Detection System of Wearing Face Masks Normatively Based on Deep Learning

The novel coronavirus COVID-19 can be transmitted, for example, by contacting with oral and nasal’s secretions, and traditional mask detection algorithms often fail to distinguish whether masks are worn regularly. In this article, we improve the algorithm network structure based on the improved YOLOV3-tiny algorithm and use the combination of nose detection and mask detection for feature fusion based on the training of massive data sets, which perfectly solves the problem of detecting whether the mask is worn in a normative way. The experiment shows that this system can detect the target of wearing face masks in different scenes with an accuracy rate of over 99%, laying a solid foundation for the detection of wearing face masks normatively.