add optional anti-spoofing module

master
Vladimir Mandic 2021-10-13 10:57:18 -04:00
parent e3e6effa32
commit 30924a8078
2 changed files with 11 additions and 0 deletions

@ -134,6 +134,14 @@ const config: Config = {
// only used when cacheSensitivity is not zero
modelPath: 'emotion.json', // face emotion model, can be absolute path or relative to modelBasePath
},
antispoof: {
enabled: false,
skipFrames: 14, // how max many frames to go without re-running the detector
// only used when cacheSensitivity is not zero
modelPath: 'antispoof.json', // face description model
// can be either absolute path or relative to modelBasePath
},
},
body: {

@ -14,6 +14,7 @@ Default models in Human library are:
- **Body Segmentation**: Google Selfie
- **Object Detection**: MB3 CenterNet
- **Body Segmentation**: Google Selfie
- **Face Anti-Spoofing**: Real-or-Fake
<br>
@ -103,6 +104,7 @@ Switching model also automatically switches implementation used inside `Human` s
| Google Selfie | 82K | selfie.json | 208K | selfie.bin | 136 |
| Hand Tracking | 605K | handtrack.json | 2.9M | handtrack.bin | 619 |
| GEAR Predictor | 28K | gear.json | 1.5M | gear.bin | 25 |
| Anti-Spoofing | 8K | antispoof.json | 834K | antispoof.bin | 11 |
<br>
@ -131,6 +133,7 @@ Switching model also automatically switches implementation used inside `Human` s
- Image Filters: [**WebGLImageFilter**](https://github.com/phoboslab/WebGLImageFilter)
- ObjectDetection: [**MB3-CenterNet**](https://github.com/610265158/mobilenetv3_centernet)
- ObjectDetection: [**NanoDet**](https://github.com/RangiLyu/nanodet)
- Anti-Spoofing: [**Real-of-Fake**](https://www.kaggle.com/anku420/fake-face-detection)
- Pinto Model Zoo: [**Pinto**](https://github.com/PINTO0309/PINTO_model_zoo)
*Included models are included under license inherited from the original model source*