Multi-Biometric Personal Authentication with 3d Face and Iris Images Using Sum Rule Based Fusion of Matching Scores

In this paper we propose a multi-biometric system for personal authentication with two biometric traits using image fusion after matching.  Regardless of significant advances in the latest years, there are still several limitations derived from utilizing one biometric trait. The problem with a unimodal biometric verification system is that since it uses only a single biometric trait it suffers from the disadvantages such as lack of universality, interclass variation and sensitivity to attacks which lead to spoofing of the authentication system. In order to overcome these shortcomings, multi- biometric systems are introduced. In this paper the combination of iris and face biometric authentication system is implemented and analyzed with several matching score level fusion techniques. In the system, a dynamic 3D face verification and improved iris segmentation and verification are developed and they are fused using sum rule based matching scores fusion technique.