Universal Material Translator: Towards Spoof Fingerprint Generalization

TL;DR

This paper introduces a style transfer-based data augmentation method to improve spoof fingerprint detectors' ability to generalize to unseen spoof materials, enhancing robustness with limited data.

Contribution

It proposes a novel style transfer augmentation wrapper that synthesizes new spoof images from few examples, boosting detector robustness to unseen spoof materials.

Findings

Improved detection accuracy on unseen spoof materials.

Enhanced robustness of spoof detectors with limited training data.

Validated on LivDet 2015 dataset.

Abstract

Spoof detectors are classifiers that are trained to distinguish spoof fingerprints from bonafide ones. However, state of the art spoof detectors do not generalize well on unseen spoof materials. This study proposes a style transfer based augmentation wrapper that can be used on any existing spoof detector and can dynamically improve the robustness of the spoof detection system on spoof materials for which we have very low data. Our method is an approach for synthesizing new spoof images from a few spoof examples that transfers the style or material properties of the spoof examples to the content of bonafide fingerprints to generate a larger number of examples to train the classifier on. We demonstrate the effectiveness of our approach on materials in the publicly available LivDet 2015 dataset and show that the proposed approach leads to robustness to fingerprint spoofs of the target material.