CONTRIBUTION TO THE AUTHENTICITY OF DIGITIZED HANDWRITTEN SIGNATURES THROUGH DEEP LEARNING WITH RESNET-50 AND OCR

Main Article Content

Tsanta Christelle Nadège Ralaibozaka
Maminiaina Alphonse Rafidison
Hajasoa Malalatiana Ramafiarisona

Abstract

This paper explores the contribution of authenticity to digitized handwritten signatures using a deep learning-based approach, implementing ResNet-50 and optical character recognition (OCR). Signature authentication is a crucial issue in various fields, such as transaction security, protection of official documents, and fraud prevention. Our approach aims to improve the reliability of signature verification systems by exploiting the advanced capabilities of deep neural networks. Experimental results demonstrate a high authentication accuracy of 94% on our collected database and 100% on ICDAR 2011, validating the effectiveness of the proposed approach. The advantages of this method include more excellent resistance to circumvention techniques, adaptability to different signature styles, and robustness against intentional tampering.

Downloads

Download data is not yet available.

Article Details

How to Cite
Tsanta Christelle Nadège Ralaibozaka, Maminiaina Alphonse Rafidison, & Hajasoa Malalatiana Ramafiarisona. (2024). CONTRIBUTION TO THE AUTHENTICITY OF DIGITIZED HANDWRITTEN SIGNATURES THROUGH DEEP LEARNING WITH RESNET-50 AND OCR. International Journal of Innovations in Engineering Research and Technology, 11(3), 20-25. https://doi.org/10.26662/ijiert.v11i3.pp20-25
Section
Engineering and Technology

How to Cite

Tsanta Christelle Nadège Ralaibozaka, Maminiaina Alphonse Rafidison, & Hajasoa Malalatiana Ramafiarisona. (2024). CONTRIBUTION TO THE AUTHENTICITY OF DIGITIZED HANDWRITTEN SIGNATURES THROUGH DEEP LEARNING WITH RESNET-50 AND OCR. International Journal of Innovations in Engineering Research and Technology, 11(3), 20-25. https://doi.org/10.26662/ijiert.v11i3.pp20-25

Similar Articles

You may also start an advanced similarity search for this article.