Automated Detection of Forgeries in Documents Using Segmentation Neural Networks

Lohvynenko, S. R.; Prosolov, V. V.

Публікація:
Automated Detection of Forgeries in Documents Using Segmentation Neural Networks

dc.contributor.author	Lohvynenko, S. R.
dc.contributor.author	Prosolov, V. V.
dc.date.accessioned	2025-10-31T22:55:11Z
dc.date.available	2025-10-31T22:55:11Z
dc.date.issued	2025
dc.description.abstract	This paper presents a neural network–based approach for automated detection of forged areas in PDF documents. The method converts document pages into image representations and applies semantic segmentation to localize manipulations such as inserted signatures or replaced text. U-Net and DeepLabV3+ architectures were trained on a dataset of authentic and synthetically forged samples. Experimental results show that segmentation models achieve high accuracy (IoU ≈ 0.91), outperforming traditional metadata-based techniques. The proposed solution can be integrated into electronic document management and cybersecurity systems for automated authenticity verification.
dc.identifier.citation	Lohvynenko S. R. Automated Detection of Forgeries in Documents Using Segmentation Neural Networks / S. R. Lohvynenko, V. V. Prosolov // Computer and information systems and technologies : Eighth International Scientific and Technical Conference, October 09-10, 2025. – Kharkiv : NURE, 2025. - P. 116.
dc.identifier.issn	2710-463X
dc.identifier.uri	https://openarchive.nure.ua/handle/document/33021
dc.language.iso	en_US
dc.publisher	ХНУРЕ
dc.rights	Attribution-NonCommercial-NoDerivatives 4.0 International	en
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject	document forgery detection
dc.title	Automated Detection of Forgeries in Documents Using Segmentation Neural Networks
dc.type	Thesis
dspace.entity.type	Publication