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

Face anti-spoofing (FAS) is crucial for securing face recognition systems.However, existing FAS methods with handcrafted binary or pixel-wise labels havelimitations due to diverse presentation attacks (PAs). In this paper, wepropose an attack type robust face anti-spoofing framework under light flash,called ATR-FAS. Due to imaging differences caused by various attack types,traditional FAS methods based on single binary classification network mayresult in excessive intra-class distance of spoof faces, leading to a challengeof decision boundary learning. Therefore, we employed multiple networks toreconstruct multi-frame depth maps as auxiliary supervision, and each networkexperts in one type of attack. A dual gate module (DGM) consisting of a typegate and a frame-attention gate is introduced, which perform attack typerecognition and multi-frame attention generation, respectively. The outputs ofDGM are utilized as weight to mix the result of multiple expert networks. Themulti-experts mixture enables ATR-FAS to generate spoof-differentiated depthmaps, and stably detects spoof faces without being affected by different typesof PAs. Moreover, we design a differential normalization procedure to convertoriginal flash frames into differential frames. This simple but effectiveprocessing enhances the details in flash frames, aiding in the generation ofdepth maps. To verify the effectiveness of our framework, we collected alarge-scale dataset containing 12,660 live and spoof videos with diverse PAsunder dynamic flash from the smartphone screen. Extensive experimentsillustrate that the proposed ATR-FAS significantly outperforms existingstate-of-the-art methods. The code and dataset will be available athttps://github.com/Chaochao-Lin/ATR-FAS.

Enhancing Mobile Face Anti-Spoofing: A Robust Framework for Diverse Attack Types under Screen Flash