HIGH FIDELITY FINGERPRINT GENERATION: QUALITY, UNIQUENESS, AND PRIVACY

被引：10

作者：

Bahmani, Keivan ^{[1
]}

Plesh, Richard ^{[1
]}

Johnson, Peter ^{[1
]}

Schuckers, Stephanie ^{[1
]}

Swyka, Timothy ^{[2
]}

机构：

[1] Clarkson Univ, Potsdam, NY 13699 USA

[2] Precise Biometr, Potsdam, NY USA

来源：

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | 2021年

基金：

美国国家科学基金会;

关键词：

Fingerprint Synthesis; Generative Adversarial Networks; Fingerprint Matching; Fingerprint Quality;

D O I：

10.1109/ICIP42928.2021.9506386

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this work, we utilize progressive growth-based Generative Adversarial Networks (GANs) to develop the Clarkson Fingerprint Generator (CFG). We demonstrate that the CFG is capable of generating realistic, high fidelity, 512x512 pixels, full, plain impression fingerprints. Our results suggest that the fingerprints generated by the CFG are unique, diverse, and resemble the training dataset in terms of minutiae configuration and quality, while not revealing the underlying identities of the training data. We make the pre-trained CFG model and the synthetically generated dataset publicly available at https: //github.com/keivanB/Clarkson_Finger_Gen

引用

页码：3018 / 3022

页数：5

共 20 条

[1]

Bontrager Philip, 2017, ARXIV170507386

[2] Fingerprint Synthesis: Evaluating Fingerprint Search at Scale [J].