Real-Time Masked Face Recognition System Using Deep Learning Based Graph Convolutional Network with Heuristic Search Algorithm

International Journal of Electronics and Communication Engineering

© 2025 by SSRG - IJECE Journal

Volume 12 Issue 12

Year of Publication : 2025

Authors : D. Gayathry, R. Latha

10.14445/23488549/IJECE-V12I12P116

How to Cite?

D. Gayathry, R. Latha, "Real-Time Masked Face Recognition System Using Deep Learning Based Graph Convolutional Network with Heuristic Search Algorithm," SSRG International Journal of Electronics and Communication Engineering, vol. 12,  no. 12, pp. 189-200, 2025. Crossref, https://doi.org/10.14445/23488549/IJECE-V12I12P116

Abstract:

With the COVID-19 pandemic worldwide, utilising face masks has become a significant part of everyone's life, and everybody uses masks to avert the spread of the infection during the epidemic. This nearly makes conventional facial recognition technology ineffectual in numerous situations, such as community visit check-ins, face authentication, and security checks. The face recognition-based security method, however, avoids redundant contact, making it much more secure than the previous one. But such methods require using an image of the complete face to do recognition successfully. So, it is vital to increase the performance of current face detection methods on masked faces. Most current cutting-edge face recognition methods rely on Deep Learning (DL), which is heavily dependent on a large number of training samples. This paper proposes a Masked Face Recognition System Using Graph Convolutional Network with Metaheuristic Optimisation Algorithm (MFRS-GCNMOA) technique. The aim is to create an accurate model for detecting masked faces in real-time for enhanced security and surveillance applications. At first, the image pre-processing phase employs the Wiener Filtering (WF) technique for improving image quality. For effective feature extraction, the MFRS-GCNMOA technique utilizes the ResNet-152 method to capture facial patterns from image data. Furthermore, the Graph Convolutional Network (GCN) technique is employed for the classification process. To improve classification performance, the parameter tuning process is achieved by using the Starfish Optimisation Algorithm (SFOA) technique. Finally, the faster-RCNN method is used for face mask detection. To show an improved performance of the presented MFRS-GCNMOA technique, a complete experimental study is conducted under the face mask detection dataset. The comparison assessment of the MFRS-GCNMOA technique portrayed a superior accuracy value of 98.49% over existing models.

Keywords:

Masked Face Recognition; Graph Convolutional Network; Starfish Optimisation Algorithm; Wiener Filtering; Deep Learning.

References:

