A Robust Multimodal Biometric System Integrating Iris, Face and Fingerprint using Multiple SVMs

Abstract

This paper presents a robust multimodal biometric recognition system integrating iris, face and fingerprint based on match score level fusion using multiple support vector machines (SVMs). Here, multiple support vector machines are applied in parallel fashion to overcome the problem of missing biometric traits. It considers every possible combination of all the three biometric traits (iris, face and fingerprint) individually. Each possible combination of biometric traits has a separate SVM to combine the available match scores to generate the final decision. Existing multimodal biometric recognition systems are based on the assumption that the set of biometric traits to be integrated is always present as a whole at the time of authentication. But sometimes it is not possible due to some unavoidable circumstances (e.g. injury may be caused, person may be under some medical treatment, corresponding trait may be missing etc.). The performance of the proposed system is evaluated on a public dataset demonstrating its recognition accuracy regarding FAR (False Accept Rate) and FRR (False Reject Rate).

Keywords: support vector machine (SVM), score level fusion, iris recognition, face recognition, fingerprint recognition, receiver operating characteristic (ROC) curve.