1 On Empirical Recognition Capacity of Biometric Systems Under Global PCA and ICA Encoding Natalia A. Schmid, Member, IEEE and Francesco Nicol` o, Student Member, IEEE Department of Computer Science and Electrical Engineering West Virginia University, Morgantown, WV 26506-6109 E-mail: Natalia.Schmid@mail.wvu.edu, fnicolo@mix.wvu.edu Contact author: Natalia A. Schmid Tel: (304) 293-0405 x 2557, Fax: (304) 293-8602 Abstract Performance of biometric-based recognition systems depends on various factors: database quality, image preprocessing, encoding techniques, etc. Given a biometric database and a selected encoding method, the capability of a recognition system is limited by the relationship between the number of classes that the recognition system can encode and the length of encoded data describing the template at a specific level of distortion. In this work, we evaluate empirical recognition capacity of biometric systems under the constraint of two global encoding techniques: Principal Component Analysis (PCA) and Independent Component Analysis (ICA). The developed methodology is applied to predict capacity of different recognition channels formed during acquisition of different iris and face databases. The proposed approach relies on data modeling and involves classical detection and information theories. The major contribution is in providing a guideline on how to evaluate capabilities of large-scale biometric recognition systems that are based on PCA and ICA encoding. Recognition capacity can also be promoted as a global quality measure of biometric databases. This work was supported by a grant from NSF IUCRC Center for Identification Technology Research. This paper is in part presented at the 2008 Int. Conf. on Acoustic, Speech, and Signal Processing. The authors would like to thank the Associate Editor and the anonymous reviewers for their insightful and invaluable suggestions and comments. March 25, 2008 DRAFT