvas');
   canvas.style.display = 'block';
   cancelAnimationFrame(ui.detectThread);
-  if (isLive(video) && !video.paused) {
+  if ((video.srcObject !== null) && !video.paused) {
     await videoPause();
+    // if (ui.drawThread) cancelAnimationFrame(ui.drawThread);
   } else {
     const cameraError = await setupCamera();
     if (!cameraError) {
@@ -770,7 +794,6 @@ function setupMenu() {
 
 async function resize() {
   window.onresize = null;
-  log('resize');
   // best setting for mobile, ignored for desktop
   // can set dynamic value such as Math.min(1, Math.round(100 * window.innerWidth / 960) / 100);
   const viewportScale = 0.7;
@@ -977,7 +1000,8 @@ async function main() {
   if (ui.modelsPreload && !ui.useWorker) {
     status('loading');
     await human.load(userConfig); // this is not required, just pre-loads all models
-    log('demo loaded models:', human.models.loaded());
+    const loaded = Object.keys(human.models).filter((a) => human.models[a]);
+    log('demo loaded models:', loaded);
   } else {
     await human.init();
   }

demo/multithread/README.md

@@ -16,7 +16,6 @@
 node demo/nodejs/node-multiprocess.js
 ```
 
-<!-- eslint-skip -->
 ```json
 2021-06-01 08:54:19 INFO:  @vladmandic/human version 2.0.0
 2021-06-01 08:54:19 INFO:  User: vlado Platform: linux Arch: x64 Node: v16.0.0

demo/multithread/index.html

@@ -9,10 +9,10 @@
     <meta name="description" content="Human: 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking, Age & Gender Prediction, Emotion Prediction & Gesture Recognition; Author: Vladimir Mandic <https://github.com/vladmandic>">
     <meta name="msapplication-tooltip" content="Human: 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking, Age & Gender Prediction, Emotion Prediction & Gesture Recognition; Author: Vladimir Mandic <https://github.com/vladmandic>">
     <meta name="theme-color" content="#000000">
-    <link rel="manifest" href="../../manifest.webmanifest">
+    <link rel="manifest" href="../manifest.webmanifest">
     <link rel="shortcut icon" href="../../favicon.ico" type="image/x-icon">
     <link rel="apple-touch-icon" href="../../assets/icon.png">
-    <script src="../multithread/index.js" type="module"></script>
+    <script src="./index.js" type="module"></script>
     <style>
       @font-face { font-family: 'Lato'; font-display: swap; font-style: normal; font-weight: 100; src: local('Lato'), url('../../assets/lato-light.woff2') }
       html { font-family: 'Lato', 'Segoe UI'; font-size: 16px; font-variant: small-caps; }

demo/multithread/index.js

@@ -8,7 +8,7 @@
 import { Human } from '../../dist/human.esm.js'; // equivalent of @vladmandic/human
 import GLBench from '../helpers/gl-bench.js';
 
-const workerJS = '../multithread/worker.js';
+const workerJS = './worker.js';
 
 const config = {
   main: { // processes input and runs gesture analysis

demo/multithread/node-multiprocess.js

@@ -8,8 +8,8 @@
 
 const fs = require('fs');
 const path = require('path');
-const childProcess = require('child_process'); // eslint-disable-line camelcase
 const log = require('@vladmandic/pilogger'); // eslint-disable-line node/no-unpublished-require
+const childProcess = require('child_process'); // eslint-disable-line camelcase
 // note that main process does not import human or tfjs at all, it's all done from worker process
 
 const workerFile = 'demo/multithread/node-multiprocess-worker.js';

