A generative adversarial network-based accurate masked face recognition model using dual scale adaptive efficient attention network
Abstract Masked identification of faces is necessary for authentication purposes. Face masks are frequently utilized in a wide range of professions and sectors including public safety, health care, schooling, catering services, production, sales, and shipping. In order to solve this issue and provid...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-02144-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850125550096482304 |
|---|---|
| author | Jafar A. Alzubi Kiran Sree Pokkuluri Rajesh Arunachalam Surendra Kumar Shukla Sumanth Venugopal Karthikayen Arunachalam |
| author_facet | Jafar A. Alzubi Kiran Sree Pokkuluri Rajesh Arunachalam Surendra Kumar Shukla Sumanth Venugopal Karthikayen Arunachalam |
| author_sort | Jafar A. Alzubi |
| collection | DOAJ |
| description | Abstract Masked identification of faces is necessary for authentication purposes. Face masks are frequently utilized in a wide range of professions and sectors including public safety, health care, schooling, catering services, production, sales, and shipping. In order to solve this issue and provide precise identification and verification in masked events, masked facial recognition equipment has emerged as a key innovation. Although facial recognition is a popular and affordable biometric security solution, it has several difficulties in correctly detecting people who are wearing masks. As a result, a reliable method for identifying the masked faces is required. In this developed model, a deep learning-assisted masked face identification framework is developed to accurately recognize the person’s identity for security concerns. At first, the input images are aggregated from standard datasets. From the database, both the masked face images and mask-free images are used for training the Generative Adversarial Network (GAN) model. Then, the collected input images are given to the GAN technique. If the input is a masked face image, then the GAN model generates a mask-free face image and it is considered as feature set 1. If the input is a mask-free image, then the GAN model generates a masked face image and these images are considered as feature set 2. If the input images contain both masked and mask-free images, then it is directly given to Dual Scale Adaptive Efficient Attention Network (DS-AEAN). Otherwise, generated feature set 1 and feature set 2 are given to the DS-AEAN for recognizing the faces to ensure the person’s identity. The effectiveness of this model is further maximized using the Enhanced Addax Optimization Algorithm (EAOA). This model is helpful for a precise biometric verification process. The outcomes of the designed masked face recognition model are evaluated with the existing models to check its capability. |
| format | Article |
| id | doaj-art-8ba985f53f31428a9b78e9564f7fc725 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-8ba985f53f31428a9b78e9564f7fc7252025-08-20T02:34:06ZengNature PortfolioScientific Reports2045-23222025-05-0115112310.1038/s41598-025-02144-2A generative adversarial network-based accurate masked face recognition model using dual scale adaptive efficient attention networkJafar A. Alzubi0Kiran Sree Pokkuluri1Rajesh Arunachalam2Surendra Kumar Shukla3Sumanth Venugopal4Karthikayen Arunachalam5Faculty of Engineering, Al-Balqa Applied UniversityDepartment of Computer Science and Engineering, Shri Vishnu Engineering College for WomenDepartment of Electronics and Communication Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical SciencesDepartment of Computer Science and Engineering , Amity School of Engineering and Technology, Amity UniversityDepartment of Information Technology, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher EducationDepartment of Electronics and Communication Engineering, P.T. Lee Chengalvaraya Naicker College of Engineering and TechnologyAbstract Masked identification of faces is necessary for authentication purposes. Face masks are frequently utilized in a wide range of professions and sectors including public safety, health care, schooling, catering services, production, sales, and shipping. In order to solve this issue and provide precise identification and verification in masked events, masked facial recognition equipment has emerged as a key innovation. Although facial recognition is a popular and affordable biometric security solution, it has several difficulties in correctly detecting people who are wearing masks. As a result, a reliable method for identifying the masked faces is required. In this developed model, a deep learning-assisted masked face identification framework is developed to accurately recognize the person’s identity for security concerns. At first, the input images are aggregated from standard datasets. From the database, both the masked face images and mask-free images are used for training the Generative Adversarial Network (GAN) model. Then, the collected input images are given to the GAN technique. If the input is a masked face image, then the GAN model generates a mask-free face image and it is considered as feature set 1. If the input is a mask-free image, then the GAN model generates a masked face image and these images are considered as feature set 2. If the input images contain both masked and mask-free images, then it is directly given to Dual Scale Adaptive Efficient Attention Network (DS-AEAN). Otherwise, generated feature set 1 and feature set 2 are given to the DS-AEAN for recognizing the faces to ensure the person’s identity. The effectiveness of this model is further maximized using the Enhanced Addax Optimization Algorithm (EAOA). This model is helpful for a precise biometric verification process. The outcomes of the designed masked face recognition model are evaluated with the existing models to check its capability.https://doi.org/10.1038/s41598-025-02144-2Masked face recognitionDual scale adaptive efficient attention networkGenerative adversarial networkEnhanced addax optimization algorithm |
| spellingShingle | Jafar A. Alzubi Kiran Sree Pokkuluri Rajesh Arunachalam Surendra Kumar Shukla Sumanth Venugopal Karthikayen Arunachalam A generative adversarial network-based accurate masked face recognition model using dual scale adaptive efficient attention network Scientific Reports Masked face recognition Dual scale adaptive efficient attention network Generative adversarial network Enhanced addax optimization algorithm |
| title | A generative adversarial network-based accurate masked face recognition model using dual scale adaptive efficient attention network |
| title_full | A generative adversarial network-based accurate masked face recognition model using dual scale adaptive efficient attention network |
| title_fullStr | A generative adversarial network-based accurate masked face recognition model using dual scale adaptive efficient attention network |
| title_full_unstemmed | A generative adversarial network-based accurate masked face recognition model using dual scale adaptive efficient attention network |
| title_short | A generative adversarial network-based accurate masked face recognition model using dual scale adaptive efficient attention network |
| title_sort | generative adversarial network based accurate masked face recognition model using dual scale adaptive efficient attention network |
| topic | Masked face recognition Dual scale adaptive efficient attention network Generative adversarial network Enhanced addax optimization algorithm |
| url | https://doi.org/10.1038/s41598-025-02144-2 |
| work_keys_str_mv | AT jafaraalzubi agenerativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT kiransreepokkuluri agenerativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT rajesharunachalam agenerativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT surendrakumarshukla agenerativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT sumanthvenugopal agenerativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT karthikayenarunachalam agenerativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT jafaraalzubi generativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT kiransreepokkuluri generativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT rajesharunachalam generativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT surendrakumarshukla generativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT sumanthvenugopal generativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork AT karthikayenarunachalam generativeadversarialnetworkbasedaccuratemaskedfacerecognitionmodelusingdualscaleadaptiveefficientattentionnetwork |