Performance Analysis of Deep Learning Approaches for Offline Signature Verification

Abstract

Signature verification plays a significant role in many biometric authentication places. Many financial institutes require a robust signature verification process for check clearance, loan sanction, processing, pension relation documents, etc. Expert forgeries make it hard to authenticate an individual's identification based on signatures. Typically, this occurs when the forger understands the user's intricate features of the signature and strives to mimic it. Online signature verification approaches can extract various features such as keystrokes, pressure of the pointer, duration between the strokes and the lettering styles, so that verification becomes effective. However, the lack of these intricate details in offline signature, the authentication process becomes much more difficult. To address these issues, in this paper we propose deep learning-based approaches for offline signature verification. In this regard, we have used ZFNet, LeNet and AlexNet architectures with CEDAR, BHSig20 and UTsig datasets for our extensive. experimentation. We propose a learning model in which the dataset consists of multiple genuine and forged signatures. Further, performance analysis of these techniques has been carried out. It was found that LeNet has provided better training and testing accuracy with above 82% performance.