SpoofGAN: Synthetic Fingerprint Spoof Images

TL;DR

This paper introduces SpoofGAN, a generative model that creates high-quality synthetic fingerprint images, including spoofs, to augment training data and significantly improve fingerprint spoof detection performance.

Contribution

It presents a novel generative architecture for synthesizing realistic live and spoof fingerprints, enhancing deep learning-based spoof detection with limited real data.

Findings

Synthetic fingerprints improve detection accuracy across multiple datasets.

Only 25% of real data needed when augmented with synthetic samples.

Synthetic data closely mimics real fingerprint distributions.

Abstract

A major limitation to advances in fingerprint spoof detection is the lack of publicly available, large-scale fingerprint spoof datasets, a problem which has been compounded by increased concerns surrounding privacy and security of biometric data. Furthermore, most state-of-the-art spoof detection algorithms rely on deep networks which perform best in the presence of a large amount of training data. This work aims to demonstrate the utility of synthetic (both live and spoof) fingerprints in supplying these algorithms with sufficient data to improve the performance of fingerprint spoof detection algorithms beyond the capabilities when training on a limited amount of publicly available real datasets. First, we provide details of our approach in modifying a state-of-the-art generative architecture to synthesize high quality live and spoof fingerprints. Then, we provide quantitative and qualitative analysis to verify the quality of our synthetic fingerprints in mimicking the distribution of real data samples. We showcase the utility of our synthetic live and spoof fingerprints in training a deep network for fingerprint spoof detection, which dramatically boosts the performance across three different evaluation datasets compared to an identical model trained on real data alone. Finally, we demonstrate that only 25% of the original (real) dataset is required to obtain similar detection performance when augmenting the training dataset with synthetic data.