Masked face recognition (MFR) has gained significant importance in recent years due to the widespread adoption of face masks driven by global health crises and increasing security requirements. Traditional face recognition systems often fail to perform effectively when key facial features are occluded, creating a need for more robust and adaptive solutions. In response, numerous deep learning (DL) and machine learning approaches—particularly those based on convolution neural networks (CNNs)—have been developed to improve recognition accuracy under masked conditions. These models are widely applied in areas such as surveillance, secure authentication, and public safety, where real-time performance is essential. This paper presents a systematic review of recent MFR techniques, focusing on deep network architectures, feature extraction strategies, and model optimization methods. It also examines commonly used tools and frameworks, along with benchmark datasets and evaluation metrics employed in existing studies. A structured methodology is adopted to ensure a transparent and reproducible selection of relevant literature. Furthermore, this review categorizes current approaches, identifies key challenges such as occlusion handling, dataset limitations, and real-time constraints, and outlines potential directions for future research aimed at developing more efficient and reliable masked face recognition systems.

Overall, this work highlights the importance of robust and efficient deep learning models for reliable masked face recognition. The proposed approach achieves strong accuracy while maintaining real-time performance, making it applicable for modern security and authentication systems. Future improvements may focus on enhancing model generalization, reducing computational cost, and integrating larger diverse datasets to further improve performance in unconstrained environments. The proposed system demonstrates that CNN-based architectures are highly effective in extracting meaningful facial features even when partial occlusion is present. By using real-time image processing through a webcam, the model successfully detects faces and classifies them as masked or unmasked with high accuracy. The system also performs well under varying conditions such as different face angles and multiple face detection in a single frame, making it suitable for practical applications like surveillance and access control. From the literature analysis, it is evident that deep learning models outperform traditional machine learning approaches in masked face recognition tasks. Techniques such as transfer learning, lightweight CNN architectures, and attention-based mechanisms have further improved system performance. However, challenges such as limited real- world datasets, variations in mask types, and computational efficiency still remain significant obstacles.

[1]Z. Zhang, B. Bowes, The future of artificial intelligence (AI) and machine learn ing (ML) in landscape design: a case study in coastal Virginia, USA, J. Digital Landscape Arch. 2019 (4) (2019) 2–9, https://doi .org /10 .14627 /537663001. [2]S.Y. Kung, M.W. Mak, Machine learning for multimodality genomic signal pro cessing, IEEE Signal Process. Mag. 23 (3) (2006) 117–121, https://doi .org /10 . 1109 /MSP.2006 .1628886. [3]D. Duarte, F. Nex, N. Kerle, G. Vosselman, Satellite image classification of build ing damages using airborne and satellite image samples in a deep learning approach, in: ISPRS Annals of the Photogrammetry, Remote Sensing and Spa tial Information Sciences, vol. 4(2), 2018, pp. 89–96. [4]P. Gupta, N. Saxena, M. Sharma, J. Tripathi, Deep neural network for human face recognition, Int. J. Eng. Manufact. 8(1) (2018) 63–71, https://doi .org /10 . 5815 /ijem .2018 .01.06. [5]K.J. Bhojane, S.S. Thorat, A review of face recognition based car ignition and security system, Int. Res. J. Eng. Technol. 