Dynamic Signature Verification System Based On One Real Signature

• Author(s): Ambica Gupta ; Aakriti Rai ; A. Pravallika ; B. SathyaBama
• Paper ID: 1701175
• Page: 140-143
• Published Date: 27-04-2019
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 2 Issue 10 April-2019

Abstract

This paper is based on dynamic signature used for image processing and biometric traits. Signature verification is essential in preventing duplication of documents in numerous financial, legal and other commercial fields. The project presents several unique and complicated difficulties: high/low intra-class variability (an individual?s signature may vary from day-to-day), large temporal variation (signature may vary completely over time), and high/low inter-class similarity (original signature should be different from one another). To build a signature, we need a signature verification system using a Neural Network (NN). Our paper focuses on building systems trained on data with varying degrees of information, as well as experimenting with different objective functions to obtain optimal error rates.

Keywords

Signature verification, bio-metric trait, Neural network (NN)

Citations

IRE Journals:
Ambica Gupta , Aakriti Rai , A. Pravallika , B. SathyaBama "Dynamic Signature Verification System Based On One Real Signature " Iconic Research And Engineering Journals Volume 2 Issue 10 2019 Page 140-143

IEEE:
Ambica Gupta , Aakriti Rai , A. Pravallika , B. SathyaBama "Dynamic Signature Verification System Based On One Real Signature " Iconic Research And Engineering Journals, 2(10)