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

Touch-based fingerprint biometrics is one of the most popular biometricmodalities with applications in several fields. Problems associated withtouch-based techniques such as the presence of latent fingerprints and hygieneissues due to many people touching the same surface motivated the community tolook for non-contact-based solutions. For the last few years, contactlessfingerprint systems are on the rise and in demand because of the ability toturn any device with a camera into a fingerprint reader. Yet, before we canfully utilize the benefit of noncontact-based methods, the biometric communityneeds to resolve a few concerns such as the resiliency of the system againstpresentation attacks. One of the major obstacles is the limited publiclyavailable data sets with inadequate spoof and live data. In this publication,we have developed a Presentation attack detection (PAD) dataset of more than7500 four-finger images and more than 14,000 manually segmentedsingle-fingertip images, and 10,000 synthetic fingertips (deepfakes). The PADdataset was collected from six different Presentation Attack Instruments (PAI)of three different difficulty levels according to FIDO protocols, with fivedifferent types of PAI materials, and different smartphone cameras with manualfocusing. We have utilized DenseNet-121 and NasNetMobile models and ourproposed dataset to develop PAD algorithms and achieved PAD accuracy of Attackpresentation classification error rate (APCER) 0.14\% and Bonafide presentationclassification error rate (BPCER) 0.18\%. We have also reported the testresults of the models against unseen spoof types to replicate uncertainreal-world testing scenarios.

Presentation Attack Detection with Advanced CNN Models for Noncontact-based Fingerprint Systems