Multibiometric Systems: An Overview of Information Fusion in Biometrics
Dr. Arun Ross
Lane Department of Computer Science and Electrical Engineering,
West Virginia University
Multibiometrics refers to the consolidation of evidence presented by multiple
sources of biometric information in order to determine or validate a person's
identity. Some of the limitations imposed by a unimodal biometric system can be
effectively addressed by employing a multibiometric system. Fusion in such a
system can occur at different modules including the sensor, feature extraction,
matching and decision-making modules. This lecture will discuss the various levels of fusion that are possible in a multibiometric system and present integration strategies based on the MCS (Multiple Classifier System) literature. Emphasis will be on fusion at the match score level and, therefore, topics related to score normalization and user-specific parameters will be presented. The lecture will also discuss the incorporation of soft-biometric traits in the fusion module of a multibiometric system. Finally, a discussion about multibiometric systems that are currently deployed will be presented.
Arun Ross is an Assistant Professor in the Lane Department of Computer Science
and Electrical Engineering at West Virginia University. Ross received his B.E. (Hons.)
degree in Computer Science from the Birla Institute of Technology and
Science, Pilani (India), in 1996. He obtained his M.S. and Ph.D. degrees in
Computer Science and Engineering from Michigan State University in 1999 and
2003, respectively. His doctoral dissertation examined fusion schemes for
enhancing the performance of fingerprint authentication systems.
Between July 1996 and December 1997, Ross worked with the Design and Development group of Tata Elxsi (India) Ltd., in Bangalore. He also spent three summers (2000-2002) with the Imaging and Visualization group at Siemens Corporate Research, Inc., Princeton, working on fingerprint recognition algorithms. His research interests include multimodal biometrics, fingerprint/iris analysis, and statistical pattern recognition. He is also actively involved in the development of Biometrics and Pattern Recognition curricula at West Virginia University.
IAPR International Conference on Biometrics 2006