GAN et: Gabor Attention Aggregation Network for Palmvein Identification
Palm vein recognition has attracted recently wide attention thanks to its robust feature representation and high accuracy. Despite advancements in the literature, however, existing solutions suffer from the following issues: 1) Insufficient large-scale data for deep learning-based recognition of vei...
Saved in:
Published in | 2024 16th International Conference on Human System Interaction (HSI) pp. 1 - 6 |
---|---|
Main Authors | , , , , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
08.07.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Palm vein recognition has attracted recently wide attention thanks to its robust feature representation and high accuracy. Despite advancements in the literature, however, existing solutions suffer from the following issues: 1) Insufficient large-scale data for deep learning-based recognition of vein biometrics, resulting in decreased generalization performance and model accuracy. 2) Lack of methods based on machine learning convolutional neural networks capable of capturing the global receptive field for vein biometric recognition. In addressing these issues, this paper proposes a method to acquire the global receptive field, termed G AN et, which extracts vein features using Gabor filters and computes an attention mechanism to capture the global receptive field for downstream palm vein recognition models. Initially, vein features are extracted using multi-scale fixed Gabor filters and multi-scale adaptive Gabor filters. Subsequently, self-attention mechanisms are employed to compute relationships between blocks to obtain the global receptive field. To perform recognition, the Euclidean distance between feature vectors is then computed. Our experiments on three datasets show that our approach outperforms existing palm vein recognition methods. |
---|---|
AbstractList | Palm vein recognition has attracted recently wide attention thanks to its robust feature representation and high accuracy. Despite advancements in the literature, however, existing solutions suffer from the following issues: 1) Insufficient large-scale data for deep learning-based recognition of vein biometrics, resulting in decreased generalization performance and model accuracy. 2) Lack of methods based on machine learning convolutional neural networks capable of capturing the global receptive field for vein biometric recognition. In addressing these issues, this paper proposes a method to acquire the global receptive field, termed G AN et, which extracts vein features using Gabor filters and computes an attention mechanism to capture the global receptive field for downstream palm vein recognition models. Initially, vein features are extracted using multi-scale fixed Gabor filters and multi-scale adaptive Gabor filters. Subsequently, self-attention mechanisms are employed to compute relationships between blocks to obtain the global receptive field. To perform recognition, the Euclidean distance between feature vectors is then computed. Our experiments on three datasets show that our approach outperforms existing palm vein recognition methods. |
Author | Liao, Hongchao El Yacoubi, Mounim A. Qin, Huafeng Jin, Xin Zhu, Hongyu Fu, Yuming |
Author_xml | – sequence: 1 givenname: Hongchao surname: Liao fullname: Liao, Hongchao email: lhc980503@163.com organization: School of Artificial Intelligence CTBU,Chongqing,China – sequence: 2 givenname: Xin surname: Jin fullname: Jin, Xin email: jinxin20001118@163.com organization: School of Artificial Intelligence CTBU,Chongqing,China – sequence: 3 givenname: Hongyu surname: Zhu fullname: Zhu, Hongyu email: zhuhongyu@ctbu.edu.cn organization: School of Artificial Intelligence CTBU,Chongqing,China – sequence: 4 givenname: Yuming surname: Fu fullname: Fu, Yuming email: 1057726877@qq.com organization: School of Artificial Intelligence CTBU,Chongqing,China – sequence: 5 givenname: Mounim A. surname: El Yacoubi fullname: El Yacoubi, Mounim A. email: mounim.el_yacoubi@telecom-sudparis.eu organization: School of Artificial Intelligence Telecom SudParis, Institut Polytechnique de Paris,Paris,France – sequence: 6 givenname: Huafeng surname: Qin fullname: Qin, Huafeng email: qinhuafengfeng@163.com organization: School of Artificial Intelligence CTBU,Chongqing,China |
