Skip to content

Latest commit

 

History

History
 
 

face_recognition_sface

README.md

SFace

SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition

Note:

  • SFace is contributed by Yaoyao Zhong.
  • Model files encode MobileFaceNet instances trained on the SFace loss function, see the SFace paper for reference.
  • ONNX file conversions from original code base thanks to Chengrui Wang.
  • (As of Sep 2021) Supporting 5-landmark warping for now, see below for details.

Results of accuracy evaluation with tools/eval.

Models Accuracy
SFace 0.9940
SFace quant 0.9932

*: 'quant' stands for 'quantized'.

Demo

NOTE: This demo uses ../face_detection_yunet as face detector, which supports 5-landmark detection for now (2021sep).

Run the following command to try the demo:

Python

# recognize on images
python demo.py --target /path/to/image1 --query /path/to/image2

# get help regarding various parameters
python demo.py --help

C++

Install latest OpenCV and CMake >= 3.24.0 to get started with:

# A typical and default installation path of OpenCV is /usr/local
cmake -B build -D OPENCV_INSTALLATION_PATH=/path/to/opencv/installation .
cmake --build build

# detect on camera input
./build/demo -t=/path/to/target_face
# detect on an image
./build/demo -t=/path/to/target_face -q=/path/to/query_face -v
# get help messages
./build/demo -h

Example outputs

sface demo

Note: Left part of the image is the target identity, the right part is the query. Green boxes are the same identity, red boxes are different identities compared to the left.

License

All files in this directory are licensed under Apache 2.0 License.

Reference