demo/nodejs/README.md

@@ -28,8 +28,7 @@ or you can pass a path to image to analyze, either on local filesystem or using
 node demo/nodejs/node.js
 ```
 
-<!-- eslint-skip -->
-```js
+```json
 2021-06-01 08:52:15 INFO:  @vladmandic/human version 2.0.0
 2021-06-01 08:52:15 INFO:  User: vlado Platform: linux Arch: x64 Node: v16.0.0
 2021-06-01 08:52:15 INFO:  Current folder: /home/vlado/dev/human
@@ -83,7 +82,7 @@ node demo/nodejs/node.js
     detector: { modelPath: 'handdetect.json' },
     skeleton: { modelPath: 'handskeleton.json' }
   },
-  object: { enabled: true, modelPath: 'centernet.json', minConfidence: 0.2, iouThreshold: 0.4, maxDetected: 10, skipFrames: 19 }
+  object: { enabled: true, modelPath: 'mb3-centernet.json', minConfidence: 0.2, iouThreshold: 0.4, maxDetected: 10, skipFrames: 19 }
 }
 08:52:15.673 Human: version: 2.0.0
 08:52:15.674 Human: tfjs version: 3.6.0
@@ -97,7 +96,7 @@ node demo/nodejs/node.js
 08:52:15.847 Human: load model: file://models/handdetect.json
 08:52:15.847 Human: load model: file://models/handskeleton.json
 08:52:15.914 Human: load model: file://models/movenet-lightning.json
-08:52:15.957 Human: load model: file://models/centernet.json
+08:52:15.957 Human: load model: file://models/mb3-centernet.json
 08:52:16.015 Human: load model: file://models/faceres.json
 08:52:16.015 Human: tf engine state: 50796152 bytes 1318 tensors
 2021-06-01 08:52:16 INFO:  Loaded: [ 'face', 'movenet', 'handpose', 'emotion', 'centernet', 'faceres', [length]: 6 ]

demo/nodejs/node-age-gender.js

@@ -1,70 +0,0 @@
-const fs = require('fs');
-const process = require('process');
-const log = require('@vladmandic/pilogger'); // eslint-disable-line node/no-unpublished-require
-const tf = require('@tensorflow/tfjs-node'); // eslint-disable-line node/no-unpublished-require
-const Human = require('../../dist/human.node.js');
-
-const humanConfig = {
-  debug: false,
-  face: {
-    enabled: true,
-    detector: { enabled: true, modelPath: 'blazeface.json' },
-    description: { enabled: true, modelPath: 'faceres.json' },
-    // gear: { enabled: true, modelPath: '/home/vlado/dev/human-models/models/gear.json' },
-    // ssrnet: { enabled: true, modelPathAge: '/home/vlado/dev/human-models/models/age.json', modelPathGender: '/home/vlado/dev/human-models/models/gender.json' },
-    emotion: { enabled: false },
-    mesh: { enabled: false },
-    iris: { enabled: false },
-    antispoof: { enabled: false },
-    liveness: { enabled: false },
-  },
-  body: { enabled: false },
-  hand: { enabled: false },
-  gesture: { enabled: false },
-};
-const human = new Human.Human(humanConfig);
-const ageThreshold = 18;
-
-async function detect(inputFile) {
-  try {
-    const buffer = fs.readFileSync(inputFile);
-    const tensor = human.tf.node.decodeImage(buffer);
-    const result = await human.detect(tensor);
-    human.tf.dispose(tensor);
-    if (!result || !result.face || result.face.length === 0) return false;
-    let msg = ` file=${inputFile} resolution=${tensor.shape}`;
-    for (const face of result.face) {
-      msg = ` file=${inputFile} resolution=${tensor.shape} age=${face.age} gender=${face.gender} confidence=${face.genderScore}`;
-      if (face.age < ageThreshold) {
-        log.warn('fail:' + msg);
-        return true;
-      }
-    }
-    log.info('pass: ' + msg);
-    return false;
-  } catch (err) {
-    log.error(`error: file=${inputFile}: ${err}`);
-  }
-  return false;
-}
-
-async function main() {
-  log.info(`Human: version=${human.version} tf=${tf.version_core}`);
-  process.noDeprecation = true;
-  if (process.argv.length < 3) return;
-  await human.load();
-  await human.warmup();
-  const t0 = performance.now();
-  const args = process.argv.slice(2);
-  let pass = 0;
-  let fail = 0;
-  for (const arg of args) {
-    const ok = await detect(arg);
-    if (ok) pass++;
-    else fail++;
-  }
-  const t1 = performance.now();
-  log.info(`Human: files=${args.length} pass=${pass} fail=${fail} time=${Math.round(t1 - t0)} fps=${Math.round(10000 * args.length / (t1 - t0)) / 10}`);
-}
-
-main();

demo/nodejs/node-bench.js

@@ -1,66 +0,0 @@
-/**
- * Human simple demo for NodeJS
- */
-
-const childProcess = require('child_process'); // eslint-disable-line camelcase
-const log = require('@vladmandic/pilogger'); // eslint-disable-line node/no-unpublished-require
-const canvas = require('canvas'); // eslint-disable-line node/no-unpublished-require
-
-const config = {
-  cacheSensitivity: 0.01,
-  wasmPlatformFetch: true,
-  modelBasePath: 'https://vladmandic.github.io/human-models/models/',
-};
-const count = 10;
-
-async function loadImage(input) {
-  const inputImage = await canvas.loadImage(input);
-  const inputCanvas = new canvas.Canvas(inputImage.width, inputImage.height);
-  const inputCtx = inputCanvas.getContext('2d');
-  inputCtx.drawImage(inputImage, 0, 0);
-  const imageData = inputCtx.getImageData(0, 0, inputCanvas.width, inputCanvas.height);
-  process.send({ input, resolution: [inputImage.width, inputImage.height] });
-  return imageData;
-}
-
-async function runHuman(module, backend) {
-  if (backend === 'wasm') require('@tensorflow/tfjs-backend-wasm'); // eslint-disable-line node/no-unpublished-require, global-require
-  const Human = require('../../dist/' + module); // eslint-disable-line global-require, import/no-dynamic-require
-  config.backend = backend;
-  const human = new Human.Human(config);
-  human.env.Canvas = canvas.Canvas;
-  human.env.Image = canvas.Image;
-  human.env.ImageData = canvas.ImageData;
-  process.send({ human: human.version, module });
-  await human.init();
-  process.send({ desired: human.config.backend, wasm: human.env.wasm, tfjs: human.tf.version.tfjs, tensorflow: human.env.tensorflow });
-  const imageData = await loadImage('samples/in/ai-body.jpg');
-  const t0 = human.now();
-  await human.load();
-  const t1 = human.now();
-  await human.warmup();
-  const t2 = human.now();
-  for (let i = 0; i < count; i++) await human.detect(imageData);
-  const t3 = human.now();
-  process.send({ backend: human.tf.getBackend(), load: Math.round(t1 - t0), warmup: Math.round(t2 - t1), detect: Math.round(t3 - t2), count, memory: human.tf.memory().numBytes });
-}
-
-async function executeWorker(args) {
-  return new Promise((resolve) => {
-    const worker = childProcess.fork(process.argv[1], args);
-    worker.on('message', (msg) => log.data(msg));
-    worker.on('exit', () => resolve(true));
-  });
-}
-
-async function main() {
-  if (process.argv[2]) {
-    await runHuman(process.argv[2], process.argv[3]);
-  } else {
-    await executeWorker(['human.node.js', 'tensorflow']);
-    await executeWorker(['human.node-gpu.js', 'tensorflow']);
-    await executeWorker(['human.node-wasm.js', 'wasm']);
-  }
-}
-
-main();

demo/nodejs/node-canvas.js

@@ -24,7 +24,6 @@ const config = { // just enable all and leave default settings
 
 async function main() {
   log.header();
-  process.noDeprecation = true;
 
   globalThis.Canvas = canvas.Canvas; // patch global namespace with canvas library
   globalThis.ImageData = canvas.ImageData; // patch global namespace with canvas library
@@ -36,13 +35,12 @@ async function main() {
   log.info('Human:', human.version, 'TF:', tf.version_core);
 
   await human.load(); // pre-load models
-  log.info('Loaded models:', human.models.loaded());
+  log.info('Loaded models:', Object.keys(human.models).filter((a) => human.models[a]));
   log.info('Memory state:', human.tf.engine().memory());
 
   // parse cmdline
   const input = process.argv[2];
-  let output = process.argv[3];
-  if (!output.toLowerCase().endsWith('.jpg')) output += '.jpg';
+  const output = process.argv[3];
   if (process.argv.length !== 4) log.error('Parameters: <input-image> <output-image> missing');
   else if (!fs.existsSync(input) && !input.startsWith('http')) log.error(`File not found: ${process.argv[2]}`);
   else {

demo/nodejs/node-event.js

@@ -5,6 +5,8 @@
 const fs = require('fs');
 const process = require('process');
 
+let fetch; // fetch is dynamically imported later
+
 const log = require('@vladmandic/pilogger'); // eslint-disable-line node/no-unpublished-require
 // in nodejs environments tfjs-node is required to be loaded before human
 const tf = require('@tensorflow/tfjs-node'); // eslint-disable-line node/no-unpublished-require
@@ -36,13 +38,13 @@ async function detect(input) {
   let buffer;
   log.info('Loading image:', input);
   if (input.startsWith('http:') || input.startsWith('https:')) {
+    fetch = (await import('node-fetch')).default; // eslint-disable-line node/no-unpublished-import
     const res = await fetch(input);
-    if (res && res.ok) buffer = Buffer.from(await res.arrayBuffer());
+    if (res && res.ok) buffer = await res.buffer();
     else log.error('Invalid image URL:', input, res.status, res.statusText, res.headers.get('content-type'));
   } else {
     buffer = fs.readFileSync(input);
   }
-  log.data('Image bytes:', buffer?.length, 'buffer:', buffer?.slice(0, 32));
 
   // decode image using tfjs-node so we don't need external depenencies
   if (!buffer) return;
@@ -65,7 +67,8 @@ async function main() {
     });
 
     human.events.addEventListener('load', () => {
-      log.info('Event Loaded:', human.models.loaded(), human.tf.engine().memory());
+      const loaded = Object.keys(human.models).filter((a) => human.models[a]);
+      log.info('Event Loaded:', loaded, human.tf.engine().memory());
     });
 
     human.events.addEventListener('image', () => {
@@ -77,7 +80,7 @@ async function main() {
       const persons = human.result.persons;
       for (let i = 0; i < persons.length; i++) {
         const face = persons[i].face;
-        const faceTxt = face ? `score:${face.score} age:${face.age} gender:${face.gender} iris:${face.distance}` : null;
+        const faceTxt = face ? `score:${face.score} age:${face.age} gender:${face.gender} iris:${face.iris}` : null;
         const body = persons[i].body;
         const bodyTxt = body ? `score:${body.score} keypoints:${body.keypoints?.length}` : null;
         log.data(`  #${i}: Face:${faceTxt} Body:${bodyTxt} LeftHand:${persons[i].hands.left ? 'yes' : 'no'} RightHand:${persons[i].hands.right ? 'yes' : 'no'} Gestures:${persons[i].gestures.length}`);

demo/nodejs/node-fetch.js

@@ -16,7 +16,8 @@ const humanConfig = {
 };
 
 async function main(inputFile) {
-  global.fetch = (await import('node-fetch')).default; // eslint-disable-line node/no-unpublished-import, import/no-unresolved, node/no-missing-import, node/no-extraneous-import
+  // @ts-ignore
+  global.fetch = (await import('node-fetch')).default; // eslint-disable-line node/no-unpublished-import
   const human = new Human.Human(humanConfig); // create instance of human using default configuration
   log.info('Human:', human.version, 'TF:', tf.version_core);
   await human.load(); // optional as models would be loaded on-demand first time they are required

demo/nodejs/node-similarity.js

@@ -27,7 +27,8 @@ async function init() {
   await human.tf.ready();
   log.info('Human:', human.version, 'TF:', tf.version_core);
   await human.load();
-  log.info('Loaded:', human.models.loaded());
+  const loaded = Object.keys(human.models).filter((a) => human.models[a]);
+  log.info('Loaded:', loaded);
   log.info('Memory state:', human.tf.engine().memory());
 }
 
@@ -45,12 +46,10 @@ async function detect(input) {
 }
 
 async function main() {
-  process.noDeprecation = true;
   log.configure({ inspect: { breakLength: 265 } });
   log.header();
   if (process.argv.length !== 4) {
-    log.error('Parameters: <first image> <second image> missing');
-    return;
+    throw new Error('Parameters: <first image> <second image> missing');
   }
   await init();
   const res1 = await detect(process.argv[2]);
@@ -58,7 +57,7 @@ async function main() {
   if (!res1 || !res1.face || res1.face.length === 0 || !res2 || !res2.face || res2.face.length === 0) {
     throw new Error('Could not detect face descriptors');
   }
-  const similarity = human.match.similarity(res1.face[0].embedding, res2.face[0].embedding, { order: 2 });
+  const similarity = human.similarity(res1.face[0].embedding, res2.face[0].embedding, { order: 2 });
   log.data('Similarity: ', similarity);
 }
 

demo/nodejs/node-simple.js

@@ -13,11 +13,9 @@ const Human = require('../../dist/human.node.js'); // use this when using human
 const humanConfig = {
   // add any custom config here
   debug: true,
-  body: { enabled: false },
 };
 
 async function detect(inputFile) {
-  process.noDeprecation = true;
   const human = new Human.Human(humanConfig); // create instance of human using default configuration
   console.log('Human:', human.version, 'TF:', tf.version_core); // eslint-disable-line no-console
   await human.load(); // optional as models would be loaded on-demand first time they are required

demo/nodejs/node-video.js

@@ -11,11 +11,10 @@
  * Working version of `ffmpeg` must be present on the system
 */
 
-const process = require('process');
 const spawn = require('child_process').spawn;
 const log = require('@vladmandic/pilogger'); // eslint-disable-line node/no-unpublished-require
 // in nodejs environments tfjs-node is required to be loaded before human
-// const tf = require('@tensorflow/tfjs-node'); // eslint-disable-line node/no-unpublished-require
+const tf = require('@tensorflow/tfjs-node'); // eslint-disable-line node/no-unpublished-require
 // const human = require('@vladmandic/human'); // use this when human is installed as module (majority of use cases)
 const Pipe2Jpeg = require('pipe2jpeg'); // eslint-disable-line node/no-missing-require, import/no-unresolved
 // const human = require('@vladmandic/human'); // use this when human is installed as module (majority of use cases)
@@ -23,8 +22,7 @@ const Human = require('../../dist/human.node.js'); // use this when using human
 
 let count = 0; // counter
 let busy = false; // busy flag
-let inputFile = './test.mp4';
-if (process.argv.length === 3) inputFile = process.argv[2];
+const inputFile = './test.mp4';
 
 const humanConfig = {
   modelBasePath: 'file://models/',
@@ -61,27 +59,24 @@ const ffmpegParams = [
   'pipe:1', // output to unix pipe that is then captured by pipe2jpeg
 ];
 
-async function detect(jpegBuffer) {
+async function process(jpegBuffer) {
   if (busy) return; // skip processing if busy
   busy = true;
   const tensor = human.tf.node.decodeJpeg(jpegBuffer, 3); // decode jpeg buffer to raw tensor
+  log.state('input frame:', ++count, 'size:', jpegBuffer.length, 'decoded shape:', tensor.shape);
   const res = await human.detect(tensor);
-  human.tf.dispose(tensor); // must dispose tensor
-  // start custom processing here
-  log.data('frame', { frame: ++count, size: jpegBuffer.length, shape: tensor.shape, face: res?.face?.length, body: res?.body?.length, hand: res?.hand?.length, gesture: res?.gesture?.length });
-  if (res?.face?.[0]) log.data('person', { score: [res.face[0].boxScore, res.face[0].faceScore], age: res.face[0].age || 0, gender: [res.face[0].genderScore || 0, res.face[0].gender], emotion: res.face[0].emotion?.[0] });
-  // at the of processing mark loop as not busy so it can process next frame
+  log.data('gesture', JSON.stringify(res.gesture));
+  // do processing here
+  tf.dispose(tensor); // must dispose tensor
   busy = false;
 }
 
 async function main() {
   log.header();
-  process.noDeprecation = true;
   await human.tf.ready();
   // pre-load models
-  log.info({ human: human.version, tf: human.tf.version_core });
-  log.info({ input: inputFile });
-  pipe2jpeg.on('data', (jpegBuffer) => detect(jpegBuffer));
+  log.info('human:', human.version, 'tf:', tf.version_core);
+  pipe2jpeg.on('jpeg', (jpegBuffer) => process(jpegBuffer));
 
   const ffmpeg = spawn('ffmpeg', ffmpegParams, { stdio: ['ignore', 'pipe', 'ignore'] });
   ffmpeg.on('error', (error) => log.error('ffmpeg error:', error));

demo/nodejs/node.js

@@ -1,11 +1,15 @@
 /**
  * Human demo for NodeJS
+ *
+ * Requires [node-fetch](https://www.npmjs.com/package/node-fetch) to provide `fetch` functionality in NodeJS environment
 */
 
+const log = require('@vladmandic/pilogger'); // eslint-disable-line node/no-unpublished-require
 const fs = require('fs');
 const path = require('path');
 const process = require('process');
-const log = require('@vladmandic/pilogger'); // eslint-disable-line node/no-unpublished-require
+
+let fetch; // fetch is dynamically imported later
 
 // in nodejs environments tfjs-node is required to be loaded before human
 const tf = require('@tensorflow/tfjs-node'); // eslint-disable-line node/no-unpublished-require
@@ -49,7 +53,8 @@ async function init() {
   log.info('Human:', human.version);
   // log.info('Active Configuration', human.config);
   await human.load();
-  log.info('Loaded:', human.models.loaded());
+  const loaded = Object.keys(human.models).filter((a) => human.models[a]);
+  log.info('Loaded:', loaded);
   // log.info('Memory state:', human.tf.engine().memory());
   log.data(tf.backend().binding ? tf.backend().binding.TF_Version : null);
 }
@@ -60,12 +65,11 @@ async function detect(input) {
   log.info('Loading image:', input);
   if (input.startsWith('http:') || input.startsWith('https:')) {
     const res = await fetch(input);
-    if (res && res.ok) buffer = Buffer.from(await res.arrayBuffer());
+    if (res && res.ok) buffer = await res.buffer();
     else log.error('Invalid image URL:', input, res.status, res.statusText, res.headers.get('content-type'));
   } else {
     buffer = fs.readFileSync(input);
   }
-  log.data('Image bytes:', buffer?.length, 'buffer:', buffer?.slice(0, 32));
 
   // decode image using tfjs-node so we don't need external depenencies
   // can also be done using canvas.js or some other 3rd party image library
@@ -92,7 +96,7 @@ async function detect(input) {
   try {
     result = await human.detect(tensor, myConfig);
   } catch (err) {
-    log.error('caught', err);
+    log.error('caught');
   }
 
   // dispose image tensor as we no longer need it
@@ -104,7 +108,7 @@ async function detect(input) {
     for (let i = 0; i < result.face.length; i++) {
       const face = result.face[i];
       const emotion = face.emotion.reduce((prev, curr) => (prev.score > curr.score ? prev : curr));
-      log.data(`  Face: #${i} boxScore:${face.boxScore} faceScore:${face.faceScore} age:${face.age} genderScore:${face.genderScore} gender:${face.gender} emotionScore:${emotion.score} emotion:${emotion.emotion} distance:${face.distance}`);
+      log.data(`  Face: #${i} boxScore:${face.boxScore} faceScore:${face.faceScore} age:${face.age} genderScore:${face.genderScore} gender:${face.gender} emotionScore:${emotion.score} emotion:${emotion.emotion} iris:${face.iris}`);
     }
   } else {
     log.data('  Face: N/A');
@@ -187,8 +191,8 @@ async function test() {
 async function main() {
   log.configure({ inspect: { breakLength: 265 } });
   log.header();
-  process.noDeprecation = true;
   log.info('Current folder:', process.env.PWD);
+  fetch = (await import('node-fetch')).default; // eslint-disable-line node/no-unpublished-import
   await init();
   const f = process.argv[2];
   if (process.argv.length !== 3) {

demo/nodejs/process-folder.js

@@ -20,7 +20,7 @@ const config = { // just enable all and leave default settings
   modelBasePath: 'file://models',
   debug: true,
   softwareKernels: true, // slower but enhanced precision since face rotation can work in software mode in nodejs environments
-  cacheSensitivity: 0.01,
+  cacheSensitivity: 0,
   face: { enabled: true, detector: { maxDetected: 100, minConfidence: 0.1 } },
   object: { enabled: true, maxDetected: 100, minConfidence: 0.1 },
   gesture: { enabled: true },
@@ -77,11 +77,10 @@ async function main() {
   globalThis.ImageData = canvas.ImageData; // patch global namespace with canvas library
 
   log.info('Human:', human.version, 'TF:', tf.version_core);
-  process.noDeprecation = true;
   const configErrors = await human.validate();
   if (configErrors.length > 0) log.error('Configuration errors:', configErrors);
   await human.load(); // pre-load models
-  log.info('Loaded models:', human.models.loaded());
+  log.info('Loaded models:', Object.keys(human.models).filter((a) => human.models[a]));
 
   const inDir = process.argv[2];
   const outDir = process.argv[3];

demo/segmentation/index.html

@@ -20,7 +20,7 @@
       body { font-size: 1rem; font-family: "CenturyGothic", "Segoe UI", sans-serif; font-variant: small-caps; width: -webkit-fill-available; height: 100%; background: black; color: white; overflow: hidden; margin: 0; }
       select { font-size: 1rem; font-family: "CenturyGothic", "Segoe UI", sans-serif; font-variant: small-caps; background: gray; color: white; border: none; }
     </style>
-    <script src="../segmentation/index.js" type="module"></script>
+  <script src="index.js" type="module"></script>
   </head>
   <body>
     <noscript><h1>javascript is required</h1></noscript>
@@ -46,9 +46,9 @@
     <main>
       <div id="main" class="main">
         <video id="webcam" style="position: fixed; top: 0; left: 0; width: 50vw; height: 50vh"></video>
-        <img id="background" alt="background" style="position: fixed; top: 0; right: 0; width: 50vw; height: 50vh" controls></img>
-        <canvas id="output" style="position: fixed; bottom: 0; left: 0; height: 50vh"></canvas>
-        <canvas id="merge" style="position: fixed; bottom: 0; right: 0; height: 50vh"></canvas>
+        <video id="video" style="position: fixed; top: 0; right: 0; width: 50vw; height: 50vh" controls></video>
+        <canvas id="output" style="position: fixed; bottom: 0; left: 0; width: 50vw; height: 50vh"></canvas>
+        <canvas id="merge" style="position: fixed; bottom: 0; right: 0; width: 50vw; height: 50vh"></canvas>
       </div>
     </main>
     <footer>

demo/segmentation/index.js

@@ -25,8 +25,6 @@ const humanConfig = { // user configuration for human, used to fine-tune behavio
   },
 };
 
-const backgroundImage = '../../samples/in/background.jpg';
-
 const human = new H.Human(humanConfig); // create instance of human with overrides from user configuration
 
 const log = (...msg) => console.log(...msg); // eslint-disable-line no-console
@@ -34,7 +32,7 @@ const log = (...msg) => console.log(...msg); // eslint-disable-line no-console