BookMark | eNqFzlFrwjAUBeC7scF09h_IyB-wy01s2vhWZFZfRNB3yeZtidZE0qD47zdle97TOXC-h9OHJ-cdAbwhTxG5fp-vFwqVFKngYpwiVyizHB8g0bkuZMalEhrVI_QEZsVIiGz8AknX7TnnEotCC-xBVZVLRnHCKvPpAytjJBetd6xsmkCNufclxYsPB1b_iJVpj2eyji12N1nbr7sZwHNt2o6S33yF4exjM52PLBFtT8EeTbhu_z7Kf-ZvGkdAXA |
ContentType | Conference Proceeding |
DBID | 6IE 6IL CBEJK RIE RIL |
DOI | 10.1109/HSI61632.2024.10613571 |
DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Electronic Library IEEE Proceedings Order Plans (POP All) 1998-Present |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISBN | 9798350362916 |
EISSN | 2158-2254 |
EndPage | 6 |
ExternalDocumentID | 10613571 |
Genre | orig-research |
GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61976030 funderid: 10.13039/501100001809 |
GroupedDBID | 6IE 6IF 6IK 6IL 6IN AAJGR ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IPLJI OCL RIE RIL |
ID | FETCH-ieee_primary_106135713 |
IEDL.DBID | RIE |
IngestDate | Wed Aug 14 05:40:31 EDT 2024 |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-ieee_primary_106135713 |
ParticipantIDs | ieee_primary_10613571 |
PublicationCentury | 2000 |
PublicationDate | 2024-July-8 |
PublicationDateYYYYMMDD | 2024-07-08 |
PublicationDate_xml | – month: 07 year: 2024 text: 2024-July-8 day: 08 |
PublicationDecade | 2020 |
PublicationTitle | 2024 16th International Conference on Human System Interaction (HSI) |
PublicationTitleAbbrev | HSI |
PublicationYear | 2024 |
Publisher | IEEE |
Publisher_xml | – name: IEEE |
SSID | ssj0003188921 |
Score | 3.8620043 |
Snippet | Palm vein recognition has attracted recently wide attention thanks to its robust feature representation and high accuracy. Despite advancements in the... |
SourceID | ieee |
SourceType | Publisher |
StartPage | 1 |
SubjectTerms | Accuracy Attention mechanisms Biological system modeling Biometrics (access control) Error analysis Euclidean distance Feature extraction Gabor filters global receptive field palm vein recognition |
Title | GAN et: Gabor Attention Aggregation Network for Palmvein Identification |
URI | https://ieeexplore.ieee.org/document/10613571 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjZ1LS4RQFMcPNatW08PoMcVdtNXxvhxtJ9GMBUlQwewGdY5DBE7EtUWfvvvQiaKgnQjqwXPlPPz_7gG4EKxgZb3kvqgx8QWywi-TivrUJPcTjGrJDe98l0fZk7idy3kHq1sWBhGt-AwDc2j_5S_XVWtaZWNTvnBpiPHtOGQO1to0VPTijBNGOwqYhsk4e7iJdLphcCsmgv7ib2NUbBSZDiHvn-_EIy9Bq8qg-vixNeO_DdwF7wvYI_ebULQHW9jsw7Cf2EC6D_gAZrM0J6guycz4nqRKObUjSVe67l5ZL5HcKcOJTmeJGa_yjs8NcUBv3XX4PBhNrx-vMt8Yt3h1O1Yserv4IQyadYNHQOREV2JYS6RcCKykmQZb8ygqGBZhQcNj8H69xckf509hx7xmq2SNRzBQby2e6XitynPrp0-mYZgH |
link.rule.ids | 310,311,786,790,795,796,802,27956,55107 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjZ1LS8NAEMcHqQc91UfER9U9eE2axyZpvAWxSbUNghV6C0k6W0RIRTYe_PTuI6koCt5CIGHYSZjH_n87AFfULdySLT2TMoxMim5hllHlmI5M7kMMmO9J3nmWBekTvVv4ixZWVywMIirxGVryUu3lL9dVI1tlQ1m-eL4kxrdFoLdDjWttWiri8xxFrtNywI4dDdPHSSASDglcudTqHv82SEXFkXEfss4CLR95sRpeWtXHj8MZ_23iHhhfyB552ASjfdjC-gD63cwG0v7Ch5AkcUaQX5NEep_EnGu9I4lXovJeKT-RTGvDiUhoiRyw8o7PNdFIL2t7fAYMxrfzm9SUxuWv-syKvLPLO4Jeva7xGIgfiloMmY-ORylWvpwHy7wgKFws7MKxT8D49RWnf9y_hJ10Ppvm00l2fwa7csmVrnU0gB5_a_BcRG9eXiiffQLZQJtb |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2024+16th+International+Conference+on+Human+System+Interaction+%28HSI%29&rft.atitle=GAN+et%3A+Gabor+Attention+Aggregation+Network+for+Palmvein+Identification&rft.au=Liao%2C+Hongchao&rft.au=Jin%2C+Xin&rft.au=Zhu%2C+Hongyu&rft.au=Fu%2C+Yuming&rft.date=2024-07-08&rft.pub=IEEE&rft.eissn=2158-2254&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FHSI61632.2024.10613571&rft.externalDocID=10613571 |