This paper presents a deep learning-based system for real-time face mask detection, aimed at enhancing public health monitoring in environments where mask compliance is critical. Utilizing a Convolutional Neural Network (CNN) built with TensorFlow and Keras, the model effectively classifies individuals as mask-wearing or non-mask-wearing. Data preprocessing and augmentation techniques improve the model’s robustness across diverse input images, ensuring high performance and generalizability. Developed on Google Colab, the system leverages cloud-based resources for efficient model training and deployment, eliminating the need for extensive local hardware. It supports real-time image analysis and is scalable for continuous video monitoring, making it suitable for large-scale applications. Integration with Google Drive streamlines data management, simplifying updates and deployment. The proposed system provides an accessible solution for mask compliance monitoring in public spaces, offering accuracy, scalability, and ease of deployment. Future work will focus on enhancing the system with multi-class classification for mask types, IoT integration for automated responses, and edge device deployment to improve accessibility. This tool demonstrates the potential of AI in promoting health and safety in public settings.
Dodda et al. (Mon,) studied this question.