English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The traditional approach to face anti-spoofing sees it as a binaryclassification problem, and binary classifiers are trained and validated onspecialized anti-spoofing databases. One of the drawbacks of this approach isthat, due to the variability of face spoofing attacks, environmental factors,and the typically small sample size, such classifiers do not generalize well topreviously unseen databases. Anomaly detection, which approaches faceanti-spoofing as a one-class classification problem, is emerging as anincreasingly popular alternative approach. Nevertheless, in all existing workon anomaly detection for face anti-spoofing, the proposed training protocolsutilize images from specialized anti-spoofing databases only, even though onlycommon images of real faces are needed. Here, we explore the use of in-the-wildimages, and images from non-specialized face databases, to train one-classclassifiers for face anti-spoofing. Employing a well-established technique, wetrain a convolutional autoencoder on real faces and compare the reconstructionerror of the input against a threshold to classify a face image accordingly aseither client or imposter.  Our results show that the inclusion in the training set of in-the-wild imagesincreases the discriminating power of the classifier significantly on an unseendatabase, as evidenced by a large increase in the value of the Area Under theCurve. In a limitation of our approach, we note that the problem of finding asuitable operating point on the unseen database remains a challenge, asevidenced by the values of the Half Total Error Rate.

Use of in-the-wild images for anomaly detection in face anti-spoofing