Palmprint recognition based on gating mechanism and adaptive feature fusion

作者全名："Zhang, Kaibi; Xu, Guofeng; Jin, Ye Kelly; Qi, Guanqiu; Yang, Xun; Bai, Litao"

作者地址："[Zhang, Kaibi; Xu, Guofeng] Chongqing Univ Posts & Telecommun, Sch Automat, Chongqing, Peoples R China; [Xu, Guofeng; Bai, Litao] Chongqing Med Univ, Affiliated Hosp 2, Dept Integrated Chinese & Western Med, Chongqing, Peoples R China; [Jin, Ye Kelly] Calif State Univ Los Angeles, Coll Business & Econ, Los Angeles, CA USA; [Jin, Ye Kelly] Double Deuce Sports, Bowling Green, KY USA; [Qi, Guanqiu] SUNY Buffalo State, Comp Informat Syst Dept, Buffalo, NY USA; [Yang, Xun] China Merchants Chongqing Commun Res & Design Inst, Chongqing, Peoples R China"

通信作者："Bai, LT (通讯作者)，Chongqing Med Univ, Affiliated Hosp 2, Dept Integrated Chinese & Western Med, Chongqing, Peoples R China."

来源：FRONTIERS IN NEUROROBOTICS

ESI学科分类：COMPUTER SCIENCE

WOS号：WOS:001009765500001

JCR分区：Q3

影响因子：2.6

年份：2023

卷号：17

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：palmprint recognition; convolutional neural networks (CNN); gate control mechanism; adaptive feature fusion; deep learning-based artificial neural networks

摘要："As a type of biometric recognition, palmprint recognition uses unique discriminative features on the palm of a person to identify his/her identity. It has attracted much attention because of its advantages of contactlessness, stability, and security. Recently, many palmprint recognition methods based on convolutional neural networks (CNN) have been proposed in academia. Convolutional neural networks are limited by the size of the convolutional kernel and lack the ability to extract global information of palmprints. This paper proposes a framework based on the integration of CNN and Transformer-GLGAnet for palmprint recognition, which can take advantage of CNN's local information extraction and Transformer's global modeling capabilities. A gating mechanism and an adaptive feature fusion module are also designed for palmprint feature extraction. The gating mechanism filters features by a feature selection algorithm and the adaptive feature fusion module fuses them with the features extracted by the backbone network. Through extensive experiments on two datasets, the experimental results show that the recognition accuracy is 98.5% for 12,000 palmprints in the Tongji University dataset and 99.5% for 600 palmprints in the Hong Kong Polytechnic University dataset. This demonstrates that the proposed method outperforms existing methods in the correctness of both palmprint recognition tasks. The source codes will be available on ."

基金机构："National Natural Science Foundation of China [82205049]; Natural Science Foundation of Chongqing [cstc2020jcyj-msxmX0259]; Chongqing Medical Scientific Research Project (Joint project of Chongqing Health Commission and Science and Technology Bureau) [2022MSXM184]; Kuanren Talents Program of the Second Affiliated Hospital of Chongqing Medical University, China; Key Project of Science and Technology of Ministry of Transport of China [2021-MS6-145]; Research on intelligent control technology of highway tunnel operation based on digital twin"

基金资助正文："This research was jointed sponsored by National Natural Science Foundation of China (82205049), Natural Science Foundation of Chongqing (cstc2020jcyj-msxmX0259), Chongqing Medical Scientific Research Project (Joint project of Chongqing Health Commission and Science and Technology Bureau, 2022MSXM184), and Kuanren Talents Program of the Second Affiliated Hospital of Chongqing Medical University, China, Research on intelligent control technology of highway tunnel operation based on digital twin, the Key Project of Science and Technology of Ministry of Transport of China (Grant No. 2021-MS6-145)."