Paper Reading AI Learner

Level Three Synthetic Fingerprint Generation

2020-02-13 18:33:01
André Brasil Vieira Wyzykowski, Mauricio Pamplona Segundo, Rubisley de Paula Lemes


Today's legal restrictions that protect the privacy of biometric data are hampering fingerprint recognition researches. For instance, all public databases of high-resolution fingerprints ceased to be publicly available. To address this problem, we present an approach to creating high-resolution synthetic fingerprints. We modified a state-of-the-art fingerprint generator to create ridge maps with sweat pores and trained a CycleGAN to transform these maps into realistic prints. We also create a synthetic database of high-resolution fingerprints using the proposed approach to propel further studies in this field without raising any legal issues. We test this database with two existing fingerprint matchers without adjustments to confirm the realism of the generated images. Besides, we provide a visual analysis that highlights the quality of our results compared to the state-of-the-art.

Abstract (translated)