A Survey on Covid-19 Face-Mask Detection Techniques

• Published in: 2021 IEEE 4th International Conference on Computing, Power and Communication Technologies (GUCON) pp. 1 - 6
• Main Authors: Gorhekar, Raj, Shah, Chaitya, Shah, Viraj, Bide, Pramod J.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 24.09.2021
• Subjects: Computational modeling; Computer Vision; Conferences; Coronavirus; COVID-19; Deep Learning; Face recognition; Face-Mask; Image processing; Pandemics; Training
• DOI: 10.1109/GUCON50781.2021.9573738

This survey primarily focuses on 9 research papers which revolve around Covid-19 Face Mask Prediction. Since Covid has affected our lives a lot in the past year, the primary motive for this survey was to applaud the work done by various people to identify the current scenario and bring valuable solutions to this problem. In this way, even we could contribute to society's betterment. The face mask has proved to be a lifesaver throughout this pandemic, where various countries have made wearing masks compulsory. The rise of the Covid-19 pandemic has led to significant betterment in computer vision, face mask detection and Image processing. Many studies have been done in the face detection or facial expression recognition domain, but there are hardly any papers describing face mask detection. The highest training accuracy was obtained in the case of MTCNN along with FaceNet which was 100% [1], and highest test accuracy was achieved by Facemasknet Architecture which was 98.6%. [2]. This paper offers a concise description and summary of previous studies in the subject detection of face masks, as well as a comparative overview of works in this domain, outlining their gaps and areas for potential development.