{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T23:49:52Z","timestamp":1791416992521,"version":"4.3.3"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T00:00:00Z","timestamp":1742342400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The provincial scientific research key project","award":["No. 2023AH051706"],"award-info":[{"award-number":["No. 2023AH051706"]}]},{"name":"The provincial scientific research key project","award":["No. 2023AH051701"],"award-info":[{"award-number":["No. 2023AH051701"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>In the research of face recognition technology, the traditional methods usually show poor recognition accuracy and insufficient generalization ability when faced with complex scenes such as lighting changes, posture changes and skin color diversity. To solve these problems, based on the improvement of adaptive boosting to improve the accuracy of face detection, the study proposes a residual network 18-layer face feature extraction algorithm based on hybrid domain attention mechanism algorithm. The study introduces channel-domain and spatial-domain attention mechanism to enhance the extraction of face image features. The outcomes indicated that the recognition accuracy of the proposed method on multiple face image datasets, labeled field face datasets, and celebrity facial attribute datasets exceeded 98.34% and reached up to 99.64%, which was better than the current state-of-the-art methods. After combining channel and spatial attention mechanism, the false detection rate was as low as 2.50%, which was lower than the false detection rate of other methods. In addition to enhancing face recognition\u2019s robustness and accuracy, the work offers fresh concepts and resources for face recognition\u2019s potential uses in intricate scenarios in the future.<\/jats:p>","DOI":"10.1371\/journal.pone.0319921","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T18:02:17Z","timestamp":1742407337000},"page":"e0319921","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["ResNet18 facial feature extraction algorithm improved based on hybrid domain attention mechanism"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6393-7962","authenticated-orcid":true,"given":"Yingying","family":"Mei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,3,19]]},"reference":[{"issue":"1","key":"pone.0319921.ref001","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s43681-022-00146-8","article-title":"The struggle for recognition in the age of facial recognition technology","volume":"3","author":"RA Waelen","year":"2022","journal-title":"AI Ethics"},{"issue":"1","key":"pone.0319921.ref002","doi-asserted-by":"crossref","first-page":"101761","DOI":"10.1016\/j.giq.2022.101761","article-title":"Under big brother\u2019s watchful eye: Cross-country attitudes toward facial recognition technology","volume":"40","author":"G Kostka","year":"2023","journal-title":"Government Information Quarterly"},{"key":"pone.0319921.ref003","first-page":"1","article-title":"The Use of Facial Recognition Technology by Law Enforcement in Europe: a Non-Orwellian Draft Proposal","author":"VL Raposo","year":"2022","journal-title":"Eur J Crim Pol Res"},{"issue":"1","key":"pone.0319921.ref004","first-page":"103","article-title":"An automated attendance system using facial detection and recognition technology","volume":"1","author":"PB Jha","year":"2023","journal-title":"Apex J Bus Mgmt"},{"key":"pone.0319921.ref005","article-title":"Facial recognition using transfer learning in the deep CNN","author":"HO Ikromovich","year":"2023","journal-title":"OA Repository"},{"issue":"3","key":"pone.0319921.ref006","doi-asserted-by":"crossref","first-page":"154","DOI":"10.47852\/bonviewAIA3202833","article-title":"Machine Learning Methodology for Identifying Vehicles Using Image Processing","volume":"1","author":"M Hasanvand","year":"2023","journal-title":"AIA"},{"issue":"2","key":"pone.0319921.ref007","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1108\/BIJ-09-2022-0588","article-title":"Modern-day marketing concepts based on face recognition and neuro-marketing: a review and future research directions","volume":"31","author":"G