A novel bimodal biometric identification system based on finger geometry and palm print

Biometrics identification system provides an convenient way to identify an individual. Such a system establishes the identity corresponding to the input image (probe) by comparing the probe template against the templates of all identities enrolled in the database. Both identification error rate and response time increases with the increase in the number of enrollees. One way to reduce the response time is to retrieve a small set of candidate identity templates from the database against which matching of probe template is performed by techniques that are fast to establish the identity. In this paper we propose such a technique by combining finger geometry and palm print modalities. The proposed approach is tested on database collected at our institute. With the proposed approach 94.44 % reduction in the search space is achieved with identification accuracy of 100%.