Abstract
Smart cards are widely used to deploy secure and cost effective identity management systems. Integration of biometrics into the smart card leads to a strong two-factor authentication system through the match on card (MOC) process. Since MOC uses fixed authentication strategies during the life cycle of smart card, this leads to a low performance and high failure to acquire error in uncontrolled noisy environments. To solve this problem, this paper proposes a sequential quality based framework for biometric authentication. In the proposed framework a set of classifiers have been used to manage the workflow of the framework based on the quality of samples. Accordingly, subjects can be dynamically authenticated using MOC and MOH. A multimodal chimera database is used to evaluate this framework. Our findings indicate that the proposed approach provides higher accuracy than the unimodal MOC and MOH by 11.29% and 5.12%, respectively. Furthermore, the proposed framework can authenticate 83.85% of users without auxiliary trait at the expense of only 1.21% lower accuracy compared to parallel fusion, which require acquisition of all traits for entire users. Analysis of the results demonstrates that the proposed approach provides a compromise between accuracy, user convenience, security and system complexity