Weighted Features Extraction Based on Signature Verification using ANN

Signature Validation is one of the most important and interesting issue in the form of authentication and security level. The aim of this paper that has been focused here is signature verification in the type of original signature and forged signature. Artificial Neural Network algorithm along with feature extraction via horizontal and vertical splitting of signature image. Generally, algorithm is use to verify the signature type. The proposed scheme is based on the technique that applies pre-processing on the signature, feature point extraction and neural network training and finally verifies the authenticity of the signature. The objective of the proposed scheme is to reduce two vital parameters False Acceptance Rate (FAR) and False Rejection Rate (FRR), Accuracy. That means results are expressed in terms of FAR and FRR and subsequently comparative analysis has been made with existing techniques. The Proposed technique will give more efficient result than most of the existing techniques.