Single-Stage Real-Time Face Mask Detection.

With the battle against COVID-19 entering a more intense stage against the new Omicron variant, the study of face mask detection technologies has become highly regarded in the research community. While there were many works published on this matter, we still noticed three research gaps that our contributions could possibly suffice. Firstly, despite the introduction of various mask detectors over the last two years, most of them were constructed following the two-stage approach and are inappropriate for usage in real-time applications The second gap is how the currently available datasets could not support the detectors in identifying correct, incorrect and no mask-wearing efficiently without the need for data pre-processing. The third and final gap concerns the costly expenses required as the other detector models were embedded into microcomputers such as Arduino and Raspberry Pi. In this paper, we will first propose a modified YOLO-based model that was explicitly designed to resolve the real-time face mask detection problem; during the process, we have updated the collected datasets and thus will also make them publicly available so that other similar experiments could benefit from; lastly, the proposed model is then implemented onto our custom web application for real-time face mask detection. Our resulted model was shown to exceed its baseline on the revised dataset, and its performance when applied to the application was satisfactory with insignificant inference time. Code available at: https://bitbucket.org/indigoYoshimaru/facemask-web