Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation
Given the current COVID-19 pandemic, most people wear a mask to effectively prevent the spread of the contagious disease. This sanitary measure has caused a significant drop in the effectiveness of current face recognition methods when handling masked faces on practical applications such as face acc...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9648153/ |
| _version_ | 1830382269837082624 |
|---|---|
| author | Yoanna Martinez-Diaz Heydi Mendez-Vazquez Luis S. Luevano Miguel Nicolas-Diaz Leonardo Chang Miguel Gonzalez-Mendoza |
| author_facet | Yoanna Martinez-Diaz Heydi Mendez-Vazquez Luis S. Luevano Miguel Nicolas-Diaz Leonardo Chang Miguel Gonzalez-Mendoza |
| author_sort | Yoanna Martinez-Diaz |
| collection | DOAJ |
| description | Given the current COVID-19 pandemic, most people wear a mask to effectively prevent the spread of the contagious disease. This sanitary measure has caused a significant drop in the effectiveness of current face recognition methods when handling masked faces on practical applications such as face access control, face attendance, and face authentication-based mobile payment. Under this situation, recent efforts have been focused on boosting the performance of the existing face recognition technology on masked faces. Some solutions trying to tackle this issue fine-tune the existing deep learning face recognition models on synthetic masked images, while others use the periocular region as a naive manner to eliminate the adverse effect of COVID-19 masks. Although the accuracy of masked face recognition remains an important issue, in the last few years, the development of efficient and lightweight face recognition methods has received an increased attention in the research community. In this paper, we study the effectiveness of three state-of-the-art lightweight face recognition models for addressing accurate and efficient masked face recognition, considering both fine-tuning on masked faces and periocular images. For the experimental evaluation, we create both real and simulated masked face databases as well as periocular datasets. Extensive experiments are conducted to determine the most effective solution and state further steps for the research community. The obtained results disclose that fine-tuning existing state-of-the-art face models on masked images achieve better performance than using periocular-based models. Besides, we evaluate and analyze the effectiveness of the trained masked-based models on well-established unmasked benchmarks for face recognition and assess the efficiency of the used lightweight architectures in comparison with state-of-the-art face models. |
| first_indexed | 2024-12-20T10:03:26Z |
| format | Article |
| id | doaj.art-f5c4fd2b62bc4244a459b8f0bc6eb965 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T10:03:26Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f5c4fd2b62bc4244a459b8f0bc6eb9652022-12-21T19:44:17ZengIEEEIEEE Access2169-35362022-01-01107341735310.1109/ACCESS.2021.31352559648153Towards Accurate and Lightweight Masked Face Recognition: An Experimental EvaluationYoanna Martinez-Diaz0Heydi Mendez-Vazquez1https://orcid.org/0000-0002-7834-1791Luis S. Luevano2https://orcid.org/0000-0001-5784-0826Miguel Nicolas-Diaz3Leonardo Chang4https://orcid.org/0000-0002-0703-2131Miguel Gonzalez-Mendoza5Advanced Technologies Application Center (CENATAV), Havana, CubaAdvanced Technologies Application Center (CENATAV), Havana, CubaSchool of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, MexicoAdvanced Technologies Application Center (CENATAV), Havana, CubaSchool of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, MexicoSchool of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, MexicoGiven the current COVID-19 pandemic, most people wear a mask to effectively prevent the spread of the contagious disease. This sanitary measure has caused a significant drop in the effectiveness of current face recognition methods when handling masked faces on practical applications such as face access control, face attendance, and face authentication-based mobile payment. Under this situation, recent efforts have been focused on boosting the performance of the existing face recognition technology on masked faces. Some solutions trying to tackle this issue fine-tune the existing deep learning face recognition models on synthetic masked images, while others use the periocular region as a naive manner to eliminate the adverse effect of COVID-19 masks. Although the accuracy of masked face recognition remains an important issue, in the last few years, the development of efficient and lightweight face recognition methods has received an increased attention in the research community. In this paper, we study the effectiveness of three state-of-the-art lightweight face recognition models for addressing accurate and efficient masked face recognition, considering both fine-tuning on masked faces and periocular images. For the experimental evaluation, we create both real and simulated masked face databases as well as periocular datasets. Extensive experiments are conducted to determine the most effective solution and state further steps for the research community. The obtained results disclose that fine-tuning existing state-of-the-art face models on masked images achieve better performance than using periocular-based models. Besides, we evaluate and analyze the effectiveness of the trained masked-based models on well-established unmasked benchmarks for face recognition and assess the efficiency of the used lightweight architectures in comparison with state-of-the-art face models.https://ieeexplore.ieee.org/document/9648153/COVID-19 pandemiclightweight deep modelsmasked face recognitionperiocular recognition |
| spellingShingle | Yoanna Martinez-Diaz Heydi Mendez-Vazquez Luis S. Luevano Miguel Nicolas-Diaz Leonardo Chang Miguel Gonzalez-Mendoza Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation IEEE Access COVID-19 pandemic lightweight deep models masked face recognition periocular recognition |
| title | Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation |
| title_full | Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation |
| title_fullStr | Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation |
| title_full_unstemmed | Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation |
| title_short | Towards Accurate and Lightweight Masked Face Recognition: An Experimental Evaluation |
| title_sort | towards accurate and lightweight masked face recognition an experimental evaluation |
| topic | COVID-19 pandemic lightweight deep models masked face recognition periocular recognition |
| url | https://ieeexplore.ieee.org/document/9648153/ |
| work_keys_str_mv | AT yoannamartinezdiaz towardsaccurateandlightweightmaskedfacerecognitionanexperimentalevaluation AT heydimendezvazquez towardsaccurateandlightweightmaskedfacerecognitionanexperimentalevaluation AT luissluevano towardsaccurateandlightweightmaskedfacerecognitionanexperimentalevaluation AT miguelnicolasdiaz towardsaccurateandlightweightmaskedfacerecognitionanexperimentalevaluation AT leonardochang towardsaccurateandlightweightmaskedfacerecognitionanexperimentalevaluation AT miguelgonzalezmendoza towardsaccurateandlightweightmaskedfacerecognitionanexperimentalevaluation |