 async function main() {
   // gather dom elements
   const dom = {
-    background: document.getElementById('background'),
+    video: document.getElementById('video'),
     webcam: document.getElementById('webcam'),
     output: document.getElementById('output'),
     merge: document.getElementById('merge'),
@@ -46,7 +44,7 @@ async function main() {
   // set defaults
   dom.fps.innerText = 'initializing';
   dom.ratio.valueAsNumber = human.config.segmentation.ratio;
-  dom.background.src = backgroundImage;
+  dom.video.src = '../assets/rijeka.mp4';
   dom.composite.innerHTML = ['source-atop', 'color', 'color-burn', 'color-dodge', 'copy', 'darken', 'destination-atop', 'destination-in', 'destination-out', 'destination-over', 'difference', 'exclusion', 'hard-light', 'hue', 'lighten', 'lighter', 'luminosity', 'multiply', 'overlay', 'saturation', 'screen', 'soft-light', 'source-in', 'source-out', 'source-over', 'xor'].map((gco) => `<option value="${gco}">${gco}</option>`).join(''); // eslint-disable-line max-len
   const ctxMerge = dom.merge.getContext('2d');
 
@@ -54,8 +52,8 @@ async function main() {
   log('platform:', human.env.platform, '| agent:', human.env.agent);
   await human.load(); // preload all models
   log('backend:', human.tf.getBackend(), '| available:', human.env.backends);
-  log('models stats:', human.models.stats());
-  log('models loaded:', human.models.loaded());
+  log('models stats:', human.getModelStats());
+  log('models loaded:', Object.values(human.models).filter((model) => model !== null).length);
   await human.warmup(); // warmup function to initialize backend for future faster detection
   const numTensors = human.tf.engine().state.numTensors;
 
@@ -68,8 +66,7 @@ async function main() {
     dom.merge.height = human.webcam.height;
     loop(); // eslint-disable-line no-use-before-define
   };
-
-  await human.webcam.start({ element: dom.webcam, crop: true, width: window.innerWidth / 2, height: window.innerHeight / 2 }); // use human webcam helper methods and associate webcam stream with a dom element
+  await human.webcam.start({ element: dom.webcam, crop: true, width: 960, height: 720 }); // use human webcam helper methods and associate webcam stream with a dom element
   if (!human.webcam.track) dom.fps.innerText = 'webcam error';
 
   // processing loop
@@ -85,10 +82,10 @@ async function main() {
       return;
     }
     dom.fps.innerText = `fps: ${Math.round(10000 / (t1 - t0)) / 10}`; // mark performance
-    human.draw.tensor(rgba, dom.output); // draw raw output
+    human.tf.browser.toPixels(rgba, dom.output); // draw raw output
     human.tf.dispose(rgba); // dispose tensors
     ctxMerge.globalCompositeOperation = 'source-over';
-    ctxMerge.drawImage(dom.background, 0, 0); // draw original video to first stacked canvas
+    ctxMerge.drawImage(dom.video, 0, 0); // draw original video to first stacked canvas
     ctxMerge.globalCompositeOperation = dom.composite.value;
     ctxMerge.drawImage(dom.output, 0, 0); // draw processed output to second stacked canvas
     if (numTensors !== human.tf.engine().state.numTensors) log({ leak: human.tf.engine().state.numTensors - numTensors }); // check for memory leaks

demo/tracker/README.md

@@ -1,28 +0,0 @@
-## Tracker
-
-### Based on
-
-<https://github.com/opendatacam/node-moving-things-tracker>  
-
-### Build
-
-- remove reference to `lodash`:  
-  > `isEqual` in <tracker.js>  
-- replace external lib:  
-  > curl https://raw.githubusercontent.com/ubilabs/kd-tree-javascript/master/kdTree.js -o lib/kdTree-min.js
-- build with `esbuild`:  
-  > node_modules/.bin/esbuild --bundle tracker.js --format=esm --platform=browser --target=esnext --keep-names --tree-shaking=false --analyze --outfile=/home/vlado/dev/human/demo/tracker/tracker.js --banner:js="/* eslint-disable */"
-
-### Usage
-
-    computeDistance(item1, item2)
-    disableKeepInMemory()
-    enableKeepInMemory()
-    getAllTrackedItems()
-    getJSONDebugOfTrackedItems(roundInt = true)
-    getJSONOfAllTrackedItems()
-    getJSONOfTrackedItems(roundInt = true)
-    getTrackedItemsInMOTFormat(frameNb)
-    reset()
-    setParams(newParams)
-    updateTrackedItemsWithNewFrame(detectionsOfThisFrame, frameNb)

demo/tracker/index.html

@@ -1,65 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-  <head>
-    <meta charset="utf-8">
-    <title>Human</title>
-    <meta name="viewport" content="width=device-width" id="viewport">
-    <meta name="keywords" content="Human">
-    <meta name="application-name" content="Human">
-    <meta name="description" content="Human: 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking, Age & Gender Prediction, Emotion Prediction & Gesture Recognition; Author: Vladimir Mandic <https://github.com/vladmandic>">
-    <meta name="msapplication-tooltip" content="Human: 3D Face Detection, Body Pose, Hand & Finger Tracking, Iris Tracking, Age & Gender Prediction, Emotion Prediction & Gesture Recognition; Author: Vladimir Mandic <https://github.com/vladmandic>">
-    <meta name="theme-color" content="#000000">
-    <link rel="manifest" href="../manifest.webmanifest">
-    <link rel="shortcut icon" href="../../favicon.ico" type="image/x-icon">
-    <link rel="apple-touch-icon" href="../../assets/icon.png">
-    <script src="./index.js" type="module"></script>
-    <style>
-      html { font-family: 'Segoe UI'; font-size: 16px; font-variant: small-caps; }
-      body { margin: 0; background: black; color: white; overflow-x: hidden; width: 100vw; height: 100vh; }
-      body::-webkit-scrollbar { display: none; }
-      input[type="file"] { font-family: 'Segoe UI'; font-size: 14px; font-variant: small-caps; }
-      ::-webkit-file-upload-button { background: #333333; color: white; border: 0; border-radius: 0; padding: 6px 16px; box-shadow: 4px 4px 4px #222222; font-family: 'Segoe UI'; font-size: 14px; font-variant: small-caps; }
-    </style>
-  </head>
-  <body>
-    <div style="display: flex">
-      <video id="video" playsinline style="width: 25vw" controls controlslist="nofullscreen nodownload noremoteplayback" disablepictureinpicture loop></video>
-      <canvas id="canvas" style="width: 75vw"></canvas> 
-    </div>
-    <div class="uploader" style="padding: 8px">
-      <input type="file" name="inputvideo" id="inputvideo" accept="video/*"></input>
-      <input type="checkbox" id="interpolation" name="interpolation"></input>
-      <label for="tracker">interpolation</label>
-    </div>
-    <form id="config" style="padding: 8px; line-height: 1.6rem;">
-      tracker | 
-      <input type="checkbox" id="tracker" name="tracker" checked></input>
-      <label for="tracker">enabled</label> | 
-      <input type="checkbox" id="keepInMemory" name="keepInMemory"></input>
-      <label for="keepInMemory">keepInMemory</label> | 
-      <br>
-      tracker source | 
-      <input type="radio" id="box-face" name="box" value="face" checked>
-      <label for="box-face">face</label> |
-      <input type="radio" id="box-body" name="box" value="body">
-      <label for="box-face">body</label> |
-      <input type="radio" id="box-object" name="box" value="object">
-      <label for="box-face">object</label> |
-      <br>
-      tracker config | 
-      <input type="range" id="unMatchedFramesTolerance" name="unMatchedFramesTolerance" min="0" max="300" step="1", value="60"></input>
-      <label for="unMatchedFramesTolerance">unMatchedFramesTolerance</label> |
-      <input type="range" id="iouLimit" name="unMatchedFramesTolerance" min="0" max="1" step="0.01", value="0.1"></input>
-      <label for="iouLimit">iouLimit</label> |
-      <input type="range" id="distanceLimit" name="unMatchedFramesTolerance" min="0" max="1" step="0.01", value="0.1"></input>
-      <label for="distanceLimit">distanceLimit</label> |
-      <input type="radio" id="matchingAlgorithm-kdTree" name="matchingAlgorithm" value="kdTree" checked>
-      <label for="matchingAlgorithm-kdTree">kdTree</label> |
-      <input type="radio" id="matchingAlgorithm-munkres" name="matchingAlgorithm" value="munkres">
-      <label for="matchingAlgorithm-kdTree">munkres</label> |
-    </form>
-    <pre id="status" style="position: absolute; top: 12px; right: 20px; background-color: grey; padding: 8px; box-shadow: 2px 2px black"></pre>
-    <pre id="log" style="padding: 8px"></pre>
-    <div id="performance" style="position: absolute; bottom: 0; width: 100%; padding: 8px; font-size: 0.8rem;"></div>
-  </body>
-</html>

demo/tracker/index.ts

@@ -1,208 +0,0 @@
-/**
- * Human demo for browsers
- * @default Human Library
- * @summary <https://github.com/vladmandic/human>
- * @author <https://github.com/vladmandic>
- * @copyright <https://github.com/vladmandic>
- * @license MIT
- */
-
-import * as H from '../../dist/human.esm.js'; // equivalent of @vladmandic/Human
-import tracker from './tracker.js';
-
-const humanConfig: Partial<H.Config> = { // user configuration for human, used to fine-tune behavior
-  debug: true,
-  backend: 'webgl',
-  // cacheSensitivity: 0,
-  // cacheModels: false,
-  // warmup: 'none',
-  modelBasePath: 'https://vladmandic.github.io/human-models/models',
-  filter: { enabled: true, equalization: false, flip: false },
-  face: {
-    enabled: true,
-    detector: { rotation: false, maxDetected: 10, minConfidence: 0.3 },
-    mesh: { enabled: true },
-    attention: { enabled: false },
-    iris: { enabled: false },
-    description: { enabled: false },
-    emotion: { enabled: false },
-    antispoof: { enabled: false },
-    liveness: { enabled: false },
-  },
-  body: { enabled: false, maxDetected: 6, modelPath: 'movenet-multipose.json' },
-  hand: { enabled: false },
-  object: { enabled: false, maxDetected: 10 },
-  segmentation: { enabled: false },
-  gesture: { enabled: false },
-};
-
-interface TrackerConfig {
-  unMatchedFramesTolerance: number, // number of frame when an object is not matched before considering it gone; ignored if fastDelete is set
-  iouLimit: number, // exclude things from beeing matched if their IOU less than; 1 means total overlap; 0 means no overlap
-  fastDelete: boolean, // remove new objects immediately if they could not be matched in the next frames; if set, ignores unMatchedFramesTolerance
-  distanceLimit: number, // distance limit for matching; if values need to be excluded from matching set their distance to something greater than the distance limit
-  matchingAlgorithm: 'kdTree' | 'munkres', // algorithm used to match tracks with new detections
-}
-
-interface TrackerResult {
-  id: number,
-  confidence: number,
-  bearing: number,
-  isZombie: boolean,
-  name: string,
-  x: number,
-  y: number,
-  w: number,
-  h: number,
-}
-
-const trackerConfig: TrackerConfig = {
-  unMatchedFramesTolerance: 100,
-  iouLimit: 0.05,
-  fastDelete: false,
-  distanceLimit: 1e4,
-  matchingAlgorithm: 'kdTree',
-};
-
-const human = new H.Human(humanConfig); // create instance of human with overrides from user configuration
-
-const dom = { // grab instances of dom objects so we dont have to look them up later
-  video: document.getElementById('video') as HTMLVideoElement,
-  canvas: document.getElementById('canvas') as HTMLCanvasElement,
-  log: document.getElementById('log') as HTMLPreElement,
-  fps: document.getElementById('status') as HTMLPreElement,
-  tracker: document.getElementById('tracker') as HTMLInputElement,
-  interpolation: document.getElementById('interpolation') as HTMLInputElement,
-  config: document.getElementById('config') as HTMLFormElement,
-  ctx: (document.getElementById('canvas') as HTMLCanvasElement).getContext('2d') as CanvasRenderingContext2D,
-};
-const timestamp = { detect: 0, draw: 0, tensors: 0, start: 0 }; // holds information used to calculate performance and possible memory leaks
-const fps = { detectFPS: 0, drawFPS: 0, frames: 0, averageMs: 0 }; // holds calculated fps information for both detect and screen refresh
-
-const log = (...msg) => { // helper method to output messages
-  dom.log.innerText += msg.join(' ') + '\n';
-  console.log(...msg); // eslint-disable-line no-console
-};
-const status = (msg) => dom.fps.innerText = msg; // print status element
-
-async function detectionLoop() { // main detection loop
-  if (!dom.video.paused && dom.video.readyState >= 2) {
-    if (timestamp.start === 0) timestamp.start = human.now();
-    // log('profiling data:', await human.profile(dom.video));
-    await human.detect(dom.video, humanConfig); // actual detection; were not capturing output in a local variable as it can also be reached via human.result
-    const tensors = human.tf.memory().numTensors; // check current tensor usage for memory leaks
-    if (tensors - timestamp.tensors !== 0) log('allocated tensors:', tensors - timestamp.tensors); // printed on start and each time there is a tensor leak
-    timestamp.tensors = tensors;
-    fps.detectFPS = Math.round(1000 * 1000 / (human.now() - timestamp.detect)) / 1000;
-    fps.frames++;
-    fps.averageMs = Math.round(1000 * (human.now() - timestamp.start) / fps.frames) / 1000;
-  }
-  timestamp.detect = human.now();
-  requestAnimationFrame(detectionLoop); // start new frame immediately
-}
-
-function drawLoop() { // main screen refresh loop
-  if (!dom.video.paused && dom.video.readyState >= 2) {
-    const res: H.Result = dom.interpolation.checked ? human.next(human.result) : human.result; // interpolate results if enabled
-    let tracking: H.FaceResult[] | H.BodyResult[] | H.ObjectResult[] = [];
-    if (human.config.face.enabled) tracking = res.face;
-    else if (human.config.body.enabled) tracking = res.body;
-    else if (human.config.object.enabled) tracking = res.object;
-    else log('unknown object type');
-    let data: TrackerResult[] = [];
-    if (dom.tracker.checked) {
-      const items = tracking.map((obj) => ({
-        x: obj.box[0] + obj.box[2] / 2,
-        y: obj.box[1] + obj.box[3] / 2,
-        w: obj.box[2],
-        h: obj.box[3],
-        name: obj.label || (human.config.face.enabled ? 'face' : 'body'),
-        confidence: obj.score,
-      }));
-      tracker.updateTrackedItemsWithNewFrame(items, fps.frames);
-      data = tracker.getJSONOfTrackedItems(true) as TrackerResult[];
-    }
-    human.draw.canvas(dom.video, dom.canvas); // copy input video frame to output canvas
-    for (let i = 0; i < tracking.length; i++) {
-      // @ts-ignore
-      const name = tracking[i].label || (human.config.face.enabled ? 'face' : 'body');
-      dom.ctx.strokeRect(tracking[i].box[0], tracking[i].box[1], tracking[i].box[1], tracking[i].box[2]);
-      dom.ctx.fillText(`id: ${tracking[i].id} ${Math.round(100 * tracking[i].score)}% ${name}`, tracking[i].box[0] + 4, tracking[i].box[1] + 16);
-      if (data[i]) {
-        dom.ctx.fillText(`t: ${data[i].id} ${Math.round(100 * data[i].confidence)}% ${data[i].name} ${data[i].isZombie ? 'zombie' : ''}`, tracking[i].box[0] + 4, tracking[i].box[1] + 34);
-      }
-    }
-  }
-  const now = human.now();
-  fps.drawFPS = Math.round(1000 * 1000 / (now - timestamp.draw)) / 1000;
-  timestamp.draw = now;
-  status(dom.video.paused ? 'paused' : `fps: ${fps.detectFPS.toFixed(1).padStart(5, ' ')} detect | ${fps.drawFPS.toFixed(1).padStart(5, ' ')} draw`); // write status
-  setTimeout(drawLoop, 30); // use to slow down refresh from max refresh rate to target of 30 fps
-}
-
-async function handleVideo(file: File) {
-  const url = URL.createObjectURL(file);
-  dom.video.src = url;
-  await dom.video.play();
-  log('loaded video:', file.name, 'resolution:', [dom.video.videoWidth, dom.video.videoHeight], 'duration:', dom.video.duration);
-  dom.canvas.width = dom.video.videoWidth;
-  dom.canvas.height = dom.video.videoHeight;
-  dom.ctx.strokeStyle = 'white';
-  dom.ctx.fillStyle = 'white';
-  dom.ctx.font = '16px Segoe UI';
-  dom.video.playbackRate = 0.25;
-}
-
-function initInput() {
-  document.body.addEventListener('dragenter', (evt) => evt.preventDefault());
-  document.body.addEventListener('dragleave', (evt) => evt.preventDefault());
-  document.body.addEventListener('dragover', (evt) => evt.preventDefault());
-  document.body.addEventListener('drop', async (evt) => {
-    evt.preventDefault();
-    if (evt.dataTransfer) evt.dataTransfer.dropEffect = 'copy';
-    const file = evt.dataTransfer?.files?.[0];
-    if (file) await handleVideo(file);
-    log(dom.video.readyState);
-  });
-  (document.getElementById('inputvideo') as HTMLInputElement).onchange = async (evt) => {
-    evt.preventDefault();
-    const file = evt.target?.['files']?.[0];
-    if (file) await handleVideo(file);
-  };
-  dom.config.onchange = () => {
-    trackerConfig.distanceLimit = (document.getElementById('distanceLimit') as HTMLInputElement).valueAsNumber;
-    trackerConfig.iouLimit = (document.getElementById('iouLimit') as HTMLInputElement).valueAsNumber;
-    trackerConfig.unMatchedFramesTolerance = (document.getElementById('unMatchedFramesTolerance') as HTMLInputElement).valueAsNumber;
-    trackerConfig.unMatchedFramesTolerance = (document.getElementById('unMatchedFramesTolerance') as HTMLInputElement).valueAsNumber;
-    trackerConfig.matchingAlgorithm = (document.getElementById('matchingAlgorithm-kdTree') as HTMLInputElement).checked ? 'kdTree' : 'munkres';
-    tracker.setParams(trackerConfig);
-    if ((document.getElementById('keepInMemory') as HTMLInputElement).checked) tracker.enableKeepInMemory();
-    else tracker.disableKeepInMemory();
-    tracker.reset();
-    log('tracker config change', JSON.stringify(trackerConfig));
-    humanConfig.face!.enabled = (document.getElementById('box-face') as HTMLInputElement).checked; // eslint-disable-line @typescript-eslint/no-non-null-assertion
-    humanConfig.body!.enabled = (document.getElementById('box-body') as HTMLInputElement).checked; // eslint-disable-line @typescript-eslint/no-non-null-assertion
-    humanConfig.object!.enabled = (document.getElementById('box-object') as HTMLInputElement).checked; // eslint-disable-line @typescript-eslint/no-non-null-assertion
-  };
-  dom.tracker.onchange = (evt) => {
-    log('tracker', (evt.target as HTMLInputElement).checked ? 'enabled' : 'disabled');
-    tracker.setParams(trackerConfig);
-    tracker.reset();
-  };
-}
-
-async function main() { // main entry point
-  log('human version:', human.version, '| tfjs version:', human.tf.version['tfjs-core']);
-  log('platform:', human.env.platform, '| agent:', human.env.agent);
-  status('loading...');
-  await human.load(); // preload all models
-  log('backend:', human.tf.getBackend(), '| available:', human.env.backends);
-  log('models loaded:', human.models.loaded());
-  status('initializing...');
-  await human.warmup(); // warmup function to initialize backend for future faster detection
-  initInput(); // initialize input
-  await detectionLoop(); // start detection loop
-  drawLoop(); // start draw loop
-}
-
-window.onload = main;

demo/typescript/index.html

@@ -21,7 +21,7 @@
     </style>
   </head>
   <body>
-    <canvas id="canvas" style="margin: 0 auto; width: 100vw"></canvas>
+    <canvas id="canvas" style="margin: 0 auto; width: 100%"></canvas>
     <video id="video" playsinline style="display: none"></video>
     <pre id="status" style="position: absolute; top: 12px; right: 20px; background-color: grey; padding: 8px; box-shadow: 2px 2px black"></pre>
     <pre id="log" style="padding: 8px"></pre>

demo/typescript/index.js

@@ -4,6 +4,6 @@
   author: <https://github.com/vladmandic>'
 */
 
-import*as m from"../../dist/human.esm.js";var v=1920,b={debug:!0,backend:"webgl",modelBasePath:"https://vladmandic.github.io/human-models/models/",filter:{enabled:!0,equalization:!1,flip:!1},face:{enabled:!0,detector:{rotation:!1},mesh:{enabled:!0},attention:{enabled:!1},iris:{enabled:!0},description:{enabled:!0},emotion:{enabled:!0},antispoof:{enabled:!0},liveness:{enabled:!0}},body:{enabled:!1},hand:{enabled:!1},object:{enabled:!1},segmentation:{enabled:!1},gesture:{enabled:!0}},e=new m.Human(b);e.env.perfadd=!1;e.draw.options.font='small-caps 18px "Lato"';e.draw.options.lineHeight=20;e.draw.options.drawPoints=!0;var a={video:document.getElementById("video"),canvas:document.getElementById("canvas"),log:document.getElementById("log"),fps:document.getElementById("status"),perf:document.getElementById("performance")},n={detect:0,draw:0,tensors:0,start:0},s={detectFPS:0,drawFPS:0,frames:0,averageMs:0},o=(...t)=>{a.log.innerText+=t.join(" ")+`
-`,console.log(...t)},i=t=>a.fps.innerText=t,g=t=>a.perf.innerText="tensors:"+e.tf.memory().numTensors.toString()+" | performance: "+JSON.stringify(t).replace(/"|{|}/g,"").replace(/,/g," | ");async function f(){if(!a.video.paused){n.start===0&&(n.start=e.now()),await e.detect(a.video);let t=e.tf.memory().numTensors;t-n.tensors!==0&&o("allocated tensors:",t-n.tensors),n.tensors=t,s.detectFPS=Math.round(1e3*1e3/(e.now()-n.detect))/1e3,s.frames++,s.averageMs=Math.round(1e3*(e.now()-n.start)/s.frames)/1e3,s.frames%100===0&&!a.video.paused&&o("performance",{...s,tensors:n.tensors})}n.detect=e.now(),requestAnimationFrame(f)}async function u(){var d,r,c;if(!a.video.paused){let l=e.next(e.result),w=await e.image(a.video);e.draw.canvas(w.canvas,a.canvas);let p={bodyLabels:`person confidence [score] and ${(c=(r=(d=e.result)==null?void 0:d.body)==null?void 0:r[0])==null?void 0:c.keypoints.length} keypoints`};await e.draw.all(a.canvas,l,p),g(l.performance)}let t=e.now();s.drawFPS=Math.round(1e3*1e3/(t-n.draw))/1e3,n.draw=t,i(a.video.paused?"paused":`fps: ${s.detectFPS.toFixed(1).padStart(5," ")} detect | ${s.drawFPS.toFixed(1).padStart(5," ")} draw`),setTimeout(u,30)}async function h(){let d=(await e.webcam.enumerate())[0].deviceId,r=await e.webcam.start({element:a.video,crop:!1,width:v,id:d});o(r),a.canvas.width=e.webcam.width,a.canvas.height=e.webcam.height,a.canvas.onclick=async()=>{e.webcam.paused?await e.webcam.play():e.webcam.pause()}}async function y(){o("human version:",e.version,"| tfjs version:",e.tf.version["tfjs-core"]),o("platform:",e.env.platform,"| agent:",e.env.agent),i("loading..."),await e.load(),o("backend:",e.tf.getBackend(),"| available:",e.env.backends),o("models stats:",e.models.stats()),o("models loaded:",e.models.loaded()),o("environment",e.env),i("initializing..."),await e.warmup(),await h(),await f(),await u()}window.onload=y;
