ABSTRACT
The COVID-19 outbreak has created a worldwide medical services crisis. It is a threat to others' health from a COVID-infected individual. The most significant risk of transmission exists in public locations. Wearing a mask is one of the most effective ways to be cautious. OpenCV is utilized to locate people wearing masks using real-time video processing. This involves a deep learning model to examine the ratio of persons wearing masks to those who are not in crowded locations, such as a market or a train station. It will evaluate the video stream using a real-time camera and issue a notification when the zone contains persons who are not wearing masks. To assess if the mask is properly worn on the face, it employs YOLOv4, an exceptionally efficient object identification algorithm. We employ the dark net framework for YOLO training, which defines the network's architecture and aids CPU and GPU processing. The user interface was created using Tkinter from the Python GUI. Our project has been widely acknowledged as having a positive impact on reducing the spread of this fatal disease.
