TY - GEN
T1 - Fingerprint Feature Extraction Using CNN with Multiple Attention Mechanisms
AU - Sasuga, Nagisa
AU - Ito, Koichi
AU - Aoki, Takafumi
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In this paper, we improve the performance of CNN-based fingerprint recognition without increasing the size of CNN, while training CNN on a limited number of data in public databases to guarantee reproducibility. We propose a Texture-Minutiae Network (TMNet) for extracting texture and minutia features based on ResNet-34. We introduce multiple attention mechanisms to TMNet in order to improve performance on fingerprint recognition without increasing the size of the network. Through experiments of performance evaluation using FVC2004 DB1, DB2, and DB3, we demonstrate that the proposed method is more effective than the conventional methods for fingerprint recognition.
AB - In this paper, we improve the performance of CNN-based fingerprint recognition without increasing the size of CNN, while training CNN on a limited number of data in public databases to guarantee reproducibility. We propose a Texture-Minutiae Network (TMNet) for extracting texture and minutia features based on ResNet-34. We introduce multiple attention mechanisms to TMNet in order to improve performance on fingerprint recognition without increasing the size of the network. Through experiments of performance evaluation using FVC2004 DB1, DB2, and DB3, we demonstrate that the proposed method is more effective than the conventional methods for fingerprint recognition.
UR - http://www.scopus.com/inward/record.url?scp=85147255107&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85147255107&partnerID=8YFLogxK
U2 - 10.1109/IJCB54206.2022.10007957
DO - 10.1109/IJCB54206.2022.10007957
M3 - Conference contribution
AN - SCOPUS:85147255107
T3 - 2022 IEEE International Joint Conference on Biometrics, IJCB 2022
BT - 2022 IEEE International Joint Conference on Biometrics, IJCB 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Joint Conference on Biometrics, IJCB 2022
Y2 - 10 October 2022 through 13 October 2022
ER -