+import*as i from"../../dist/human.esm.js";var m={modelBasePath:"../../models",filter:{enabled:!0,equalization:!1,flip:!1},face:{enabled:!0,detector:{rotation:!1},mesh:{enabled:!0},attention:{enabled:!1},iris:{enabled:!0},description:{enabled:!0},emotion:{enabled:!0}},body:{enabled:!0},hand:{enabled:!0},object:{enabled:!1},segmentation:{enabled:!1},gesture:{enabled:!0}},e=new i.Human(m);e.env.perfadd=!1;e.draw.options.font='small-caps 18px "Lato"';e.draw.options.lineHeight=20;var a={video:document.getElementById("video"),canvas:document.getElementById("canvas"),log:document.getElementById("log"),fps:document.getElementById("status"),perf:document.getElementById("performance")},n={detect:0,draw:0,tensors:0,start:0},s={detectFPS:0,drawFPS:0,frames:0,averageMs:0},o=(...t)=>{a.log.innerText+=t.join(" ")+`
+`,console.log(...t)},d=t=>a.fps.innerText=t,f=t=>a.perf.innerText="tensors:"+e.tf.memory().numTensors.toString()+" | performance: "+JSON.stringify(t).replace(/"|{|}/g,"").replace(/,/g," | ");async function l(){if(!a.video.paused){n.start===0&&(n.start=e.now()),await e.detect(a.video);let t=e.tf.memory().numTensors;t-n.tensors!==0&&o("allocated tensors:",t-n.tensors),n.tensors=t,s.detectFPS=Math.round(1e3*1e3/(e.now()-n.detect))/1e3,s.frames++,s.averageMs=Math.round(1e3*(e.now()-n.start)/s.frames)/1e3,s.frames%100===0&&!a.video.paused&&o("performance",{...s,tensors:n.tensors})}n.detect=e.now(),requestAnimationFrame(l)}async function c(){if(!a.video.paused){let r=e.next(e.result);e.config.filter.flip?e.draw.canvas(r.canvas,a.canvas):e.draw.canvas(a.video,a.canvas),await e.draw.all(a.canvas,r),f(r.performance)}let t=e.now();s.drawFPS=Math.round(1e3*1e3/(t-n.draw))/1e3,n.draw=t,d(a.video.paused?"paused":`fps: ${s.detectFPS.toFixed(1).padStart(5," ")} detect | ${s.drawFPS.toFixed(1).padStart(5," ")} draw`),setTimeout(c,30)}async function u(){await e.webcam.start({element:a.video,crop:!0}),a.canvas.width=e.webcam.width,a.canvas.height=e.webcam.height,a.canvas.onclick=async()=>{e.webcam.paused?await e.webcam.play():e.webcam.pause()}}async function w(){o("human version:",e.version,"| tfjs version:",e.tf.version["tfjs-core"]),o("platform:",e.env.platform,"| agent:",e.env.agent),d("loading..."),await e.load(),o("backend:",e.tf.getBackend(),"| available:",e.env.backends),o("models stats:",e.getModelStats()),o("models loaded:",Object.values(e.models).filter(t=>t!==null).length),d("initializing..."),await e.warmup(),await u(),await l(),await c()}window.onload=w;
 //# sourceMappingURL=index.js.map

demo/typescript/index.ts

@@ -9,20 +9,12 @@
 
 import * as H from '../../dist/human.esm.js'; // equivalent of @vladmandic/Human
 
-const width = 1920; // used by webcam config as well as human maximum resultion // can be anything, but resolutions higher than 4k will disable internal optimizations
-
 const humanConfig: Partial<H.Config> = { // user configuration for human, used to fine-tune behavior
-  debug: true,
-  backend: 'webgl',
-  // cacheSensitivity: 0,
-  // cacheModels: false,
-  // warmup: 'none',
-  // modelBasePath: '../../models',
-  modelBasePath: 'https://vladmandic.github.io/human-models/models/',
+  modelBasePath: '../../models',
   filter: { enabled: true, equalization: false, flip: false },
-  face: { enabled: true, detector: { rotation: false }, mesh: { enabled: true }, attention: { enabled: false }, iris: { enabled: true }, description: { enabled: true }, emotion: { enabled: true }, antispoof: { enabled: true }, liveness: { enabled: true } },
-  body: { enabled: false },
-  hand: { enabled: false },
+  face: { enabled: true, detector: { rotation: false }, mesh: { enabled: true }, attention: { enabled: false }, iris: { enabled: true }, description: { enabled: true }, emotion: { enabled: true } },
+  body: { enabled: true },
+  hand: { enabled: true },
   object: { enabled: false },
   segmentation: { enabled: false },
   gesture: { enabled: true },
@@ -33,7 +25,6 @@ const human = new H.Human(humanConfig); // create instance of human with overrid
 human.env.perfadd = false; // is performance data showing instant or total values
 human.draw.options.font = 'small-caps 18px "Lato"'; // set font used to draw labels when using draw methods
 human.draw.options.lineHeight = 20;
-human.draw.options.drawPoints = true; // draw points on face mesh
 // human.draw.options.fillPolygons = true;
 
 const dom = { // grab instances of dom objects so we dont have to look them up later
@@ -51,7 +42,7 @@ const log = (...msg) => { // helper method to output messages
   console.log(...msg); // eslint-disable-line no-console
 };
 const status = (msg) => dom.fps.innerText = msg; // print status element
-const perf = (msg) => dom.perf.innerText = 'tensors:' + human.tf.memory().numTensors.toString() + ' | performance: ' + JSON.stringify(msg).replace(/"|{|}/g, '').replace(/,/g, ' | '); // print performance element
+const perf = (msg) => dom.perf.innerText = 'tensors:' + (human.tf.memory().numTensors as number).toString() + ' | performance: ' + JSON.stringify(msg).replace(/"|{|}/g, '').replace(/,/g, ' | '); // print performance element
 
 async function detectionLoop() { // main detection loop
   if (!dom.video.paused) {
@@ -73,11 +64,9 @@ async function detectionLoop() { // main detection loop
 async function drawLoop() { // main screen refresh loop
   if (!dom.video.paused) {
     const interpolated = human.next(human.result); // smoothen result using last-known results
-    const processed = await human.image(dom.video); // get current video frame, but enhanced with human.filters
-    human.draw.canvas(processed.canvas as HTMLCanvasElement, dom.canvas);
-
-    const opt: Partial<H.DrawOptions> = { bodyLabels: `person confidence [score] and ${human.result?.body?.[0]?.keypoints.length} keypoints` };
-    await human.draw.all(dom.canvas, interpolated, opt); // draw labels, boxes, lines, etc.
+    if (human.config.filter.flip) human.draw.canvas(interpolated.canvas as HTMLCanvasElement, dom.canvas); // draw processed image to screen canvas
+    else human.draw.canvas(dom.video, dom.canvas); // draw original video to screen canvas // better than using procesed image as this loop happens faster than processing loop
+    await human.draw.all(dom.canvas, interpolated); // draw labels, boxes, lines, etc.
     perf(interpolated.performance); // write performance data
   }
   const now = human.now();
@@ -88,10 +77,7 @@ async function drawLoop() { // main screen refresh loop
 }
 
 async function webCam() {
-  const devices = await human.webcam.enumerate();
-  const id = devices[0].deviceId; // use first available video source
-  const webcamStatus = await human.webcam.start({ element: dom.video, crop: false, width, id }); // use human webcam helper methods and associate webcam stream with a dom element
-  log(webcamStatus);
+  await human.webcam.start({ element: dom.video, crop: true }); // use human webcam helper methods and associate webcam stream with a dom element
   dom.canvas.width = human.webcam.width;
   dom.canvas.height = human.webcam.height;
   dom.canvas.onclick = async () => { // pause when clicked on screen and resume on next click
@@ -106,9 +92,8 @@ async function main() { // main entry point
   status('loading...');
   await human.load(); // preload all models
   log('backend:', human.tf.getBackend(), '| available:', human.env.backends);
-  log('models stats:', human.models.stats());
-  log('models loaded:', human.models.loaded());
-  log('environment', human.env);
+  log('models stats:', human.getModelStats());
+  log('models loaded:', Object.values(human.models).filter((model) => model !== null).length);
   status('initializing...');
   await human.warmup(); // warmup function to initialize backend for future faster detection
   await webCam(); // start webcam

dist/tfjs.version.js

@@ -4,4 +4,4 @@
   author: <https://github.com/vladmandic>'
 */
 
-var e="4.22.0";var s="4.22.0";var t="4.22.0";var n="4.22.0";var r="4.22.0";var i="4.22.0";var h={tfjs:e,"tfjs-core":e,"tfjs-converter":s,"tfjs-backend-cpu":t,"tfjs-backend-webgl":n,"tfjs-backend-wasm":r,"tfjs-backend-webgpu":i};export{h as version};
+var e="3.21.0";var s="3.21.0";var t="3.21.0";var i="3.21.0";var n="3.21.0";var r="3.21.0";var l="3.21.0";var V={tfjs:e,"tfjs-core":s,"tfjs-data":t,"tfjs-layers":i,"tfjs-converter":n,"tfjs-backend-webgl":r,"tfjs-backend-wasm":l};export{V as version};

models/models.json

@@ -1,38 +1,37 @@
 {
   "antispoof": 853098,
   "blazeface": 538928,
-  "centernet": 4030290,
   "emotion": 820516,
   "facemesh": 1477958,
   "faceres": 6978814,
-  "handlandmark-lite": 2023432,
+  "handlandmark-full": 5431368,
   "handtrack": 2964837,
   "iris": 2599092,
   "liveness": 592976,
+  "mb3-centernet": 4030290,
   "models": 0,
   "movenet-lightning": 4650216,
-  "affectnet-mobilenet": 6920630,
   "age": 161240,
   "blazeface-back": 538928,
   "blazeface-front": 402048,
-  "blazepose-detector": 5928856,
-  "blazepose-full": 6339202,
-  "blazepose-heavy": 27502466,
-  "blazepose-lite": 2726402,
+  "blazepose-detector2d": 7499400,
+  "blazepose-detector3d": 5928856,
+  "blazepose-full": 6338290,
+  "blazepose-heavy": 27501554,
+  "blazepose-lite": 2725490,
   "efficientpose": 5651240,
   "faceboxes": 2013002,
-  "facemesh-attention-pinto": 2387598,
+  "facemesh-attention-alt": 2387598,
   "facemesh-attention": 2382414,
   "facemesh-detection-full": 1026192,
   "facemesh-detection-short": 201268,
+  "facemesh-orig": 2955780,
   "faceres-deep": 13957620,
-  "gear-e1": 112438,
-  "gear-e2": 112438,
   "gear": 1498916,
   "gender-ssrnet-imdb": 161236,
   "gender": 201808,
   "handdetect": 3515612,
-  "handlandmark-full": 5431368,
+  "handlandmark-lite": 2023432,
   "handlandmark-sparse": 5286322,
   "handskeleton": 5502280,
   "meet": 372228,
@@ -44,6 +43,7 @@
   "posenet": 5032780,
   "rvm": 3739355,
   "selfie": 212886,
+  "blazepose-detect": 5928804,
   "anti-spoofing": 853098,
   "efficientpose-i-lite": 2269064,
   "efficientpose-ii-lite": 5651240,

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@vladmandic/human",
-  "version": "3.3.6",
+  "version": "2.11.1",
   "description": "Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gesture Recognition",
   "sideEffects": false,
   "main": "dist/human.node.js",
@@ -8,24 +8,16 @@
   "browser": "dist/human.esm.js",
   "types": "types/human.d.ts",
   "exports": {
-    "node": "./dist/human.node.js",
+    "node": {
+      "require": "./dist/human.node.js",
+      "import": "./dist/human.node.js",
+      "module": "./dist/human.node.js"
+    },
+    "require": "./dist/human.node.js",
+    "import": "./dist/human.esm.js",
     "script": "./dist/human.js",
     "module": "./dist/human.esm.js",
-    "types": "./types/human.d.ts",
-    "dist/human": "./dist/human.js",
-    "dist/human.js": "./dist/human.js",
-    "dist/human.esm": "./dist/human.esm.js",
-    "dist/human.esm.js": "./dist/human.esm.js",
-    "dist/human.esm-nobundle": "./dist/human.esm-nobundle.js",
-    "dist/human.esm-nobundle.js": "./dist/human.esm-nobundle.js",
-    "dist/human.node": "./dist/human.node.js",
-    "dist/human.node.js": "./dist/human.node.js",
-    "dist/human.node-wasm": "./dist/human.node-wasm.js",
-    "dist/human.node-wasm.js": "./dist/human.node-wasm.js",
-    "dist/human.node-gpu": "./dist/human.node-gpu.js",
-    "dist/human.node-gpu.js": "./dist/human.node-gpu.js",
-    "require": "./dist/human.node.js",
-    "import": "./dist/human.esm.js"
+    "types": "./types/human.d.ts"
   },
   "author": "Vladimir Mandic <mandic00@live.com>",
   "bugs": {
@@ -46,7 +38,7 @@
     "clean": "build --profile clean",
     "build": "rimraf test/build.log && node build.js",
     "test": "node --no-warnings --unhandled-rejections=strict --trace-uncaught test/node.js",
-    "lint": "eslint *.json *.js src demo test models wiki",
+    "lint": "eslint *.json *.js src demo test models",
     "scan": "npx auditjs@latest ossi --dev --quiet"
   },
   "keywords": [
@@ -74,40 +66,45 @@
     "tensorflow"
   ],
   "devDependencies": {
-    "@html-eslint/eslint-plugin": "^0.46.1",
-    "@html-eslint/parser": "^0.46.0",
-    "@microsoft/api-extractor": "^7.52.11",
-    "@tensorflow/tfjs-backend-cpu": "^4.22.0",
-    "@tensorflow/tfjs-backend-wasm": "^4.22.0",
-    "@tensorflow/tfjs-backend-webgl": "^4.22.0",
-    "@tensorflow/tfjs-backend-webgpu": "4.22.0",
-    "@tensorflow/tfjs-converter": "^4.22.0",
-    "@tensorflow/tfjs-core": "^4.22.0",
-    "@tensorflow/tfjs-data": "^4.22.0",
-    "@tensorflow/tfjs-layers": "^4.22.0",
-    "@tensorflow/tfjs-node": "^4.22.0",
-    "@tensorflow/tfjs-node-gpu": "^4.22.0",
-    "@types/emscripten": "^1.40.1",
-    "@types/node": "^24.3.0",
-    "@types/offscreencanvas": "^2019.7.3",
-    "@typescript-eslint/eslint-plugin": "^8.41.0",
-    "@typescript-eslint/parser": "^8.41.0",
-    "@vladmandic/build": "^0.10.3",
-    "@vladmandic/pilogger": "^0.5.2",
+    "@html-eslint/eslint-plugin": "^0.15.0",
+    "@html-eslint/parser": "^0.15.0",
+    "@microsoft/api-extractor": "^7.32.0",
+    "@tensorflow/tfjs": "^3.21.0",
+    "@tensorflow/tfjs-backend-cpu": "^3.21.0",
+    "@tensorflow/tfjs-backend-wasm": "^3.21.0",
+    "@tensorflow/tfjs-backend-webgl": "^3.21.0",
+    "@tensorflow/tfjs-backend-webgpu": "0.0.1-alpha.14",
+    "@tensorflow/tfjs-converter": "^3.21.0",
+    "@tensorflow/tfjs-core": "^3.21.0",
+    "@tensorflow/tfjs-data": "^3.21.0",
+    "@tensorflow/tfjs-layers": "^3.21.0",
+    "@tensorflow/tfjs-node": "^3.21.1",
+    "@tensorflow/tfjs-node-gpu": "^3.21.0",
+    "@tensorflow/tfjs-tflite": "0.0.1-alpha.9",
+    "@types/emscripten": "^1.39.6",
+    "@types/node": "^18.8.3",
+    "@types/offscreencanvas": "^2019.7.0",
+    "@typescript-eslint/eslint-plugin": "^5.39.0",
+    "@typescript-eslint/parser": "^5.39.0",
+    "@vladmandic/build": "^0.7.14",
+    "@vladmandic/pilogger": "^0.4.6",
     "@vladmandic/tfjs": "github:vladmandic/tfjs",
-    "canvas": "^3.2.0",
-    "esbuild": "^0.25.9",
-    "eslint": "8.57.0",
+    "@webgpu/types": "^0.1.22",
+    "canvas": "^2.10.1",
+    "esbuild": "^0.15.10",
+    "eslint": "8.25.0",
     "eslint-config-airbnb-base": "^15.0.0",
-    "eslint-plugin-html": "^8.1.3",
-    "eslint-plugin-import": "^2.32.0",
-    "eslint-plugin-json": "^4.0.1",
-    "eslint-plugin-markdown": "^5.1.0",
+    "eslint-plugin-html": "^7.1.0",
+    "eslint-plugin-import": "^2.26.0",
+    "eslint-plugin-json": "^3.1.0",
     "eslint-plugin-node": "^11.1.0",
-    "eslint-plugin-promise": "^7.2.1",
-    "rimraf": "^6.0.1",
-    "tslib": "^2.8.1",
-    "typedoc": "0.28.11",
-    "typescript": "5.9.2"
+    "eslint-plugin-promise": "^6.0.1",
+    "long": "^5.2.0",
+    "node-fetch": "^3.2.10",
+    "rimraf": "^3.0.2",
+    "seedrandom": "^3.0.5",
+    "tslib": "^2.4.0",
+    "typedoc": "0.23.15",
+    "typescript": "4.8.4"
   }
 }

src/body/blazepose.ts

@@ -2,47 +2,64 @@
  * BlazePose model implementation
  */
 
-import * as tf from 'dist/tfjs.esm.js';
+import * as tf from '../../dist/tfjs.esm.js';
 import { loadModel } from '../tfjs/load';
 import { constants } from '../tfjs/constants';
 import { log, now } from '../util/util';
 import type { BodyKeypoint, BodyResult, BodyLandmark, Box, Point, BodyAnnotation } from '../result';
-import type { GraphModel, Tensor, Tensor4D } from '../tfjs/types';
+import type { GraphModel, Tensor } from '../tfjs/types';
 import type { Config } from '../config';
 import * as coords from './blazeposecoords';
-import { loadDetector, detectBoxes, DetectedBox } from './blazeposedetector';
+import * as detect from './blazeposedetector';
 import * as box from '../util/box';
-import { env } from '../util/env';
 
+const env = { initial: true };
 // const models: [GraphModel | null, GraphModel | null] = [null, null];
-let model: GraphModel | null;
-let inputSize = 256;
+const models: { detector: GraphModel | null, landmarks: GraphModel | null } = { detector: null, landmarks: null };
+const inputSize: { detector: [number, number], landmarks: [number, number] } = { detector: [224, 224], landmarks: [256, 256] };
 let skipped = Number.MAX_SAFE_INTEGER;
 const outputNodes: { detector: string[], landmarks: string[] } = {
   landmarks: ['ld_3d', 'activation_segmentation', 'activation_heatmap', 'world_3d', 'output_poseflag'],
   detector: [],
 };
 
-const cache: BodyResult[] = [];
+let cache: BodyResult | null = null;
+let cropBox: Box | undefined;
 let padding: [number, number][] = [[0, 0], [0, 0], [0, 0], [0, 0]];
 let lastTime = 0;
 
 const sigmoid = (x) => (1 - (1 / (1 + Math.exp(x))));
 
-export const loadDetect = (config: Config): Promise<GraphModel> => loadDetector(config);
-
-export async function loadPose(config: Config): Promise<GraphModel> {
-  if (env.initial) model = null;
-  if (!model) {
-    model = await loadModel(config.body.modelPath);
-    const inputs = model?.['executor'] ? Object.values(model.modelSignature['inputs']) : undefined;
-    // @ts-ignore model signature properties are not typed and inputs are unreliable for this model
-    inputSize = Array.isArray(inputs) ? parseInt(inputs[0].tensorShape.dim[1].size) : 0;
-  } else if (config.debug) log('cached model:', model['modelUrl']);
-  return model;
+export async function loadDetect(config: Config): Promise<GraphModel> {
+  if (env.initial) models.detector = null;
+  if (!models.detector && config.body['detector'] && config.body['detector'].modelPath || '') {
+    models.detector = await loadModel(config.body['detector'].modelPath);
+    const inputs = models.detector?.['executor'] ? Object.values(models.detector.modelSignature['inputs']) : undefined;
+    inputSize.detector[0] = Array.isArray(inputs) ? parseInt(inputs[0].tensorShape.dim[1].size) : 0;
+    inputSize.detector[1] = Array.isArray(inputs) ? parseInt(inputs[0].tensorShape.dim[2].size) : 0;
+  } else if (config.debug && models.detector) log('cached model:', models.detector['modelUrl']);
+  detect.createAnchors();
+  return models.detector as GraphModel;
 }
 
-function prepareImage(input: Tensor4D, size: number, cropBox?: Box): Tensor {
+export async function loadPose(config: Config): Promise<GraphModel> {
+  if (env.initial) models.landmarks = null;
+  if (!models.landmarks) {
+    models.landmarks = await loadModel(config.body.modelPath);
+    const inputs = models.landmarks?.['executor'] ? Object.values(models.landmarks.modelSignature['inputs']) : undefined;
+    inputSize.landmarks[0] = Array.isArray(inputs) ? parseInt(inputs[0].tensorShape.dim[1].size) : 0;
+    inputSize.landmarks[1] = Array.isArray(inputs) ? parseInt(inputs[0].tensorShape.dim[2].size) : 0;
+  } else if (config.debug) log('cached model:', models.landmarks['modelUrl']);
+  return models.landmarks;
+}
+
+export async function load(config: Config): Promise<[GraphModel | null, GraphModel | null]> {
+  if (!models.detector) await loadDetect(config);
+  if (!models.landmarks) await loadPose(config);
+  return [models.detector, models.landmarks];
+}
+
+function prepareImage(input: Tensor, size: number): Tensor {
   const t: Record<string, Tensor> = {};
   if (!input?.shape?.[1] || !input?.shape?.[2]) return input;
   let final: Tensor;
@@ -65,10 +82,10 @@ function prepareImage(input: Tensor4D, size: number, cropBox?: Box): Tensor {
       [0, 0], // dont touch rbg
     ];
     t.pad = tf.pad(t.cropped || input, padding); // use cropped box if it exists
-    t.resize = tf.image.resizeBilinear(t.pad as Tensor4D, [size, size]);
+    t.resize = tf.image.resizeBilinear(t.pad, [size, size]);
     final = tf.div(t.resize, constants.tf255);
   } else if (input.shape[1] !== size) { // if input needs resizing
-    t.resize = tf.image.resizeBilinear(t.cropped as Tensor4D || input, [size, size]);
+    t.resize = tf.image.resizeBilinear(t.cropped || input, [size, size]);
     final = tf.div(t.resize, constants.tf255);
   } else { // if input is already in a correct resolution just normalize it
     final = tf.div(t.cropped || input, constants.tf255);
@@ -77,7 +94,7 @@ function prepareImage(input: Tensor4D, size: number, cropBox?: Box): Tensor {
   return final;
 }
 
-function rescaleKeypoints(keypoints: BodyKeypoint[], outputSize: [number, number], cropBox?: Box): BodyKeypoint[] {
+function rescaleKeypoints(keypoints: BodyKeypoint[], outputSize: [number, number]): BodyKeypoint[] {
   for (const kpt of keypoints) { // first rescale due to padding
     kpt.position = [
       Math.trunc(kpt.position[0] * (outputSize[0] + padding[2][0] + padding[2][1]) / outputSize[0] - padding[2][0]),
@@ -87,12 +104,10 @@ function rescaleKeypoints(keypoints: BodyKeypoint[], outputSize: [number, number
     kpt.positionRaw = [kpt.position[0] / outputSize[0], kpt.position[1] / outputSize[1], 2 * (kpt.position[2] as number) / (outputSize[0] + outputSize[1])];
   }
   if (cropBox) { // second rescale due to cropping
-    const width = cropBox[2] - cropBox[0];
-    const height = cropBox[3] - cropBox[1];
     for (const kpt of keypoints) {
       kpt.positionRaw = [
-        kpt.positionRaw[0] / height + cropBox[1], // correct offset due to crop
-        kpt.positionRaw[1] / width + cropBox[0], // correct offset due to crop
+        kpt.positionRaw[0] + cropBox[1], // correct offset due to crop
+        kpt.positionRaw[1] + cropBox[0], // correct offset due to crop
         kpt.positionRaw[2] as number,
       ];
       kpt.position = [
@@ -125,9 +140,9 @@ async function detectLandmarks(input: Tensor, config: Config, outputSize: [numbe
    * t.world: 39 keypoints [x,y,z] normalized to -1..1
    * t.poseflag: body score
   */
-  if (!model?.['executor']) return null;
+  if (!models.landmarks?.['executor']) return null;
   const t: Record<string, Tensor> = {};
-  [t.ld/* 1,195(39*5) */, t.segmentation/* 1,256,256,1 */, t.heatmap/* 1,64,64,39 */, t.world/* 1,117(39*3) */, t.poseflag/* 1,1 */] = model?.execute(input, outputNodes.landmarks) as Tensor[]; // run model
+  [t.ld/* 1,195(39*5) */, t.segmentation/* 1,256,256,1 */, t.heatmap/* 1,64,64,39 */, t.world/* 1,117(39*3) */, t.poseflag/* 1,1 */] = models.landmarks?.execute(input, outputNodes.landmarks) as Tensor[]; // run model
   const poseScore = (await t.poseflag.data())[0];
   const points = await t.ld.data();
   const distances = await t.world.data();
@@ -138,7 +153,7 @@ async function detectLandmarks(input: Tensor, config: Config, outputSize: [numbe
     const score = sigmoid(points[depth * i + 3]);
     const presence = sigmoid(points[depth * i + 4]);
