Face Databases

介绍了人脸识别中常用的人脸库

AR Face Database

Richard's MIT database
CVL Database
The Psychological Image Collection at Stirling
Labeled Faces in the Wild
The MUCT Face Database
The Yale Face Database B
The Yale Face Database 
PIE Database
The UMIST Face Database 
Olivetti - Att - ORL 
The Japanese Female Facial Expression (JAFFE) Database
The Human Scan Database
The University of Oulu Physics-Based Face Database 

XM2VTSDB 

Databases with over 100 unique individuals in them

Name: AR Face Database  
Color Images: Yes  
Image Size: 576 x 768  
Number of unique people: 126; 70 Male, 56 Female  
Number of pictures per person: 26  
Different Conditions: All frontal views of: neutral expression, smile, anger, scream, left light on, right light on, all sides lights on, wearing sun glasses, wearing sun glassses and left light on, wearing sun glasses and right light on, wearing scarf, wearing scarf and left light on, wearing scarf and right light on; second sessions repeated same conditions.  
Citation reference: A.M. Martinez and R. Benavente. The AR Face Database. CVC Technical Report #24, June 1998  
Available: Yes  



Name: Richard's MIT database  
Color Images: Yes  
Image Size: 480 x 640  
Number of unique people: 154; 82 Male, 74 Female  
Number of pictures per person: 6  
Different Conditions: 2 frontal, profile, and 3/4 view - also some additional pictures of students wearing makeup
Available: Yes  



Name: CVL Database  
Color Images: Yes  
Image Size: 640 x 480  
Number of unique people: 114; 108 Male, 6 Female  
Number of pictures per person: 7  
Different Conditions: profile left/right, 45 degrees left/right, frontal, frontal smile, frontal smile with teeth  
Citation reference: Franc Solina, Peter Peer, Borut Batagelj, Samo Juvan, Jure Kovac, "Color-based face detection in the "15 seconds of fame" art installation", In: Mirage 2003, Conference on Computer Vision / Computer Graphics Collaboration for Model-based Imaging, Rendering, image Analysis and Graphical special Effects, March 10-11 2003, INRIA Rocquencourt, France, Wilfried Philips, Rocquencourt, INRIA, 2003, pp. 38-47.  
Available : Yes  



Name: The Psychological Image Collection at Stirling (PICS)  
Note: The Psychological Image Collection at Stirling contains a number of databases, below are listed the four largest ones.  
Citation reference: Not sure - contact Peter Hancock ([email protected]) to find out who to reference  
Available : Yes  



Name: notingham scans  
Color Images: No  
Image Size: 438 x 538  
Number of unique people: 100; 50 Male, 50 Female  
Number of pictures per person: 1  
Different Conditions: All frontal views  



Name: aberdeen  
Color Images: Yes  
Image Size: 432 x 528  
Number of unique people: 116  
Number of pictures per person: Ranges from 1 to around 18, there is a total of 690 image in the database  
Different Conditions: All frontal view, two main differences in lighting and some expression variation  



Name: nott-faces-originals  
Color Images: No  
Image Size: 288 x 384  
Number of unique people: around 100 - almost all male  
Number of pictures per person: 7  
Different Conditions: Mostly frontal, a few profile  



Name: notingham scans  
Color Images: No  
Image Size: 438 x 538  
Number of unique people: 100; 50 Male, 50 Female  
Number of pictures per person: 1  
Different Conditions: All frontal views  



Name: Stirling_faces  
Color Images: No  
Image Size: 280 x 365  
Number of unique people: 36; 18 Males, 18 Females  
Number of pictures per person: ~9  
Different Conditions: Frontal and profile views  



Name: Labeled Faces in the Wild  
Color Images: Yes  
Image Size: 150 x 150  
Number of unique people: 13,233  
Number of pictures per person: Varies, but 1,680 individuals with more than 1 image  
Different Conditions: Un-posed photos, but mainly frontal views  
Citation reference: Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. University of Massachusetts, Amherst, Technical Report 07-49, October, 2007.  
Available : Free download from website  



Name: The MUCT Face Database  
Color Images: Yes  
Image Size: 480 x 640  
Number of unique people: 276  
Number of pictures per person: 10 to 15  
Different Conditions: frontal and three-quarter views, different lighting sets, manual landmarks  
Citation reference: S. Milborrow, J. Morkel, and F. Nicolls. The MUCT Landmarked Face Database. PRASA. 2010.  
Available : Yes  



Databases with less than 100 unique individuals in them


Name: The Yale Face Database B  
Color Images: No  
Image Size: 640 x 480  
Number of unique people: 10  
Number of pictures per person: 576  
Different Conditions: 9 poses x 64 illumination conditions  
Citation reference: Georghiades, A.S. and Belhumeur, P.N. and Kriegman, D.J. From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose. IEEE Trans. Pattern Anal. Mach. Intelligence 23(6):643-660 (2001).  
Available : Yes - facial marker points also available  


