Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition

age-estimation body-segmentation body-tracking emotion-detection face-detection face-matching face-mesh face-position face-recognition faceid gaze-tracking gender-prediction gesture-recognition hand-tracking iris-tracking tensorflowjs tfjs

Go to file

Vladimir Mandic 41ff6e50af fix emotion labels		2021-01-06 06:51:20 -05:00
.github/ISSUE_TEMPLATE	Delete bug_report.md	2020-11-07 09:38:45 -05:00
assets	web worker fix	2021-01-03 10:41:56 -05:00
demo	remove iris coords if iris is disabled	2021-01-05 16:41:54 -05:00
dist	fix emotion labels	2021-01-06 06:51:20 -05:00
models	major work on body module	2020-12-16 18:36:24 -05:00
server	update to tfjs 2.8.2	2021-01-03 10:23:45 -05:00
src	fix emotion labels	2021-01-06 06:51:20 -05:00
wiki@766a4e2504	full rebuild	2021-01-05 16:50:25 -05:00
.eslintrc.json	ui redesign	2020-11-19 14:45:59 -05:00
.gitignore	major work on body module	2020-12-16 18:36:24 -05:00
.gitmodules	updated wiki	2020-11-07 09:42:54 -05:00
LICENSE	Initial commit	2020-10-11 19:14:20 -04:00
README.md	updated readme	2020-12-21 08:12:18 -05:00
config.js	added rawBox and rawMesh	2020-12-22 12:34:47 -05:00
favicon.ico	refactored package file layout	2020-10-17 06:30:00 -04:00
manifest.json	fixed memory leaks and updated docs	2020-11-06 16:21:20 -05:00
package-lock.json	full rebuild	2021-01-05 16:50:25 -05:00
package.json	0.9.22	2021-01-05 16:49:55 -05:00
tsconfig.json	stricter linting, fix face annotations	2020-12-27 08:12:22 -05:00

README.md

Human Library

3D Face Detection, Face Embedding & Recognition, Body Pose Tracking, Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction & Gesture Recognition

Project pages:

Wiki pages:

Additional notes:

Compatible with Browser, WebWorker and NodeJS execution on both Windows and Linux

Browser/WebWorker: Compatible with CPU, WebGL, WASM and WebGPU backends
NodeJS: Compatible with software tfjs-node and CUDA accelerated backends tfjs-node-gpu
(and maybe with React-Native as it doesn't use any DOM objects)

This is a pre-release project, see issues for list of known limitations and planned enhancements

Suggestions are welcome!

Options

Examples

Using static images:

Using webcam: