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

StatusVoR
Simple item page
dc.abstract.enVerification 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.
dc.affiliationWydziaƂ Projektowania
dc.affiliationWydziaƂ Projektowania w Warszawie
dc.conferenceThe 34th International Conference on Information Systems Development (ISD 2026)
dc.conference.countryCzechy
dc.conference.datefinish2026-09-04
dc.conference.datestart2026-09-02
dc.conference.placePraga
dc.conference.seriesInternational Conference on Information Systems Development
dc.conference.seriesshortcutISD
dc.conference.seriesweblinkhttps://isd2026.ksi.fit.cvut.cz/
dc.conference.shortcutISD 2026 Proceedings
dc.contributor.authorJanik, Mateusz
dc.contributor.authorNowak, Jakub
dc.contributor.authorKorytkowski, Marcin
dc.contributor.authorScherer, RafaƂ
dc.contributor.authorStachowiak, Sylwia
dc.contributor.authorWitkowski, Maciej
dc.contributor.editorValenta, MichaƂ
dc.contributor.editorMannovĂĄ, Boba
dc.contributor.editorPergl, Robert
dc.contributor.editorPrzybyƂek, Adam
dc.contributor.editorLang, Michael
dc.contributor.editorLinger, Henry
dc.contributor.editorSchneider, Christoph
dc.contributor.editorIivari, Netta
dc.contributor.editorInsfran, Emilio
dc.date.access2026-10-20
dc.date.accessioned2026-10-20T11:36:58Z
dc.date.available2026-10-20T11:36:58Z
dc.date.created2026
dc.date.issued2026-09-17
dc.description.accesstimeat_publication
dc.description.physical1-5
dc.description.sdgIndustryInnovationAndInfrastructure
dc.description.versionfinal_published
dc.identifier.doi10.62036/ISD.2026.90
dc.identifier.isbn9788001075852
dc.identifier.issn2938-5202
dc.identifier.urihttps://share.swps.edu.pl/handle/swps/2642
dc.identifier.weblinkhttps://aisel.aisnet.org/isd2014/proceedings2026/datascience/57/
dc.languageen
dc.pbn.affiliationinformatyka techniczna i telekomunikacja
dc.pbn.affiliationinformatyka
dc.publisher.ministerialCzech Technical University in Prague
dc.relation.bookMaking ISD Sustainable: Reloaded with AI and Automation (ISD2026 Proceedings)
dc.rightsOther
dc.rights.questionYes_rights
dc.share.monoOTHER
dc.subject.enDocument authenticity verification
dc.subject.enAutoencoder
dc.subject.enReconstruction error
dc.subject.enConvolu- tional neural networks
dc.subject.enAnomaly detection
dc.subject.enDocument reproduction
dc.swps.sciencecloudsend
dc.titleReconstruction Error-Based Detection of Structural Anomalies in Scanned Documents Using Autoencoders and CNNs
dc.title.journalInternational Conference on Information Systems Development
dc.title.journalProceedings of the 34th International Conference on Information Systems Development
dc.typeMonographyChapterConference
dspace.entity.typeBook