TY - GEN
T1 - Domain transformation of fingerprint images using CycleGAN
AU - Takahashi, Ai
AU - Koda, Yoshinori
AU - Ito, Koichi
AU - Aoki, Takafumi
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - 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.
AB - 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.
KW - Biometrics
KW - Fingerprint
KW - GAN
KW - Image normalization
UR - http://www.scopus.com/inward/record.url?scp=85081951519&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85081951519&partnerID=8YFLogxK
U2 - 10.1109/GCCE46687.2019.9014646
DO - 10.1109/GCCE46687.2019.9014646
M3 - Conference contribution
AN - SCOPUS:85081951519
T3 - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
SP - 9
EP - 10
BT - 2019 IEEE 8th Global Conference on Consumer Electronics, GCCE 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th IEEE Global Conference on Consumer Electronics, GCCE 2019
Y2 - 15 October 2019 through 18 October 2019
ER -