Standard Scores Correlation Based Off-Line Signature Verification System

Abstract

Abstract— The fact that the signature is widely used as a means of personal verification emphasizes the need for a signature verification system. In this paper, Standard Scores Correlation based Off-line Signature Verification (SSCOSV) System is presented. The comparison is made on the basis of Pixel density and geometric feature points. Before extracting the features, preprocessing of a scanned signature image is performed to isolate the signature part and to remove any spurious noise present. The concept of Correlation is used to compare the genuine signature with the test signature. If the value of Correlation Coefficient is greater than the predefined threshold (corresponding to minimum acceptable degree of similarity), the test signature is verified to be that of the claimed subject else detected as a forgery. It is found that the values of FAR, FRR and EER for optimal threshold correlation are better compared to that of existing systems.