Lightweight Hybrid CNN Model for Face Presentation Attack Detection

Basit Öğe Kaydı
dc.authorid0000-0002-5627-1833
dc.authorid0000-0003-0314-8134
dc.authorid0000-0003-3960-5085
dc.contributor.authorTurhal, Ugur
dc.contributor.authorYilmaz, Asuman Gunay
dc.contributor.authorNabiyev, Vasif
dc.date.accessioned2026-02-28T12:17:41Z
dc.date.available2026-02-28T12:17:41Z
dc.date.issued2025
dc.departmentBayburt Üniversitesi
dc.description2nd International Conference on Information Technologies and Their Applications -- APR 23-25, 2024 -- Baku, AZERBAIJAN
dc.description.abstractToday, face recognition systems are widely used in many areas that require biometric-based verification, especially because they are contactless and require low user cooperation. Despite their ease of implementation, these systems are vulnerable to attacks. Especially the increasing use of social media, makes it easier to spoof face recognition systems. Therefore, it is very important to develop new methods for Face Presentation Attack (FPA) detection. In this study, FPA detection performances of the lightweight Convolutional Neural Network (CNN) models -MobileNetV3-Small, ShuffleNet, SqueezeNet- and lightweight hybrid CNN models designed with combinations of these networks were investigated. In the experiments, the change in FPA detection performance was examined by giving the cropped face regions and the whole images as input to the networks. Using the whole image instead of the cropped face region significantly improved the FPA detection performance of the CNN models. These results showed that non-facial areas carry important information in FPA detection. Also, the FPA detection performance of the proposed lightweight hybrid CNN models were better than the single use of the networks for both inputs. 0.17% HTER performance was achieved with the hybrid CNN model built from the combination of ShuffleNet + SqueezeNet on the Replay-Attack dataset.
dc.description.sponsorshipEge University
dc.identifier.doi10.1007/978-3-031-73420-5_19
dc.identifier.endpage240
dc.identifier.isbn978-3-031-73419-9
dc.identifier.isbn978-3-031-73420-5
dc.identifier.issn1865-0929
dc.identifier.issn1865-0937
dc.identifier.scopus2-s2.0-85207833155
dc.identifier.scopusqualityQ3
dc.identifier.startpage228
dc.identifier.urihttps://doi.org/10.1007/978-3-031-73420-5_19
dc.identifier.urihttps://hdl.handle.net/20.500.12403/5916
dc.identifier.volume2226
dc.identifier.wosWOS:001436940700019
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSpringer International Publishing Ag
dc.relation.ispartofInformation Technologies And Their Applications, Pt Ii, Itta 2024
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WoS_20260218
dc.subjectFace Presentation Attack Detection
dc.subjectFace Spoofing
dc.subjectDeep Learning
dc.subjectLightweight CNN Model
dc.subjectFake Image Detection
dc.titleLightweight Hybrid CNN Model for Face Presentation Attack Detection
dc.typeConference Object

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu