Multimodal Biometrics: Analysis of Handvein & Palmprint Combination Used for Person Verification

Abstract

There is a global concern to implement accurate person verification in various facets of social and professional life. These include banking, travel and secure access to social security services. While biometrics have been deployed with various choices as face, finger print, etc the importance to higher levels of security have influenced two things. One is of finding newer and more universal biometrics and other of multimodal options. Recently, hand vein based person verification has attracted increased attention. The reason seems to be that hand vein patterns are unique, universal and invariant over time and extremely non intrusive. In this paper, we analyze hand vein biometric in unimodal status and also in combination with palm print in multimodal situation. One of the key aspects of this is extracting hand vein features. It is here that the standard edge detection masks yield poor result. We then propose using non standard edge mask in schemes to accurately extract the hand vein pattern which in turn is classified using Kernel Direct Discriminant Analysis (KDDA) to make the decision about accept/reject. The performance of the proposed non-standard edge masks are compared with conventional edge detection masks and statistical validation of the results are presented with 90% confidence interval. Robustness of such scheme is analyzed by evaluating these algorithms and schemes on data corrupted by noise. The final results show the efficacy of our schemes.