In this paper we analyze the performance limits of multimodal biometric identification systems in the multiple hypothesis testing formulation. For the sake of tractability, we approximate the performance of the actual system by a set of pairwise binary tests. We point out that the attainable error exponent that can be achieved for such an approximation is limited by the worst pairwise Chernoff distance between alternative hypothesis prior models. We consider impact of the inter-modal dependencies on the attainable performance measure and demonstrate that, contrarily to the binary multimodal hypothesis testing framework, an expected performance gain from fusion of independent modalities does not any more play the role of lower bound on the gain one can expect from multimodal fusion.

Date Published: 18 March 2008
PDF: 8 pages
Proc. SPIE 6819, Security, Forensics, Steganography, and Watermarking of Multimedia Contents X, 68190P (18 March 2008); doi: 10.1117/12.764849

Published in SPIE Proceedings Vol. 6819:
Security, Forensics, Steganography, and Watermarking of Multimedia Contents X
Edward J. Delp III; Ping Wah Wong; Jana Dittmann; Nasir D. Memon, Editor(s)