05 (01) (2018) 532–533. [6]S. Mahmud, J. Kim, An Automated System to Limit COVID-19 Using Facial Mask Detection in Smart City Network, 2021, pp. 11–15. [7]Sushovan Chaudhury, Manik Rakhra, Naz Memon, Kartik Sau, Melkamu Teshome Ayana, Breast cancer calcifications: identification using anovel segmentation approach, Comput. Math. Methods Med. 2021 (2021) 9905808, https://doi .org /10 .1155 /2021 /9905808, 13 pages. Fig.4.2. [8]J.T. Sunny, S.M. George, Applications and challenges of human activity recogni tion using sensors in a smart environment, 2(04) (2015) 50– 57. [9]M. Rakhra, R. Singh, Economic and social survey on renting and hiring of agri cultural equipment of farmers in Punjab, in: 2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Di rections) (ICRITO), 2021, pp. 1–5. [10]D. Bhamare, P. Suryawanshi, Review on reliable pattern recognition with ma chine learning techniques, Fuzzy Inf. Eng. 10 (1) (2019) 1– 16, https://doi .org / 10 .1080 /16168658 .2019 .1611030. [11]V. Vinitha, V. Velantina, COVID-19 Facemask Detection with Deep Learning and Computer Vision, 2020. [12]R. Bhuiyan, A Deep Learning Based Assistive System to Classify COVID-19 Face Mask for Human Safety with YOLOv3, 2020. [13]T. Meenpal, Facial mask detection using semantic segmentation, in: 2019 4th International Conference on Computing, Communications and Security (ICCCS) (October), 2019, pp. 1–5. [14]https://drive .google .com /drive /folders /1Dm2sV8UrMd6OKzjVk W859WznhfSXFZF8. [15]K. Grolinger, M. Hayes, W.A. Higashino, A. L’Heureux, D.S. Allison, M.A.M. Capretz, Challenges for MapReduce in big data, in: Proc. IEEE World Congr. Services (SERVICES), Jun. 2014, pp. 182–189. [16]M.M. Najafabadi, F. Villanustre, T.M. Khoshgoftaar, N. Seliya, R. Wald, E. Muharemagic, Deep learning applications and challenges in big data analytics, Big Data 2(1) (Feb. 2015) 1. [17]K.F. Tasneem, et al., Affordable black box: a smart accident detection system for cars, in: 2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), 2021, pp. 1–5. [18]Al-Nabulsi, J.; Turab, N.; Owida, H.A.; Al-Naami, B.; De Fazio, R.; Visconti, P. IoT solutions and AI-based frameworks for masked-face and face recognition to fight the COVID-19 pandemic. Sensors 2023, 23, 7193. [CrossRef] [PubMed] [19]Zhang, L.; Verma, B.; Tjondronegoro, D.; Chandran, V. Facial expression analysis under partial occlusion: A survey. ACM Comput. Surv. 2018, 51, 1–49. [CrossRef] 20. Lahasan, B.; Lutfi, S.L.; San-Segundo, R. A survey on techniques to handle face recognition challenges: Occlusion, single sample per subject and expression. Artif. Intell. Rev. 2019, 52, 949– 979. [CrossRef] [21]Zeng, D.; Veldhuis, R.; Spreeuwers, L. A survey of face recognition techniques under occlusion. IET Biom. 2021, 10, 581–606. [CrossRef] [22]Hasan, M.R.; Guest, R.; Deravi, F. Presentation-level privacy protection techniques for automated face recognition—A survey. ACMComput. Surv. 2023, 55, 1–27. [CrossRef] [23]Sharma, R.; Ross, A. Periocular biometrics and its relevance to partially masked faces: A survey. Comput. Vis. Image Underst. 2023, 226, 103583. [CrossRef] [24] Duong,H.T.; Nguyen-Thi, T.A. A review: Preprocessing techniques and data augmentation for sentiment analysis. Comput. Soc. Netw. 2021, 8, 1. [CrossRef] [25]Maharana, K.; Mondal, S.; Nemade, B. A review: Data pre-processing and data augmentation techniques. Glob. Transit. Proc. 2022, 3, 91–99. [CrossRef] [26]Liu, X.; Zou, Y.; Kuang, H.; Ma, X. Face image age estimation based on data augmentation and lightweight convolutional neural network. Symmetry 2020, 12, 146. [CrossRef] [27]Charoqdouz, E.; Hassanpour, H. Feature extraction from several angular faces using a deep learning based fusion technique for face recognition. Int. J. Eng. Trans. B Appl. 2023, 36, 1548– 1555. [CrossRef] [28]Riaz, Z.; Mayer, C.; Beetz, M.; Radig, B. Model based analysis of face images for facial feature extraction. In Proceedings of the Computer Analysis of Images and Patterns: 13th International Conference, CAIP 2009, Münster, Germany, 2–4 September 2009; Springer: Berlin/Heidelberg, Germany, 2009; pp. 99–106. [29]Feihong, L.; Hang, C.; Kang, L.; Qiliang, D.; Jian, Z.; Kaipeng, Z.; Hong, H. Toward high-quality face-mask occluded restoration. ACMTrans. Multimed. Comput. Commun. Appl. 2023, 19, 1–23. [CrossRef] [30]Shukla, R.K.; Tiwari, A.K. Masked face recognition using MobileNet V2 with transfer learning. Comput. Syst. Sci. Eng. 2023, 45, 293–309. [CrossRef]