Development of a face mask detection and masked facial recognition model based on a hybrid convolutional neural network

Pillay, Chezlyn and Joseph, Seena and van Niekerk, Brett (2025) Development of a face mask detection and masked facial recognition model based on a hybrid convolutional neural network. IET Image Processing, 19 (1). ISSN 1751-9667

Text Joseph, Seena (2025) Development of a face mask detection.pdf - Published Version Available under License CC-BY-NC Creative Commons Attribution Non-commercial. Download (3MB)

Abstract

The rapid growth of facial recognition technology has faced hindrances due to the COVID‐19 pandemic, where mandatory face mask usage obscured facial features, challenging existing authentication methods. Despite the rapid development of several methods for face mask detection and recognition that highlighted prevalent issues such as poor lighting, varied angles, failed detection for improper use of face masks, computational complexity, difficulty in detecting smaller faces and low‐resolution targets, these have led to suboptimal accuracy rates. Hence, this work addresses these challenges by introducing a hybrid convolutional neural network (CNN) architecture tailored for face mask detection (FMD) and masked facial recognition (MFR). The models are developed using MobileNetV2 and FaceNet InceptionResNetV1 with CNN, for FMD and MFR, respectively. Experimental results on both models utilising a total of five distinct datasets, with two for FMD and three for MFR, show the superiority of the developed model in comparison to state‐of‐the art models. In addition, the models are tested in real‐time for both FMD and MFR to determine their robustness, efficiency and accuracy in a real‐time context. For this purpose, a ‘custom real‐time masked face recognition’ (CRMFR) dataset was developed to perform real‐time MFR. Leveraging advanced FMD and MFR technologies, the models contribute to the real‐world need for enhanced security in scenarios where traditional methods are insufficient.

Item Type:	Article
Additional Information:	** Article version: VoR ** From Wiley via Jisc Publications Router ** History: ppub 01-01-2025; received 13-05-2025; rev-recd 09-09-2025; accepted 19-10-2025; epub 03-11-2025. ** Licence for VoR version of this article: http://creativecommons.org/licenses/by-nc/4.0/
Uncontrolled Keywords:	face mask detection, facial recognition, convolutional neural networks, masked facial recognition, object detection, image processing
Subjects:	T Technology > T Technology (General)
Divisions:	Institutes and Academies > Wales Institute for Science & Art (WISA) > Academic Discipline: Applied Computing
Identification Number:	https://doi.org/10.1049/ipr2.70239
SWORD Depositor:	JISC Publications Router
Depositing User:	JISC Publications Router
Date Deposited:	06 Nov 2025 12:02
Last Modified:	06 Nov 2025 12:02
URI:	https://repository.uwtsd.ac.uk/id/eprint/3975

Administrator Actions (login required)

Edit Item - Repository Staff Only