Chaos-Based Cancelable Palmprint Authentication System

While biometrics presents obvious advantages over password and token-based security, the security concerns that biometric authentication raises need to be addressed. In this paper, we outlined cancelable palmprint binary orientation co-occurrence vector(BOCV) based on anisotropic filter(AF) using feedforward-feedback nonlinear dynamic filter (FFNDF) and then the independent matching scores is fused at the score level, which can efficiently protect the security of template and enhance the user's privacy. The cancelable system can provide large re-issuance ability and can be implemented very fast for real applications. It also has better robustness--- even in the stolen-token case, the result just reverts to the original performance without loss in performance and it can still achieve state-of-the-art authentication accuracy, i.e., the EER is 0.07%.. Experiments on PolyU Palmprint Database confirm the effectiveness of the proposed approach. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of Harbin University of Science and Technology