This is an open source library for CNN-based face detection in images. The CNN model has been converted to static variables in C source files. The source code does not depend on any other libraries. What you need is just a C++ compiler. You can compile the source code under Windows, Linux, ARM and any platform with a C++ compiler.
SIMD instructions are used to speed up the detection. You can enable AVX2 if you use Intel CPU or NEON for ARM.
The model files are provided in src/facedetectcnn-data.cpp (C++ arrays) & the model (ONNX) from OpenCV Zoo. You can try our scripts (C++ & Python) in opencv_dnn/ with the ONNX model. View the network architecture here.
examples/detect-image.cpp and examples/detect-camera.cpp show how to use the library.
The library was trained by libfacedetection.train.
You can copy the files in directory src/ into your project, and compile them as the other files in your project. The source code is written in standard C/C++. It should be compiled at any platform which supports C/C++.
Some tips:
- Please add facedetection_export.h file in the position where you copy your facedetectcnn.h files, add #define FACEDETECTION_EXPORT to facedetection_export.h file. See: issues #222
- Please add -O3 to turn on optimizations when you compile the source code using g++.
- Please choose 'Maximize Speed/-O2' when you compile the source code using Microsoft Visual Studio.
- You can enable OpenMP to speedup. But the best solution is to call the detection function in different threads.
You can also compile the source code to a static or dynamic library, and then use it in your project.
| Method | Time | FPS | Time | FPS |
|---|---|---|---|---|
| X64 | X64 | X64 | X64 | |
| Single-thread | Single-thread | Multi-thread | Multi-thread | |
| cnn (CPU, 640x480) | 58.06ms. | 17.22 | 12.93ms | 77.34 |
| cnn (CPU, 320x240) | 13.77ms | 72.60 | 3.19ms | 313.14 |
| cnn (CPU, 160x120) | 3.26ms | 306.81 | 0.77ms | 1293.99 |
| cnn (CPU, 128x96) | 1.41ms | 711.69 | 0.49ms | 2027.74 |
- Minimal face size ~10x10
- Intel(R) Core(TM) i7-1065G7 CPU @ 1.3GHz
| Method | Time | FPS | Time | FPS |
|---|---|---|---|---|
| Single-thread | Single-thread | Multi-thread | Multi-thread | |
| cnn (CPU, 640x480) | 492.99ms | 2.03 | 149.66ms | 6.68 |
| cnn (CPU, 320x240) | 116.43ms | 8.59 | 34.19ms | 29.25 |
| cnn (CPU, 160x120) | 27.91ms | 35.83 | 8.43ms | 118.64 |
| cnn (CPU, 128x96) | 17.94ms | 55.74 | 5.24ms | 190.82 |
- Minimal face size ~10x10
- Raspberry Pi 4 B, Broadcom BCM2835, Cortex-A72 (ARMv8) 64-bit SoC @ 1.5GHz
Run on default settings: scales=[1.], confidence_threshold=0.02, floating point:
AP_easy=0.887, AP_medium=0.871, AP_hard=0.768
- Shiqi Yu, shiqi.yu@gmail.com
All contributors who contribute at GitHub.com are listed here.
The contributors who were not listed at GitHub.com:
- Jia Wu (吴佳)
- Dong Xu (徐栋)
- Shengyin Wu (伍圣寅)
The work was partly supported by the Science Foundation of Shenzhen (Grant No. 20170504160426188).
We published a paper on face detection to evaluate different methods. This project has also been evaluated in the paper.
@article{facedetect-yu,
author={Yuantao Feng and Shiqi Yu and Hanyang Peng and Yan-ran Li and Jianguo Zhang}
title={Detect Faces Efficiently: A Survey and Evaluations},
journal={IEEE Transactions on Biometrics, Behavior, and Identity Science},
year={2021}
}
The paper can be open accessed at https://ieeexplore.ieee.org/document/9580485
The loss used in training is EIoU, a novel extended IoU. More details can be found in:
@article{eiou,
author={Peng, Hanyang and Yu, Shiqi},
journal={IEEE Transactions on Image Processing},
title={A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization},
year={2021},
volume={30},
pages={5032-5044},
doi={10.1109/TIP.2021.3077144}
}
The paper can be open accessed at https://ieeexplore.ieee.org/document/9429909.