A multiexpert collaborative biometric system for people identification

Present identification through single-biometric systems suffer from a number of limitations, due to the fact that no single bodily or behavioral feature is able to satisfy at the same time acceptability, speed and reliability constraints of authentication in real applications. Multibiometric systems can solve a number of problems of single-biometry approaches. A crucial issue to be investigated relates to how results from different systems should be evaluated and fused, in Order to obtain an as reliable as possible global response. A further source of flaws for present systems, both single-biometric and multibiometric, can be found in the lack of dynamic update of parameters, which does not allow them to adapt to changes in the working settings. They are generally calibrated once and for all, so that they are tuned and optimized with respect to specific conditions. In this work, we investigate an architecture where single-biometry subsystems work in parallel, yet exchanging information at fixed points, according to the N-Cross Testing Protocol. In particular, the integrated subsystems work on the same biometric feature, the face in this case, yet exploiting different classifiers, Notice that such specific configuration is interesting to underline how the strengths of one classifier can compensate for flaws of other classifiers, so that the final result is more accurate and reliable. Moreover, parameters of each subsystem are also dynamically optimized according to the behavior of all the others. This is achieved by an additional component, the supervisor module. which analyzes the responses from all subsystems and modifies the degree of reliability required from each of them to accept the respective responses. In this way subsystems collaborate at a twofold level, both for returning a common answer and for tuning to changing operating conditions. The paper explores the combination of these two novel approaches, demonstrating that component collaboration increases system accuracy and allows identifying unstable subsystems. (C) 2009 Elsevier Ltd. All rights reserved.