Ensemble classifiers for dynamic signature authentication

Rapid advances in technology, that made almost everything goes digital have entailed a persistent need for a stronger means of information security. Furthermore, new advanced devices are now available to capture the dynamic of a person's signature. Therefore, the reliance on the dynamic signature for authenticating entities in secure system became crucial. In this paper, we investigate the problem of dynamic signature verification and recognition using Ensemble of Classifiers, where we used multiple Fisher based probabilistic neural networks as the component classifiers to construct the Ensemble. Two key issues are studied; the first issue is how to construct the Ensemble. The second issue is how to combine the predictions of the component classifiers in order to accomplish the decision-making process. Data sets from SVC dataset have been used to assess the performance of the proposed ensemble of classifiers. Obtained results are very encouraging and show the ability of ensemble classifiers to deal with the tackled problem.