Awesome
Face-Resources
Following is a growing list of some of the materials I found on the web for research on face recognition algorithm.
Papers
-
DeepFace.A work from Facebook.
-
FaceNet.A work from Google.
-
One Millisecond Face Alignment with an Ensemble of Regression Trees. Dlib implements the algorithm.
-
A Discriminative Feature Learning Approach for Deep Face Recognition
-
NormFace: L2 Hypersphere Embedding for Face Verification.* attention: model released !*
Datasets
- CASIA WebFace Database. 10,575 subjects and 494,414 images
- Labeled Faces in the Wild.13,000 images and 5749 subjects
- Large-scale CelebFaces Attributes (CelebA) Dataset 202,599 images and 10,177 subjects. 5 landmark locations, 40 binary attributes.
- MSRA-CFW. 202,792 images and 1,583 subjects.
- MegaFace Dataset 1 Million Faces for Recognition at Scale 690,572 unique people
- FaceScrub. A Dataset With Over 100,000 Face Images of 530 People.
- FDDB.Face Detection and Data Set Benchmark. 5k images.
- AFLW.Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization. 25k images.
- AFW. Annotated Faces in the Wild. ~1k images. 10.3D Mask Attack Dataset. 76500 frames of 17 persons using Kinect RGBD with eye positions (Sebastien Marcel)
- Audio-visual database for face and speaker recognition.Mobile Biometry MOBIO http://www.mobioproject.org/
- BANCA face and voice database. Univ of Surrey
- Binghampton Univ 3D static and dynamic facial expression database. (Lijun Yin, Peter Gerhardstein and teammates)
- The BioID Face Database. BioID group
- Biwi 3D Audiovisual Corpus of Affective Communication. 1000 high quality, dynamic 3D scans of faces, recorded while pronouncing a set of English sentences.
- Cohn-Kanade AU-Coded Expression Database. 500+ expression sequences of 100+ subjects, coded by activated Action Units (Affect Analysis Group, Univ. of Pittsburgh.
- CMU/MIT Frontal Faces . Training set: 2,429 faces, 4,548 non-faces; Test set: 472 faces, 23,573 non-faces.
- AT&T Database of Faces 400 faces of 40 people (10 images per people)
Trained Model
-
openface. Face recognition with Google's FaceNet deep neural network using Torch.
-
VGG-Face. VGG-Face CNN descriptor. Impressed embedding loss.
-
SeetaFace Engine. SeetaFace Engine is an open source C++ face recognition engine, which can run on CPU with no third-party dependence.
-
Caffe-face - Caffe Face is developed for face recognition using deep neural networks.
-
Norm-Face - Norm Face, finetuned from center-face and Light-CNN
Tutorial
- Deep Learning for Face Recognition. Shiguan Shan, Xiaogang Wang, and Ming yang.
Software
- OpenCV. With some trained face detector models.
- dlib. Dlib implements a state-of-the-art of face Alignment algorithm.
- ccv. With a state-of-the-art frontal face detector
- libfacedetection. A binary library for face detection in images.
- SeetaFaceEngine. An open source C++ face recognition engine.
##Frameworks
Miscellaneous
- faceswap Face swapping with Python, dlib, and OpenCV
- Facial Keypoints Detection Competition on Kaggle.
- An implementation of Face Alignment at 3000fps via Local Binary Features
Created by betars on 27/10/2015.