[1] Bilal Saoud et al., “Review of Masked Face Recognition Based on Deep Learning,” Technologies, vol. 13, no. 7, pp. 1-38, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Rani Kurnia Putri, and Muhammad Athoillah, “Detection of Facial Mask using Deep Learning Classification Algorithm,” Journal of Data Science and Intelligent Systems, vol. 2, no. 1, pp. 58-63, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Sansiri Tarnpradab et al., “Real-Time Masked Face Recognition and Authentication with Convolutional Neural Networks on the Web Application,” Multimedia Tools and Applications, vol. 84, pp. 22655-22679, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Faezeh Mosayyebi, Hadi Seyedarabi, and Reza Afrouzian, “Gender Recognition in Masked Facial Images using EfficientNet and Transfer Learning Approach,” International Journal of Information Technology, vol. 16, pp. 2693-2703, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Mohamed Mahmoud, Mahmoud SalahEldin Kasem, and Hyun-Soo Kang, “A Comprehensive Survey of Masked Faces: Recognition, Detection, and Unmasking,” arXiv preprint, pp. 1-33, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Omer T. Hamajan, and Abbas M. Ali, “Masked Face Recognition using Deep Learning Models,” Zanco Journal of Pure and Applied Sciences, vol. 36, no. 2, pp. 12-24, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Mohamed Elhoseny et al., “Advanced Deep Learning for Masked Individual Surveillance,” International Journal of Cognitive Computing in Engineering, vol. 5, pp. 406-415, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Binay Kumar Pandey, Digvijay Pandey, and Mesfin Esayas Lelisho, “Face Mask Identification with Enhanced Cuckoo Optimisation and Deep Learning-Based Faster Regional Neural Network,” Scientific Reports, vol. 14, pp. 1-18, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Shivani Sharma et al., “Deep-MFR: A Deep Learning Ensemble Approach for Improved Masked Face Recognition,” International Conference on Advanced Network Technologies and Intelligent Computing, Varanasi, India, pp. 212-228, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Arpit Jain et al., “Deep Learning-Based Mask Identification System using ResNet Transfer Learning Architecture,” Computer Systems Science and Engineering, vol. 48, no. 2, pp. 341-362, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Aroobah Iftikhar, Arslan Shaukat, and Rimsha Tariq, “Masked Face Detection and Recognition Using a Unified Feature Extractor,” 2024 5th International Conference on Advancements in Computational Sciences (ICACS), Lahore, Pakistan, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Ashwan A. Abdulmunem, Noor D. Al-Shakarchy, and Mais Saad Safoq, “Deep Learning based Masked Face Recognition in the Era of the COVID-19 Pandemic,” International Journal of Electrical and Computer Engineering, vol. 13, no. 2, pp. 1550-1559, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Parul Dubey et al., “Enhanced IoT-Based Face Mask Detection Framework using Optimised Deep Learning Models: A Hybrid Approach with Adaptive Algorithms,” IEEE Access, vol. 13, pp. 17325-17339, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ming Chun Yo, Siew Chin Chong, and Lee Ying Chong, “Sparse CNN: Leveraging Deep Learning and Sparse Representation for Masked Face Recognition,” International Journal of Information Technology, vol. 17, pp. 4643-4658, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Nay Kyi Tun, Aye Min Myat, “Proposed Activation Function Based Deep Learning Approach for Real-Time Face Mask Detection System,” International Journal of Electrical Engineering and Computer Science, vol. 6, pp. 211-217, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Hayat Al-Dmour et al., “Masked Face Detection and Recognition System based on Deep Learning Algorithms,” Journal of Advances in Information Technology, vol. 14, no. 2, pp. 224-232, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Akhil Kumar, “A Cascaded Deep-Learning-Based Model for Face Mask Detection,” Data Technologies and Applications, vol. 57, no. 1, pp. 84-107, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Mohammed Eman et al., “Innovative Hybrid Approach for Masked Face Recognition using Pretrained Mask Detection and Segmentation, Robust PCA, and KNN Classifier,” Sensors, vol. 23, no. 15, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Imène Issaouı, and Afef Selmi, “Weighted Soft Discernibility Matrix with Deep Learning Assisted Face Mask Detection for Smart City Environment,” International Journal of Neutrosophic Science, vol. 25, no. 1, pp. 179-189, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[20] G. Sumathy et al., “Real-Time Masked Face Recognition using Deep Learning-Based Double Generator Network,” Signal, Image and Video Processing, vol. 18, pp. 325-334, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Sasan Karamizadeh, Saman Shojae Chaeikar, and Hamidreza Salarian, “Combining MTCNN and Enhanced FaceNet with Adaptive Feature Fusion for Robust Face Recognition,” Technologies, vol. 13, no. 10, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Athanasios Kanavos et al., “Real-Time Detection of Face Mask Usage Using Convolutional Neural Networks,” Computers, vol. 13, no. 7, pp. 1-21, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Siriki Atchuta Bhavani, and C. Karthikeyan, “An Attention Based Deep Learning with Effective SVM-ConvFaceNeXt Model for Face Recognition in Unconstrained Environment,” Signal, Image and Video Processing, vol. 19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Abhilash Nelson, and R.S. Shaji, “A Novel Occluded Face Detection Approach using Enhanced ORB and Optimized GAN,” International Journal of Wavelets, Multiresolution and Information Processing, vol. 22, no. 2, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Mohammed Aly, “Revolutionizing Online Education: Advanced Facial Expression Recognition for Real-Time Student Progress Tracking via Deep Learning Model,” Multimedia Tools and Applications, vol. 84, pp. 12575-12614, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[26] V.G. Manjunatha Guru, V.N. Kamalesh, and K.B. Apoorva, “An Ensemble Learning Based Approach for Real-Time Face Mask Detection,” International Journal of Scientific Research in Computer Science and Engineering, vol. 13, no. 3, pp. 8-13, 2024.
[Google Scholar] [Publisher Link]
[27] Mst Jannatul Kobra et al., “Effectiveness of Fourier, Wiener, Bilateral, and CLAHE Denoising Methods for CT Scan Image Noise Reduction,” Scientific Journal of Engineering Research, vol. 1, no. 3, pp. 96-108, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Abrar Almjally, and Wafa Sulaiman Almukadi, “Deep Computer Vision with Artificial Intelligence Based sign Language Recognition to Assist Hearing and Speech-Impaired Individuals,” Scientific Reports, vol. 15, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Sasan Azad, and Mohammad Taghi Ameli, “An Imbalanced Deep Learning Framework for Pre-Fault Flexible Multi-Zone Dynamic Security Assessment via Transfer Learning Based Graph Convolutional Network,” Results in Engineering, vol. 25, pp. 1-15, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Guangjian Zhang, Shilun Ma, and Xulong Wang, “Fault Diagnosis of a Bogie Gearbox Based on Pied Kingfisher Optimizer-Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise, Improved Multi-Scale Weighted Permutation Entropy, and Starfish Optimization Algorithm–Least-Squares Support Vector Machine,” Entropy, vol. 27, no. 9, pp. 1-28, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Sohaib Asif et al., “Real-Time Face Mask Detection System Using Transfer Learning with Faster-RCNN in the Era of the COVID-19 Pandemic,” 2021 4th International Conference on Artificial Intelligence and Big Data (ICAIBD), Chengdu, China, pp. 70-75, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Face Mask Detection Dataset, Kaggle. [Online]. Available: https://www.kaggle.com/datasets/omkargurav/face-mask-dataset