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

Morphing attacks are a form of presentation attacks that gathered increasingattention in recent years. A morphed image can be successfully verified tomultiple identities. This operation, therefore, poses serious security issuesrelated to the ability of a travel or identity document to be verified tobelong to multiple persons. Previous works touched on the issue of the qualityof morphing attack images, however, with the main goal of quantitativelyproofing the realistic appearance of the produced morphing attacks. We theorizethat the morphing processes might have an effect on both, the perceptual imagequality and the image utility in face recognition (FR) when compared to bonafide samples. Towards investigating this theory, this work provides anextensive analysis of the effect of morphing on face image quality, includingboth general image quality measures and face image utility measures. Thisanalysis is not limited to a single morphing technique, but rather looks at sixdifferent morphing techniques and five different data sources using tendifferent quality measures. This analysis reveals consistent separabilitybetween the quality scores of morphing attack and bona fide samples measured bycertain quality measures. Our study goes further to build on this effect andinvestigate the possibility of performing unsupervised morphing attackdetection (MAD) based on quality scores. Our study looks intointra andinter-dataset detectability to evaluate the generalizability of such adetection concept on different morphing techniques and bona fide sources. Ourfinal results point out that a set of quality measures, such as MagFace andCNNNIQA, can be used to perform unsupervised and generalized MAD with a correctclassification accuracy of over 70%.

Face Morphing Attacks and Face Image Quality: The Effect of Morphing and the Unsupervised Attack Detection by Quality