Face Mask Detection using MobileNetV2 and OpenCV

Abstract

Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. The best way to prevent and slow down transmission is by staying at least 2 meters apart from others and wearing a properly fitted face mask. The use of face masks is mandatory as per World Health Organization (WHO) guidelines to avert the spread of CORONA virus. Presently the inspection of people with/without masks is being done manually and visually by sentries/guards present at entry/exit points. Guards/Sentries cannot be stationed at every place to keep a check on such people. In this work, efforts have been made in inspecting people with/without masks automatically with the help of Computer vision and Artificial Intelligence. This module detects the face of the individual and identifies whether he/she is wearing a mask or not. The rectangular bounding box is drawn on the face which is displayed on the camera to detect whether the individual is wearing the facemask or not. The face mask detection in the work is performed by using the deep learning model MobileNetV2 and OpenCV and an accuracy of 99% is achieved.