资讯
访谈百度IDL林元庆:百度大脑如何在人脸识别上战胜人类「最强大脑」
https://www.jiqizhixin.com/articles/2017-01-09
新智元–首发:人脸识别世界杯榜单出炉,微软百万名人识别竞赛冠军分享
https://mp.weixin.qq.com/s?__biz=MzI3MTA0MTk1MA==&mid=2652001114&idx=1&sn=decf0edb4f21dba0925c002f7c0ef0e2
新智元–【世界最大人脸对齐数据集】ICCV 2017:距离解决人脸对齐已不远
https://mp.weixin.qq.com/s/s5HL6y2P9_KqpSAQg08URw
雷锋网–详解苹果Face ID,将让深度摄像头成主流
https://mp.weixin.qq.com/s?__biz=MTM2ODM0ODYyMQ==&mid=2651429348&idx=1&sn=89b82730d645e2de518cf3706d6e6e40
深度学习大讲堂–韩琥:深度学习让机器给人脸“贴标签”
https://mp.weixin.qq.com/s/CLgyaAslE4hYHi62UhzeGw
SeetaFace开源人脸识别引擎介绍
http://blog.csdn.net/u013146742/article/details/52816640
深度学习大讲堂–【Technical Review】ECCV16 Center Loss及其在人脸识别中的应用
https://zhuanlan.zhihu.com/p/23340343
雷锋网–CNCC 2016 | 山世光:深度化的人脸检测与识别技术—进展与展望
https://www.leiphone.com/news/201610/rZ2Mn9UFF3x8FaEt.html
人脸识别中的活体检测
https://zhuanlan.zhihu.com/p/25401788
深度学习大讲堂–人脸检测与识别年度进展概述
https://mp.weixin.qq.com/s?__biz=MzI1NTE4NTUwOQ==&mid=2650326590&idx=1&sn=c195e063bc4bcd60edb6b7a83a751067
海康威视–人脸识别的两大系统方案PK,结果是
https://mp.weixin.qq.com/s/qG8R4RMKXJizPmZyEUqyMA
海康威视–强势解码后端人脸智能分析应用,奥秘原来在这儿
https://mp.weixin.qq.com/s/4zOYZU20hREtiiLbfSrW2A
海康威视–人脸识别99%准确率背后的秘密
http://www.7its.com/html/2017/anli_1207/6115.html
《人工智能强势来袭,听旷视(Face++)为你揭开智能零售的秘密》干货分享
http://www.sohu.com/a/73894297_355045
人脸图像保护和网纹人脸识别–李志航
https://mp.weixin.qq.com/s?src=11×tamp=1513759696&ver=585&signature=0Tbw-Jx9ffdWd86x1QChx7Pdbs3IUOBwn6xg63bjdPFsbK79M9JnX4aPOUGvVo3FISXSpgp7cSU3o4pdLEwREbrcbU0NGe1WqqPFqXWggBPPceyT4fiPQJUfey6geFxH&new=1
机器之心–从传统方法到深度学习,人脸关键点检测方法综述
https://mp.weixin.qq.com/s?__biz=MzA3MzI4MjgzMw==&mid=2650734809&idx=1&sn=f5dd841fb56b668dbc4dc4c2a668c195&chksm=871ac4a7b06d4db1befb03fb1616cea7ea158561125df55798209a2926bcfa31e131eb46d7d4#rd
Demystifying Face Recognition(1\2\3\4)
http://blcv.pl/static/2017/11/07/demystifying-face-recognition-i-introduction/
【VALSE 前沿技术选介17-06期】探究最陌生的老朋友Softmax
http://mp.weixin.qq.com/s/D4X_GMAwUu_WtC0layWZGA
新智元–【难度越大,优势越大】腾讯AI Lab刷新人脸识别与人脸检测国际记录
https://mp.weixin.qq.com/s/FcbCA7dHEeTpbCruYd4TjA
新智元–【深度】申省梅颜水成团队获国际非受限人脸识别竞赛IJB-A冠军,主要负责人熊霖技术分享
https://mp.weixin.qq.com/s/s9H_OXX-CCakrTAQUFDm8g
新智元–【微信身份证后的刷脸时代】活体识别告诉你为什么照片无法破解人脸系统
https://mp.weixin.qq.com/s/A1pbiU5PA9Owe69lGX9afw
机器之心–AAAI 2018 | 如何高效进行大规模分类?港中文联合商汤提出新方法
https://mp.weixin.qq.com/s/kLXJsHbBnRIFC3NLChPhzA
知乎–InsightFace - 使用篇, 如何一键刷分LFW 99.80%, MegaFace 98%.
