International Research Journal of Education and Technology

A multimodal biometric system integrates information from multiple biometric sources to compensate for the limitations in performance of each individual biometric system. Different approaches have been proposed in the literature for developing unimodal and multimodal biometric systems. Multi-biometric systems are developed by fusing different biometric features pertaining to various biometric modalities at different levels. Many researchers have shown that the multimodal systems outperform the unimodal systems, giving better discrimination of genuine from imposters. In existing system they we present multimodal systems at feature level and score level fusions using our already reported unimodal palm print and fingerprint identifiers. The unimodal finger- and palm print identification systems utilize directional energies of texture as features, extracted using contourlet transform. To improve the optimization in result it can propose the pareto-optimal search method in order to handle the top-k query in the high-dimension record set with that the nearest neighbor search is found and it is used to make dominant relationship between them while fusion. After that the scores of palm print and fingerprint images are multiplied together to produce a new set of values consisting of combined values of both the systems. Then the total number of generated score of test image corresponding to trained database obtained from that decision making will be done.