Offline signature verification scheme using feature extraction method

Abstract

In this project a new improved offline signature verification scheme has been proposed. The scheme is based on selecting 60 feature points from the geometric centre of the signature and compares them with the already trained feature points. The classification of the feature points utilizes statistical parameters like mean and variance. The suggested scheme discriminates between two types of originals and forged signatures. The method takes care of skill, simple and random forgeries. The objective of the work is to reduce the two vital parameters False Acceptance Rate (FAR) and False Rejection Rate (FRR) normally used in any signature verification scheme. Comparative analysis has been made with standard existing schemes. The Algorithms are based on the Geometric Center of an image so images are splitted into different parts to get the geometric centers of each which are called as Feature points in our thesis. We have taken 60(30+30) Feature points for calculation purpose(in extended Algorithm). As Feature points increases results will be more accurate but complexity and time require for testing will be more. So we have taken 60 feature points which improves security and maintains same complexity level. All calculations are done on the basis of these feature points. Results are expressed in terms of FAR (False Acceptance Rate) and FRR (False Rejection Rate) and subsequently compare these results with other existing Techniques. Results obtained by this algorithm are quite impressive. Random and Simple forgeries are eliminated and skilled forgeries are also eliminated in greater extent. As signature image is tested rigorously so FRR is more in the Algorithm proposed by us.