Fingerprint Synthesis: Search with 100 Million Prints

TL;DR

This paper introduces a GAN-based method to synthesize a large-scale fingerprint dataset of 100 million images, improving realism and distinctiveness for large-scale fingerprint search evaluation.

Contribution

It presents a novel fingerprint synthesis approach with identity loss, enabling realistic and distinct fingerprints suitable for large-scale search testing.

Findings

Synthesized fingerprints are more similar to real ones across eight metrics.

Synthetic fingerprints are more distinct than previous methods.

Achieved 89.7% Rank-1 accuracy on 100 million fingerprint search.

Abstract

Evaluation of large-scale fingerprint search algorithms has been limited due to lack of publicly available datasets. To address this problem, we utilize a Generative Adversarial Network (GAN) to synthesize a fingerprint dataset consisting of 100 million fingerprint images. In contrast to existing fingerprint synthesis algorithms, we incorporate an identity loss which guides the generator to synthesize fingerprints corresponding to more distinct identities. The characteristics of our synthesized fingerprints are shown to be more similar to real fingerprints than existing methods via eight different metrics (minutiae count - block and template, minutiae direction - block and template, minutiae convex hull area, minutiae spatial distribution, block minutiae quality distribution, and NFIQ 2.0 scores). Additionally, the synthetic fingerprints based on our approach are shown to be more distinct than synthetic fingerprints based on published methods through search results and imposter distribution statistics. Finally, we report for the first time in open literature, search accuracy against a gallery of 100 million fingerprint images (NIST SD4 Rank-1 accuracy of 89.7%).