Abstract
The COVID-19 pandemic has caused a global health crisis. In response, the World Health Organization (WHO) has suggested wearing a face mask in public for effective protection. While much of the global population has adhered to these recommendations, some continue to wear the face mask improperly or refuse to wear the mask at all. It is essential that face masks are properly worn in public. To address this, we implemented computer vision, a recent advanced technology, to detect the status of face masks on individuals in crowded public places. Our research is intended to aid in minimizing the spread of coronavirus by developing technology for authorities to discern if face masks are being worn properly. We collected data from the Internet and increased it synthetically by augmentation. Two publicly available datasets were merged: the face mask detection dataset and the MASKEDFACE-NET dataset. Our data was annotated manually and then made into a graphical user interface (GUI) for semi-automatic annotation. The multiple object detection networks were trained for three states of face mask wearing: with_mask, without_mask, and mask_weared_incorrect. Four two-stage object detection models were trained and tested during the experiment. The results are compared based on the mean average precisions and scores. The networks achieved above 91% accuracy in both mean average precisions and scores for the three classes of object. We applied these object detectors to our annotation tool for quick semi-supervised annotation. The proposed mask status detection system can aid in reducing the spread of COVID-19 if deployed in a real-world scenario. Our data labeling tool with annotation, augmentation, and automatic suggestion can help further research into these types of technologies.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have