Multibiometrics User Recognition using Adaptive Cohort Ranking

Personal identification using multibiometrics is desirable in a wide range of high-security and/or forensic application as it can address performance limitations from unimodal biometrics systems. This paper presents a new scheme the multibiometrics fusion to achieve performance improvement for the user identification/recognition. We model the biometric identification solution using an adaptive cohort ranking approach, which can more effectively utilize the cohort information for maximizing the true positive identification rates. In contrast to the tradition cohort-based methods, the proposed cohort ranking approach offers merit of being matcher independence as it does not make any assumption on the nature of score distributions from any of the biometric matcher(s). In addition, our scheme is adaptive and can be incorporated for any biometric matcher/technologies. The proposed approach is evaluated on publicly available unimodal and multimodal biometrics databases, i.e., BSSR1 multimodal matching scores for fingerprint and face matchers and XM2VTS matching scores from synchronize databases of face and voice. In both the unimodal and multimodal databases, our results indicate that the proposed approach can outperform the conventional adaptive identification approaches. The experimental results from both public databases are quite promising and validate the contributions from this work.