Contactless Fingerprint Biometric Anti-Spoofing: An Unsupervised Deep Learning Approach

TL;DR

This paper presents an unsupervised deep learning method for contactless fingerprint anti-spoofing that effectively detects unseen presentation attacks without using spoofed samples during training.

Contribution

It introduces a novel autoencoder-based model with attention mechanisms trained solely on bonafide images, enhancing generalization to unseen spoofing attacks.

Findings

Achieved an average BPCER of 0.96%

Achieved an APCER of 1.6%

Effective against various unseen presentation attacks

Abstract

Contactless fingerprint recognition offers a higher level of user comfort and addresses hygiene concerns more effectively. However, it is also more vulnerable to presentation attacks such as photo paper, paper-printout, and various display attacks, which makes it more challenging to implement in biometric systems compared to contact-based modalities. Limited research has been conducted on presentation attacks in contactless fingerprint systems, and these studies have encountered challenges in terms of generalization and scalability since both bonafide samples and presentation attacks are utilized during training model. Although this approach appears promising, it lacks the ability to handle unseen attacks, which is a crucial factor for developing PAD methods that can generalize effectively. We introduced an innovative anti-spoofing approach that combines an unsupervised autoencoder with a convolutional block attention module to address the limitations of existing methods. Our model is exclusively trained on bonafide images without exposure to any spoofed samples during the training phase. It is then evaluated against various types of presentation attack images in the testing phase. The scheme we proposed has achieved an average BPCER of 0.96\% with an APCER of 1.6\% for presentation attacks involving various types of spoofed samples.