Reconstruction Error-Based Detection of Structural Anomalies in Scanned Documents Using Autoencoders and CNNs

StatusVoR
Dublin Core metadata
Alternative title
Authors
Janik, Mateusz
Nowak, Jakub
Korytkowski, Marcin
Scherer, RafaƂ
Stachowiak, Sylwia
Witkowski, Maciej
Monograph
Making ISD Sustainable: Reloaded with AI and Automation (ISD2026 Proceedings)
Monograph (alternative title)
Editor
Valenta, MichaƂ
MannovĂĄ, Boba
Pergl, Robert
PrzybyƂek, Adam
Lang, Michael
Linger, Henry
Schneider, Christoph
Iivari, Netta
Insfran, Emilio
Date
2026-09-17
Place of publication
Publisher
Czech Technical University in Prague
Journal title
International Conference on Information Systems Development
Proceedings of the 34th International Conference on Information Systems Development
Volume
Pages
1-5
DOI
ISSN
2938-5202
ISBN
9788001075852
eISBN
Series
Series number
ISSN of series
Weblink
https://aisel.aisnet.org/isd2014/proceedings2026/datascience/57/
Access date
2026-10-20
Remarks
Abstract PL
Abstract EN
Verification of scanned document authenticity is important for digital archiving, information security, and forensic analysis. This paper proposes a reconstruction error-based method for detecting structural anomalies in scanned documents. A convolutional autoencoder is trained on authentic document patches and used to generate reconstruction error maps. These maps are then classified by a CNN to distinguish the original scans from the reproduced samples. Experiments on a controlled dataset show that reconstruction error maps provide discriminative information for detecting artefacts introduced by document reproduction. The results should be interpreted as a proof of concept for controlled reproduction detection rather than as a complete solution for all real-world forgery scenarios.
Abstract other
Keywords PL
Keywords EN
Document authenticity verification
Autoencoder
Reconstruction error
Convolu- tional neural networks
Anomaly detection
Document reproduction
Keywords other
Conference edition name
The 34th International Conference on Information Systems Development (ISD 2026)
Conference place
Praga
Start date
2026-09-02
Finish date
2026-09-04
Sustainable Development Goals
SDG 9. Industry, innovation and infrastructure
Exhibition title
Place of exhibition (institution)
Exhibition curator
Organisational Unit
WydziaƂ Projektowania
WydziaƂ Projektowania w Warszawie
URI
https://share.swps.edu.pl/handle/swps/2642
Type
Version
Version of Record
License type
other
This item is shared on a different license
Funder
Time range from
Time range to
Contact person name
item.page.relation.dataset
Related publication
Related publication
Grant/project name
Grant number
Views
Views0
Acquisition Date20.10.2022
Downloads
Downloads0
Acquisition Date20.10.2022