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

Despite the high biometric performance, finger-vein recognition systems arevulnerable to presentation attacks (aka., spoofing attacks). In this paper, wepresent a new and robust approach for detecting presentation attacks onfinger-vein biometric systems exploiting the 3D Shape (normal-map) and materialproperties (diffuse-map) of the finger. Observing the normal-map anddiffuse-map exhibiting enhanced textural differences in comparison with theoriginal finger-vein image, especially in the presence of varying illuminationintensity, we propose to employ textural feature-descriptors on both of themindependently. The features are subsequently used to compute a separatinghyper-plane using Support Vector Machine (SVM) classifiers for the featurescomputed from normal-maps and diffuse-maps independently. Given the scores fromeach classifier for normal-map and diffuse-map, we propose sum-rule based scorelevel fusion to make detection of such presentation attack more robust. To thisend, we construct a new database of finger-vein images acquired using a customcapture device with three inbuilt illuminations and validate the applicabilityof the proposed approach. The newly collected database consists of 936 images,which corresponds to 468 bona fide images and 468 artefact images. We establishthe superiority of the proposed approach by benchmarking it with classicaltextural feature-descriptor applied directly on finger-vein images. Theproposed approach outperforms the classical approaches by providing the AttackPresentation Classification Error Rate (APCER) & Bona fide PresentationClassification Error Rate (BPCER) of 0% compared to comparable traditionalmethods.

Detecting Finger-Vein Presentation Attacks Using 3D Shape & Diffuse Reflectance Decomposition