数据库
属性
CelebA: 10,177 number of identities,202,599 number of face images, and 5 landmark locations, 40 binary attributes annotations per image.The ORL Database of Faces: 来自AT&T,图片有40个属性,受限场景,均匀背景幕布下采集,1992-1994年龄、性别、人种
MORPH: 需要$499,13673个人,共55608张。属性主打年龄,人种,性别。非受限条件采集图片。额外的还包括头发颜色(人种特征)眼镜,详细简介看这里UTKFace: 2W张人脸,主打人种、性别、年龄。CARC: 2k个名人的16W张图片,主要是年龄FG-NET:(82个人,共1002张),论文为ECCV论文Adience: 2284个人,共26580张,主要为年龄、性别识别CACD2000 :(2000个人,共163446张)LAPIMDB-Wiki dataset: 10W个艺人,由IMDB的2W名人的46W张人脸和Wikipedia的6W张人脸组成。主要是年龄、姓名、性别(20284个人,共523051张)MegaAge-Asian dataset: 4W张照片,主打年龄,亚洲人脸图片。主要用来后处理的方法。表情
JAFFECK+MMIFER- Faces Database: 约3w张图片,7种表情,微软表情比赛数据MSFDE: 多种族7种表情EmotiW一堆数据集关键点
BioID(1000张 20个关键点)LFPW:(1132 张,29个关键点)AFLW(25993张,21个关键点)COFW:(1852张,每个人脸标定29个关键点)ICCV13/MVFW :(2500张,68个关键点)OCFW: (3837张,68个关键点)300-W :(600张,68个关键点)WFLW: 10000 faces (7500 for training and 2500 for testing) with 98 fully manual annotated landmarks颜值
**SCUT-FBP5500-Database: 性别和颜值,亚洲和高加索人种,5500张图片开源项目(基本上都是多任务学习)
年龄
race_gender_recognition
数据:UTF论文: Gender and Race recognition: Transfer, Multi-task Learning for the Laziest
AgeGenderDeepLearning
数据:论文:Age and Gender Classification Using Convolutional Neural Networks,
smile detection, age and gender classification
数据:GENKI4k, IMDB-Wiki dataset论文:DEX: Deep EXpectation of apparent age from a single image
age-gender-estimation
数据: IMDB-WIKI dataset论文:[1]R. Rothe, R. Timofte, and L. V. Gool, “DEX: Deep EXpectation of apparent age from a single image,” in Proc. of ICCV, .[2]R. Rothe, R. Timofte, and L. V. Gool, “Deep expectation of real and apparent age from a single image without facial landmarks,” in IJCV, .
Agendernet
数据:IMDB-Wiki、Adience、UTKFace、FGNET论文:修改网络结构的SSR-NetIJCAI18 SSR-Net: A Compact Soft Stagewise Regression Network for Age Estimation
SSR-Net年龄和性别
数据: IMDB-WIKI dataset、Morph2论文:SSR。速度快
DEX表情年龄性别
相关论文
《Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach (PAMI- )》
《Deep Attribute Guided Representation for Heterogeneous Face Recognition (IJCAI-18)》
参考blog
人脸数据库大全(包括人脸识别、关键点检测、表情识别,人脸姿态等等)人脸属性分析–性别、年龄和表情识别额外年龄的数据库汇总
表格中的链接,需要参考这儿