Signature Verification using Normalized Static Features and Neural Network Classification

Abstract

Signature verification is very widely used in verification of the identity of any person. Now a days other biometric verification system has been evolved very widely like figure print, iris etc., but signature verification through computer system is still in development phase. The verification system is either through offline mode or online mode in online systems the dynamic information of a signature captured at the time the signature is made while in offline systems based on the scanned image of a signature. In this paper, a method is presented for Offline signatures Verification, for this verification system signature image is first pre-processed and converted into binary image of same size with 200x200 Pixels and then different features are extracted from the image like Eccentricity, Kurtosis, Skewness etc. and that features are used to train the neural network using back-propagation technique. For this verification system 6 different user signatures are taken to make database of the feature and results are analysed. The result demonstrate the efficiency of the proposed methodology when compared with other existing studies. The proposed algorithm gives False Acceptance Rate (FAR) as 5.05% and False Rejection rate (FRR) as 4.25%.