Efficient multimodal fusion for person authentication combining three biometric modalities

Fusion of multiple biometric modalities for person authentication can compensate for the limitations in performance of each individual biometric system. This paper proposed an efficient person authentication method based on multimodal biometric fusion at the matching score level. For score level fusion, MPM (minimax probability machine) based fusion rule is applied to combine multiple matching scores, respectively from iris, facer and palmprint, to generate a single scalar score which is used to make the final decision. Experimental results show that the performance of the proposed method can bring obvious improvement comparing to the previous multimodal methods.