A Survey on Unknown Presentation Attack Detection for Fingerprint

Fingerprint recognition systems are widely deployed in various real-life applications as they have achieved high accuracy. The used include border control, automated teller machine (ATM), and attendance monitoring systems. However, these critical prone to spoofing attacks (a.k.a presentation (PA)). PA for fingerprint can be performed by presenting gummy fingers made from different materials such silicone, gelatine, play-doh, ecoflex, 2D printed paper, 3D material, or latex. Biometrics Researchers developed Presentation Attack Detection (PAD) methods a countermeasure PA. PAD is usually done training learning classifier known given dataset, achieve accuracy this task. generalizing unknown an essential problem applicability real-world systems, mainly because cannot exhaustively listed advance. In survey we present comprehensive on existing algorithms specifically detecting PAD. We categorize algorithms, point out their advantages/disadvantages, future directions area.