Local feature encoding for unknown presentation attack detection: An analysis of different local feature descriptors

• Published in: IET biometrics Vol. 10; no. 4; pp. 374 - 391
• Main Authors: González‐Soler, Lázaro J., Gomez‐Barrero, Marta, Kolberg, Jascha, Chang, Leonardo, Pérez‐Suárez, Airel, Busch, Christoph
• Format: Journal Article
• Language: English
• Published: Stevenage John Wiley & Sons, Inc 01.07.2021; Wiley
• Subjects: Access control; Analysis; Art techniques; authorisation; Biometric recognition systems; Biometrics; Biometry; computer crime; feature extraction; Feature recognition; fingerprint identification; Fingerprint verification; image classification; Methods; Performance evaluation; Software; vectors
• ISSN: 2047-4938; 2047-4946
• DOI: 10.1049/bme2.12023

In spite of the advantages of using fingerprints for subject authentication, several works have shown that fingerprint recognition systems can be easily circumvented by means of artificial fingerprints or presentation attack instruments (PAIs). In order to address that threat, the existing presentation attack detection (PAD) methods have reported a high detection performance when materials used for the fabrication of PAIs and capture devices are known. However, for more complex and realistic scenarios where one of those factors remains unknown, these PAD methods are unable to correctly separate a PAI from a real fingerprint (i.e. bona fide presentation). In this article, a new PAD approach based on the Fisher Vector technique, which combines local and global information of several local feature descriptors in order to improve the PAD generalisation capabilities, was proposed. The experimental results over unknown scenarios taken from LivDet 2011 to LivDet 2017 show that our proposal reduces the top state‐of‐the‐art average classification error rates by up to four times, thereby making it suitable in real applications demanding high security. In addition, the best single configuration achieved the best results in the LivDet 2019 competition, with an overall accuracy of 96.17%.