Training Dataset Construction for Anomaly Detection in Face Anti-spoofing

Simple item page
dc.contributor.authorAbduh, Latifahen_US
dc.contributor.authorIvrissimtzis, Ioannisen_US
dc.contributor.editorXu, Kai and Turner, Martinen_US
dc.date.accessioned2021-09-07T05:44:59Z
dc.date.available2021-09-07T05:44:59Z
dc.date.issued2021
dc.description.abstractAnomaly detection, which is approaching the problem of face anti-spoofing as a one-class classification problem, is emerging as an increasingly popular alternative to the traditional approach of training binary classifiers on specialized anti-spoofing databases which contain both client and imposter samples. In this paper, we discuss the training protocols in the existing work on anomaly detection for face anti-spoofing, and note that they use images exclusively from specialized anti-spoofing databases, even though only common images of real faces are needed. In a proof-of-concept experiment, we demonstrate the potential benefits of adding in the anomaly detection training sets images from general face recognition, rather than specialised face anti-spoofing, databases, or images from the in-the-wild images. We train a convolutional autoencoder on real faces and compare the reconstruction error against a threshold to classify a face image as either client or imposter. Our results show that the inclusion in the training set of in-the-wild images increases the discriminating power of the classifier on an unseen database, as evidenced by an increase in the value of the Area Under the Curve.en_US
dc.description.sectionheadersComputer Vision
dc.description.seriesinformationComputer Graphics and Visual Computing (CGVC)
dc.identifier.doi10.2312/cgvc.20211312
dc.identifier.isbn978-3-03868-158-8
dc.identifier.pages21-26
dc.identifier.urihttps://doi.org/10.2312/cgvc.20211312
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/cgvc20211312
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subjectComputer vision tasks
dc.subjectImage manipulation
dc.titleTraining Dataset Construction for Anomaly Detection in Face Anti-spoofingen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
021-026.pdf
Size:
482.25 KB
Format:
Adobe Portable Document Format
Download
Collections
Computer Graphics & Visual Computing (CGVC) 2021