Srivastava","year":"2023","journal-title":"BIJ"},{"issue":"5","key":"pone.0319921.ref008","doi-asserted-by":"crossref","first-page":"1025","DOI":"10.1109\/TPAMI.2019.2961900","article-title":"Adversarial Cross-Spectral Face Completion for NIR-VIS Face Recognition","volume":"42","author":"R He","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"pone.0319921.ref009","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1109\/TPAMI.2018.2885995","article-title":"Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition","volume":"42","author":"F Liu","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0319921.ref010","doi-asserted-by":"crossref","first-page":"3634","DOI":"10.1109\/TIFS.2021.3080496","article-title":"CASIA-Face-Africa: A Large-Scale African Face Image Database","volume":"16","author":"J Muhammad","year":"2021","journal-title":"IEEE TransInformForensic Secur"},{"issue":"4","key":"pone.0319921.ref011","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1109\/TBIOM.2022.3213845","article-title":"Face Shape-Guided Deep Feature Alignment for Face Recognition Robust to Face Misalignment","volume":"4","author":"H-I Kim","year":"2022","journal-title":"IEEE Trans Biom Behav Identity Sci"},{"key":"pone.0319921.ref012","doi-asserted-by":"crossref","first-page":"119049","DOI":"10.1109\/ACCESS.2021.3107841","article-title":"Robust Semantic Segmentation With Multi-Teacher Knowledge Distillation","volume":"9","author":"A Amirkhani","year":"2021","journal-title":"IEEE Access"},{"key":"pone.0319921.ref013","doi-asserted-by":"crossref","first-page":"77810","DOI":"10.1109\/ACCESS.2023.3298369","article-title":"EBCDet: Energy-Based Curriculum for Robust Domain Adaptive Object Detection","volume":"11","author":"A Banitalebi-Dehkordi","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0319921.ref014","doi-asserted-by":"crossref","first-page":"2627","DOI":"10.1109\/TIP.2021.3054476","article-title":"CapsField: Light Field-Based Face and Expression Recognition in the Wild Using Capsule Routing","volume":"30","author":"A Sepas-Moghaddam","year":"2021","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"pone.0319921.ref015","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1109\/TBIOM.2024.3391759","article-title":"Template Inversion Attack Using Synthetic Face Images Against Real Face Recognition Systems","volume":"6","author":"H Otroshi Shahreza","year":"2024","journal-title":"IEEE Trans Biom Behav Identity Sci"},{"issue":"3","key":"pone.0319921.ref016","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1109\/TBIOM.2022.3233769","article-title":"RGB-D Face Recognition With Identity-Style Disentanglement and Depth Augmentation","volume":"5","author":"M-T Chiu","year":"2023","journal-title":"IEEE Trans Biom Behav Identity Sci"},{"key":"pone.0319921.ref017","doi-asserted-by":"crossref","first-page":"2068","DOI":"10.1109\/LSP.2021.3116861","article-title":"Domain Discrepancy Elimination and Mean Face Representation Learning for NIR-VIS Face Recognition","volume":"28","author":"W Hu","year":"2021","journal-title":"IEEE Signal Process Lett"},{"key":"pone.0319921.ref018","article-title":"Optimization of one versus All-SVM using AdaBoost algorithm for rainfall classification and estimation from multispectral MSG data","author":"A Belghit","year":"2023","journal-title":"Adv Space Res"},{"issue":"2","key":"pone.0319921.ref019","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1007\/s12652-021-03332-4","article-title":"Vehicle recognition algorithm based on Haar-like features and improved Adaboost classifier","volume":"14","author":"L Zhang","year":"2021","journal-title":"J Ambient Intell Human Comput"},{"issue":"5","key":"pone.0319921.ref020","doi-asserted-by":"crossref","first-page":"3047","DOI":"10.1177\/14759217221140645","article-title":"Bearing fault diagnosis method based on comprehensive information divergence and improved BP-AdaBoost algorithm","volume":"22","author":"C Zhao","year":"2023","journal-title":"Structural Health Monitoring"},{"issue":"4","key":"pone.0319921.ref021","doi-asserted-by":"crossref","first-page":"3173","DOI":"10.1007\/s00521-022-07856-4","article-title":"An investigation of feature selection