New approach for the on-line signature verification based on method of horizontal partitioning

Abstract

Identity verification is one of the biometric issues which may be realized using dynamic signature biometric attribute. One of the methods of signature verification is the method based on partitioning of signature trajectories. In this paper we propose a new method for verification of signature which signals were horizontally partitioned. This method assumes use of all partitions during classification process. Classifier presented in our method is based on the flexible neuro-fuzzy system of the Mamdani type. The algorithm was tested with use of the BioSecure Database (BMDB) distributed by the BioSecure Association. © 2013 Springer-Verlag.