Adaptive Deep Convolutional GAN for Fingerprint Sample Synthesis

Abstract

Real biometric fingerprint samples belong to the category of personal data, and therefore their usage for deep learning model training may have certain limitations. Artificially generated fingerprint images do not relate to a real person and can be used freely (“privacy-friendly”). Synthesized fingerprint samples are of interest for applied research: biological (papillary lines structure and alteration), forensic (computer fingerprint identification, reconstruction, and restoration of damaged samples), technological (various methods of biometric security). Generation of artificial fingerprints that accurately reproduce the textural features of real fingerprints could be a difficult task. In this paper, we present a deep learning framework — Adaptive Deep Convolutional Generative Adversarial Network (ADCGAN) — that we have developed and researched, and which has demonstrated the ability to generate realistic fingerprint samples that are similar to real ones in terms of their feature spectrum. ADCGAN makes it possible to conduct fingerprint research, without restrictions related to the confidential nature of biometric data.