A Systematic Literature Review on Optimizing Mask Detection Systems Using Convolutional Neural Networks for Public Health and Safety

The COVID-19 pandemic has emphasized the critical importance of mask-wearing as a preventive measure to mitigate virus transmission. However, ensuring compliance with mask mandates in public spaces remains a challenge. This study conducts a Systematic Literature Review (SLR) to explore the application of Convolutional Neural Networks (CNNs) in developing automated mask detection systems. CNNs are widely recognized for their ability to process complex visual patterns with high accuracy, making them ideal for real-time detection in images and videos. This review evaluates various CNN architectures, datasets, and preprocessing techniques used in mask detection systems. The findings highlight significant advancements, such as achieving detection accuracies exceeding 95% under controlled conditions, while also identifying challenges like dataset diversity, model generalization, and computational requirements. Additionally, the integration of CNN-based mask detection systems with Internet of Things (IoT) technologies is explored for enhanced monitoring and enforcement of health protocols. This research aims to provide a comprehensive understanding of current approaches and future directions for optimizing mask detection systems, contributing to public health and safety