Signature Verification Using CNN with Information Retrieval
Utkarsh Shukla, Srishti Verma, Tushar Gwal, Verma, Atul Kumar · Zenodo (CERN European Organization for Nuclear Research) · 2018
When it comes to information security, biometric systems play a significant role in it. Signature verification is a popular research area in field of pattern recognition and image processing. It is a technique used by banks, intelligence agencies and high-profile institutions to validate the identity of an individual by comparing signatures and checking for authenticity. In this paper, the approach for the verification of signatures is based on Conventional Neural Network (CNN). This method saves time and energy and also helps to prevent human error during the signature process and lowers chances of fraud in the process of authentication. We achieved test accuracy of 89% and validation accuracy of 93%.