Name: The Yale Face Database  
Color Images: No  
Image Size: 320 x 243  
Number of unique people: 15  
Number of pictures per person: 11  
Different Conditions: center-light, w/glasses, happy, left-light, w/no glasses, normal, right-light, sad, sleepy, surprised, wink  
Citation reference: P. N. Bellhumer, J. Hespanha, and D. Kriegman. Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, Special Issue on Face Recognition, 17(7):711--720, 1997.  
Available : Yes  


Name: PIE Database  
Color Images: Yes  
Image Size: 640 x 486  
Number of unique people: 68  
Number of pictures per person: A lot (40GB total) - we have a subset of one picture per individual  
Different Conditions: 13 different poses, 43 different illumination conditions, and with 4 different expressions.  
Citation reference: The CMU Pose, Illumination, and Expression Database T. Sim, S. Baker, and M. Bsat IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, No. 12, December, 2003  
Available : Subset (one picture of each individual); to get the whole database (40GB) send a hard drive to [email protected]  


Name: The UMIST Face Database  
Color Images: No  
Image Size: 220 x 220  
Number of unique people: 20  
Number of pictures per person: From around 19 to 36  
Different Conditions: Various angles from left profile to right profile.  
Citation reference: TCharacterizing Virtual Eigensignatures for General Purpose Face Recognition. Daniel B Graham and Nigel M Allinson. Face Recognition: From Theory to Applications, NATO ASI Series F, Computer and Systems Sciences, Vol. 163. H. Wechsler, P. J. Phillips, V. Bruce, F. Fogelman-Soulie and T. S. Huang (eds), pp 446-456, 1998.  
Available : Yes  


Name: Olivetti - Att - ORL  
Color Images: No  
Image Size: 92 x 112  
Number of unique people: 40  
Number of pictures per person: 10  
Different Conditions: All frontal and slight tilt of the head  
Citation reference: Ferdinando Samaria, Andy Harter. Parameterisation of a Stochastic Model for Human Face Identification. Proceedings of 2nd IEEE Workshop on Applications of Computer Vision, Sarasota FL, December 1994  
Available : Yes  


Name: The Japanese Female Facial Expression (JAFFE) Database  
Color Images: No  
Image Size: 256 x 256  
Number of unique people: 10  
Number of pictures per person: 7  
Different Conditions: 7 different emotional facial expressions  
Citation reference: Coding Facial Expressions with Gabor Wavelets Michael J. Lyons, Shigeru Akamatsu, Miyuki Kamachi & Jiro Gyoba Proceedings, Third IEEE International Conference on Automatic Face and Gesture Recognition, April 14-16 1998, Nara Japan, IEEE Computer Society, pp. 200-205.  
Available : Yes  


Name: The Human Scan Database  
Color Images: No  
Image Size: 384 x 286  
Number of unique people: 23  
Number of pictures per person: around 66 on average  
Different Conditions: mainly frontal views, a bunch random different photos of different people  
Citation reference: O. Jesorsky, K. Kirchberg, R. Frischholz.Robust Face Detection Using the Hausdorff Distance. In J. Bigun and F. Smeraldi, editors, Audio and Video based Person Authentication - AVBPA 2001, pages 90-95. Springer, 2001.  
Available : Yes - facial points also available  




Databases that cost money


Name: The University of Oulu Physics-Based Face Database  
Color Images: Yes  
Image Size: 428 x 569  
Number of unique people: 125  
Number of pictures per person: 16  
Different Conditions: All frontal images: 16 different camera calibration and illuminations  
Citation reference: E. Marszalec, B. Martinkauppi, M. Soriano, M. Pietik鋓nen (2000), 'A physics-based face database for color research', Journal of Electronic Imaging Vol. 9 No. 1 pp. 32-38.  
Available : No - Cost $50, email Prof. Matti Pietikainen ([email protected])  


Name: XM2VTSDB  
Color Images: Yes  
Image Size: 576 x 720  
Number of unique people: 295  
Number of pictures per person: Depends on database purchased - 4 in frontal database; 4 of both left/right profile in profile database  
Different Conditions: frontal, profile, VRML modles, speech, and more, see website  
Citation reference: K Messer, J Matas, J Kittler, J Luettin, and G maitre. Xm2vtsdb: The extended m2vts database. In Second International Conference of Audio and Video-based Biometric Person Authentication, March 1999  
Available : No: costs a fair amount to purchase - Frontal Image Set = $153, Side Profile Image Set = $229.5  



Other useful links

Computer Vision Test Images  - a page with links to other sites with more images 
Irfan View  - a great image viewer that has useful conversion and renaming utilities 

数据来源:http://web.mit.edu/emeyers/www/face_databases.html#yaleB

你可能感兴趣的:(模式识别)