Research on Mask Wearing Recognition Based on Deep Learning

ABSTRACT

Since the outbreak of COVID-19 epidemic, research results have shown that the COVID-19 transmitted by droplets, and the most effective means of epidemic prevention is to wear masks. In public places where crowds gather, it is particularly important to use technical means to detect the situation of wearing masks, and remind people to wear masks in time to prevent cross-infection. This paper mainly starts with the target detection and tracking technology in the field of computer vision, and takes the recognition of whether to wear a mask as the entry point. Using python as the development tool, based on the convolutional neural network, the YOLOv2 algorithm is used as the core algorithm, and the ResNet50 network structure is built. Compared with other existing system test experiments, we can see that the system we built has better detection performance. © 2022 Association for Computing Machinery.