Evaluating the Complexity of Databases for Person Identification and Verification
Databases play an important role for the development and evaluation of methods for person identification, verification, and other tasks. Despite this fact, there exists no measure that indicates whether a given database is sufficient to train and/or to test a given algorithm. This paper proposes a method to rank the complexity of databases, respectively to validate whether a database is appropriate for the simulation of a given application. The first nearest neighbor and the mean square distance are validated to be suitable as minimal performance measures with respect to the problems of person verification and person identification.
KeywordsPerson identification person verification database evaluation
Unable to display preview. Download preview PDF.
- 1.B. Ackermann: Bern data base (1995). Anonymous ftp://iamftp.unibe.ch/pub/Images/FaceImages/55 Evaluating the Complexity of Databases for Person Identification and Verification
- 3.IEEE Int. Conf. on Automatic Face and Gesture Recognition, Killington, Vermont, IEEE (October 14–16, 1998).Google Scholar
- 4.IEEE Proc. of the Second Int. Conf. on Automatic Face and Gesture Recognition, Nara, Japan, IEEE (April 14–16 1998).Google Scholar
- 5.P. N. Belhumeur and D. J. Kriegman: The Yale face database (1997). http://giskard.eng.yale.edu/yalefaces/yalefaces.html.
- 6.J. Bigün, G. Chollet, and G. Borgefors, eds.: Audio-and Video-based Biometric Person Authentication (AVBPA'97), Lecture Notes in Computer Science 1206, Crans-Montana, Switzerland, Springer (March 1997).Google Scholar
- 7.H. Burkhardt and B. Neumann, eds.: Computer Vision — ECCV'98, II of Lecture Notes in Computer Science 1406, Freiburg, Germany, Springer (June 1998).Google Scholar
- 8.IEEE Computer Society Conf. on Computer Vision and Pattern Recognition (CVPR-96), San Francisco, California (June 18—20, 1996).Google Scholar
- 9.P. Kruizinga: The face recognition home page. http://www.cs.rug.nl/~peterkr/FACE/face.html.
- 12.S.Z. Li and J. Lu: Generalized capacity of face database for face recognition, in  402–405.Google Scholar
- 13.K. Messer, J. Matas, J. Kittler, J. Luettin, and G. Maitre: XM2VTSDB: The extended m2vts database, in Proc. Second Int. Conf. on Audio-and Video-based Biometric Person Authentication (AVBPA'99) (1999). http://www.ee.surrey.ac.uk/research/vssp/xm2vts
- 14.Y. Moses: Weizmann institute database (1997). Anonymous ftp://ftp.eris.weizmann.ac.il/pub/FaceBase.
- 16.A. V. Nefian and M. H. HayesIII: Hidden markov models for face recognition, in ICASSP'98 5, IEEE (1998) 2721–2724.Google Scholar
- 17.S. Pigeon and L. Vandendorpe: The M2VTS multimodal face database, in J. Bigün, G. Chollet, and G. Borgefors, eds.: Audio-and Video-based Biometric Person Authentication (AVBPA'97), Lecture Notes in Computer Science 1206, Crans-Montana, Switzerland, Springer (March 1997) .Google Scholar
- 18.P. Phillips, H. Wechsler, J. Huang, and P. Rauss: The FERET database and evaluation procedure for face recognition algorithms. To appear in: Image and Vision Computing Journal (1998).Google Scholar
- 19.F. Samaria and A. Harter: Parameterization of a stochastic model for human face identification, in Proc. of 2nd IEEE Workshop on Applications of Computer Vision, Sarasota, FL (1994). http://www.cam-orl.co.uk/facedatabase.html.
- 20.F. S. Samaria: Face Recognition using Hidden Markov Models. PhD thesis, Trinity College, University of Cambridge, Cambridge (1995).Google Scholar
- 23.J. Zhang, Y. Yan, and M. Lades: Face recognition: Eigenface, elasic matching, and neural nets, Proc. of the IEEE: Automated Biometric Systems 85 (1997) 1423–1435.Google Scholar