     const adjScore = Math.trunc(100 * score * presence * poseScore) / 100;
-    const positionRaw: Point = [points[depth * i + 0] / inputSize, points[depth * i + 1] / inputSize, points[depth * i + 2] + 0];
+    const positionRaw: Point = [points[depth * i + 0] / inputSize.landmarks[0], points[depth * i + 1] / inputSize.landmarks[1], points[depth * i + 2] + 0];
     const position: Point = [Math.trunc(outputSize[0] * positionRaw[0]), Math.trunc(outputSize[1] * positionRaw[1]), positionRaw[2] as number];
     const distance: Point = [distances[depth * i + 0], distances[depth * i + 1], distances[depth * i + 2] + 0];
     keypointsRelative.push({ part: coords.kpt[i] as BodyLandmark, positionRaw, position, distance, score: adjScore });
@@ -162,31 +177,52 @@ async function detectLandmarks(input: Tensor, config: Config, outputSize: [numbe
   return body;
 }
 
-export async function predict(input: Tensor4D, config: Config): Promise<BodyResult[]> {
+/*
+interface DetectedBox { box: Box, boxRaw: Box, score: number }
+
+function rescaleBoxes(boxes: Array<DetectedBox>, outputSize: [number, number]): Array<DetectedBox> {
+  for (const b of boxes) {
+    b.box = [
+      Math.trunc(b.box[0] * (outputSize[0] + padding[2][0] + padding[2][1]) / outputSize[0]),
+      Math.trunc(b.box[1] * (outputSize[1] + padding[1][0] + padding[1][1]) / outputSize[1]),
+      Math.trunc(b.box[2] * (outputSize[0] + padding[2][0] + padding[2][1]) / outputSize[0]),
+      Math.trunc(b.box[3] * (outputSize[1] + padding[1][0] + padding[1][1]) / outputSize[1]),
+    ];
+    b.boxRaw = [b.box[0] / outputSize[0], b.box[1] / outputSize[1], b.box[2] / outputSize[0], b.box[3] / outputSize[1]];
+  }
+  return boxes;
+}
+
+async function detectBoxes(input: Tensor, config: Config, outputSize: [number, number]) {
+  const t: Record<string, Tensor> = {};
+  t.res = models.detector?.execute(input, ['Identity']) as Tensor; //
+  t.logitsRaw = tf.slice(t.res, [0, 0, 0], [1, -1, 1]);
+  t.boxesRaw = tf.slice(t.res, [0, 0, 1], [1, -1, -1]);
+  t.logits = tf.squeeze(t.logitsRaw);
+  t.boxes = tf.squeeze(t.boxesRaw);
+  const boxes = await detect.decode(t.boxes, t.logits, config, outputSize);
+  rescaleBoxes(boxes, outputSize);
+  Object.keys(t).forEach((tensor) => tf.dispose(t[tensor]));
+  return boxes;
+}
+*/
+
+export async function predict(input: Tensor, config: Config): Promise<BodyResult[]> {
   const outputSize: [number, number] = [input.shape[2] || 0, input.shape[1] || 0];
   const skipTime = (config.body.skipTime || 0) > (now() - lastTime);
   const skipFrame = skipped < (config.body.skipFrames || 0);
   if (config.skipAllowed && skipTime && skipFrame && cache !== null) {
     skipped++;
   } else {
-    let boxes: DetectedBox[] = [];
-    if (config.body?.['detector']?.['enabled']) {
-      const preparedImage = prepareImage(input, 224);
-      boxes = await detectBoxes(preparedImage, config, outputSize);
-      tf.dispose(preparedImage);
-    } else {
-      boxes = [{ box: [0, 0, 0, 0] as Box, boxRaw: [0, 0, 1, 1], score: 0 }]; // running without detector
-    }
-    for (let i = 0; i < boxes.length; i++) {
-      const preparedBox = prepareImage(input, 256, boxes[i]?.boxRaw); // padded and resized
-      cache.length = 0;
-      const bodyResult = await detectLandmarks(preparedBox, config, outputSize);
-      tf.dispose(preparedBox);
-      if (!bodyResult) continue;
-      bodyResult.id = i;
-      // bodyResult.score = 0; // TBD
-      cache.push(bodyResult);
+    const t: Record<string, Tensor> = {};
+    /*
+    if (config.body['detector'] && config.body['detector']['enabled']) {
+      t.detector = await prepareImage(input, 224);
+      const boxes = await detectBoxes(t.detector, config, outputSize);
     }
+    */
+    t.landmarks = prepareImage(input, 256); // padded and resized
+    cache = await detectLandmarks(t.landmarks, config, outputSize);
     /*
     cropBox = [0, 0, 1, 1]; // reset crop coordinates
     if (cache?.boxRaw && config.skipAllowed) {
@@ -201,8 +237,9 @@ export async function predict(input: Tensor4D, config: Config): Promise<BodyResu
       }
     }
     */
+    Object.keys(t).forEach((tensor) => tf.dispose(t[tensor]));
     lastTime = now();
     skipped = 0;
   }
-  return cache;
+  return cache ? [cache] : [];
 }

src/body/blazeposedetector.ts

@@ -1,15 +1,11 @@
-import * as tf from 'dist/tfjs.esm.js';
-import { log } from '../util/util';
-import { env } from '../util/env';
-import { loadModel } from '../tfjs/load';
+import * as tf from '../../dist/tfjs.esm.js';
+import type { Tensor } from '../tfjs/types';
 import type { Box } from '../result';
 import type { Config } from '../config';
-import type { GraphModel, Tensor, Tensor1D, Tensor2D } from '../tfjs/types';
 
-export interface DetectedBox { box: Box, boxRaw: Box, score: number }
+interface DetectedBox { box: Box, boxRaw: Box, score: number }
 
-let model: GraphModel | null;
-let inputSize = 224;
+const inputSize = 224;
 let anchorTensor: { x, y };
 const numLayers = 5;
 const strides = [8, 16, 32, 32, 32];
@@ -39,20 +35,8 @@ export function createAnchors() {
   anchorTensor = { x: tf.tensor1d(anchors.map((a) => a.x)), y: tf.tensor1d(anchors.map((a) => a.y)) };
 }
 
-export async function loadDetector(config: Config): Promise<GraphModel> {
-  if (env.initial) model = null;
-  if (!model && config.body['detector'] && config.body['detector'].modelPath || '') {
-    model = await loadModel(config.body['detector'].modelPath);
-    const inputs = model?.['executor'] ? Object.values(model.modelSignature['inputs']) : undefined;
-    // @ts-ignore model signature properties are not typed and inputs are unreliable for this model
-    inputSize = Array.isArray(inputs) ? parseInt(inputs[0].tensorShape.dim[1].size) : 0;
-  } else if (config.debug && model) log('cached model:', model['modelUrl']);
-  createAnchors();
-  return model as GraphModel;
-}
-
 const cropFactor = [5.0, 5.0];
-export function decodeBoxes(boxesTensor, anchor) {
+function decodeBoxes(boxesTensor, anchor): Tensor {
   return tf.tidy(() => {
     const split = tf.split(boxesTensor, 12, 1); // first 4 are box data [x,y,w,h] and 4 are keypoints data [x,y] for total of 12
     let xCenter = tf.squeeze(split[0]);
@@ -65,41 +49,39 @@ export function decodeBoxes(boxesTensor, anchor) {
     height = tf.mul(tf.div(height, inputSize), cropFactor[1]);
     const xMin = tf.sub(xCenter, tf.div(width, 2));
     const yMin = tf.sub(yCenter, tf.div(height, 2));
-    const xMax = tf.add(xMin, width);
-    const yMax = tf.add(yMin, height);
-    const boxes = tf.stack([xMin, yMin, xMax, yMax], 1);
+    const boxes = tf.stack([xMin, yMin, width, height], 1);
     return boxes;
   });
 }
 
-async function decodeResults(boxesTensor: Tensor, logitsTensor: Tensor, config: Config, outputSize: [number, number]): Promise<DetectedBox[]> {
-  const detectedBoxes: DetectedBox[] = [];
+export async function decode(boxesTensor: Tensor, logitsTensor: Tensor, config: Config, outputSize: [number, number]): Promise<DetectedBox[]> {
   const t: Record<string, Tensor> = {};
   t.boxes = decodeBoxes(boxesTensor, anchorTensor);
   t.scores = tf.sigmoid(logitsTensor);
-  t.nms = await tf.image.nonMaxSuppressionAsync(t.boxes as Tensor2D, t.scores as Tensor1D, 1, config.body['detector']?.minConfidence || 0.1, config.body['detector']?.iouThreshold || 0.1);
-  const nms = await t.nms.data();
+  t.argmax = tf.argMax(t.scores);
+  const i = (await t.argmax.data())[0];
   const scores = await t.scores.data();
+  const detected: { box: Box, boxRaw: Box, score: number }[] = [];
+  const minScore = config.body?.['detector']?.minConfidence || 0;
+  if (scores[i] >= minScore) {
     const boxes = await t.boxes.array();
-  for (const i of Array.from(nms)) {
-    const score = scores[i];
     const boxRaw: Box = boxes[i];
-    const box: Box = [Math.round(boxRaw[0] * outputSize[0]), Math.round(boxRaw[1] * outputSize[1]), Math.round(boxRaw[2] * outputSize[0]), Math.round(boxRaw[3] * outputSize[1])];
-    const detectedBox: DetectedBox = { score, boxRaw, box };
-    detectedBoxes.push(detectedBox);
+    const box: Box = [boxRaw[0] * outputSize[0], boxRaw[1] * outputSize[1], boxRaw[2] * outputSize[0], boxRaw[3] * outputSize[1]];
+    // console.log(box);
+    detected.push({ box, boxRaw, score: scores[i] });
   }
+  /*
+  t.nms = await tf.image.nonMaxSuppressionAsync(t.boxes, t.scores, 1, config.body.detector?.minConfidence || 0.1, config.body.detector?.iouThreshold || 0.1);
+  const boxes = t.boxes.arraySync();
+  const scores = t.scores.dataSync();
+  const nms = t.nms.dataSync();
+  const detected: Array<DetectedBox> = [];
+  for (const i of Array.from(nms)) {
+    const boxRaw: Box = boxes[i];
+    const box: Box = [boxRaw[0] * outputSize[0], boxRaw[0] * outputSize[1], boxRaw[3] * outputSize[0], boxRaw[2] * outputSize[1]];
+    detected.push({ box, boxRaw, score: scores[i] });
+  }
+  */
   Object.keys(t).forEach((tensor) => tf.dispose(t[tensor]));
-  return detectedBoxes;
-}
-
-export async function detectBoxes(input: Tensor, config: Config, outputSize: [number, number]) {
-  const t: Record<string, Tensor> = {};
-  t.res = model?.execute(input, ['Identity']) as Tensor; //
-  t.logitsRaw = tf.slice(t.res, [0, 0, 0], [1, -1, 1]);
-  t.boxesRaw = tf.slice(t.res, [0, 0, 1], [1, -1, -1]);
-  t.logits = tf.squeeze(t.logitsRaw);
-  t.boxes = tf.squeeze(t.boxesRaw);
-  const boxes = await decodeResults(t.boxes, t.logits, config, outputSize);
-  Object.keys(t).forEach((tensor) => tf.dispose(t[tensor]));
-  return boxes;
+  return detected;
 }

src/body/efficientpose.ts

@@ -4,13 +4,13 @@
  * Based on: [**EfficientPose**](https://github.com/daniegr/EfficientPose)
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log, now } from '../util/util';
+import * as tf from '../../dist/tfjs.esm.js';
 import { loadModel } from '../tfjs/load';
 import * as coords from './efficientposecoords';
 import { constants } from '../tfjs/constants';
 import type { BodyResult, Point, BodyLandmark, BodyAnnotation } from '../result';
-import type { GraphModel, Tensor4D } from '../tfjs/types';
+import type { GraphModel, Tensor } from '../tfjs/types';
 import type { Config } from '../config';
 import { env } from '../util/env';
 
@@ -50,8 +50,8 @@ async function max2d(inputs, minScore): Promise<[number, number, number]> {
   return [0, 0, newScore];
 }
 
-export async function predict(image: Tensor4D, config: Config): Promise<BodyResult[]> {
-  if (!model?.['executor'] || !model?.inputs[0].shape) return [];
+export async function predict(image: Tensor, config: Config): Promise<BodyResult[]> {
+  if (!model?.['executor']) return [];
   const skipTime = (config.body.skipTime || 0) > (now() - lastTime);
   const skipFrame = skipped < (config.body.skipFrames || 0);
   if (config.skipAllowed && skipTime && skipFrame && Object.keys(cache.keypoints).length > 0) {
@@ -61,7 +61,8 @@ export async function predict(image: Tensor4D, config: Config): Promise<BodyResu
   skipped = 0;
   return new Promise(async (resolve) => {
     const tensor = tf.tidy(() => {
-      const resize = tf.image.resizeBilinear(image, [model?.inputs[0].shape?.[2] || 0, model?.inputs[0].shape?.[1] || 0], false);
+      if (!model?.inputs[0].shape) return null;
+      const resize = tf.image.resizeBilinear(image, [model.inputs[0].shape[2], model.inputs[0].shape[1]], false);
       const enhance = tf.mul(resize, constants.tf2);
       const norm = tf.sub(enhance, constants.tf1);
       return norm;

src/body/movenet.ts

@@ -4,9 +4,9 @@
  * Based on: [**MoveNet**](https://blog.tensorflow.org/2021/05/next-generation-pose-detection-with-movenet-and-tensorflowjs.html)
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log, now } from '../util/util';
 import * as box from '../util/box';
+import * as tf from '../../dist/tfjs.esm.js';
 import * as coords from './movenetcoords';
 import * as fix from './movenetfix';
 import { loadModel } from '../tfjs/load';
@@ -39,8 +39,6 @@ export async function load(config: Config): Promise<GraphModel> {
   } else if (config.debug) log('cached model:', model['modelUrl']);
   inputSize = (model?.['executor'] && model?.inputs?.[0].shape) ? model.inputs[0].shape[2] : 0;
   if (inputSize < 64) inputSize = 256;
-  // @ts-ignore private property
-  if (tf.env().flagRegistry.WEBGL_USE_SHAPES_UNIFORMS) tf.env().set('WEBGL_USE_SHAPES_UNIFORMS', false); // default=false <https://github.com/tensorflow/tfjs/issues/5205>
   return model;
 }
 
@@ -86,8 +84,8 @@ function parseMultiPose(res, config, image) {
   const bodies: BodyResult[] = [];
   for (let id = 0; id < res[0].length; id++) {
     const kpt = res[0][id];
-    const boxScore = Math.round(100 * kpt[51 + 4]) / 100;
-    if (boxScore > config.body.minConfidence) {
+    const totalScore = Math.round(100 * kpt[51 + 4]) / 100;
+    if (totalScore > config.body.minConfidence) {
       const keypoints: BodyKeypoint[] = [];
       for (let i = 0; i < 17; i++) {
         const score = kpt[3 * i + 2];
@@ -101,10 +99,10 @@ function parseMultiPose(res, config, image) {
           });
         }
       }
-      // const newBox = box.calc(keypoints.map((pt) => pt.position), [image.shape[2], image.shape[1]]);
+      const newBox = box.calc(keypoints.map((pt) => pt.position), [image.shape[2], image.shape[1]]);
       // movenet-multipose has built-in box details
-      const boxRaw: Box = [kpt[51 + 1], kpt[51 + 0], kpt[51 + 3] - kpt[51 + 1], kpt[51 + 2] - kpt[51 + 0]];
-      const boxNorm: Box = [Math.trunc(boxRaw[0] * (image.shape[2] || 0)), Math.trunc(boxRaw[1] * (image.shape[1] || 0)), Math.trunc(boxRaw[2] * (image.shape[2] || 0)), Math.trunc(boxRaw[3] * (image.shape[1] || 0))];
+      // const boxRaw: Box = [kpt[51 + 1], kpt[51 + 0], kpt[51 + 3] - kpt[51 + 1], kpt[51 + 2] - kpt[51 + 0]];
+      // const box: Box = [Math.trunc(boxRaw[0] * (image.shape[2] || 0)), Math.trunc(boxRaw[1] * (image.shape[1] || 0)), Math.trunc(boxRaw[2] * (image.shape[2] || 0)), Math.trunc(boxRaw[3] * (image.shape[1] || 0))];
       const annotations: Record<BodyAnnotation, Point[][]> = {} as Record<BodyAnnotation, Point[][]>;
       for (const [name, indexes] of Object.entries(coords.connected)) {
         const pt: Point[][] = [];
@@ -115,8 +113,7 @@ function parseMultiPose(res, config, image) {
         }
         annotations[name] = pt;
       }
-      // const body: BodyResult = { id, score: totalScore, box: newBox.box, boxRaw: newBox.boxRaw, keypoints: [...keypoints], annotations };
-      const body: BodyResult = { id, score: boxScore, box: boxNorm, boxRaw, keypoints: [...keypoints], annotations };
+      const body: BodyResult = { id, score: totalScore, box: newBox.box, boxRaw: newBox.boxRaw, keypoints: [...keypoints], annotations };
       fix.bodyParts(body);
       bodies.push(body);
     }
@@ -138,6 +135,39 @@ export async function predict(input: Tensor, config: Config): Promise<BodyResult
   return new Promise(async (resolve) => {
     const t: Record<string, Tensor> = {};
     skipped = 0;
+    // run detection on squared input and cached boxes
+    /*
+    cache.bodies = []; // reset bodies result
+    if (cache.boxes.length >= (config.body.maxDetected || 0)) { // if we have enough cached boxes run detection using cache
+      for (let i = 0; i < cache.boxes.length; i++) { // run detection based on cached boxes
+        t.crop = tf.image.cropAndResize(input, [cache.boxes[i]], [0], [inputSize, inputSize], 'bilinear');
+        t.cast = tf.cast(t.crop, 'int32');
+        // t.input = prepareImage(input);
+        t.res = model?.execute(t.cast) as Tensor;
+        const res = await t.res.array();
+        const newBodies = (t.res.shape[2] === 17) ? await parseSinglePose(res, config, input, cache.boxes[i]) : await parseMultiPose(res, config, input, cache.boxes[i]);
+        cache.bodies = cache.bodies.concat(newBodies);
+        Object.keys(t).forEach((tensor) => tf.dispose(t[tensor]));
+      }
+    }
+    if (cache.bodies.length !== config.body.maxDetected) { // did not find enough bodies based on cached boxes so run detection on full frame
+      t.input = prepareImage(input);
+      t.res = model?.execute(t.input) as Tensor;
+      const res = await t.res.array();
+      cache.bodies = (t.res.shape[2] === 17) ? await parseSinglePose(res, config, input, [0, 0, 1, 1]) : await parseMultiPose(res, config, input, [0, 0, 1, 1]);
+      for (const body of cache.bodies) rescaleBody(body, [input.shape[2] || 1, input.shape[1] || 1]);
+      Object.keys(t).forEach((tensor) => tf.dispose(t[tensor]));
+    }
+    cache.boxes.length = 0; // reset cache
+    for (let i = 0; i < cache.bodies.length; i++) {
+      if (cache.bodies[i].keypoints.length > (coords.kpt.length / 2)) { // only update cache if we detected at least half keypoints
+        const scaledBox = box.scale(cache.bodies[i].boxRaw, boxExpandFact);
+        const cropBox = box.crop(scaledBox);
+        cache.boxes.push(cropBox);
+      }
+    }
+    */
+
     // run detection on squared input and no cached boxes
     t.input = fix.padInput(input, inputSize);
     t.res = model?.execute(t.input) as Tensor;

src/body/movenetfix.ts

@@ -1,8 +1,8 @@
-import * as tf from 'dist/tfjs.esm.js';
 import type { BodyKeypoint, BodyResult } from '../result';
 import * as box from '../util/box';
 import * as coords from './movenetcoords';
-import type { Tensor, Tensor3D } from '../tfjs/types';
+import * as tf from '../../dist/tfjs.esm.js';
+import type { Tensor } from '../tfjs/types';
 
 const maxJitter = 0.005; // default allowed jitter is within 0.5%
 
@@ -83,7 +83,7 @@ export function padInput(input: Tensor, inputSize: number): Tensor {
     [0, 0], // dont touch rbg
   ];
   t.pad = tf.pad(input, cache.padding);
-  t.resize = tf.image.resizeBilinear(t.pad as Tensor3D, [inputSize, inputSize]);
+  t.resize = tf.image.resizeBilinear(t.pad, [inputSize, inputSize]);
   const final = tf.cast(t.resize, 'int32');
   Object.keys(t).forEach((tensor) => tf.dispose(t[tensor]));
   return final;

src/body/posenet.ts

@@ -4,11 +4,11 @@
  * Based on: [**PoseNet**](https://medium.com/tensorflow/real-time-human-pose-estimation-in-the-browser-with-tensorflow-js-7dd0bc881cd5)
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log } from '../util/util';
+import * as tf from '../../dist/tfjs.esm.js';
 import { loadModel } from '../tfjs/load';
 import type { BodyResult, BodyLandmark, Box } from '../result';
-import type { Tensor, GraphModel, Tensor4D } from '../tfjs/types';
+import type { Tensor, GraphModel } from '../tfjs/types';
 import type { Config } from '../config';
 import { env } from '../util/env';
 import * as utils from './posenetutils';
@@ -155,7 +155,7 @@ export function decode(offsets, scores, displacementsFwd, displacementsBwd, maxD
   return poses;
 }
 
-export async function predict(input: Tensor4D, config: Config): Promise<BodyResult[]> {
+export async function predict(input: Tensor, config: Config): Promise<BodyResult[]> {
   /** posenet is mostly obsolete
    * caching is not implemented
    */

src/config.ts

@@ -1,7 +1,7 @@
 /* eslint-disable no-multi-spaces */
 
 /** Possible TensorFlow backends */
-export type BackendEnum = '' | 'cpu' | 'wasm' | 'webgl' | 'humangl' | 'tensorflow' | 'webgpu' | 'none';
+export type BackendEnum = '' | 'cpu' | 'wasm' | 'webgl' | 'humangl' | 'tensorflow' | 'webgpu';
 
 /** Possible values for `human.warmup` */
 export type WarmupEnum = '' | 'none' | 'face' | 'full' | 'body';
@@ -33,14 +33,8 @@ export interface FaceDetectorConfig extends GenericConfig {
   maxDetected: number,
   /** minimum confidence for a detected face before results are discarded */
   minConfidence: number,
-  /** minimum size in pixels of a detected face box before resutls are discared */
-  minSize: number,
   /** minimum overlap between two detected faces before one is discarded */
   iouThreshold: number,
-  /** how much should face box be enlarged over the min/max facial coordinates */
-  scale: number,
-  /** automatically pad image to square */
-  square: boolean,
   /** should child models perform on masked image of a face */
   mask: boolean,
   /** should face detection return processed and cropped face tensor that can with an external model for addtional processing?
@@ -55,10 +49,7 @@ export interface FaceMeshConfig extends GenericConfig {
 }
 
 /** Iris part of face configuration */
-export interface FaceIrisConfig extends GenericConfig {
-  /** how much should iris box be enlarged over the min/max iris coordinates */
-  scale: number,
-}
+export interface FaceIrisConfig extends GenericConfig {}
 
 /** Attention part of face configuration */
 export interface FaceAttentionConfig extends GenericConfig {}
@@ -195,8 +186,6 @@ export interface FilterConfig {
   return: boolean,
   /** flip input as mirror image */
   flip: boolean,
-  /** apply auto-brighness */
-  autoBrightness: boolean,
   /** range: -1 (darken) to 1 (lighten) */
   brightness: number,
   /** range: -1 (reduce contrast) to 1 (increase contrast) */
@@ -361,7 +350,6 @@ const config: Config = {
     height: 0,
     flip: false,
     return: true,
-    autoBrightness: true,
     brightness: 0,
     contrast: 0,
     sharpness: 0,
@@ -383,14 +371,12 @@ const config: Config = {
     enabled: true,
     detector: {
       modelPath: 'blazeface.json',
-      rotation: false,
+      rotation: true,
       maxDetected: 1,
       skipFrames: 99,
       skipTime: 2500,
       minConfidence: 0.2,
-      minSize: 0,
       iouThreshold: 0.1,
-      scale: 1.4,
       mask: false,
       return: false,
     },
@@ -405,7 +391,6 @@ const config: Config = {
     },
     iris: {
       enabled: true,
-      scale: 2.3,
       modelPath: 'iris.json',
     },
     emotion: {
@@ -456,12 +441,12 @@ const config: Config = {
       modelPath: 'handtrack.json',
     },
     skeleton: {
-      modelPath: 'handlandmark-lite.json',
+      modelPath: 'handlandmark-full.json',
     },
   },
   object: {
     enabled: false,
-    modelPath: 'centernet.json',
+    modelPath: 'mb3-centernet.json',
     minConfidence: 0.2,
     iouThreshold: 0.4,
     maxDetected: 10,

src/draw/body.ts

@@ -1,5 +1,5 @@
 import { mergeDeep } from '../util/util';
-import { getCanvasContext, rect, point, curves, colorDepth, replace, labels } from './primitives';
+import { getCanvasContext, rect, point, curves, colorDepth } from './primitives';
