On the generalisation capabilities of fingerprint presentation attack detection methods in the short wave infrared domain

Abstract

Nowadays, fingerprint-based biometric recognition systems are becoming increasingly popular. However, in spite of their numerous advantages, biometric capture devices are usually exposed to the public and thus vulnerable to presentation attacks (PAs). Therefore, presentation attack detection (PAD) methods are of utmost importance in order to distinguish between bona fide and attack presentations. Owing to the nearly unlimited possibilities to create new presentation attack instruments (PAIs), unknown attacks are a threat to the existing PAD algorithms. This fact motivates research on generalisation capabilities in order to find PAD methods that are resilient to new attacks. In this context, the authors evaluate the generalisability of multiple PAD algorithms on a dataset of 19,711 bona fide and 4339 PA samples, including 45 different PAI species. The PAD data is captured in the short wave infrared domain, and the results discuss the advantages and drawbacks of this PAD technique regarding unknown attacks.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

On the Effectiveness of Impedance-Based Fingerprint Presentation Attack Detection

“…In this context, it was shown that complementary information channels can be fused to improve the overall PAD performance [ 47 , 60 ]. For this particular capture device, the optical fingerprint image could be used as a second data source, thereby combining software and hardware-based fingerprint PAD approaches.…”

“…However, both works did not collect APs to confirm the PAD capabilities. On the other hand, Kolberg et al [ 47 ] presented an extensive benchmark of multiple fingerprint PAD algorithms for multi-spectral images. The leave-one-out (LOO) experiments showed that a fusion of complementary input data benefits the PAD performance in the presence of unknown attacks.…”