Offline Handwritten Signature Verification

Abstract

The main idea of our project is to implement a high level of security personnel identification system using biometrics to create an identity database and to verify the identity of authorized persons. This project aims to use the methodology to verify the authenticity of the signature and the identity of the owner by using image processing techniques. In this project, suggests the main features of the form of the signature, and proposed as a case study, signatures of teachers and the staff of Palestine Polytechnic University. Since human beings feel comfortable using pens and papers for authentication and authorization in legal transactions, this project presents a method for off line hand written signature verification system. So, it is very necessary to a person's hand written signature to be identified uniquely. The development of this efficient technique is to extract features from Handwritten Signature Image and verify the signature with high resolution. That computed feature is used for verification. Here we use SURF features in offline handwritten signature verification. For each known writer we take a sample of three genuine signatures and extract their SURF descriptors and key points from Handwritten. On other hand we achieved from this system the verification of handwritten signature using SURF algorithm, finding the match between signatures for the same person, Extract features from signature to compare it between signature, and Determined who owns the signature.