Multi-Modal Fingerprint Presentation Attack Detection: Evaluation On A New Dataset

TL;DR

This paper explores the use of multiple new sensing modalities, including short-wave-infrared, near-infrared, and laser illumination, for fingerprint presentation attack detection, demonstrating their superiority over legacy data through comprehensive analysis.

Contribution

It introduces a multi-modal sensing approach for fingerprint liveness detection and evaluates its effectiveness across various datasets and attack scenarios, highlighting the benefits of unconventional sensing modalities.

Findings

New sensing modalities outperform legacy data in most cases.

Fusion of modalities improves detection accuracy.

Data quality, not classification method, drives performance.

Abstract

Fingerprint presentation attack detection is becoming an increasingly challenging problem due to the continuous advancement of attack preparation techniques, which generate realistic-looking fake fingerprint presentations. In this work, rather than relying on legacy fingerprint images, which are widely used in the community, we study the usefulness of multiple recently introduced sensing modalities. Our study covers front-illumination imaging using short-wave-infrared, near-infrared, and laser illumination; and back-illumination imaging using near-infrared light. Toward studying the effectiveness of each of these unconventional sensing modalities and their fusion for liveness detection, we conducted a comprehensive analysis using a fully convolutional deep neural network framework. Our evaluation compares different combination of the new sensing modalities to legacy data from one of our collections as well as the public LivDet2015 dataset, showing the superiority of the new sensing modalities in most cases. It also covers the cases of known and unknown attacks and the cases of intra-dataset and inter-dataset evaluations. Our results indicate that the power of our approach stems from the nature of the captured data rather than the employed classification framework, which justifies the extra cost for hardware-based (or hybrid) solutions. We plan to publicly release one of our dataset collections.