methods for soil liquefaction prediction based on tree-based ensemble algorithms using AdaBoost, gradient boosting, and XGBoost","volume":"35","author":"S Demir","year":"2022","journal-title":"Neural Comput & Applic"},{"issue":"1","key":"pone.0319921.ref022","doi-asserted-by":"crossref","first-page":"27","DOI":"10.56705\/ijaimi.v1i1.86","article-title":"Classification Optimization of Skin Cancer Using the Adaboost Algorithm","volume":"1","author":"A Maulidinnawati","year":"2023","journal-title":"ijaimi"},{"issue":"3","key":"pone.0319921.ref023","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1007\/s11053-024-10321-9","article-title":"Prospectivity and Uncertainty Analysis of Tungsten Polymetallogenic Mineral Resources in the Nanling Metallogenic Belt, South China: A Comparative Study of AdaBoost, GBDT, and XgBoost Algorithms","volume":"33","author":"T Li","year":"2024","journal-title":"Nat Resour Res"},{"issue":"2","key":"pone.0319921.ref024","doi-asserted-by":"crossref","first-page":"165","DOI":"10.4314\/swj.v18i2.1","article-title":"Heart failure prediction framework using random forest and J48 with Adaboost algorithms","volume":"18","author":"O Gold","year":"2023","journal-title":"SWJ"},{"issue":"5","key":"pone.0319921.ref025","doi-asserted-by":"crossref","first-page":"3173","DOI":"10.1007\/s11831-023-09899-9","article-title":"On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks","volume":"30","author":"S Iqbal","year":"2023","journal-title":"Arch Comput Methods Eng"},{"issue":"4","key":"pone.0319921.ref026","doi-asserted-by":"crossref","first-page":"2793","DOI":"10.1007\/s11831-023-09898-w","article-title":"Convolutional Neural Network in Medical Image Analysis: A Review","volume":"30","author":"SS Kshatri","year":"2023","journal-title":"Arch Computat Methods Eng"},{"issue":"11","key":"pone.0319921.ref027","doi-asserted-by":"crossref","first-page":"17437","DOI":"10.1007\/s11042-022-14107-0","article-title":"Federated learning: a deep learning model based on resnet18 dual path for lung nodule detection","volume":"82","author":"L Liu","year":"2022","journal-title":"Multimed Tools Appl"},{"issue":"6","key":"pone.0319921.ref028","doi-asserted-by":"crossref","first-page":"2731","DOI":"10.1007\/s11760-023-02490-6","article-title":"DTL-I-ResNet18: facial emotion recognition based on deep transfer learning and improved ResNet18","volume":"17","author":"R Helaly","year":"2023","journal-title":"SIViP"},{"issue":"8","key":"pone.0319921.ref029","doi-asserted-by":"crossref","first-page":"1982","DOI":"10.1364\/AO.515383","article-title":"Reconstruction of a three-dimensional temperature field in flames based on ES-ResNet18","volume":"63","author":"L Shan","year":"2024","journal-title":"Appl Opt"},{"issue":"1","key":"pone.0319921.ref030","doi-asserted-by":"crossref","first-page":"101","DOI":"10.32604\/cmc.2023.030790","article-title":"RBEBT: A ResNet-Based BA-ELM for Brain Tumor Classification","volume":"74","author":"Z Zhu","year":"2023","journal-title":"Computers, Materials & Continua"},{"issue":"2","key":"pone.0319921.ref031","doi-asserted-by":"crossref","first-page":"41","DOI":"10.20527\/jtiulm.v8i2.174","article-title":"Comparison of detection with transfer learning architecture restnet18, restnet50, restnet101 on corn leaf disease","volume":"8","author":"D Hindarto","year":"2023","journal-title":"JTekInfULM"},{"issue":"1","key":"pone.0319921.ref032","doi-asserted-by":"crossref","first-page":"175","DOI":"10.23919\/JCC.ja.2022-0739","article-title":"A correlation-based stochastic model for massive MIMO channel","volume":"21","author":"Y Liu","year":"2024","journal-title":"China Commun"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0319921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T18:03:04Z","timestamp":1742407384000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0319921"}},"subtitle":[],"editor":[{"given":"Dhasarathan","family":"Chandramohan,","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,3,19]]},"references-count":32,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,3,19]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0319921","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,19]]}}}