基于坐标关注和AdaCos损失的ConvNeXt蒙面人脸识别

IF 1.8 4区计算机科学 Q3 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

IET Biometrics Pub Date : 2025-09-17 DOI:10.1049/bme2/8878553

Chaoying Tang, Yanbin Cui, Qiaoyue Huang

{"title":"基于坐标关注和AdaCos损失的ConvNeXt蒙面人脸识别","authors":"Chaoying Tang, Yanbin Cui, Qiaoyue Huang","doi":"10.1049/bme2/8878553","DOIUrl":null,"url":null,"abstract":"<p>Compared with traditional identity authentication methods, biometric recognition technologies offer superior security, reliability, and accuracy, among them, face recognition is of great research value. However, the outbreak of the COVID-19 epidemic, as well as the cold and hazy weather conditions have led to a widespread preference for wearing masks. The masks will cause the failure of traditional face recognition methods. This paper develops a deep learning-based biometric recognition method for masked faces. A simulated masked face (SMF) dataset and a real masked face dataset are constructed first. The images are preprocessed with masked face detection and mask edges are identified to segment the face area. A ConvNeXt network with coordinate attention (CA) is proposed and AdaCos is employed for comprehensive feature extraction. The results of extensive experiments demonstrate a remarkable 99% recognition rate on the SMF dataset and 94% on the real masked face dataset. It shows that our method can effectively process face recognition task with masks, with very high performance in terms of accuracy.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2025 1","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/8878553","citationCount":"0","resultStr":"{\"title\":\"Masked Face Recognition Based on ConvNeXt With Coordinate Attention and AdaCos Loss\",\"authors\":\"Chaoying Tang, Yanbin Cui, Qiaoyue Huang\",\"doi\":\"10.1049/bme2/8878553\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Compared with traditional identity authentication methods, biometric recognition technologies offer superior security, reliability, and accuracy, among them, face recognition is of great research value. However, the outbreak of the COVID-19 epidemic, as well as the cold and hazy weather conditions have led to a widespread preference for wearing masks. The masks will cause the failure of traditional face recognition methods. This paper develops a deep learning-based biometric recognition method for masked faces. A simulated masked face (SMF) dataset and a real masked face dataset are constructed first. The images are preprocessed with masked face detection and mask edges are identified to segment the face area. A ConvNeXt network with coordinate attention (CA) is proposed and AdaCos is employed for comprehensive feature extraction. The results of extensive experiments demonstrate a remarkable 99% recognition rate on the SMF dataset and 94% on the real masked face dataset. It shows that our method can effectively process face recognition task with masks, with very high performance in terms of accuracy.</p>\",\"PeriodicalId\":48821,\"journal\":{\"name\":\"IET Biometrics\",\"volume\":\"2025 1\",\"pages\":\"\"},\"PeriodicalIF\":1.8000,\"publicationDate\":\"2025-09-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/8878553\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IET Biometrics\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/bme2/8878553\",\"RegionNum\":4,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IET Biometrics","FirstCategoryId":"94","ListUrlMain":"https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/bme2/8878553","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

摘要

与传统身份认证方法相比，生物特征识别技术具有更高的安全性、可靠性和准确性，其中人脸识别具有重要的研究价值。然而，新冠肺炎疫情的爆发，以及寒冷和雾霾的天气条件，导致人们普遍喜欢戴口罩。这些面具会导致传统的人脸识别方法失效。提出了一种基于深度学习的蒙面人脸生物特征识别方法。首先构建了模拟掩蔽人脸（SMF）数据集和真实掩蔽人脸数据集。采用掩模人脸检测对图像进行预处理，识别掩模边缘，分割人脸区域。提出了一种具有坐标关注（CA）的ConvNeXt网络，并采用AdaCos进行综合特征提取。大量的实验结果表明，该方法在SMF数据集上的识别率达到了99%，在真实人脸数据集上的识别率达到了94%。结果表明，该方法可以有效地处理人脸识别任务，在准确率方面具有很高的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

Masked Face Recognition Based on ConvNeXt With Coordinate Attention and AdaCos Loss

查看原文本刊更多论文

Masked Face Recognition Based on ConvNeXt With Coordinate Attention and AdaCos Loss

Compared with traditional identity authentication methods, biometric recognition technologies offer superior security, reliability, and accuracy, among them, face recognition is of great research value. However, the outbreak of the COVID-19 epidemic, as well as the cold and hazy weather conditions have led to a widespread preference for wearing masks. The masks will cause the failure of traditional face recognition methods. This paper develops a deep learning-based biometric recognition method for masked faces. A simulated masked face (SMF) dataset and a real masked face dataset are constructed first. The images are preprocessed with masked face detection and mask edges are identified to segment the face area. A ConvNeXt network with coordinate attention (CA) is proposed and AdaCos is employed for comprehensive feature extraction. The results of extensive experiments demonstrate a remarkable 99% recognition rate on the SMF dataset and 94% on the real masked face dataset. It shows that our method can effectively process face recognition task with masks, with very high performance in terms of accuracy.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

IET Biometrics COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-

CiteScore

5.90

自引率

0.00%

发文量

审稿时长

33 weeks

期刊介绍： The field of biometric recognition - automated recognition of individuals based on their behavioural and biological characteristics - has now reached a level of maturity where viable practical applications are both possible and increasingly available. The biometrics field is characterised especially by its interdisciplinarity since, while focused primarily around a strong technological base, effective system design and implementation often requires a broad range of skills encompassing, for example, human factors, data security and database technologies, psychological and physiological awareness, and so on. Also, the technology focus itself embraces diversity, since the engineering of effective biometric systems requires integration of image analysis, pattern recognition, sensor technology, database engineering, security design and many other strands of understanding. The scope of the journal is intentionally relatively wide. While focusing on core technological issues, it is recognised that these may be inherently diverse and in many cases may cross traditional disciplinary boundaries. The scope of the journal will therefore include any topics where it can be shown that a paper can increase our understanding of biometric systems, signal future developments and applications for biometrics, or promote greater practical uptake for relevant technologies: Development and enhancement of individual biometric modalities including the established and traditional modalities (e.g. face, fingerprint, iris, signature and handwriting recognition) and also newer or emerging modalities (gait, ear-shape, neurological patterns, etc.) Multibiometrics, theoretical and practical issues, implementation of practical systems, multiclassifier and multimodal approaches Soft biometrics and information fusion for identification, verification and trait prediction Human factors and the human-computer interface issues for biometric systems, exception handling strategies Template construction and template management, ageing factors and their impact on biometric systems Usability and user-oriented design, psychological and physiological principles and system integration Sensors and sensor technologies for biometric processing Database technologies to support biometric systems Implementation of biometric systems, security engineering implications, smartcard and associated technologies in implementation, implementation platforms, system design and performance evaluation Trust and privacy issues, security of biometric systems and supporting technological solutions, biometric template protection Biometric cryptosystems, security and biometrics-linked encryption Links with forensic processing and cross-disciplinary commonalities Core underpinning technologies (e.g. image analysis, pattern recognition, computer vision, signal processing, etc.), where the specific relevance to biometric processing can be demonstrated Applications and application-led considerations Position papers on technology or on the industrial context of biometric system development Adoption and promotion of standards in biometrics, improving technology acceptance, deployment and interoperability, avoiding cross-cultural and cross-sector restrictions Relevant ethical and social issues