Fingerprint Presentation Attacks Detection in the Deep Learning Era: a “LivDet” Story
Fingerprint Presentation Attacks Detection in the Deep Learning Era: a “LivDet” Story
Online
October 20, 2020, 12:30pm CE(S)T
More than 15 years ago, the research community claimed that fingerprints are very difficult to reproduce and steal. We lost our “innocence” when, between 2001 and 2002, some scholars fabricated artificial replicas of the fingers, named “fake fingers” or “gummy fingers”, that, if put on the fingerprint sensor surface, provided images impossible to distinguish from those of the live fingers, even by visual inspection of experts.
Since the fundamental problem was the lack of data, the organization of the International Fingerprint Liveness Detection Competition, known as “LivDet”, helped our research group to acquire strong know-how on the difficulties in fabricating fake fingers.
From 2015 to the 2019 edition, deep-learning-based algorithms outnumbered the ones based on handcraft features. In this webinar, we firstly review the main techniques for fingerprint presentation attack detection. We also summarize the LivDet experience. Finally, we provide some anticipations of what we expect by the incoming Livdet 2021. Our goal is to answer the following question: what did we gain, and what did we lose on moving from methods based on handcrafted features to deep learning ones? What can a possible pathway for the future of this topic be?
Article Topics
biometric liveness detection | biometrics | biometrics research | EAB | European Association for Biometrics | fingerprint biometrics | spoof detection | webinar
Comments