Signature Originality Verification Using A Deep Learning Approach

Saputra, Muhammad Azi and Nurhaida, Ida (2024) Signature Originality Verification Using A Deep Learning Approach. Electronic Journal of Education, Social Economics and Technology, 5 (1). pp. 19-29. ISSN 2723-6250

	Text Pendahuluan.pdf Download (914kB)
	Text [3]-310-778-1-SM-Muhammad Azi Saputra-[19-29] (1).pdf Download (757kB)
	Text Berita Acara KTI TA_Muhammad Azi.pdf Download (286kB)

Official URL: https://doi.org/10.33122/ejeset.v5i1.310

Abstract

The rapid advancement of digital technology has heightened the need for reliable methods to verify signature authenticity, a critical aspect of document and transaction security. This study uses a deep learning approach to develop a mobile application to verify the originality of paper and digital media signatures. The dataset comprises 1,060 signature images, including authentic and forged categories for both media types. The system employs the EfficientNetV2M model, trained with augmented data, to enhance robustness. Model evaluation demonstrates strong performance with an accuracy of 82.07%, a global precision of 81.31%, a global recall of 83.25%, and a global F1-score of 82.18%. The model is implemented in an Android-based mobile application, providing an intuitive interface for users to upload and verify signatures in real time. These results underscore the potential of EfficientNetV2M for mitigating signature fraud across various domains while highlighting areas for improvement, particularly in classifying paper - based signatures. Future work will focus on expanding the dataset and refining feature extraction t echniques to enhance classification performance.

Item Type:	Artikel Jurnal/Prosiding
Uncontrolled Keywords:	Deep learning, Digital signature, EfficientNetV2M, Paper signature, Signature verification
Subjects:	T Technology > T Technology (General)
Divisions:	Fakultas Teknologi dan Desain > Informatika
Depositing User:	Admin Repository
Date Deposited:	04 Mar 2025 06:47
Last Modified:	04 Mar 2025 06:49
URI:	http://eprints.upj.ac.id/id/eprint/10876

Actions (login required)

View Item