Domain transformation of fingerprint images using CycleGAN

Ai Takahashi, Yoshinori Koda, Koichi Ito, Takafumi Aoki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Fingerprint recognition has been used in various situations because of its high accuracy of person authentication. Fingerprint images taken by the different sensors have different brightness, resolution and noise even in the same fingers. Therefore, such fingerprint images have to be normalized so as to keep high-accuracy fingerprint recognition. This paper proposes a fingerprint image normalization method using domain conversion by CycleGAN. Though experiments, we demonstrate that the fingerprint image normalized by the proposed method improve the performance of fingerprint recognition.

Original languageEnglish
Title of host publication2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages9-10
Number of pages2
ISBN (Electronic)9781728135755
DOIs
Publication statusPublished - 2019 Oct
Event8th IEEE Global Conference on Consumer Electronics, GCCE 2019 - Osaka, Japan
Duration: 2019 Oct 152019 Oct 18

Publication series

Name2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019

Conference

Conference8th IEEE Global Conference on Consumer Electronics, GCCE 2019
CountryJapan
CityOsaka
Period19/10/1519/10/18

Keywords

  • Biometrics
  • Fingerprint
  • GAN
  • Image normalization

ASJC Scopus subject areas

  • Instrumentation
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Domain transformation of fingerprint images using CycleGAN'. Together they form a unique fingerprint.

Cite this