Auto Signature Verification Using Line Projection Features Combined With Different Classifiers and Selection Methods

Abstract

: Signature verification plays a role in the commercial, legal and financial fields. The signature continues to be one of the most preferred types of authentication for many documents such as checks, credit card transaction receipts, and other legal documents. In this study, we propose a system for validating handwritten bank check signatures to determine whether the signature is original or forged. The proposed system includes several steps including improving the signature image quality, noise reduction, feature extraction, and analysis. The extracted features depend on the signature line and projection features. To verify signatures, different classification methods are used. The system is then trained with a set of signatures to demonstrate the validity of the proposed signature verification system. The experimental results show that the best accuracy of 100% was obtained by combining several classification methods.