•        26

The Deep Face Representation Experiment is based on Convolution Neural Network to learn a robust feature for face verification task. The popular deep learning framework caffe is used for training on face datasets such as CASIA-WebFace, VGG-Face and MS-Celeb-1M. And the feature extraction is realized by python code caffe_ftr.py. The single convolution net testing is evaluated on unsupervised setting only computing cosine similarity for lfw pairs.




Related Projects

node-facenet - Solve face verification, recognition and clustering problems: A TensorFlow backed FaceNet implementation for Node

  •    TypeScript

A TensorFlow backed FaceNet implementation for Node.js, which can solve face verification, recognition and clustering problems. FaceNet is a deep convolutional network designed by Google, trained to solve face verification, recognition and clustering problem with efficiently at scale.

LargeMargin_Softmax_Loss - Implementation for <Large-Margin Softmax Loss for Convolutional Neural Networks> in ICML'16

  •    C++

We introduce a large-margin softmax (L-Softmax) loss for convolutional neural networks. L-Softmax loss can greatly improve the generalization ability of CNNs, so it is very suitable for general classification, feature embedding and biometrics (e.g. face) verification. We give the 2D feature visualization on MNIST to illustrate our L-Softmax loss. The paper is published in ICML 2016 and also available at arXiv.

sphereface - Implementation for <SphereFace: Deep Hypersphere Embedding for Face Recognition> in CVPR'17

  •    Jupyter

SphereFace is released under the MIT License (refer to the LICENSE file for details). 2018.8.14: We recommand an interesting ECCV 2018 paper that comprehensively evaluates SphereFace (A-Softmax) on current widely used face datasets and their proposed noise-controlled IMDb-Face dataset. Interested users can try to train SphereFace on their IMDb-Face dataset. Take a look here.

NormFace - NormFace: L2 HyperSphere Embedding for Face Verification, 99.21% on LFW

  •    Matlab

* It is 98.13% on Light CNN's project page. After applying the mirror face trick, it becomes 98.41%. Evaluation codes are in my another github repository. Please refer to the second paragraph of the Update section.

FaceVerification - An Experimental Implementation of Face Verification, 96.8% on LFW.

  •    Matlab

A messy code for developing a face verfication program. It includes a C++ face detection / alignment program, joint bayesian and several supplementary codes. My Caffe model define file is also provided. Note that I use a fresh layer called Insanity to replace the ReLU activation. The Insanity layer can be found in my Caffe repository. Please feel free to use the codes if you need.

LightCNN - A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018

  •    Python

A pytorch implementation of A Light CNN for Deep Face Representation with Noisy Labels from the paper by Xiang Wu, Ran He, Zhenan Sun and Tieniu Tan. The official and original Caffe code can be found here. Download face dataset such as CASIA-WebFace, VGG-Face and MS-Celeb-1M.


  •    Javascript

Simple Node.js API for robust face detection and face recognition. This a Node.js wrapper library for the face detection and face recognition tools implemented in dlib. Installing the package will build dlib for you and download the models. Note, this might take some time.

facenet - Face recognition using Tensorflow

  •    Python

This is a TensorFlow implementation of the face recognizer described in the paper "FaceNet: A Unified Embedding for Face Recognition and Clustering". The project also uses ideas from the paper "Deep Face Recognition" from the Visual Geometry Group at Oxford. The code is tested using Tensorflow r1.7 under Ubuntu 14.04 with Python 2.7 and Python 3.5. The test cases can be found here and the results can be found here.

libface - Face Recognition Library

  •    C++

Libface is a cross platform framework for developing face recognition algorithms and testing its performance. The library uses OpenCV 2.0 and aims to be a middleware for developers that don’t have to include any OpenCV code in order to use face recognition and face detection detection.

face_recognition - The world's simplest facial recognition api for Python and the command line

  •    Python

Recognize and manipulate faces from Python or from the command line with the world's simplest face recognition library. Built using dlib's state-of-the-art face recognition built with deep learning. The model has an accuracy of 99.38% on the Labeled Faces in the Wild benchmark.

openface - Face recognition with deep neural networks.

  •    Lua

Free and open source face recognition with deep neural networks. This research was supported by the National Science Foundation (NSF) under grant number CNS-1518865. Additional support was provided by the Intel Corporation, Google, Vodafone, NVIDIA, and the Conklin Kistler family fund. Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and should not be attributed to their employers or funding sources.

AMSoftmax - A simple yet effective loss function for face verification.

  •    Matlab

The paper is available as a technical report at arXiv. In this work, we design a new loss function which merges the merits of both NormFace and SphereFace. It is much easier to understand and train, and outperforms the previous state-of-the-art loss function (SphereFace) by 2-5% on MegaFace.

mtcnn-caffe - Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks

  •    Python

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks. This project provide you a method to update multi-task-loss for multi-input source.



Malic is realtime face recognition system that based on Malib and CSU Face Identification Evaluation System (csuFaceIdEval). Uses Malib library for realtime image processing and some of csuFaceIdEval for face recognition.

Face-It - A repository of Processing examples for ITP fall workshop about face detection, recognition, and miscellaneous tracking methods

  •    Processing

A "syllabus" and repository of Processing examples for ITP fall workshop about face detection, recognition, and miscellaneous tracking methods.


  •    C++

SeetaFace Engine is an open source C++ face recognition engine, which can run on CPU with no third-party dependence. It contains three key parts, i.e., SeetaFace Detection, SeetaFace Alignment and SeetaFace Identification, which are necessary and sufficient for building a real-world face recognition applicaiton system. SeetaFace Detection implements a funnel-structured (FuSt) cascade schema for real-time multi-view face detection, which achieves a good trade-off between detection accuracy and speed. State of the art accuracy can be achieved on the public dataset FDDB in high speed. See SeetaFace Detection for more details.

OpenBR - Open Source Biometric Recognition

  •    C++

OpenBR is a framework for investigating new modalities, improving existing algorithms, interfacing with commercial systems, measuring recognition performance, and deploying automated biometric systems. Off-the-shelf algorithms are also available for specific modalities including Face Recognition, Age Estimation, and Gender Estimation.

PCN - Progressive Calibration Networks (PCN) is an accurate rotation-invariant face detector running at real-time speed on CPU, published in CVPR 2018

  •    C++

Progressive Calibration Networks (PCN) is an accurate rotation-invariant face detector running at real-time speed on CPU. This is a binary library for PCN (the networks in FastPCN is smaller than PCN). In this implementation, we don't use network quantization or compression, and the program runs on CPU with a single thread. PCN is designed aiming for low time-cost. We compare PCN's speed with other rotation-invariant face detectors' on standard VGA images(640x480) with 40x40 minimum face size. The detectors run on a desktop computer with 3.4GHz CPU, GTX Titan X. The speed results together with the recall rate at 100 false positives on multi-oriented FDDB are shown in the following table. Detailed experiment settings can be found in our paper.

Face Detection For Windows Phone 7


A library for performing face detection on windows phone 7. This library uses the same algorithms and detection models as OpenCV and is written in C# and built for the Windows Phone. Also includes a camera user control that supports automated taking of photos and showing camer...

We have large collection of open source products. Follow the tags from Tag Cloud >>

Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.