Multimodal Biometrics: Issues in Design and Testing

Published

November 1, 2003

Author(s)

Robert D. Snelick, Michael D. Indovina, James H. Yen, Alan Mink

Abstract

The results of experimental studies on multimodal biometric systems for small-scale populations have shown better performance compared to single-mode biometric systems. We examine if such techniques scale to larger populations, introduce a methodology to test the performance of such systems, and assess the feasibility of using commercial off-the-shelf (COTS) products to construct deployable multimodal biometric systems. A key aspect of our approach is to leverage confidence level scores from preexisting single-mode data. An example of a multimodal biometrics system analysis is presented that explores various normalization and fusion techniques for face and fingerprint classifiers. This multimodal analysis uses a population of about 1000 subjects, which is a population size ten-times larger than used in any previously reported study. Experimental results combining face and fingerprint biometric classifiers reveal significant performance improvement over single-mode systems.

Proceedings Title

International Conference on Multimodal Interfaces | 5th | | ACM

Conference Dates

November 5-7, 2003

Conference Location

B.C.

Conference Title

International Conference on Multimodal Interfaces

Pub Type

Conferences

Download Paper

Local Download

Keywords

biometric classifiers, biometrics, face and fingerprint biometrics, multimodal biometric systems

Citation

Snelick, R. , Indovina, M. , Yen, J. and Mink, A. (2003), Multimodal Biometrics: Issues in Design and Testing, International Conference on Multimodal Interfaces | 5th | | ACM, B.C., -1, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=151577 (Accessed October 10, 2025)