ABSTRACT

In this paper, a new technique for dynamic signature modeling and classification framework is proposed. Raw dynamic data obtained from a digitizer are analyzed using statistic tools. The variation within the same person signatures is obtained for effective signature training and accurate classification of genuine signature against all kind of forgeries. The proposed system is robust enough to prevent forgery of dynamic signatures. It has False Rejection Rate (FRR) of 0.2% for genuine signatures and False Acceptance Rate (FAR) of 0.25%, 0% and 0% for skilled, simple and random forgeries respectively. These results are better in comparison with the results obtained from previous systems.