Entropy in Biometric Face Template Analysis
We will consider systems whose galleries contain more templates for each subject, and will explore the concept of representativeness of a biometric sample. This parameter varies from subject to subject, and is not a feature of the whole gallery. The gallery samples of certain subject might be too much similar, just because they are all of excellent quality, due to a systematic acquisitions in well-controlled conditions. In this situation, even a moderately different sample probe of the subject in input will cause an error, even by an accurate system, if the excellent conditions are not maintained. This seems to indicate that quality measures alone cannot guarantee good performances. Correct recognition in different situations may require a sufficient amount of variation in gallery templates. We call this (subject’s) gallery feature representativeness, and investigate the role of mutual information/entropy in defining it.
KeywordsFace Recognition Mutual Information Representativeness
Unable to display preview. Download preview PDF.
- 2.Adler, A., Youmaran, R., Loyka, S.: Towards a measure of biometric information. In: Proc. of Canadian Conf. on Electrical and Computer Engineering, pp. 210–213 (2006)Google Scholar
- 3.Bhatnagar, J., Kumar, A.: On Estimating Some Performance Indices for Biometric Identification. Pattern Recognition 42(5), 1805–1818 (2009)Google Scholar
- 4.Bhatnagar, J., Kumar, A., Saggar, N.: A Novel Approach to Improve Biometric Recognition Using Rank Level Fusion. In: Proc. of the IEEE CVPR 2007, pp. 1–6 (2007)Google Scholar
- 5.De Marsico, M., Nappi, M., Riccio, D.: FACE: Face Analysis for Commercial Entities. In: Proceedings of the International Conference on Image Processing, pp. 1597–1600 (2010)Google Scholar
- 6.De Marsico, M., Nappi, M., Riccio, D.: Measuring Measures for Face Sample Quality. In: Proc. of Int. ACM Work. on Multimedia in Forensics and Intelligence (MiFor 2011) (2011)Google Scholar
- 7.Doddington, G., Liggett, W., Martin, A., Przybocki, M., Reynolds, D.: Sheep, Goats, Lambs and Wolves: A Statistical Analysis of Speaker Performance in the NIST 1998 Speaker Recognition Evaluation. In: Proc. of ICSLP, vol. 4, pp. 1351–1354 (1998)Google Scholar
- 8.Jassim, A.J., Al-Assam, H., Abbound, A.J., Sellahewa, H.: Analysis of Relative Entropy, Accuracy, and Quality of Face Biometric. In: Proceedings of the Workshop on Pattern Recognition for IT (2010)Google Scholar
- 10.Phillips, P.J., Beveridge, J.R., Draper, B.A., Givens, G., O’Toole, A.J., Bolme, D.S., Dunlop, J., Lui, Y.M., Sahibzada, H., Weimer, S.: An introduction to the good, the bad, & the ugly face recognition challenge problem. In: IEEE Int. Conf. on Automatic Face & Gesture Recognition and Workshops (FG 2011), pp. 346–353 (2011)Google Scholar