FinPAD: State-of-the-art of fingerprint presentation attack detection mechanisms, taxonomy and future perspectives

Abstract

In the recent times, with an increase in human identity thefts, the fingerprint-based biometric systems play a significant role in secured authentication and access restrictions. The security and privacy are key aspects that need peculiar reflection while designing these recognition systems. However, imposters practice several presentation attack instruments (PAIs) to exploit the biometrical infrastructure to breach the security aspects. Though, biometric systems are receptive to diverse threats, but the presentation attacks (PAs) are the most widely attempted in current scenario. In PA, an attacker makes use of an artifact of a real biometric trait in order to circumvent the sensor module of the system. In this article, we expound state-of-the-art fingerprint presentation attack detection (FinPAD) mechanisms along with taxonomy covering the period of 2001–2021. The article presents a comprehensive survey of classical hardware-based, handcrafted fingerprint PAD approaches with a special focus on recent deep leaning-based techniques. We provide a summary of publically available fingerprint anti-spoofing databases, standard PAD evaluation protocols, and fingerprint liveness detection competition (LivDet) series till the year 2021. The study explored several open research challenges that yield future directions to the investigators in this active field of research. Our study reveals that the modern data-driven FinPAD techniques are robust and efficient as compared to their hardware-based counterpart in terms of performance. However, designing lightweight fingerprint PAD techniques with smaller datasets that offer better performance in cross-dataset, cross-material, and cross-sensor scenario still remain an open research issue.