 import { options } from './options';
 import type { BodyResult } from '../result';
 import type { AnyCanvas, DrawOptions } from '../exports';
@@ -8,7 +8,7 @@ import type { AnyCanvas, DrawOptions } from '../exports';
 export function body(inCanvas: AnyCanvas, result: BodyResult[], drawOptions?: Partial<DrawOptions>) {
   const localOptions: DrawOptions = mergeDeep(options, drawOptions);
   if (!result || !inCanvas) return;
-  const ctx = getCanvasContext(inCanvas) as CanvasRenderingContext2D;
+  const ctx = getCanvasContext(inCanvas);
   if (!ctx) return;
   ctx.lineJoin = 'round';
   for (let i = 0; i < result.length; i++) {
@@ -18,11 +18,13 @@ export function body(inCanvas: AnyCanvas, result: BodyResult[], drawOptions?: Pa
     ctx.font = localOptions.font;
     if (localOptions.drawBoxes && result[i].box && result[i].box.length === 4) {
       rect(ctx, result[i].box[0], result[i].box[1], result[i].box[2], result[i].box[3], localOptions);
-      if (localOptions.drawLabels && (localOptions.bodyLabels?.length > 0)) {
-        let l = localOptions.bodyLabels.slice();
-        l = replace(l, '[id]', result[i].id.toFixed(0));
-        l = replace(l, '[score]', 100 * result[i].score);
-        labels(ctx, l, result[i].box[0], result[i].box[1], localOptions);
+      if (localOptions.drawLabels) {
+        if (localOptions.shadowColor && localOptions.shadowColor !== '') {
+          ctx.fillStyle = localOptions.shadowColor;
+          ctx.fillText(`body ${100 * result[i].score}%`, result[i].box[0] + 3, 1 + result[i].box[1] + localOptions.lineHeight, result[i].box[2]);
+        }
+        ctx.fillStyle = localOptions.labelColor;
+        ctx.fillText(`body ${100 * result[i].score}%`, result[i].box[0] + 2, 0 + result[i].box[1] + localOptions.lineHeight, result[i].box[2]);
       }
     }
     if (localOptions.drawPoints && result[i].keypoints) {
@@ -32,14 +34,12 @@ export function body(inCanvas: AnyCanvas, result: BodyResult[], drawOptions?: Pa
         point(ctx, result[i].keypoints[pt].position[0], result[i].keypoints[pt].position[1], 0, localOptions);
       }
     }
-    if (localOptions.drawLabels && (localOptions.bodyPartLabels?.length > 0) && result[i].keypoints) {
+    if (localOptions.drawLabels && result[i].keypoints) {
       ctx.font = localOptions.font;
       for (const pt of result[i].keypoints) {
         if (!pt.score || (pt.score === 0)) continue;
-        let l = localOptions.bodyPartLabels.slice();
-        l = replace(l, '[label]', pt.part);
-        l = replace(l, '[score]', 100 * pt.score);
-        labels(ctx, l, pt.position[0], pt.position[1], localOptions);
+        ctx.fillStyle = colorDepth(pt.position[2], localOptions);
+        ctx.fillText(`${pt.part} ${Math.trunc(100 * pt.score)}%`, pt.position[0] + 4, pt.position[1] + 4);
       }
     }
     if (localOptions.drawPolygons && result[i].keypoints && result[i].annotations) {

src/draw/draw.ts

@@ -2,7 +2,6 @@
  * Module that implements helper draw functions, exposed as human.draw
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { mergeDeep, now } from '../util/util';
 import { env } from '../util/env';
 import { getCanvasContext, rect } from './primitives';
@@ -12,10 +11,8 @@ import { body } from './body';
 import { hand } from './hand';
 import { object } from './object';
 import { gesture } from './gesture';
-import { defaultLabels } from './labels';
 import type { Result, PersonResult } from '../result';
 import type { AnyCanvas, DrawOptions } from '../exports';
-import type { Tensor2D } from '../tfjs/types';
 
 let drawTime = 0;
 
@@ -30,7 +27,7 @@ export { gesture } from './gesture';
 export function person(inCanvas: AnyCanvas, result: PersonResult[], drawOptions?: Partial<DrawOptions>) {
   const localOptions: DrawOptions = mergeDeep(options, drawOptions);
   if (!result || !inCanvas) return;
-  const ctx = getCanvasContext(inCanvas) as CanvasRenderingContext2D;
+  const ctx = getCanvasContext(inCanvas);
   if (!ctx) return;
   ctx.lineJoin = 'round';
   ctx.font = localOptions.font;
@@ -57,27 +54,11 @@ export function person(inCanvas: AnyCanvas, result: PersonResult[], drawOptions?
 /** draw processed canvas */
 export function canvas(input: AnyCanvas | HTMLImageElement | HTMLVideoElement, output: AnyCanvas) {
   if (!input || !output) return;
-  const ctx = getCanvasContext(output) as CanvasRenderingContext2D;
+  const ctx = getCanvasContext(output);
   if (!ctx) return;
   ctx.drawImage(input, 0, 0);
 }
 
-/** draw processed canvas */
-export async function tensor(input: Tensor2D, output: HTMLCanvasElement) {
-  if (!input || !output) return;
-  if (!env.browser) return;
-  // const backend = tf.getBackend();
-  // if (backend === 'webgpu') tf.browser.draw(input, output);
-  // else await tf.browser.toPixels(input, output);
-  await tf.browser.toPixels(input, output);
-  // const ctx = getCanvasContext(output) as CanvasRenderingContext2D;
-  // if (!ctx) return;
-  // const image = await process(input);
-  // result.canvas = image.canvas;
-  // human.tf.dispose(image.tensor);
-  // ctx.drawImage(image.canvas, 0, 0);
-}
-
 /** meta-function that performs draw for: canvas, face, body, hand */
 export async function all(inCanvas: AnyCanvas, result: Result, drawOptions?: Partial<DrawOptions>) {
   if (!result?.performance || !inCanvas) return null;
@@ -95,14 +76,3 @@ export async function all(inCanvas: AnyCanvas, result: Result, drawOptions?: Par
   result.performance.draw = drawTime;
   return promise;
 }
-
-/** sets default label templates for face/body/hand/object/gestures */
-export function init() {
-  options.faceLabels = defaultLabels.face;
-  options.bodyLabels = defaultLabels.body;
-  options.bodyPartLabels = defaultLabels.bodyPart;
-  options.handLabels = defaultLabels.hand;
-  options.fingerLabels = defaultLabels.finger;
-  options.objectLabels = defaultLabels.object;
-  options.gestureLabels = defaultLabels.gesture;
-}

src/draw/face.ts

@@ -1,66 +1,77 @@
 import { TRI468 as triangulation } from '../face/facemeshcoords';
 import { mergeDeep } from '../util/util';
-import { getCanvasContext, rad2deg, rect, point, lines, arrow, labels, replace } from './primitives';
+import { getCanvasContext, rad2deg, rect, point, lines, arrow } from './primitives';
 import { options } from './options';
 import * as facemeshConstants from '../face/constants';
 import type { FaceResult } from '../result';
 import type { AnyCanvas, DrawOptions } from '../exports';
 
-let localOptions: DrawOptions;
+let opt: DrawOptions;
 
 function drawLabels(f: FaceResult, ctx: CanvasRenderingContext2D | OffscreenCanvasRenderingContext2D) {
-  if (!localOptions.drawLabels || (localOptions.faceLabels?.length === 0)) return;
-  let l = localOptions.faceLabels.slice();
-  l = replace(l, '[id]', f.id.toFixed(0));
-  if (f.score) l = replace(l, '[score]', 100 * f.score);
-  if (f.gender) l = replace(l, '[gender]', f.gender);
-  if (f.genderScore) l = replace(l, '[genderScore]', 100 * f.genderScore);
-  if (f.age) l = replace(l, '[age]', f.age);
-  if (f.distance) l = replace(l, '[distance]', 100 * f.distance);
-  if (f.real) l = replace(l, '[real]', 100 * f.real);
-  if (f.live) l = replace(l, '[live]', 100 * f.live);
+  if (opt.drawLabels) {
+    // silly hack since fillText does not suport new line
+    const labels:string[] = [];
+    labels.push(`face: ${Math.trunc(100 * f.score)}%`);
+    if (f.genderScore) labels.push(`${f.gender || ''} ${Math.trunc(100 * f.genderScore)}%`);
+    if (f.age) labels.push(`age: ${f.age || ''}`);
+    if (f.iris) labels.push(`distance: ${f.iris}`);
+    if (f.real) labels.push(`real: ${Math.trunc(100 * f.real)}%`);
+    if (f.live) labels.push(`live: ${Math.trunc(100 * f.live)}%`);
     if (f.emotion && f.emotion.length > 0) {
       const emotion = f.emotion.map((a) => `${Math.trunc(100 * a.score)}% ${a.emotion}`);
       if (emotion.length > 3) emotion.length = 3;
-    l = replace(l, '[emotions]', emotion.join(' '));
+      labels.push(emotion.join(' '));
+    }
+    if (f.rotation?.angle && f.rotation?.gaze) {
+      if (f.rotation.angle.roll) labels.push(`roll: ${rad2deg(f.rotation.angle.roll)}° yaw:${rad2deg(f.rotation.angle.yaw)}° pitch:${rad2deg(f.rotation.angle.pitch)}°`);
+      if (f.rotation.gaze.bearing) labels.push(`gaze: ${rad2deg(f.rotation.gaze.bearing)}°`);
+    }
+    if (labels.length === 0) labels.push('face');
+    ctx.fillStyle = opt.color;
+    for (let i = labels.length - 1; i >= 0; i--) {
+      const x = Math.max(f.box[0], 0);
+      const y = i * opt.lineHeight + f.box[1];
+      if (opt.shadowColor && opt.shadowColor !== '') {
+        ctx.fillStyle = opt.shadowColor;
+        ctx.fillText(labels[i], x + 5, y + 16);
+      }
+      ctx.fillStyle = opt.labelColor;
+      ctx.fillText(labels[i], x + 4, y + 15);
+    }
   }
-  if (f.rotation?.angle?.roll) l = replace(l, '[roll]', rad2deg(f.rotation.angle.roll));
-  if (f.rotation?.angle?.yaw) l = replace(l, '[yaw]', rad2deg(f.rotation.angle.yaw));
-  if (f.rotation?.angle?.pitch) l = replace(l, '[pitch]', rad2deg(f.rotation.angle.pitch));
-  if (f.rotation?.gaze?.bearing) l = replace(l, '[gaze]', rad2deg(f.rotation.gaze.bearing));
-  labels(ctx, l, f.box[0], f.box[1], localOptions);
 }
 
 function drawIrisElipse(f: FaceResult, ctx: CanvasRenderingContext2D | OffscreenCanvasRenderingContext2D) {
   // iris: array[center, left, top, right, bottom]
   if (f.annotations?.leftEyeIris && f.annotations?.leftEyeIris[0]) {
-    ctx.strokeStyle = localOptions.useDepth ? 'rgba(255, 200, 255, 0.3)' : localOptions.color;
+    ctx.strokeStyle = opt.useDepth ? 'rgba(255, 200, 255, 0.3)' : opt.color;
     ctx.beginPath();
     const sizeX = Math.abs(f.annotations.leftEyeIris[3][0] - f.annotations.leftEyeIris[1][0]) / 2;
     const sizeY = Math.abs(f.annotations.leftEyeIris[4][1] - f.annotations.leftEyeIris[2][1]) / 2;
     ctx.ellipse(f.annotations.leftEyeIris[0][0], f.annotations.leftEyeIris[0][1], sizeX, sizeY, 0, 0, 2 * Math.PI);
     ctx.stroke();
-    if (localOptions.fillPolygons) {
-      ctx.fillStyle = localOptions.useDepth ? 'rgba(255, 255, 200, 0.3)' : localOptions.color;
+    if (opt.fillPolygons) {
+      ctx.fillStyle = opt.useDepth ? 'rgba(255, 255, 200, 0.3)' : opt.color;
       ctx.fill();
     }
   }
   if (f.annotations?.rightEyeIris && f.annotations?.rightEyeIris[0]) {
-    ctx.strokeStyle = localOptions.useDepth ? 'rgba(255, 200, 255, 0.3)' : localOptions.color;
+    ctx.strokeStyle = opt.useDepth ? 'rgba(255, 200, 255, 0.3)' : opt.color;
     ctx.beginPath();
     const sizeX = Math.abs(f.annotations.rightEyeIris[3][0] - f.annotations.rightEyeIris[1][0]) / 2;
     const sizeY = Math.abs(f.annotations.rightEyeIris[4][1] - f.annotations.rightEyeIris[2][1]) / 2;
     ctx.ellipse(f.annotations.rightEyeIris[0][0], f.annotations.rightEyeIris[0][1], sizeX, sizeY, 0, 0, 2 * Math.PI);
     ctx.stroke();
-    if (localOptions.fillPolygons) {
-      ctx.fillStyle = localOptions.useDepth ? 'rgba(255, 255, 200, 0.3)' : localOptions.color;
+    if (opt.fillPolygons) {
+      ctx.fillStyle = opt.useDepth ? 'rgba(255, 255, 200, 0.3)' : opt.color;
       ctx.fill();
     }
   }
 }
 
 function drawGazeSpheres(f: FaceResult, ctx: CanvasRenderingContext2D | OffscreenCanvasRenderingContext2D) {
-  if (localOptions.drawGaze && f.rotation?.angle && typeof Path2D !== 'undefined') {
+  if (opt.drawGaze && f.rotation?.angle && typeof Path2D !== 'undefined') {
     ctx.strokeStyle = 'pink';
     const valX = (f.box[0] + f.box[2] / 2) - (f.box[3] * rad2deg(f.rotation.angle.yaw) / 90);
     const valY = (f.box[1] + f.box[3] / 2) + (f.box[2] * rad2deg(f.rotation.angle.pitch) / 90);
@@ -84,7 +95,7 @@ function drawGazeSpheres(f: FaceResult, ctx: CanvasRenderingContext2D | Offscree
 }
 
 function drawGazeArrows(f: FaceResult, ctx: CanvasRenderingContext2D | OffscreenCanvasRenderingContext2D) {
-  if (localOptions.drawGaze && f.rotation?.gaze.strength && f.rotation.gaze.bearing && f.annotations.leftEyeIris && f.annotations.rightEyeIris && f.annotations.leftEyeIris[0] && f.annotations.rightEyeIris[0]) {
+  if (opt.drawGaze && f.rotation?.gaze.strength && f.rotation.gaze.bearing && f.annotations.leftEyeIris && f.annotations.rightEyeIris && f.annotations.leftEyeIris[0] && f.annotations.rightEyeIris[0]) {
     ctx.strokeStyle = 'pink';
     ctx.fillStyle = 'pink';
     const leftGaze = [
@@ -101,16 +112,16 @@ function drawGazeArrows(f: FaceResult, ctx: CanvasRenderingContext2D | Offscreen
 }
 
 function drawFacePolygons(f: FaceResult, ctx: CanvasRenderingContext2D | OffscreenCanvasRenderingContext2D) {
-  if (localOptions.drawPolygons && f.mesh.length >= 468) {
+  if (opt.drawPolygons && f.mesh.length >= 468) {
     ctx.lineWidth = 1;
     for (let i = 0; i < triangulation.length / 3; i++) {
       const points = [triangulation[i * 3 + 0], triangulation[i * 3 + 1], triangulation[i * 3 + 2]].map((index) => f.mesh[index]);
-      lines(ctx, points, localOptions);
+      lines(ctx, points, opt);
     }
     drawIrisElipse(f, ctx);
   }
   /*
-  if (localOptions.drawPolygons && f.contours.length > 1) {
+  if (opt.drawPolygons && f.contours.length > 1) {
     ctx.lineWidth = 5;
     lines(ctx, f.contours, opt);
   }
@@ -119,42 +130,33 @@ function drawFacePolygons(f: FaceResult, ctx: CanvasRenderingContext2D | Offscre
 }
 
 function drawFacePoints(f: FaceResult, ctx: CanvasRenderingContext2D | OffscreenCanvasRenderingContext2D) {
-  if (localOptions.drawPoints) {
-    if (f?.mesh.length >= 468) {
+  if (opt.drawPoints && f.mesh.length >= 468) {
     for (let i = 0; i < f.mesh.length; i++) {
-        point(ctx, f.mesh[i][0], f.mesh[i][1], f.mesh[i][2], localOptions);
-        if (localOptions.drawAttention) {
-          if (facemeshConstants.LANDMARKS_REFINEMENT_LIPS_CONFIG.includes(i)) point(ctx, f.mesh[i][0], f.mesh[i][1], (f.mesh[i][2] as number) + 127, localOptions);
-          if (facemeshConstants.LANDMARKS_REFINEMENT_LEFT_EYE_CONFIG.includes(i)) point(ctx, f.mesh[i][0], f.mesh[i][1], (f.mesh[i][2] as number) - 127, localOptions);
-          if (facemeshConstants.LANDMARKS_REFINEMENT_RIGHT_EYE_CONFIG.includes(i)) point(ctx, f.mesh[i][0], f.mesh[i][1], (f.mesh[i][2] as number) - 127, localOptions);
-        }
-      }
-    } else {
-      for (const [k, v] of Object.entries(f?.annotations || {})) {
-        if (!v?.[0]) continue;
-        const pt = v[0];
-        point(ctx, pt[0], pt[1], 0, localOptions);
-        if (localOptions.drawLabels) labels(ctx, k, pt[0], pt[1], localOptions);
+      point(ctx, f.mesh[i][0], f.mesh[i][1], f.mesh[i][2], opt);
+      if (opt.drawAttention) {
+        if (facemeshConstants.LANDMARKS_REFINEMENT_LIPS_CONFIG.includes(i)) point(ctx, f.mesh[i][0], f.mesh[i][1], (f.mesh[i][2] as number) + 127, opt);
+        if (facemeshConstants.LANDMARKS_REFINEMENT_LEFT_EYE_CONFIG.includes(i)) point(ctx, f.mesh[i][0], f.mesh[i][1], (f.mesh[i][2] as number) - 127, opt);
+        if (facemeshConstants.LANDMARKS_REFINEMENT_RIGHT_EYE_CONFIG.includes(i)) point(ctx, f.mesh[i][0], f.mesh[i][1], (f.mesh[i][2] as number) - 127, opt);
       }
     }
   }
 }
 
 function drawFaceBoxes(f: FaceResult, ctx) {
-  if (localOptions.drawBoxes) {
-    rect(ctx, f.box[0], f.box[1], f.box[2], f.box[3], localOptions);
+  if (opt.drawBoxes) {
+    rect(ctx, f.box[0], f.box[1], f.box[2], f.box[3], opt);
   }
 }
 
 /** draw detected faces */
 export function face(inCanvas: AnyCanvas, result: FaceResult[], drawOptions?: Partial<DrawOptions>) {
-  localOptions = mergeDeep(options, drawOptions);
+  opt = mergeDeep(options, drawOptions);
   if (!result || !inCanvas) return;
-  const ctx = getCanvasContext(inCanvas) as CanvasRenderingContext2D;
+  const ctx = getCanvasContext(inCanvas);
   if (!ctx) return;
-  ctx.font = localOptions.font;
-  ctx.strokeStyle = localOptions.color;
-  ctx.fillStyle = localOptions.color;
+  ctx.font = opt.font;
+  ctx.strokeStyle = opt.color;
+  ctx.fillStyle = opt.color;
   for (const f of result) {
     drawFaceBoxes(f, ctx);
     drawLabels(f, ctx);

src/draw/gesture.ts

@@ -1,5 +1,5 @@
 import { mergeDeep } from '../util/util';
-import { getCanvasContext, replace, labels } from './primitives';
+import { getCanvasContext } from './primitives';
 import { options } from './options';
 import type { GestureResult } from '../result';
 import type { AnyCanvas, DrawOptions } from '../exports';
@@ -8,21 +8,25 @@ import type { AnyCanvas, DrawOptions } from '../exports';
 export function gesture(inCanvas: AnyCanvas, result: GestureResult[], drawOptions?: Partial<DrawOptions>) {
   const localOptions: DrawOptions = mergeDeep(options, drawOptions);
   if (!result || !inCanvas) return;
-  if (localOptions.drawGestures && (localOptions.gestureLabels?.length > 0)) {
-    const ctx = getCanvasContext(inCanvas) as CanvasRenderingContext2D;
+  if (localOptions.drawGestures) {
+    const ctx = getCanvasContext(inCanvas);
     if (!ctx) return;
     ctx.font = localOptions.font;
     ctx.fillStyle = localOptions.color;
     let i = 1;
     for (let j = 0; j < result.length; j++) {
-      const [where, what] = Object.entries(result[j]);
+      let where: unknown[] = []; // what&where is a record
+      let what: unknown[] = []; // what&where is a record
+      [where, what] = Object.entries(result[j]);
       if ((what.length > 1) && ((what[1] as string).length > 0)) {
         const who = where[1] as number > 0 ? `#${where[1]}` : '';
-        let l = localOptions.gestureLabels.slice();
-        l = replace(l, '[where]', where[0]);
-        l = replace(l, '[who]', who);
-        l = replace(l, '[what]', what[1]);
-        labels(ctx, l, 8, 2 + (i * localOptions.lineHeight), localOptions);
+        const label = `${where[0]} ${who}: ${what[1]}`;
+        if (localOptions.shadowColor && localOptions.shadowColor !== '') {
+          ctx.fillStyle = localOptions.shadowColor;
+          ctx.fillText(label, 8, 2 + (i * localOptions.lineHeight));
+        }
+        ctx.fillStyle = localOptions.labelColor;
+        ctx.fillText(label, 6, 0 + (i * localOptions.lineHeight));
         i += 1;
       }
     }

src/draw/hand.ts

@@ -1,5 +1,5 @@
 import { mergeDeep } from '../util/util';
-import { getCanvasContext, rect, point, colorDepth, replace, labels } from './primitives';
+import { getCanvasContext, rect, point, colorDepth } from './primitives';
 import { options } from './options';
 import type { HandResult } from '../result';
 import type { AnyCanvas, DrawOptions, Point } from '../exports';
@@ -8,7 +8,7 @@ import type { AnyCanvas, DrawOptions, Point } from '../exports';
 export function hand(inCanvas: AnyCanvas, result: HandResult[], drawOptions?: Partial<DrawOptions>) {
   const localOptions: DrawOptions = mergeDeep(options, drawOptions);
   if (!result || !inCanvas) return;
-  const ctx = getCanvasContext(inCanvas) as CanvasRenderingContext2D;
+  const ctx = getCanvasContext(inCanvas);
   if (!ctx) return;
   ctx.lineJoin = 'round';
   ctx.font = localOptions.font;
@@ -17,12 +17,13 @@ export function hand(inCanvas: AnyCanvas, result: HandResult[], drawOptions?: Pa
       ctx.strokeStyle = localOptions.color;
       ctx.fillStyle = localOptions.color;
       rect(ctx, h.box[0], h.box[1], h.box[2], h.box[3], localOptions);
-      if (localOptions.drawLabels && (localOptions.handLabels?.length > 0)) {
-        let l = localOptions.handLabels.slice();
-        l = replace(l, '[id]', h.id.toFixed(0));
-        l = replace(l, '[label]', h.label);
-        l = replace(l, '[score]', 100 * h.score);
-        labels(ctx, l, h.box[0], h.box[1], localOptions);
+      if (localOptions.drawLabels) {
+        if (localOptions.shadowColor && localOptions.shadowColor !== '') {
+          ctx.fillStyle = localOptions.shadowColor;
+          ctx.fillText(`hand:${Math.trunc(100 * h.score)}%`, h.box[0] + 3, 1 + h.box[1] + localOptions.lineHeight, h.box[2]); // can use h.label
+        }
+        ctx.fillStyle = localOptions.labelColor;
+        ctx.fillText(`hand:${Math.trunc(100 * h.score)}%`, h.box[0] + 2, 0 + h.box[1] + localOptions.lineHeight, h.box[2]); // can use h.label
       }
       ctx.stroke();
     }
@@ -34,12 +35,20 @@ export function hand(inCanvas: AnyCanvas, result: HandResult[], drawOptions?: Pa
         }
       }
     }
-    if (localOptions.drawLabels && h.annotations && (localOptions.fingerLabels?.length > 0)) {
-      for (const [part, pt] of Object.entries(h.annotations)) {
-        let l = localOptions.fingerLabels.slice();
-        l = replace(l, '[label]', part);
-        labels(ctx, l, pt[pt.length - 1][0], pt[pt.length - 1][1], localOptions);
-      }
+    if (localOptions.drawLabels && h.annotations) {
+      const addHandLabel = (part: Point[], title: string) => {
+        if (!part || part.length === 0 || !part[0]) return;
+        const z = part[part.length - 1][2] || -256;
+        ctx.fillStyle = colorDepth(z, localOptions);
+        ctx.fillText(title, part[part.length - 1][0] + 4, part[part.length - 1][1] + 4);
+      };
+      ctx.font = localOptions.font;
+      addHandLabel(h.annotations.index, 'index');
+      addHandLabel(h.annotations.middle, 'middle');
+      addHandLabel(h.annotations.ring, 'ring');
+      addHandLabel(h.annotations.pinky, 'pinky');
+      addHandLabel(h.annotations.thumb, 'thumb');
+      addHandLabel(h.annotations.palm, 'palm');
     }
     if (localOptions.drawPolygons && h.annotations) {
       const addHandLine = (part: Point[]) => {

src/draw/labels.ts

@@ -1,18 +0,0 @@
-export const defaultLabels = {
-  face: `face
-    confidence: [score]%
-    [gender] [genderScore]%
-    age: [age] years
-    distance: [distance]cm
-    real: [real]%
-    live: [live]%
-    [emotions]
-    roll: [roll]° yaw:[yaw]° pitch:[pitch]°
-    gaze: [gaze]°`,
-  body: 'body [score]%',
-  bodyPart: '[label] [score]%',
-  object: '[label] [score]%',
-  hand: '[label] [score]%',
-  finger: '[label]',
-  gesture: '[where] [who]: [what]',
-};

src/draw/object.ts

@@ -1,5 +1,5 @@
 import { mergeDeep } from '../util/util';
-import { getCanvasContext, rect, replace, labels } from './primitives';
+import { getCanvasContext, rect } from './primitives';
 import { options } from './options';
 import type { ObjectResult } from '../result';
 import type { AnyCanvas, DrawOptions } from '../exports';
@@ -8,7 +8,7 @@ import type { AnyCanvas, DrawOptions } from '../exports';
