Distribution of local curvature values as a sign for static signature verification

Abstract

This paper proposes a new feature for describing a digital image of a handwritten signature based on the frequency distribution of local curvature values of the contours of this signature. The computation of this feature on a binary signature image is described in detail. A normalized histogram of the distributions of local curvature values for 40 intervals is generated. The frequency values, written as a 40-dimensional vector, are named the local curvature code of the signature. Experimental studies are performed on digitized images of genuine and fake signatures from two databases. The accuracy of automatic verification of signatures on the publicly available CEDAR database was 99.77% and on the TUIT database 88.62%.