Face recognition algorithm incorporating CBAM and Siamese neural network

Xiangzhou MENG, Yingjun LI, Guicong WANG, Tiansheng MENG
{"title":"Face recognition algorithm incorporating CBAM and Siamese neural network","authors":"Xiangzhou MENG, Yingjun LI, Guicong WANG, Tiansheng MENG","doi":"10.37188/ope.20233121.3192","DOIUrl":null,"url":null,"abstract":"é’ˆå¯¹ä¼ ç»Ÿäººè„¸è¯†åˆ«æ–¹æ³•è¯†åˆ«æ€§èƒ½è¾ƒå·®ï¼ŒåŸºäºŽæ·±åº¦å­¦ä¹ çš„æ–¹æ³•åœ¨éžé™åˆ¶æ¡ä»¶ä¸‹è¯†åˆ«è¾ƒä¸ºå›°éš¾ï¼Œäººè„¸ç‰¹å¾åŒºåˆ†æ€§å¼±ï¼Œè¯†åˆ«ç²¾åº¦å®¹æ˜“å—åˆ°å§¿åŠ¿ã€è¡¨æƒ ç­‰æ–¹é¢å½±å“çš„é—®é¢˜ï¼Œæå‡ºäº†ä¸€ç§å¼•å ¥å·ç§¯å—æ³¨æ„åŠ›æ¨¡å—çš„å­ªç”Ÿç¥žç»ç½‘ç»œæ¨¡åž‹ç»“æž„ã€‚è¯¥ç»“æž„æ˜¯åŸºäºŽå­ªç”Ÿç¥žç»ç½‘ç»œï¼ˆSiamese neural networkï¼‰çš„åŸºç¡€æ¡†æž¶è¿›è¡Œæ”¹è¿›çš„ï¼Œåœ¨æ¡†æž¶ä¸­å¼•å ¥æ”¹è¿›çš„VGG11_BN模型进行特征提取。该模型是在VGG11ç»“æž„çš„åŸºç¡€ä¸Šå¼•å ¥æ‰¹å½’ä¸€åŒ–ï¼ˆBatch Normalization,BNï¼‰æŠ€æœ¯ï¼Œåœ¨åŽŸæ¨¡åž‹ç»“æž„çš„åŸºç¡€ä¸Šï¼Œæå‡ºå¼•å ¥CBAMæ··åˆæ³¨æ„åŠ›æœºåˆ¶çš„ç‰¹å¾æå–ç½‘ç»œï¼›æœ€åŽï¼Œé’ˆå¯¹ç›®å‰äºšæ´²äººçš„äººè„¸è¯†åˆ«è®­ç»ƒè¾ƒå°‘çš„æƒ å†µï¼Œé‡‡ç”¨æ›´åŠ ç¬¦åˆäºšæ´²äººè„¸ç‰¹å¾çš„CASIA-FaceV5数据集进行识别训练。实验结果表明:本文算法在人脸识别方面的准确率达到了96.67%,并且在CAS-PEAL-R1人脸数据集上比SRGES,VGG11+siamese算法的准确率分别提升6.05%,6.7%ã€‚è¯¥ç®—æ³•å¯ä»¥åœ¨å¤šå› ç´ å½±å“ä¸‹æ›´å¥½åœ°è¿›è¡Œäººè„¸è¯†åˆ«éªŒè¯ï¼Œå ·æœ‰è‰¯å¥½çš„ç¨³å®šæ€§ã€‚","PeriodicalId":39778,"journal":{"name":"Guangxue Jingmi Gongcheng/Optics and Precision Engineering","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Guangxue Jingmi Gongcheng/Optics and Precision Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37188/ope.20233121.3192","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Materials Science","Score":null,"Total":0}
引用次数: 0

