face detection alignment recognition reconstruction base on some projects on github, aim to build state of art face system. currently reconstruction is not available, code is not elegant.
- OpenFace: an open source facial behavior analysis toolkit
- Constrained Local Neural Fields for robust facial landmark detection in the wild
- Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields
- Hand Keypoint Detection in Single Images using Multiview Bootstrapping
- Convolutional pose machines
- Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks
- SphereFace: Deep Hypersphere Embedding for Face Recognition
- Large-Margin Softmax Loss for Convolutional Neural Networks
Success algin 453078 of 455594 images, take about 1.11hour, hope someone can increase detection rate and reduce run time.
- Aligned example
- Failed example
- OpenCV (>=3.0)
- Boost (>=1.63)
- SphereCaffe
- CUDA (>=8.0)
- Install all requirements
- git clone https://github.com/tpys/face-everthing.git
- change line 44 & 45 in CMakeList.txt to your spherecaffe corresponding directory
- cd face-everthing && mkdir build && cd build && make -j4
- Download trained model(https://pan.baidu.com/s/1boOOBNL code: juk3)
- Modify example/mtcnn_align_dataset.cpp, change the input parameters to yours
- Modify example/all_in_one.cpp, change the input parameters to yours
- move cln part to tracking modules
- add recently fan 2d & 3d alignment
- speed up alignment, maybe batch gpu forward, small model, gpu implementation tracking.
- train more accurate recognition model
- Anything helps this repo, including discussion, testing, promotion and of course your awesome code.