Robust Signature Verification and Recognition using Weighted Features Point

Abstract

This paper robust signature verification and recognition using weighted features point that applies artificial neural network which discriminates between two types of signature (i) forged and (ii) original signature. The proposed scheme performs pre-processing on the signature, feature point extraction and neural network training and finally verifies the authenticity of the signature. The aim here is to reduce two vital parameters False Acceptance Rate (FAR) and False Rejection Rate (FRR). Results are also maintained in terms of FAR and FRR and parallel comparative analysis is made with existing techniques. The Proposed technique provides more accurate and precise results than most of the existing technique in this field.