Abstract

é’ˆå¯¹ä¼ ç»Ÿäººè„¸è¯†åˆ«æ–¹æ³•è¯†åˆ«æ€§èƒ½è¾ƒå·®ï¼ŒåŸºäºŽæ·±åº¦å­¦ä¹ çš„æ–¹æ³•åœ¨éžé™åˆ¶æ¡ä»¶ä¸‹è¯†åˆ«è¾ƒä¸ºå›°éš¾ï¼Œäººè„¸ç‰¹å¾åŒºåˆ†æ€§å¼±ï¼Œè¯†åˆ«ç²¾åº¦å®¹æ˜“å—åˆ°å§¿åŠ¿ã€è¡¨æƒ ç­‰æ–¹é¢å½±å“çš„é—®é¢˜ï¼Œæå‡ºäº†ä¸€ç§å¼•å ¥å·ç§¯å—æ³¨æ„åŠ›æ¨¡å—çš„å­ªç”Ÿç¥žç»ç½‘ç»œæ¨¡åž‹ç»“æž„ã€‚è¯¥ç»“æž„æ˜¯åŸºäºŽå­ªç”Ÿç¥žç»ç½‘ç»œï¼ˆSiamese neural networkï¼‰çš„åŸºç¡€æ¡†æž¶è¿›è¡Œæ”¹è¿›çš„ï¼Œåœ¨æ¡†æž¶ä¸­å¼•å ¥æ”¹è¿›çš„VGG11_BN模型进行特征提取。该模型是在VGG11ç»“æž„çš„åŸºç¡€ä¸Šå¼•å ¥æ‰¹å½’ä¸€åŒ–ï¼ˆBatch Normalization,BNï¼‰æŠ€æœ¯ï¼Œåœ¨åŽŸæ¨¡åž‹ç»“æž„çš„åŸºç¡€ä¸Šï¼Œæå‡ºå¼•å ¥CBAMæ··åˆæ³¨æ„åŠ›æœºåˆ¶çš„ç‰¹å¾æå–ç½‘ç»œï¼›æœ€åŽï¼Œé’ˆå¯¹ç›®å‰äºšæ´²äººçš„äººè„¸è¯†åˆ«è®­ç»ƒè¾ƒå°‘çš„æƒ å†µï¼Œé‡‡ç”¨æ›´åŠ ç¬¦åˆäºšæ´²äººè„¸ç‰¹å¾çš„CASIA-FaceV5数据集进行识别训练。实验结果表明:本文算法在人脸识别方面的准确率达到了96.67%,并且在CAS-PEAL-R1人脸数据集上比SRGES,VGG11+siamese算法的准确率分别提升6.05%,6.7%ã€‚è¯¥ç®—æ³•å¯ä»¥åœ¨å¤šå› ç´ å½±å“ä¸‹æ›´å¥½åœ°è¿›è¡Œäººè„¸è¯†åˆ«éªŒè¯ï¼Œå ·æœ‰è‰¯å¥½çš„ç¨³å®šæ€§ã€‚
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
结合CBAM和Siamese神经网络的人脸识别算法
我是一名学生,我想在这里和大家分享一下我的故事。暹罗神经网络(Siamese neural network)网络VGG11CBAM的 "FaceV5 "功能FaceV5 FaceV5 FaceV5 FaceV5 FaceV5 FaceV567%CAS-PEAL-R1RGESVGG11+siamese6.05%6.7%ã该ç®ç®æ³å¯ä"¥å¨¨å¤å´ å½±åä¸æ´å¥å°½è¿è¿è¡è¡äº¸¸è¯å "é "ªè¯¼å -æ该稳å®æ§ã
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Guangxue Jingmi Gongcheng/Optics and Precision Engineering
Guangxue Jingmi Gongcheng/Optics and Precision Engineering Materials Science-Electronic, Optical and Magnetic Materials
CiteScore
2.40
自引率
0.00%
发文量
95
期刊最新文献
Lightweight target detection network for UAV platforms Research of ultra-precision gear pitch artifact based on dividing mechanism with multi-tooth position Spatial information adaptive regulation and feature alignment for infrared methane instance segmentation Photoelectric inequivalence characteristics of an electric substitution radiative heat flux meter Coupled hysteresis model and its inverse compensation for three-degree-of-freedom tip-tilt-piston piezoelectric stage
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1