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

In recent years, face biometric security systems are rapidly increasing,therefore, the presentation attack detection (PAD) has received significantattention from research communities and has become a major field of research.Researchers have tackled the problem with various methods, from exploitingconventional texture feature extraction such as LBP, BSIF, and LPQ to usingdeep neural networks with different architectures. Despite the results each ofthese techniques has achieved for a certain attack scenario or dataset, most ofthem still failed to generalized the problem for unseen conditions, as theefficiency of each is limited to certain type of presentation attacks andinstruments (PAI). In this paper, instead of completely extracting hand-craftedtexture features or relying only on deep neural networks, we address theproblem via fusing both wide and deep features in a unified neuralarchitecture. The main idea is to take advantage of the strength of bothmethods to derive well-generalized solution for the problem. We also evaluatedthe effectiveness of our method by comparing the results with each of thementioned techniques separately. The procedure is done on different spoofingdatasets such as ROSE-Youtu, SiW and NUAA Imposter datasets.  In particular, we simultanously learn a low dimensional latent spaceempowered with data-driven features learnt via Convolutional Neural Networkdesignes for spoofing detection task (i.e., deep channel) as well as leveragesspoofing detection feature already popular for spoofing in frequency andtemporal dimensions ( i.e., via wide channel).

A Compact Deep Learning Model for Face Spoofing Detection