Abstract
While the COVID-19 outbreak poses several major hazards to the world, it also serves as a reminder that we must take care to prevent the virus from spreading. Wearing a mask is one of the most effective non-pharmaceutical strategies for preventing the spread of infectious diseases. Therefore, to aid in the prevention of a public epidemic, an automatic real-time mask recognition and categorization solution is urgently required. The efficiency of facemasks has been called into question, owing to poor mask selection. N95 masks must be worn in jobs where there is a high danger of contracting the virus. Surgical, DIY, and N95 masks all have varied degrees of effectiveness. To safeguard public safety, we created a deep learning model that can classify different types of masks as well as determine if there is no mask in real-time video or images. Our framework consists of three main phases: Face detection using object detection API, application of face mask classifier and classification of masks into four different categories. In this study, we show that SSD MobileNet V2 outperforms both SSD MobileNet V1 and SSD Resnet50 V1 in terms of sensitivity and precision.