■Annotated Database (Hand, Meat, LV Cardiac, IMM face) (http://www2.imm.dtu.dk/~aam/)
■AR Face Database (http://cobweb.ecn.purdue.edu/~aleix/aleix_face_DB.html)
■BioID Face Database (http://www.bioid.com/downloads/facedb/index.php)
■Caltech Computational Vision Group Archive (Cars, Motorcycles, Airplanes, Faces, Leaves, Background) (http://www.vision.caltech.edu/html-files/archive.html)
■Carnegie Mellon Image Database (motion, stereo, face, car, ...) (http://vasc.ri.cmu.edu/idb/)
■CAS-PEAL Face Database (http://www.jdl.ac.cn/peal/index.html)
■CMU Cohn-Kanade AU-Coded Facial Expression Database (http://www.ri.cmu.edu/projects/project_421.html
■CMU Face Detection Databases (http://www.ri.cmu.edu/projects/project_419.html)
■CMU Face Expression Database (http://amp.ece.cmu.edu/projects/FaceAuthentication/download.htm)
■CMU Face Pose, Illumination, and Expression (PIE) Database (http://www.ri.cmu.edu/projects/project_418.html)
■CMU VASC Image Database (motion, road sequences, stereo, CIL’s stereo data with ground truth, JISCT, face, face expressions, car) (http://www.ius.cs.cmu.edu/idb/)
■Content-based Image Retrieval Database (http://www.cs.washington.edu/research/imagedatabase/groundtruth/)
■Face Video Database of the Max Planck Institute for Biological Cybernetics (http://vdb.kyb.tuebingen.mpg.de/)
■FERET Database (http://www.frvt.org/)
■FERET Color Database (http://www.itl.nist.gov/iad/humanid/colorferet/home.html http://face.nist.gov/colorferet/ )
■Georgia Tech Face Database (http://www.anefian.com/face_reco.htm)
■German Fingerspelling Database (http://www.anefian.com/face_reco.htm )
■Indian Face Database (http:// www.cs.umass.edu/~vidit/IndianFaceDatabase)
■MIT-CBCL Car Database (http://cbcl.mit.edu/software-datasets/CarData.html)
■MIT-CBCL Face Recognition Database (http://cbcl.mit.edu/software-datasets/heisele/facerecognition-database.html)
■MIT-CBCL Face Databases (http://cbcl.mit.edu/software-datasets/FaceData2.html)
■MIT-CBCL Pedestrian Database (http://cbcl.mit.edu/software-datasets/PedestrianData.html)
■MIT-CBCL Street Scenes Database (http://cbcl.mit.edu/software-datasets/streetscenes/)
■NIST/Equinox Visible and Infrared Face Image Database (http://www.equinoxsensors.com/products/HID.html)
■NIST Fingerprint Data at Columbia (Link)
■ORL Database of Faces (http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html)
■Rutgers Skin Texture Database (http://www.caip.rutgers.edu/rutgers_texture/)
■The Japanese Female Facial Expression (JAFFE) Database (http://www.kasrl.org/jaffe.html
■The Ohio State University SAMPL Image Database (3D, still, motion) (http://sampl.ece.ohio-state.edu/database.htm)
■The University of Oulu Physics-Based Face Database (http://www.ee.oulu.fi/research/imag/color/pbfd.html)
■UMIST Face Database (http://images.ee.umist.ac.uk/danny/database.html)
■USF Range Image Data (with ground truth) (http://marathon.csee.usf.edu/range/DataBase.html)
■Usenix Face Database (hundreds of images, several formats) (Link)
■UCI Machine Learning Repository (http://www1.ics.uci.edu/~mlearn/MLSummary.html)
■USC-SIPI Image Database (collection of digitized images) (http://sipi.usc.edu/services/database/Database.html)
■UCD VALID Database (multimodal for still face, audio, and video) (http://ee.ucd.ie/validdb/)
■UCD Color Face Image (UCFI) Database for Face Detection (http://ee.ucd.ie/~prag/)
■UCL M2VTS Multimodal Face Database (http://www.tele.ucl.ac.be/PROJECTS/M2VTS/m2fdb.html)
■Vision Image Archive at UMass (sequences, stereo, medical, indoor, outlook, road, underwater, aerial, satellite, space and more) (http://sipi.usc.edu/database/)
■Where can I find Lenna and other images? (http://www.faqs.org/faqs/compression-faq/part1/section-30.html)
■Yale Face Database (http://cvc.yale.edu/projects/yalefaces/yalefaces.html)
■Yale Face Database B (http://cvc.yale.edu/projects/yalefaces/yalefaces.html)
目前人脸识别领域常用的人脸数据库主要有:
1. FERET人脸数据库[2]
由FERET项目创建,包含14,051张多姿态,光照的灰度人脸图像,是人脸识别领域应用最广泛
的人脸数据库之一.其中的多数人是西方人,每个人所包含的人脸图像的变化比较单一.
2. MIT人脸数据库[4]
由麻省理工大学媒体实验室创建,包含16位志愿者的2,592张不同姿态,光照和大小的面部图像.
3. Yale人脸数据库[5]
由耶鲁大学计算视觉与控制中心创建,包含15位志愿者的165张图片,包含光照,表情和姿态
的变化.
4. Yale人脸数据库B[6]
包含了10个人的5,850幅多姿态,多光照的图像.其中的姿态和光照变化的图像都是在严格控制
的条件下采集的,主要用于光照和姿态问题的建模与分析.由于采集人数较少,该数据库的进一步应
用受到了比较大的限制.
5. PIE人脸数据库[7]
由美国卡耐基梅隆大学创建,包含68位志愿者的41,368张多姿态,光照和表情的面部图像.其
中的姿态和光照变化图像也是在严格控制的条件下采集的,目前已经逐渐成为人脸识别领域的一个重
要的测试集合.
6. ORL人脸数据库[8]
由剑桥大学AT&T实验室创建,包含40人共400张面部图像,部分志愿者的图像包括了姿态,
表情和面部饰物的变化.该人脸库在人脸识别研究的早期经常被人们采用,但由于变化模式较少,多
数系统的识别率均可以达到90%以上,因此进一步利用的价值已经不大.
7. PF01人脸数据库[9]
由韩国浦项科技大学创建,包含103人的1,751张不同光照,姿态,表情的面部图像,志愿者以
韩国人为主.
8. AR人脸数据库[10]
由西班牙巴塞罗那计算机视觉中心建立,包含116人的3,288幅图像.采集环境中的摄像机参数,
光照环境,摄像机距离等都是严格控制的.
9. BANCA人脸数据库[11]
该数据库是欧洲BANCA计划的一部分,包含了208人,每人12幅不同时间段的面部图像.
10. KFDB人脸数据库[12]
包含了1,000人,共52,000幅多姿态,多光照,多表情的面部图像,其中姿态和光照变化的图像
是在严格控制的条件下采集的.志愿者以韩国人为主.
11. MPI人脸数据库[13]
该人脸数据库包含了200人的头部3维结构数据和1,400幅多姿态的人脸图像.
12. XM2VTS人脸数据库[14]
包含了295人在4个不同时间段的图像和语音视频片断.在每个时间段,每人被记录了2个头部
旋转的视频片断和6个语音视频片断.此外,其中的293人的3维模型也可得到.