Offline Signature Verification – Simplified for BFSI

Abstract

This paper proposes an approach for offline signature verification in BFSI. We take DFT and DWT of the preprocessed signature image, obtained on the bank documents. This image is matched with the one in the bank’s database. The similarity score is obtained by means of Cosine Similarity (CS) and Cross-Correlation function (CCF). The proposed methodology also finds the forgery or mismatch of the signatures. Experimental results show that the proposed methodology is more suitable for banks as machine learning based solutions require more than one signature per customer in the database or artificially generated signatures for matching.