Advancements in Machine Learning-Based Face Mask Detection: A Review of Methods and Challenges

Abstract

Wearing face masks is crucial in various environments, particularly where there is high potential of viral transmission. Proper wearing of face masks always is important in hospitals and healthcare facilities where the risk of transmission of different contagious diseases is very high. The COVID-19 pandemic has been recognized as a global health crisis, exerting deep impacts on various sectors such as industry, economy, public transportation, education, and residential domains. This rapidly spreading virus has created considerable public health risks, resulting in serious health consequences and fatalities. Wearing face masks in public locations and crowded regions has been identified as one of the most effective preventive methods for reducing viral transmission. Using powerful face mask detection systems in such contexts can thus significantly improve infection control efforts while protecting the health and well-being of healthcare personnel, patients, and visitors. In this paper, we present a comprehensive review of recent advancements in machine learning techniques applied to face mask identification. The existing approaches in this sector can be broadly categorized into three main groups: mask/no mask detection approaches, proper/improper mask detection approaches, and human identification through masked faces approaches. We discuss the advantages and limitations associated with each approach. Further, we explore into the technical challenges encountered in this field. Through this study, we aim to provide researchers and practitioners with a comprehensive understanding of the state-of-the-art machine learning techniques for face mask detection.