Partial Fingerprint on Combined Evaluation using Deep Learning and Feature Descriptor

Chrisantonius, Tri Kuntoro Priyambodo, Farchan Hakim Raswa, Jia Ching Wang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

4 引文 斯高帕斯(Scopus)

摘要

Partial fingerprint recognition has become crucial to identifying a user's authenticity in mobile device transactions. As a result, developments are increasing for more effective and accurate identification and authentication of a user using a scanner that captures a small fingerprint image. However, there is a reduction in the number of features from a full fingerprint to a partial fingerprint image during partial to partial fingerprint matching. Therefore, we propose a method combining deep learning and feature descriptors for partial fingerprint recognition. The matching score is obtained by the weighted combination of the scores from deep learning and feature descriptors. Experiments have been carried out with data variations such as the image size, epoch numbers and dataset types. The proposed method of combining deep learning and feature descriptors in the matching score evaluation process has obtained good results for the FVC2002 DB1, DB2 and DB3 datasets.

原文???core.languages.en_GB???
主出版物標題2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1611-1614
頁數4
ISBN(電子)9789881476890
出版狀態已出版 - 2021
事件2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Tokyo, Japan
持續時間: 14 12月 202117 12月 2021

出版系列

名字2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021 - Proceedings

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2021
國家/地區Japan
城市Tokyo
期間14/12/2117/12/21

指紋

深入研究「Partial Fingerprint on Combined Evaluation using Deep Learning and Feature Descriptor」主題。共同形成了獨特的指紋。

引用此