 export function object(inCanvas: AnyCanvas, result: ObjectResult[], drawOptions?: Partial<DrawOptions>) {
   const localOptions: DrawOptions = mergeDeep(options, drawOptions);
   if (!result || !inCanvas) return;
-  const ctx = getCanvasContext(inCanvas) as CanvasRenderingContext2D;
+  const ctx = getCanvasContext(inCanvas);
   if (!ctx) return;
   ctx.lineJoin = 'round';
   ctx.font = localOptions.font;
@@ -17,12 +17,14 @@ export function object(inCanvas: AnyCanvas, result: ObjectResult[], drawOptions?
       ctx.strokeStyle = localOptions.color;
       ctx.fillStyle = localOptions.color;
       rect(ctx, h.box[0], h.box[1], h.box[2], h.box[3], localOptions);
-      if (localOptions.drawLabels && (localOptions.objectLabels?.length > 0)) {
-        let l = localOptions.objectLabels.slice();
-        l = replace(l, '[id]', h.id.toFixed(0));
-        l = replace(l, '[label]', h.label);
-        l = replace(l, '[score]', 100 * h.score);
-        labels(ctx, l, h.box[0], h.box[1], localOptions);
+      if (localOptions.drawLabels) {
+        const label = `${h.label} ${Math.round(100 * h.score)}%`;
+        if (localOptions.shadowColor && localOptions.shadowColor !== '') {
+          ctx.fillStyle = localOptions.shadowColor;
+          ctx.fillText(label, h.box[0] + 3, 1 + h.box[1] + localOptions.lineHeight, h.box[2]);
+        }
+        ctx.fillStyle = localOptions.labelColor;
+        ctx.fillText(label, h.box[0] + 2, 0 + h.box[1] + localOptions.lineHeight, h.box[2]);
       }
       ctx.stroke();
     }

src/draw/options.ts

@@ -1,7 +1,6 @@
 /** Draw Options
  * - Accessed via `human.draw.options` or provided per each draw method as the drawOptions optional parameter
  */
-
 export interface DrawOptions {
   /** draw line color */
   color: string,
@@ -41,20 +40,6 @@ export interface DrawOptions {
   useDepth: boolean,
   /** should lines be curved? */
   useCurves: boolean,
-  /** string template for face labels */
-  faceLabels: string,
-  /** string template for body labels */
-  bodyLabels: string,
-  /** string template for body part labels */
-  bodyPartLabels: string,
-  /** string template for hand labels */
-  handLabels: string,
-  /** string template for hand labels */
-  fingerLabels: string,
-  /** string template for object labels */
-  objectLabels: string,
-  /** string template for gesture labels */
-  gestureLabels: string,
 }
 
 /** currently set draw options {@link DrawOptions} */
@@ -78,11 +63,4 @@ export const options: DrawOptions = {
   fillPolygons: false as boolean,
   useDepth: true as boolean,
   useCurves: false as boolean,
-  faceLabels: '' as string,
-  bodyLabels: '' as string,
-  bodyPartLabels: '' as string,
-  objectLabels: '' as string,
-  handLabels: '' as string,
-  fingerLabels: '' as string,
-  gestureLabels: '' as string,
 };

src/draw/primitives.ts

@@ -7,7 +7,7 @@ export const getCanvasContext = (input: AnyCanvas) => {
   if (!input) log('draw error: invalid canvas');
   else if (!input.getContext) log('draw error: canvas context not defined');
   else {
-    const ctx = input.getContext('2d', { willReadFrequently: true });
+    const ctx = input.getContext('2d');
     if (!ctx) log('draw error: cannot get canvas context');
     else return ctx;
   }
@@ -16,28 +16,12 @@ export const getCanvasContext = (input: AnyCanvas) => {
 
 export const rad2deg = (theta: number) => Math.round((theta * 180) / Math.PI);
 
-export const replace = (str: string, source: string, target: string | number) => str.replace(source, typeof target === 'number' ? target.toFixed(1) : target);
-
 export const colorDepth = (z: number | undefined, opt: DrawOptions): string => { // performance optimization needed
   if (!opt.useDepth || typeof z === 'undefined') return opt.color;
   const rgb = Uint8ClampedArray.from([127 + (2 * z), 127 - (2 * z), 255]);
   return `rgba(${rgb[0]}, ${rgb[1]}, ${rgb[2]}, ${opt.alpha})`;
 };
 
-export function labels(ctx: CanvasRenderingContext2D | OffscreenCanvasRenderingContext2D, str: string, startX: number, startY: number, localOptions: DrawOptions) {
-  const line: string[] = str.replace(/\[.*\]/g, '').split('\n').map((l) => l.trim()); // remove unmatched templates and split into array
-  const x = Math.max(0, startX);
-  for (let i = line.length - 1; i >= 0; i--) {
-    const y = i * localOptions.lineHeight + startY;
-    if (localOptions.shadowColor && localOptions.shadowColor !== '') {
-      ctx.fillStyle = localOptions.shadowColor;
-      ctx.fillText(line[i], x + 5, y + 16);
-    }
-    ctx.fillStyle = localOptions.labelColor;
-    ctx.fillText(line[i], x + 4, y + 15);
-  }
-}
-
 export function point(ctx: CanvasRenderingContext2D | OffscreenCanvasRenderingContext2D, x: number, y: number, z: number | undefined, localOptions: DrawOptions) {
   ctx.fillStyle = colorDepth(z, localOptions);
   ctx.beginPath();

src/exports.ts

@@ -6,10 +6,8 @@ export * from './config';
 /* Export results details */
 export * from './result';
 
-/**
- * Explict reexport of main @tensorflow/tfjs types
- */
-export type { Tensor, Tensor1D, Tensor2D, Tensor3D, Tensor4D, TensorLike, GraphModel, Rank } from './tfjs/types';
+/* Explict reexport of main @tensorflow/tfjs types */
+export type { Tensor, TensorLike, GraphModel, Rank } from './tfjs/types';
 
 // re-export types
 export type { DrawOptions } from './draw/options';
@@ -21,6 +19,8 @@ export type { WebCam, WebCamConfig } from './util/webcam';
 // export type { Models, ModelStats, KernelOps } from './models';
 export type { ModelInfo } from './tfjs/load';
 
+// define enum types
+
 /** Events dispatched by `human.events`
  * - `create`: triggered when Human object is instantiated
  * - `load`: triggered when models are loaded (explicitly or on-demand)

src/face/angles.ts

@@ -60,9 +60,7 @@ export const calculateFaceAngle = (face: FaceResult, imageSize: [number, number]
     let thetaZ: number;
     if (r10 < 1) { // YZX calculation
       if (r10 > -1) {
-        // thetaZ = Math.asin(r10);
-        const cosThetaZ = Math.sqrt(r00 * r00 + r20 * r20); // <https://github.com/vladmandic/human/issues/464>
-        thetaZ = Math.atan2(r10, cosThetaZ);
+        thetaZ = Math.asin(r10);
         thetaY = Math.atan2(-r20, r00);
         thetaX = Math.atan2(-r12, r11);
       } else {
@@ -78,9 +76,9 @@ export const calculateFaceAngle = (face: FaceResult, imageSize: [number, number]
     if (Number.isNaN(thetaX)) thetaX = 0;
     if (Number.isNaN(thetaY)) thetaY = 0;
     if (Number.isNaN(thetaZ)) thetaZ = 0;
-    // return { pitch: 2 * -thetaX, yaw: 2 * -thetaY, roll: 2 * -thetaZ };
-    return { pitch: -thetaX, yaw: -thetaY, roll: -thetaZ };
+    return { pitch: 2 * -thetaX, yaw: 2 * -thetaY, roll: 2 * -thetaZ };
   };
+
   /*
   const meshToEulerAngle = (mesh) => { // simple Euler angle calculation based existing 3D mesh
     const radians = (a1, a2, b1, b2) => Math.atan2(b2 - a2, b1 - a1);

src/face/anthropometry.ts

@@ -1,28 +0,0 @@
-import type { FaceResult } from '../result';
-
-export function calculateCameraDistance(face: FaceResult, width: number): number {
-  // iris points are [center, left, top, right, bottom]
-  // average size of human iris is 11.7mm - fairly constant for all ages/genders/races
-  const f = face?.annotations;
-  if (!f?.leftEyeIris || !f?.rightEyeIris) return 0;
-  // get size of left and right iris in pixels, pick larger one as its likely to be more accurate and normalize to 0..1 range instead of pixels
-  const irisSize = Math.max(Math.abs(f.leftEyeIris[3][0] - f.leftEyeIris[1][0]), Math.abs(f.rightEyeIris[3][0] - f.rightEyeIris[1][0])) / width;
-  // distance of eye from camera in meters
-  const cameraDistance = Math.round(1.17 / irisSize) / 100;
-  return cameraDistance;
-}
-
-export function calculateEyesDistance(face: FaceResult, width: number): number {
-  // average distance between eyes is 65mm - fairly constant for typical adult male, but varies otherwise
-  const f = face?.annotations;
-  if (!f?.leftEyeIris || !f?.rightEyeIris) return 0;
-  // get size of left and right iris in pixels, pick larger one as its likely to be more accurate and normalize to 0..1 range instead of pixels
-  const irisSize = Math.max(Math.abs(f.leftEyeIris[3][0] - f.leftEyeIris[1][0]), Math.abs(f.rightEyeIris[3][0] - f.rightEyeIris[1][0])) / width;
-  // pixel x and y distance of centers of left and right iris, you can use edges instead
-  const irisDistanceXY = [f.leftEyeIris[0][0] - f.rightEyeIris[0][0], f.leftEyeIris[0][1] - f.rightEyeIris[0][1]];
-  // absolute distance bewtween eyes in 0..1 range to account for head pitch (we can ignore yaw)
-  const irisDistance = Math.sqrt((irisDistanceXY[0] * irisDistanceXY[0]) + (irisDistanceXY[1] * irisDistanceXY[1])) / width;
-  // distance between eyes in meters
-  const eyesDistance = Math.round(1.17 * irisDistance / irisSize) / 100;
-  return eyesDistance;
-}

src/face/antispoof.ts

@@ -2,10 +2,10 @@
  * Anti-spoofing model implementation
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log, now } from '../util/util';
 import type { Config } from '../config';
-import type { GraphModel, Tensor, Tensor4D } from '../tfjs/types';
+import type { GraphModel, Tensor } from '../tfjs/types';
+import * as tf from '../../dist/tfjs.esm.js';
 import { loadModel } from '../tfjs/load';
 import { env } from '../util/env';
 
@@ -22,8 +22,8 @@ export async function load(config: Config): Promise<GraphModel> {
   return model;
 }
 
-export async function predict(image: Tensor4D, config: Config, idx: number, count: number): Promise<number> {
-  if (!model?.['executor']) return 0;
+export async function predict(image: Tensor, config: Config, idx: number, count: number): Promise<number> {
+  if (!model || !model?.['executor']) return 0;
   const skipTime = (config.face.antispoof?.skipTime || 0) > (now() - lastTime);
   const skipFrame = skipped < (config.face.antispoof?.skipFrames || 0);
   if (config.skipAllowed && skipTime && skipFrame && (lastCount === count) && cached[idx]) {

src/face/blazeface.ts

@@ -3,23 +3,24 @@
  * See `facemesh.ts` for entry point
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log } from '../util/util';
+import * as tf from '../../dist/tfjs.esm.js';
 import * as util from './facemeshutil';
 import { loadModel } from '../tfjs/load';
 import { constants } from '../tfjs/constants';
 import type { Config } from '../config';
-import type { Tensor, GraphModel, Tensor1D, Tensor2D, Tensor4D } from '../tfjs/types';
+import type { Tensor, GraphModel } from '../tfjs/types';
 import { env } from '../util/env';
 import type { Point } from '../result';
 
 const keypointsCount = 6;
+const faceBoxScaleFactor = 1.4;
 let model: GraphModel | null;
 let anchors: Tensor | null = null;
 let inputSize = 0;
 let inputSizeT: Tensor | null = null;
 
-export interface DetectBox { startPoint: Point, endPoint: Point, landmarks: Point[], confidence: number, size: [number, number] }
+interface DetectBox { startPoint: Point, endPoint: Point, landmarks: Point[], confidence: number }
 
 export const size = () => inputSize;
 
@@ -34,7 +35,6 @@ export async function load(config: Config): Promise<GraphModel> {
 }
 
 function decodeBoxes(boxOutputs: Tensor) {
-  if (!anchors || !inputSizeT) return tf.zeros([0, 0]);
   const t: Record<string, Tensor> = {};
   t.boxStarts = tf.slice(boxOutputs, [0, 1], [-1, 2]);
   t.centers = tf.add(t.boxStarts, anchors);
@@ -46,36 +46,25 @@ function decodeBoxes(boxOutputs: Tensor) {
   t.ends = tf.add(t.centersNormalized, t.halfBoxSize);
   t.startNormalized = tf.mul(t.starts, inputSizeT);
   t.endNormalized = tf.mul(t.ends, inputSizeT);
-  const boxes = tf.concat2d([t.startNormalized as Tensor2D, t.endNormalized as Tensor2D], 1);
+  const boxes = tf.concat2d([t.startNormalized, t.endNormalized], 1);
   Object.keys(t).forEach((tensor) => tf.dispose(t[tensor]));
   return boxes;
 }
 
-export async function getBoxes(inputImage: Tensor4D, config: Config): Promise<DetectBox[]> {
+export async function getBoxes(inputImage: Tensor, config: Config) {
   // sanity check on input
   if ((!inputImage) || (inputImage['isDisposedInternal']) || (inputImage.shape.length !== 4) || (inputImage.shape[1] < 1) || (inputImage.shape[2] < 1)) return [];
   const t: Record<string, Tensor> = {};
-  let pad = [0, 0];
-  let scale = [1, 1];
-  if (config?.face?.detector?.square) {
-    const xy = Math.max(inputImage.shape[2], inputImage.shape[1]);
-    pad = [Math.floor((xy - inputImage.shape[2]) / 2), Math.floor((xy - inputImage.shape[1]) / 2)];
-    t.padded = tf.pad(inputImage, [[0, 0], [pad[1], pad[1]], [pad[0], pad[0]], [0, 0]]);
-    scale = [inputImage.shape[2] / xy, inputImage.shape[1] / xy];
-    pad = [pad[0] / inputSize, pad[1] / inputSize];
-  } else {
-    t.padded = inputImage.clone();
-  }
-  t.resized = tf.image.resizeBilinear(t.padded as Tensor4D, [inputSize, inputSize]);
+  t.resized = tf.image.resizeBilinear(inputImage, [inputSize, inputSize]);
   t.div = tf.div(t.resized, constants.tf127);
-  t.normalized = tf.sub(t.div, constants.tf1);
+  t.normalized = tf.sub(t.div, constants.tf05);
   const res = model?.execute(t.normalized) as Tensor[];
   if (Array.isArray(res) && res.length > 2) { // pinto converted model?
     const sorted = res.sort((a, b) => a.size - b.size);
     t.concat384 = tf.concat([sorted[0], sorted[2]], 2); // dim: 384, 1 + 16
     t.concat512 = tf.concat([sorted[1], sorted[3]], 2); // dim: 512, 1 + 16
     t.concat = tf.concat([t.concat512, t.concat384], 1);
-    t.batch = tf.squeeze(t.concat, [0]);
+    t.batch = tf.squeeze(t.concat, 0);
   } else if (Array.isArray(res)) { // new facemesh-detection tfhub model
     t.batch = tf.squeeze(res[0]);
   } else { // original blazeface tfhub model
@@ -86,7 +75,7 @@ export async function getBoxes(inputImage: Tensor4D, config: Config): Promise<De
   t.logits = tf.slice(t.batch, [0, 0], [-1, 1]);
   t.sigmoid = tf.sigmoid(t.logits);
   t.scores = tf.squeeze(t.sigmoid);
-  t.nms = await tf.image.nonMaxSuppressionAsync(t.boxes as Tensor2D, t.scores as Tensor1D, (config.face.detector?.maxDetected || 0), (config.face.detector?.iouThreshold || 0), (config.face.detector?.minConfidence || 0));
+  t.nms = await tf.image.nonMaxSuppressionAsync(t.boxes, t.scores, (config.face.detector?.maxDetected || 0), (config.face.detector?.iouThreshold || 0), (config.face.detector?.minConfidence || 0));
   const nms = await t.nms.array() as number[];
   const boxes: DetectBox[] = [];
   const scores = await t.scores.data();
@@ -99,24 +88,16 @@ export async function getBoxes(inputImage: Tensor4D, config: Config): Promise<De
       b.squeeze = tf.squeeze(b.slice);
       b.landmarks = tf.reshape(b.squeeze, [keypointsCount, -1]);
       const points = await b.bbox.data();
-      const unpadded = [ // TODO fix this math
-        points[0] * scale[0] - pad[0],
-        points[1] * scale[1] - pad[1],
-        points[2] * scale[0] - pad[0],
-        points[3] * scale[1] - pad[1],
-      ];
       const rawBox = {
-        startPoint: [unpadded[0], unpadded[1]] as Point,
-        endPoint: [unpadded[2], unpadded[3]] as Point,
+        startPoint: [points[0], points[1]] as Point,
+        endPoint: [points[2], points[3]] as Point,
         landmarks: (await b.landmarks.array()) as Point[],
         confidence,
       };
-      b.anchor = tf.slice(anchors as Tensor, [nms[i], 0], [1, 2]);
-      const anchor = await b.anchor.data();
-      const scaledBox = util.scaleBoxCoordinates(rawBox, [(inputImage.shape[2] || 0) / inputSize, (inputImage.shape[1] || 0) / inputSize], anchor);
-      const enlargedBox = util.enlargeBox(scaledBox, config.face.detector?.scale || 1.4);
+      const scaledBox = util.scaleBoxCoordinates(rawBox, [(inputImage.shape[2] || 0) / inputSize, (inputImage.shape[1] || 0) / inputSize]);
+      const enlargedBox = util.enlargeBox(scaledBox, config.face['scale'] || faceBoxScaleFactor);
       const squaredBox = util.squarifyBox(enlargedBox);
-      if (squaredBox.size[0] > (config.face.detector?.['minSize'] || 0) && squaredBox.size[1] > (config.face.detector?.['minSize'] || 0)) boxes.push(squaredBox);
+      boxes.push(squaredBox);
       Object.keys(b).forEach((tensor) => tf.dispose(b[tensor]));
     }
   }

src/face/face.ts

@@ -3,9 +3,9 @@
  * Uses FaceMesh, Emotion and FaceRes models to create a unified pipeline
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log, now } from '../util/util';
 import { env } from '../util/env';
+import * as tf from '../../dist/tfjs.esm.js';
 import * as facemesh from './facemesh';
 import * as emotion from '../gear/emotion';
 import * as faceres from './faceres';
@@ -18,14 +18,13 @@ import * as ssrnetGender from '../gear/ssrnet-gender';
 import * as mobilefacenet from './mobilefacenet';
 import * as insightface from './insightface';
 import type { FaceResult, Emotion, Gender, Race } from '../result';
-import type { Tensor4D } from '../tfjs/types';
+import type { Tensor } from '../tfjs/types';
 import type { Human } from '../human';
 import { calculateFaceAngle } from './angles';
-import { calculateCameraDistance } from './anthropometry';
 
 interface DescRes { age: number, gender: Gender, genderScore: number, descriptor: number[], race?: { score: number, race: Race }[] }
 
-export const detectFace = async (instance: Human /* instance of human */, input: Tensor4D): Promise<FaceResult[]> => {
+export const detectFace = async (instance: Human /* instance of human */, input: Tensor): Promise<FaceResult[]> => {
   // run facemesh, includes blazeface and iris
   let timeStamp: number = now();
   let ageRes: { age: number } | Promise<{ age: number }> | null;
@@ -40,7 +39,8 @@ export const detectFace = async (instance: Human /* instance of human */, input:
 
   const faceRes: FaceResult[] = [];
   instance.state = 'run:face';
-  const faces: FaceResult[] = await facemesh.predict(input, instance.config);
+
+  const faces = await facemesh.predict(input, instance.config);
   instance.performance.face = env.perfadd ? (instance.performance.face || 0) + Math.trunc(now() - timeStamp) : Math.trunc(now() - timeStamp);
   if (!input.shape || input.shape.length !== 4) return [];
   if (!faces) return [];
@@ -68,11 +68,11 @@ export const detectFace = async (instance: Human /* instance of human */, input:
     // run emotion, inherits face from blazeface
     instance.analyze('Start Emotion:');
     if (instance.config.async) {
-      emotionRes = instance.config.face.emotion?.enabled ? emotion.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : [];
+      emotionRes = instance.config.face.emotion?.enabled ? emotion.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : [];
     } else {
       instance.state = 'run:emotion';
       timeStamp = now();
-      emotionRes = instance.config.face.emotion?.enabled ? await emotion.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : [];
+      emotionRes = instance.config.face.emotion?.enabled ? await emotion.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : [];
       instance.performance.emotion = env.perfadd ? (instance.performance.emotion || 0) + Math.trunc(now() - timeStamp) : Math.trunc(now() - timeStamp);
     }
     instance.analyze('End Emotion:');
@@ -80,11 +80,11 @@ export const detectFace = async (instance: Human /* instance of human */, input:
     // run antispoof, inherits face from blazeface
     instance.analyze('Start AntiSpoof:');
     if (instance.config.async) {
-      antispoofRes = instance.config.face.antispoof?.enabled ? antispoof.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : 0;
+      antispoofRes = instance.config.face.antispoof?.enabled ? antispoof.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : 0;
     } else {
       instance.state = 'run:antispoof';
       timeStamp = now();
-      antispoofRes = instance.config.face.antispoof?.enabled ? await antispoof.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : 0;
+      antispoofRes = instance.config.face.antispoof?.enabled ? await antispoof.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : 0;
       instance.performance.antispoof = env.perfadd ? (instance.performance.antispoof || 0) + Math.trunc(now() - timeStamp) : Math.trunc(now() - timeStamp);
     }
     instance.analyze('End AntiSpoof:');
@@ -92,11 +92,11 @@ export const detectFace = async (instance: Human /* instance of human */, input:
     // run liveness, inherits face from blazeface
     instance.analyze('Start Liveness:');
     if (instance.config.async) {
-      livenessRes = instance.config.face.liveness?.enabled ? liveness.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : 0;
+      livenessRes = instance.config.face.liveness?.enabled ? liveness.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : 0;
     } else {
       instance.state = 'run:liveness';
       timeStamp = now();
-      livenessRes = instance.config.face.liveness?.enabled ? await liveness.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : 0;
+      livenessRes = instance.config.face.liveness?.enabled ? await liveness.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : 0;
       instance.performance.liveness = env.perfadd ? (instance.performance.antispoof || 0) + Math.trunc(now() - timeStamp) : Math.trunc(now() - timeStamp);
     }
     instance.analyze('End Liveness:');
@@ -104,25 +104,25 @@ export const detectFace = async (instance: Human /* instance of human */, input:
     // run gear, inherits face from blazeface
     instance.analyze('Start GEAR:');
     if (instance.config.async) {
-      gearRes = instance.config.face.gear?.enabled ? gear.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
+      gearRes = instance.config.face.gear?.enabled ? gear.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
     } else {
       instance.state = 'run:gear';
       timeStamp = now();
-      gearRes = instance.config.face.gear?.enabled ? await gear.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
+      gearRes = instance.config.face.gear?.enabled ? await gear.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
       instance.performance.gear = Math.trunc(now() - timeStamp);
     }
     instance.analyze('End GEAR:');
 
-    // run ssrnet, inherits face from blazeface
+    // run gear, inherits face from blazeface
     instance.analyze('Start SSRNet:');
     if (instance.config.async) {
-      ageRes = instance.config.face['ssrnet']?.enabled ? ssrnetAge.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
-      genderRes = instance.config.face['ssrnet']?.enabled ? ssrnetGender.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
+      ageRes = instance.config.face['ssrnet']?.enabled ? ssrnetAge.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
+      genderRes = instance.config.face['ssrnet']?.enabled ? ssrnetGender.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
     } else {
       instance.state = 'run:ssrnet';
       timeStamp = now();
-      ageRes = instance.config.face['ssrnet']?.enabled ? await ssrnetAge.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
-      genderRes = instance.config.face['ssrnet']?.enabled ? await ssrnetGender.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
+      ageRes = instance.config.face['ssrnet']?.enabled ? await ssrnetAge.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
+      genderRes = instance.config.face['ssrnet']?.enabled ? await ssrnetGender.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
       instance.performance.ssrnet = Math.trunc(now() - timeStamp);
     }
     instance.analyze('End SSRNet:');
@@ -130,11 +130,11 @@ export const detectFace = async (instance: Human /* instance of human */, input:
     // run mobilefacenet alternative, inherits face from blazeface
     instance.analyze('Start MobileFaceNet:');
     if (instance.config.async) {
-      mobilefacenetRes = instance.config.face['mobilefacenet']?.enabled ? mobilefacenet.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
+      mobilefacenetRes = instance.config.face['mobilefacenet']?.enabled ? mobilefacenet.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
     } else {
       instance.state = 'run:mobilefacenet';
       timeStamp = now();
-      mobilefacenetRes = instance.config.face['mobilefacenet']?.enabled ? await mobilefacenet.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
+      mobilefacenetRes = instance.config.face['mobilefacenet']?.enabled ? await mobilefacenet.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
       instance.performance.mobilefacenet = Math.trunc(now() - timeStamp);
     }
     instance.analyze('End MobileFaceNet:');
@@ -142,11 +142,11 @@ export const detectFace = async (instance: Human /* instance of human */, input:
     // run insightface alternative, inherits face from blazeface
     instance.analyze('Start InsightFace:');
     if (instance.config.async) {
-      insightfaceRes = instance.config.face['insightface']?.enabled ? insightface.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
+      insightfaceRes = instance.config.face['insightface']?.enabled ? insightface.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
     } else {
       instance.state = 'run:mobilefacenet';
       timeStamp = now();
-      insightfaceRes = instance.config.face['insightface']?.enabled ? await insightface.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length) : null;
+      insightfaceRes = instance.config.face['insightface']?.enabled ? await insightface.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length) : null;
       instance.performance.mobilefacenet = Math.trunc(now() - timeStamp);
     }
     instance.analyze('End InsightFace:');
@@ -154,11 +154,11 @@ export const detectFace = async (instance: Human /* instance of human */, input:
     // run faceres, inherits face from blazeface
     instance.analyze('Start Description:');
     if (instance.config.async) {
-      descRes = faceres.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length);
+      descRes = faceres.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length);
     } else {
       instance.state = 'run:description';
       timeStamp = now();
-      descRes = await faceres.predict(faces[i].tensor as Tensor4D || tf.tensor([]), instance.config, i, faces.length);
+      descRes = await faceres.predict(faces[i].tensor || tf.tensor([]), instance.config, i, faces.length);
       instance.performance.description = env.perfadd ? (instance.performance.description || 0) + Math.trunc(now() - timeStamp) : Math.trunc(now() - timeStamp);
     }
     instance.analyze('End Description:');
@@ -194,10 +194,20 @@ export const detectFace = async (instance: Human /* instance of human */, input:
       (descRes as DescRes).descriptor = insightfaceRes as number[];
     }
 
-    const irisSize = instance.config.face.iris?.enabled ? calculateCameraDistance(faces[i], input.shape[2]) : 0;
+    // calculate iris distance
+    // iris: array[ center, left, top, right, bottom]
+    if (!instance.config.face.iris?.enabled) {
+      // if (faces[i]?.annotations?.leftEyeIris) delete faces[i].annotations.leftEyeIris;
+      // if (faces[i]?.annotations?.rightEyeIris) delete faces[i].annotations.rightEyeIris;
+    }
+    const irisSize = (faces[i]?.annotations?.leftEyeIris?.[0] && faces[i]?.annotations?.rightEyeIris?.[0]
+      && (faces[i].annotations.leftEyeIris.length > 0) && (faces[i].annotations.rightEyeIris.length > 0)
+      && (faces[i].annotations.leftEyeIris[0] !== null) && (faces[i].annotations.rightEyeIris[0] !== null))
+      ? Math.max(Math.abs(faces[i].annotations.leftEyeIris[3][0] - faces[i].annotations.leftEyeIris[1][0]), Math.abs(faces[i].annotations.rightEyeIris[4][1] - faces[i].annotations.rightEyeIris[2][1])) / input.shape[2]
+      : 0; // note: average human iris size is 11.7mm
 
     // optionally return tensor
-    const tensor = instance.config.face.detector?.return ? tf.squeeze(faces[i].tensor as Tensor4D) : null;
+    const tensor = instance.config.face.detector?.return ? tf.squeeze(faces[i].tensor) : null;
     // dispose original face tensor
     tf.dispose(faces[i].tensor);
     // delete temp face image
@@ -215,7 +225,7 @@ export const detectFace = async (instance: Human /* instance of human */, input:
     if (emotionRes) res.emotion = emotionRes as { score: number, emotion: Emotion }[];
     if (antispoofRes) res.real = antispoofRes as number;
     if (livenessRes) res.live = livenessRes as number;
-    if (irisSize > 0) res.distance = irisSize;
+    if (irisSize && irisSize !== 0) res.iris = Math.trunc(500 / irisSize / 11.7) / 100;
     if (rotation) res.rotation = rotation;
     if (tensor) res.tensor = tensor;
     faceRes.push(res);

src/face/faceboxes.ts

@@ -1,7 +1,7 @@
 // https://github.com/TropComplique/FaceBoxes-tensorflow
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log } from '../util/util';
+import * as tf from '../../dist/tfjs.esm.js';
 import { loadModel } from '../tfjs/load';
 import type { GraphModel, Tensor } from '../tfjs/types';
 import type { Config } from '../config';
@@ -9,11 +9,13 @@ import type { Config } from '../config';
 type Box = [number, number, number, number];
 
 export class FaceBoxes {
+  enlarge: number;
   model: GraphModel;
   config: Config;
   inputSize: 0;
 
   constructor(model, config: Config) {
+    this.enlarge = 1.1;
     this.model = model;
     this.config = config;
     this.inputSize = model.inputs[0].shape ? model.inputs[0].shape[2] : 0;
@@ -21,23 +23,22 @@ export class FaceBoxes {
 
   async estimateFaces(input, config) {
     if (config) this.config = config;
-    const enlarge = this.config.face.detector?.minConfidence || 0.1;
     const results: { confidence: number, box: Box, boxRaw: Box, image: Tensor }[] = [];
     const resizeT = tf.image.resizeBilinear(input, [this.inputSize, this.inputSize]);
     const castT = resizeT.toInt();
     const [scoresT, boxesT, numT] = await this.model.executeAsync(castT) as Tensor[];
     const scores = await scoresT.data();
     const squeezeT = tf.squeeze(boxesT);
-    const boxes = squeezeT.arraySync() as number[][];
+    const boxes = squeezeT.arraySync();
     scoresT.dispose();
     boxesT.dispose();
     squeezeT.dispose();
     numT.dispose();
     castT.dispose();
     resizeT.dispose();
-    for (let i = 0; i < boxes.length; i++) {
+    for (const i in boxes) {
       if (scores[i] && scores[i] > (this.config.face.detector?.minConfidence || 0.1)) {
-        const crop = [boxes[i][0] / enlarge, boxes[i][1] / enlarge, boxes[i][2] * enlarge, boxes[i][3] * enlarge];
+        const crop = [boxes[i][0] / this.enlarge, boxes[i][1] / this.enlarge, boxes[i][2] * this.enlarge, boxes[i][3] * this.enlarge];
         const boxRaw: Box = [crop[1], crop[0], (crop[3]) - (crop[1]), (crop[2]) - (crop[0])];
         const box: Box = [
           parseInt((boxRaw[0] * input.shape[2]).toString()),

src/face/facemesh.ts

@@ -7,9 +7,9 @@
  * - Eye Iris Details: [**MediaPipe Iris**](https://drive.google.com/file/d/1bsWbokp9AklH2ANjCfmjqEzzxO1CNbMu/view)
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log, now } from '../util/util';
 import { loadModel } from '../tfjs/load';
+import * as tf from '../../dist/tfjs.esm.js';
 import * as blazeface from './blazeface';
 import * as util from './facemeshutil';
 import * as coords from './facemeshcoords';
@@ -17,10 +17,11 @@ import * as iris from './iris';
 import * as attention from './attention';
 import { histogramEqualization } from '../image/enhance';
 import { env } from '../util/env';
-import type { GraphModel, Tensor, Tensor4D } from '../tfjs/types';
+import type { GraphModel, Tensor } from '../tfjs/types';
 import type { FaceResult, FaceLandmark, Point } from '../result';
 import type { Config } from '../config';
-import type { DetectBox } from './blazeface';
+
+interface DetectBox { startPoint: Point, endPoint: Point, landmarks: Point[], confidence: number }
 
 const cache = {
   boxes: [] as DetectBox[],
@@ -31,7 +32,8 @@ const cache = {
 let model: GraphModel | null = null;
 let inputSize = 0;
 
-export async function predict(input: Tensor4D, config: Config): Promise<FaceResult[]> {
+export async function predict(input: Tensor, config: Config): Promise<FaceResult[]> {
+  if (!model?.['executor']) return [];
   // reset cached boxes
   const skipTime = (config.face.detector?.skipTime || 0) > (now() - cache.timestamp);
   const skipFrame = cache.skipped < (config.face.detector?.skipFrames || 0);
@@ -59,7 +61,6 @@ export async function predict(input: Tensor4D, config: Config): Promise<FaceResu
       score: 0,
       boxScore: 0,
       faceScore: 0,
-      size: [0, 0],
       // contoursRaw: [],
       // contours: [],
       annotations: {} as Record<FaceLandmark, Point[]>,
@@ -73,14 +74,18 @@ export async function predict(input: Tensor4D, config: Config): Promise<FaceResu
       if (equilized) face.tensor = equilized;
     }
     face.boxScore = Math.round(100 * box.confidence) / 100;
-    if (!config.face.mesh?.enabled || !model?.['executor']) { // mesh not enabled or not loaded, return resuts from detector only
+    if (!config.face.mesh?.enabled) { // mesh not enabled, return resuts from detector only
       face.box = util.clampBox(box, input);
       face.boxRaw = util.getRawBox(box, input);
       face.score = face.boxScore;
-      face.size = box.size;
-      face.mesh = box.landmarks;
+      face.mesh = box.landmarks.map((pt) => [
+        ((box.startPoint[0] + box.endPoint[0])) / 2 + ((box.endPoint[0] + box.startPoint[0]) * pt[0] / blazeface.size()),
+        ((box.startPoint[1] + box.endPoint[1])) / 2 + ((box.endPoint[1] + box.startPoint[1]) * pt[1] / blazeface.size()),
+      ]);
       face.meshRaw = face.mesh.map((pt) => [pt[0] / (input.shape[2] || 0), pt[1] / (input.shape[1] || 0), (pt[2] || 0) / size]);
-      for (const key of Object.keys(coords.blazeFaceLandmarks)) face.annotations[key] = [face.mesh[coords.blazeFaceLandmarks[key] as number]]; // add annotations
+      for (const key of Object.keys(coords.blazeFaceLandmarks)) {
+        face.annotations[key] = [face.mesh[coords.blazeFaceLandmarks[key] as number]]; // add annotations
+      }
     } else if (!model) { // mesh enabled, but not loaded
       if (config.debug) log('face mesh detection requested, but model is not loaded');
     } else { // mesh enabled
@@ -95,12 +100,14 @@ export async function predict(input: Tensor4D, config: Config): Promise<FaceResu
       face.faceScore = Math.round(100 * faceConfidence[0]) / 100;
       if (face.faceScore < (config.face.detector?.minConfidence || 1)) { // low confidence in detected mesh
         box.confidence = face.faceScore; // reset confidence of cached box
-        if (config.face.mesh['keepInvalid']) {
+        if (config.face.mesh.keepInvalid) {
           face.box = util.clampBox(box, input);
           face.boxRaw = util.getRawBox(box, input);
-          face.size = box.size;
           face.score = face.boxScore;
-          face.mesh = box.landmarks;
+          face.mesh = box.landmarks.map((pt) => [
+            ((box.startPoint[0] + box.endPoint[0])) / 2 + ((box.endPoint[0] + box.startPoint[0]) * pt[0] / blazeface.size()),
+            ((box.startPoint[1] + box.endPoint[1])) / 2 + ((box.endPoint[1] + box.startPoint[1]) * pt[1] / blazeface.size()),
+          ]);
           face.meshRaw = face.mesh.map((pt) => [pt[0] / (input.shape[2] || 1), pt[1] / (input.shape[1] || 1), (pt[2] || 0) / size]);
           for (const key of Object.keys(coords.blazeFaceLandmarks)) {
             face.annotations[key] = [face.mesh[coords.blazeFaceLandmarks[key] as number]]; // add annotations
@@ -114,21 +121,15 @@ export async function predict(input: Tensor4D, config: Config): Promise<FaceResu
         if (config.face.attention?.enabled) {
           rawCoords = await attention.augment(rawCoords, results); // augment iris results using attention model results
         } else if (config.face.iris?.enabled) {
-          rawCoords = await iris.augmentIris(rawCoords, face.tensor, inputSize, config); // run iris model and augment results
+          rawCoords = await iris.augmentIris(rawCoords, face.tensor, inputSize); // run iris model and augment results
         }
         face.mesh = util.transformRawCoords(rawCoords, box, angle, rotationMatrix, inputSize); // get processed mesh
         face.meshRaw = face.mesh.map((pt) => [pt[0] / (input.shape[2] || 0), pt[1] / (input.shape[1] || 0), (pt[2] || 0) / size]);
         for (const key of Object.keys(coords.meshAnnotations)) face.annotations[key] = coords.meshAnnotations[key].map((index) => face.mesh[index]); // add annotations
         face.score = face.faceScore;
-        const calculatedBox = {
-          ...util.calculateFaceBox(face.mesh, box),
-          confidence: box.confidence,
-          landmarks: box.landmarks,
-          size: box.size,
-        };
+        const calculatedBox = { ...util.calculateFaceBox(face.mesh, box), confidence: box.confidence, landmarks: box.landmarks };
         face.box = util.clampBox(calculatedBox, input);
         face.boxRaw = util.getRawBox(calculatedBox, input);
-        face.size = calculatedBox.size;
         /*
         const contoursT = results.find((t) => t.shape[t.shape.length - 1] === 266) as Tensor;
         const contoursData = contoursT && await contoursT.data(); // 133 x 2d points

src/face/facemeshutil.ts

@@ -3,7 +3,7 @@
  * See `facemesh.ts` for entry point
  */
 
-import * as tf from 'dist/tfjs.esm.js';
+import * as tf from '../../dist/tfjs.esm.js';
 import * as coords from './facemeshcoords';
 import { constants } from '../tfjs/constants';
 import type { Box, Point } from '../result';
@@ -31,19 +31,10 @@ export const getRawBox = (box, input): Box => (box ? [
   (box.endPoint[1] - box.startPoint[1]) / (input.shape[1] || 0),
 ] : [0, 0, 0, 0]);
 
-export const scaleBoxCoordinates = (box, factor, anchor) => {
+export const scaleBoxCoordinates = (box, factor) => {
   const startPoint: Point = [box.startPoint[0] * factor[0], box.startPoint[1] * factor[1]];
   const endPoint: Point = [box.endPoint[0] * factor[0], box.endPoint[1] * factor[1]];
-  // const centerPoint = [(startPoint[0] + endPoint[0]) / 2, (startPoint[1] + endPoint[1]) / 2];
-  const landmarks = box.landmarks.map((pt) => [(pt[0] + anchor[0]) * factor[0], (pt[1] + anchor[1]) * factor[1]]);
-  /**
-  face.mesh = box.landmarks.map((pt) => [
-    ((box.startPoint[0] + box.endPoint[0]) / 2) + (pt[0] * input.shape[2] / blazeface.size()),
-    ((box.startPoint[1] + box.endPoint[1]) / 2) + (pt[1] * input.shape[1] / blazeface.size()),
-  ]);
-  */
-
-  return { startPoint, endPoint, landmarks, confidence: box.confidence };
+  return { startPoint, endPoint, landmarks: box.landmarks, confidence: box.confidence };
 };
 
 export const cutAndResize = (box, image, cropSize) => {
@@ -60,36 +51,20 @@ export const enlargeBox = (box, factor) => {
   const center = getBoxCenter(box);
   const size = getBoxSize(box);
   const halfSize: [number, number] = [factor * size[0] / 2, factor * size[1] / 2];
-  return {
-    startPoint: [center[0] - halfSize[0], center[1] - halfSize[1]] as Point,
-    endPoint: [center[0] + halfSize[0], center[1] + halfSize[1]] as Point,
-    landmarks: box.landmarks,
-    confidence: box.confidence,
-    size,
-  };
+  return { startPoint: [center[0] - halfSize[0], center[1] - halfSize[1]] as Point, endPoint: [center[0] + halfSize[0], center[1] + halfSize[1]] as Point, landmarks: box.landmarks, confidence: box.confidence };
 };
 
 export const squarifyBox = (box) => {
   const centers = getBoxCenter(box);
   const size = getBoxSize(box);
   const halfSize = Math.max(...size) / 2;
-  return {
-    startPoint: [Math.round(centers[0] - halfSize), Math.round(centers[1] - halfSize)] as Point,
-    endPoint: [Math.round(centers[0] + halfSize), Math.round(centers[1] + halfSize)] as Point,
-    landmarks: box.landmarks,
-    confidence: box.confidence,
-    size: [Math.round(size[0]), Math.round(size[1])] as [number, number],
-  };
+  return { startPoint: [Math.round(centers[0] - halfSize), Math.round(centers[1] - halfSize)] as Point, endPoint: [Math.round(centers[0] + halfSize), Math.round(centers[1] + halfSize)] as Point, landmarks: box.landmarks, confidence: box.confidence };
 };
 
 export const calculateLandmarksBoundingBox = (landmarks) => {
   const x = landmarks.map((d) => d[0]);
   const y = landmarks.map((d) => d[1]);
-  return {
-    startPoint: [Math.min(...x), Math.min(...y)] as Point,
-    endPoint: [Math.max(...x), Math.max(...y)] as Point,
-    landmarks,
-  };
+  return { startPoint: [Math.min(...x), Math.min(...y)] as Point, endPoint: [Math.max(...x), Math.max(...y)] as Point, landmarks };
 };
 
 export const fixedRotationMatrix = [[1, 0, 0], [0, 1, 0], [0, 0, 1]];
@@ -200,7 +175,7 @@ export function correctFaceRotation(rotate, box, input, inputSize) {
     if (largeAngle) { // perform rotation only if angle is sufficiently high
       const center: Point = getBoxCenter(box);
       const centerRaw: Point = [center[0] / input.shape[2], center[1] / input.shape[1]];
-      const rotated = tf.image.rotateWithOffset(input, angle, 0, [centerRaw[0], centerRaw[1]]);
+      const rotated = tf.image.rotateWithOffset(input, angle, 0, centerRaw);
       rotationMatrix = buildRotationMatrix(-angle, center);
       face = cutAndResize(box, rotated, [inputSize, inputSize]);
       tf.dispose(rotated);

src/face/faceres.ts

@@ -2,17 +2,17 @@
  * FaceRes model implementation
  *
  * Returns Age, Gender, Descriptor
- * Implements Face similarity function
+ * Implements Face simmilarity function
  *
  * Based on: [**HSE-FaceRes**](https://github.com/HSE-asavchenko/HSE_FaceRec_tf)
  */
 
-import * as tf from 'dist/tfjs.esm.js';
 import { log, now } from '../util/util';
 import { env } from '../util/env';
+import * as tf from '../../dist/tfjs.esm.js';
 import { loadModel } from '../tfjs/load';
 import { constants } from '../tfjs/constants';
-import type { Tensor, GraphModel, Tensor4D, Tensor1D } from '../tfjs/types';
+import type { Tensor, GraphModel } from '../tfjs/types';
 import type { Config } from '../config';
 import type { Gender, Race } from '../result';
 
@@ -32,17 +32,10 @@ export async function load(config: Config): Promise<GraphModel> {
   return model;
 }
 
-export function enhance(input, config: Config): Tensor {
-  const tensor = (input.image || input.tensor || input) as Tensor4D; // input received from detector is already normalized to 0..1, input is also assumed to be straightened
+export function enhance(input): Tensor {
+  const tensor = (input.image || input.tensor || input) as Tensor; // input received from detector is already normalized to 0..1, input is also assumed to be straightened
   if (!model?.inputs[0].shape) return tensor; // model has no shape so no point continuing
-  let crop: Tensor;
-  if (config.face.description?.['crop'] > 0) { // optional crop
-    const cropval = config.face.description?.['crop'];
-    const box = [[cropval, cropval, 1 - cropval, 1 - cropval]];
-    crop = tf.image.cropAndResize(tensor, box, [0], [model.inputs[0].shape[2], model.inputs[0].shape[1]]);
-  } else {
-    crop = tf.image.resizeBilinear(tensor, [model.inputs[0].shape[2], model.inputs[0].shape[1]], false);
-  }
+  const crop: Tensor = tf.image.resizeBilinear(tensor, [model.inputs[0].shape[2], model.inputs[0].shape[1]], false);
   const norm: Tensor = tf.mul(crop, constants.tf255);
   tf.dispose(crop);
   return norm;
@@ -65,7 +58,7 @@ export function enhance(input, config: Config): Tensor {
   */
 }
 
-export async function predict(image: Tensor4D, config: Config, idx: number, count: number): Promise<FaceRes> {
+export async function predict(image: Tensor, config: Config, idx: number, count: number): Promise<FaceRes> {
   const obj: FaceRes = {
     age: 0 as number,
     gender: 'unknown' as Gender,
@@ -82,7 +75,7 @@ export async function predict(image: Tensor4D, config: Config, idx: number, coun
   skipped = 0;
   return new Promise(async (resolve) => {
     if (config.face.description?.enabled) {
-      const enhanced = enhance(image, config);
+      const enhanced = enhance(image);
       const resT = model?.execute(enhanced) as Tensor[];
       lastTime = now();
       tf.dispose(enhanced);
@@ -93,7 +86,7 @@ export async function predict(image: Tensor4D, config: Config, idx: number, coun
         obj.gender = gender[0] <= 0.5 ? 'female' : 'male';
         obj.genderScore = Math.min(0.99, confidence);
       }
-      const argmax = tf.argMax(resT.find((t) => t.shape[1] === 100) as Tensor1D, 1);
+      const argmax = tf.argMax(resT.find((t) => t.shape[1] === 100), 1);
       const ageIdx: number = (await argmax.data())[0];
       tf.dispose(argmax);
       const ageT = resT.find((t) => t.shape[1] === 100) as Tensor;