Pattern spectrum as a local shape factor for off-line signature verification

A fundamental problem in the field of off-line signature verification is the lack of a pertinent shape representation or shape factor. The main difficulty in the definition of pertinent features lies in the local variability of the signature line which is closely related to the intrinsic characteristic of human beings. In this paper we proposed a new formalism for signature representation based on visual perception. A signature image of 512x128 pixels is centered onto a grid of rectangular retinas which are excited by a local portion of the signature image. So each retina has only a local perception of the entire scene. Granulometric size distributions have been used for the definition of local shape descriptors in attempt to characterized the amount of signal activity in front of each retina located on the focus of attention grid. Experimental evaluation of this scheme has been made using a signature database of 800 genuine signatures from 20 individuals. Two types of classifiers, a 1NN and a threshold classifiers show a total error rate below 0.02% and 1.0% respectively in the context of random forgeries.