Fingerprint Feature Extraction Using CNN with Multiple Attention Mechanisms

Nagisa Sasuga, Koichi Ito, Takafumi Aoki

研究成果: 書籍の章/レポート/Proceedings会議への寄与査読

2 被引用数 (Scopus)

抄録

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.

本文言語英語
ホスト出版物のタイトル2022 IEEE International Joint Conference on Biometrics, IJCB 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781665463942
DOI
出版ステータス出版済み - 2022
イベント2022 IEEE International Joint Conference on Biometrics, IJCB 2022 - Abu Dhabi, アラブ首長国連邦
継続期間: 2022 10月 102022 10月 13

出版物シリーズ

名前2022 IEEE International Joint Conference on Biometrics, IJCB 2022

会議

会議2022 IEEE International Joint Conference on Biometrics, IJCB 2022
国/地域アラブ首長国連邦
CityAbu Dhabi
Period22/10/1022/10/13

フィンガープリント

「Fingerprint Feature Extraction Using CNN with Multiple Attention Mechanisms」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル