AI-app development for Yolov5-based face mask wearing detection

ABSTRACT

Corona is one of the most destructive viruses that has ever produced a pandemic in human life, not only in terms of direct victims but also in terms of the socio-economic consequences of the virus' transmission. The 2nd anniversary of the global coronavirus pandemic passed away in 2021. However, it's still impossible to say how long the epidemic will last. After reviewing a study by the World Health Organization on COVID-19, the country's national government urged residents to use facemask in order to reduce the incidence of COVID-19 transmission. As a result of COVID-19, there are presently no facemask detection app that are in great demand for ensuring safety in public area. In the context of the outbreak of COVID-19, A facemask detection model based on deep learning approach of state-of-the-art YOLOv5 may be useful in real-time applications. In this paper, we propose a web app for detecting if the people wears facemask or not in real-time via webcam or public camera. In the app, we deployed and persisted many different YOLOv5-based models that the users can switch between them to guarantee the performance and timing trade-off. Furthermore, our system is able to detect if an individual person captured by surveillance cameras is wearing facemask in acceptable counting time at staging level. In our opinion, this kind of system is extremely efficient for use in airports, train stations, offices, and other public areas, as well as in military. © 2022 IEEE.