https://zhuanlan.zhihu.com/p/33750684
知乎–深度挖坑:从数据角度看人脸识别中Feature Normalization,Weight Normalization以及Triplet的作用
https://zhuanlan.zhihu.com/p/33288325
深入浅出谈人脸识别技术
http://www.infoq.com/cn/articles/deep-learning-face-recognition
Head Pose Estimation using OpenCV and Dlib
https://www.learnopencv.com/head-pose-estimation-using-opencv-and-dlib/
https://www.learnopencv.com/rotation-matrix-to-euler-angles/
Blur detection with OpenCV
https://www.pyimagesearch.com/2015/09/07/blur-detection-with-opencv/
依图 1765 万元中标德清县公安局“雪亮工程”建设之人脸识别、车脸识别应用软件采购项目
http://www.sohu.com/a/225482558_465914
性能测试指标
http://blog.csdn.net/blueblood7/article/details/41823593
- 注册失败率 failure-to-enrol rate FTE
注册失败的用户在总注册用户中所占的比例 - 错误采集率 failure-to-acquire rate FTA
在辨识或验证的尝试中,采集不到样本或样本质量无法达到要求的比例 - 错误不匹配率 false non-match rate FNMR
正确的尝试样本被错误的判定微不匹配的比例 - 错误匹配率 false match rate FMR
零效攻击尝试样本被错误的判为匹配的比例 - 错误拒绝率 false refect rate FRR
验证识别过程中,真实者被错误判为拒绝的比例 - 错误接受率 false accept rate FAR
验证识别过程中,冒充者被错误判定为接受的比例 - 检测错误权衡曲线 detection error trade-off curve
DET曲线(x轴为FAR,y轴为FRR) - 接受者操作特性曲线 receiver operating character istic curve
ROC曲线(x轴为FAR,y轴为TPR)
FAR = FMR (1 – FTA)
FRR = FTA + FNMR (1 – FTA)
数据
MS-Celeb-1M: Recognizing One Million Celebrities in the Real World
http://www.msceleb.org/
微软人脸识别挑战比赛,相当于人脸识别领域的imagenet,包含10万人的约1000万人脸数据,是目前为止最大规模的数据集和比赛。
VGGFace2
http://www.robots.ox.ac.uk/~vgg/data/vgg_face2/
9131个id的331万人脸图像。
百度网盘: https://pan.baidu.com/s/1i4NYnuH 密码: dukf
CelebA: Large-scale CelebFaces Attributes (CelebA) Dataset
http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
香港中文大学组2015年搞的一个最新的目前最大的人脸集,包含10177个人,202599张人脸图片,而且每张图片有5个关键点标注信息以及40个2值属性,属性包括是否带眼睛,是否在笑,是否带帽子,是不是卷发,是否年轻,性别等等,是非常珍贵的人脸数据。
WIDER FACE: A Face Detection Benchmark
http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/
香港中文大学再放大招,2015年11月又推出人脸检测标注数据库,包含32203张图片,393703张人脸。其中50%的测试数据集并没有公开标注信息。
IMDB-WIKI
https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/
有人脸位置、性别、年龄的标注信息,共52万的标注图片
CASIA WebFace Database
http://www.cbsr.ia.ac.cn/english/CASIA-WebFace-Database.html
10,575 subjects and 494,414 images
CASIA clean-list:
https://github.com/happynear/FaceVerification
http://zhengyingbin.cc/ActiveAnnotationLearning/
Labeled Faces in the Wild
http://vis-www.cs.umass.edu/lfw/
13,000 images and 5749 subjects
MSRA-CFW
http://research.microsoft.com/en-us/projects/msra-cfw/
202,792 images and 1,583 subjects.
MegaFace Dataset
http://megaface.cs.washington.edu
passwd:bRx!XOx%of
1 Million Faces for Recognition at Scale 690,572 unique people
FaceScrub
http://vintage.winklerbros.net/facescrub.html
A Dataset With Over 100,000 Face Images of 530 People.
FDDB
http://vis-www.cs.umass.edu/fddb
Face Detection and Data Set Benchmark. 5k images.
AFLW
https://lrs.icg.tugraz.at/research/aflw/
Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark Localization. 25k images.
AFW
http://www.ics.uci.edu/~xzhu/face/
Annotated Faces in the Wild. ~1k images.
3D Mask Attack Dataset]
https://www.idiap.ch/dataset/3dmad
76500 frames of 17 persons using Kinect RGBD with eye positions (Sebastien Marcel)
Audio-visual database for face and speaker recognition
https://www.idiap.ch/dataset/mobio
Mobile Biometry MOBIO http://www.mobioproject.org/
BANCA face and voice database
http://www.ee.surrey.ac.uk/CVSSP/banca/
Univ of Surrey
Binghampton Univ 3D static and dynamic facial expression database
http://www.cs.binghamton.edu/~lijun/Research/3DFE/3DFE_Analysis.html
(Lijun Yin, Peter Gerhardstein and teammates)
The BioID Face Database
https://www.bioid.com/About/BioID-Face-Database
BioID group
Biwi 3D Audiovisual Corpus of Affective Communication
http://www.vision.ee.ethz.ch/datasets/b3dac2.en.html
1000 high quality, dynamic 3D scans of faces, recorded while pronouncing a set of English sentences.
Cohn-Kanade AU-Coded Expression Database
http://www.pitt.edu/~emotion/ck-spread.htm
500+ expression sequences of 100+ subjects, coded by activated Action Units (Affect Analysis Group, Univ. of Pittsburgh.
CMU/MIT Frontal Faces
http://cbcl.mit.edu/software-datasets/FaceData2.html
Training set: 2,429 faces, 4,548 non-faces; Test set: 472 faces, 23,573 non-faces.
kaggle表情数据
https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data
人脸表情数据集,7种表情(0=Angry, 1=Disgust, 2=Fear, 3=Happy, 4=Sad, 5=Surprise, 6=Neutral),训练集28709张图片,测试集3589张,像素48*48
人脸素描数据集
http://mmlab.ie.cuhk.edu.hk/archive/facesketch.html
606张人脸的素描和证件照的一一对应图像