A Multimodal Biometric Fusion Approach based on Binary Particle Optimization

In this paper, we propose a novel fusion scheme of iris and online signature biometrics at feature level space. The features are extracted from the pre-processed images of iris and the dynamics of signatures. We propose different fusion schemes at feature level, which we compare on a database of 108 virtual people. Moreover, in order to reduce the complexity of the fusion scheme, we implement a binary particle swarm optimization (BPSO) procedure which allows the number of features to be significantly reduced while keeping the same level of performance. This paper studies the advantage of multimodal biometric system over unimodal biometric system. We also examine how the accuracy will be improved as several biometric data are integrated in an identification system. Results show a significant improvement in performance when classification performed at feature fusion level.