Reconstruction and enhancement techniques for overcoming occlusion in facial recognition

Simple item page
dc.contributor.authorPleško, Filipcs
dc.contributor.authorGoldmann, Tomášcs
dc.contributor.authorMalinka, Kamilcs
dc.coverage.issue1cs
dc.coverage.volume2025cs
dc.date.issued2025-05-20cs
dc.description.abstractFace occlusions on CCTV cameras obscure important key facial features, preventing face recognition (FR) systems from recognizing people. This work mainly focuses on reconstructing these missing facial parts using Generative Adversarial Neural Networks (GANs) to improve FR accuracy while maintaining a low False Acceptance Rate (FAR). In addition, we are trying to improve the generated images further by using different image enhancement methods to test whether they can be used to improve the FR accuracy. To test the results, we perform experiments using state-of-the-art FR methods such as QMagFace and ArcFace to see whether image reconstruction and image enhancement help to improve FR accuracy.en
dc.description.abstractFace occlusions on CCTV cameras obscure important key facial features, preventing face recognition (FR) systems from recognizing people. This work mainly focuses on reconstructing these missing facial parts using Generative Adversarial Neural Networks (GANs) to improve FR accuracy while maintaining a low False Acceptance Rate (FAR). In addition, we are trying to improve the generated images further by using different image enhancement methods to test whether they can be used to improve the FR accuracy. To test the results, we perform experiments using state-of-the-art FR methods such as QMagFace and ArcFace to see whether image reconstruction and image enhancement help to improve FR accuracy.en
dc.formattextcs
dc.format.extent1-21cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationEURASIP Journal on Image and Video Processing. 2025, vol. 2025, issue 1, p. 1-21.en
dc.identifier.doi10.1186/s13640-025-00670-7cs
dc.identifier.issn1687-5176cs
dc.identifier.orcid0009-0000-1238-4062cs
dc.identifier.orcid0000-0002-0286-2523cs
dc.identifier.orcid0000-0002-9009-2193cs
dc.identifier.other193306cs
dc.identifier.researcheridKSL-9159-2024cs
dc.identifier.researcheridAAB-5046-2022cs
dc.identifier.scopus57222737290cs
dc.identifier.scopus24824985000cs
dc.identifier.urihttp://hdl.handle.net/11012/255186
dc.language.isoencs
dc.relation.ispartofEURASIP Journal on Image and Video Processingcs
dc.relation.urihttps://jivp-eurasipjournals.springeropen.com/articles/10.1186/s13640-025-00670-7cs
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivatives 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/1687-5176/cs
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/cs
dc.subjectface recognitionen
dc.subjectface reconstructionen
dc.subjectimage enhancementen
dc.subjectArcFaceen
dc.subjectMagFaceen
dc.subjectQMagFaceen
dc.subjectGANen
dc.subjectface recognition
dc.subjectface reconstruction
dc.subjectimage enhancement
dc.subjectArcFace
dc.subjectMagFace
dc.subjectQMagFace
dc.subjectGAN
dc.titleReconstruction and enhancement techniques for overcoming occlusion in facial recognitionen
dc.title.alternativeReconstruction and enhancement techniques for overcoming occlusion in facial recognitionen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-193306en
sync.item.dbtypeVAVen
sync.item.insts2025.10.14 14:13:20en
sync.item.modts2025.10.14 10:03:24en
thesis.grantorVysoké učení technické v Brně. Fakulta informačních technologií. Ústav inteligentních systémůcs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s13640025006707.pdf
Size:
2.22 MB
Format:
Adobe Portable Document Format
Description:
file s13640025006707.pdf
Download
Collections
Ústav inteligentních systémů