Authors : Girish Katkar; Lekha Prajapati; Ajay Ramteke

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/yczrztfz

Scribd : https://tinyurl.com/38s6awaf

DOI : https://doi.org/10.38124/ijisrt/26apr835

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The widespread use of face masks during and after the COVID-19 pandemic has posed significant challenges to traditional face recognition systems that rely on complete facial features. This paper presents an efficient and robust masked face recognition approach based solely on the EfficientNetB0 architecture, achieving an accuracy of 97% on the MFR2 dataset. The proposed method leverages transfer learning to utilize pre-trained ImageNet features, enabling effective extraction of discriminative information from the visible upper facial regions while maintaining computational efficiency. The model is trained and evaluated on the MFR2 benchmark, which contains real-world masked and unmasked face images across multiple identities. Experimental results demonstrate that EfficientNetB0 can deliver high recognition performance with a relatively small number of parameters, making it suitable for resource-constrained environments. The approach effectively addresses key challenges such as facial occlusion, loss of identity-specific features, and the need for robust maskinvariant representations. This work contributes to the development of practical and scalable masked face recognition systems for real-world applications, including security, surveillance, and access control.

Keywords : Masked Face Recognition, EfficientNetB0, Deep Learning, Transfer Learning, MFR2 Dataset, Biometric Authentication.

References :

1. S. Iftikhar, A. Shaukat, and R. Tariq, "Masked Face Detection and Recognition Using a Unified Feature Extractor," in Proceedings of the International Conference on Advances in Computing and Systems (ICACS), 2024.
2. S. M. S. Ahmad, M. N. M. Noor, and A. R. Abdullah, "Facial recognition for partially occluded faces," Indonesian Journal of Electrical Engineering and Computer Science, vol. 29, no. 2, pp. 1045-1053, 2023.
3. M. Tan and Q. V. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proceedings of the 36th International Conference on Machine Learning (ICML), 2019, pp. 6105-6114.
4. A. Anwar and A. Raychowdhury, "Masked Face Recognition for Secure Authentication," arXivpreprintarXiv:2008.11104,2020.[Online]. Available: https://sites.google.com/view/masktheface/mfr2-dataset
5. S. E. Sitepu, R. Wardoyo, and A. E. Permanasari, "FaceNet with RetinaFace to Identify Masked Face," in Proceedings of the International Workshop on Big Data and Information Security (IWBIS), 2021, pp. 89-94.
6. N. Vatsalkumar, "Discriminative Features for Masked Face Recognition," International Journal of Computer Vision and Image Processing, vol. 12, no. 3, pp. 45-58, 2022.
7. C. Huang, Y. Li, C. C. Loy, and X. Tang, "Learning Deep Representation for Imbalanced Classification," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 5375-5384.
8. T.-H. Tsai, Y.-C. Chen, and C.-W. Lin, "Joint Masked Face Recognition and Temperature Measurement System Using Convolutional Neural Networks," Sensors, vol. 23, no. 4, pp. 2103, 2023.
9. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779-788.
10. Y. Ganin and V. Lempitsky, "Unsupervised Domain Adaptation by Backpropagation," in Proceedings of the 32nd International Conference on Machine Learning (ICML), 2015, pp. 1180-1189.
11. Salehin, M. N., Islam, M. R., Haque, M. M., & Sultana, I. (2026, January). A Lightweight Transfer Learning Model for Face Mask Identification and Masked Face Recognition with Cross-Validation. In 2026 5th International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE) (pp. 1-6). IEEE.
12. Harrath, Y., Bhutta, M., Adohinzin, O., & KC, N. (2025, July). Optimized face recognition using reinforcement learning and deep learning feature extraction. In 2025 IEEE 11th International Conference on Big Data Computing Service and Machine Learning Applications (BigDataService) (pp. 218-225). IEEE.