Residential Collegefalse
Status已發表Published
CO3Net: Coordinate-Aware Contrastive Competitive Neural Network for Palmprint Recognition
Yang,Ziyuan1; Xia,Wenjun1; Qiao,Yifan1; Lu,Zexin1; Zhang,Bob2; Leng,Lu3; Zhang,Yi4
2023
Source PublicationIEEE Transactions on Instrumentation and Measurement
ISSN0018-9456
Volume72
Abstract

Palmprint recognition achieves high discrimination for identity verification. Compared with handcrafted local texture descriptors, convolutional neural networks (CNNs) can spontaneously learn optimal discriminative features without any prior knowledge. To further enhance the features' representation and discrimination, we propose a coordinate-aware contrastive competitive neural network (CO3Net) for palmprint recognition. To extract the multiscale textures, CO3Net consists of three parallel learnable Gabor filters (LGFs)-based texture extraction branches that learn the discriminative and robust ordering features. Due to the heterogeneity of palmprints, the effects of different textures on the final recognition performance are inconsistent, and dynamically focusing on the textures is beneficial to the performance improvement. Then, CO3Net introduces the attention modules to explore the spatial information, and selects more robust and discriminative textures. Specifically, coordinate attention (CA) is embedded into CO3Net to adaptively focus on the important textures from the positional information. Since it is difficult for the cross-entropy loss to build a compact intraclass and separate interclass feature space, the contrastive loss is employed to jointly optimize the network. CO3Net is validated on four public datasets, and the results demonstrate the remarkable recognition performance of the proposed CO3Net compared to the other state-of-the-art methods.

KeywordContrastive Learning Coordinate Attention (Ca) Deep Learning (Dl) Gabor Filter Palmprint Recognition
DOI10.1109/TIM.2023.3276506
URLView the original
Indexed BySCIE
Language英語English
WOS Research AreaEngineering ; Instruments & Instrumentation
WOS SubjectEngineering, Electrical & Electronic ; Instruments & Instrumentation
WOS IDWOS:000996515600022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Scopus ID2-s2.0-85161296627
Fulltext Access
Citation statistics
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorZhang,Yi
Affiliation1.Sichuan University,College of Computer Science,Chengdu,610065,China
2.University of Macau,Pattern Analysis and Machine Intelligence Group,Department of Computer and Information Science,Macao
3.Nanchang Hangkong University,School of Software,Nanchang,330063,China
4.Sichuan University,School of Cyber Science and Engineering,Chengdu,610065,China
Recommended Citation
GB/T 7714
Yang,Ziyuan,Xia,Wenjun,Qiao,Yifan,et al. CO3Net: Coordinate-Aware Contrastive Competitive Neural Network for Palmprint Recognition[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72.
APA Yang,Ziyuan., Xia,Wenjun., Qiao,Yifan., Lu,Zexin., Zhang,Bob., Leng,Lu., & Zhang,Yi (2023). CO3Net: Coordinate-Aware Contrastive Competitive Neural Network for Palmprint Recognition. IEEE Transactions on Instrumentation and Measurement, 72.
MLA Yang,Ziyuan,et al."CO3Net: Coordinate-Aware Contrastive Competitive Neural Network for Palmprint Recognition".IEEE Transactions on Instrumentation and Measurement 72(2023).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang,Ziyuan]'s Articles
[Xia,Wenjun]'s Articles
[Qiao,Yifan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang,Ziyuan]'s Articles
[Xia,Wenjun]'s Articles
[Qiao,Yifan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang,Ziyuan]'s Articles
[Xia,Wenjun]'s Articles
[Qiao,Yifan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.