Face mask detection application and dataset

Abstract

The COVID–19 pandemic is, without any doubt, changing our world in ways that are beyond our wildest imagination. In a bid to curb the spiraling negative fallouts from the virus that has resulted in a large number of casualties and security concerns. The World Health Organization, amongst other safety protocols, recommended the compulsory wearing of face masks by individuals in public spaces. The problem with the enforcement of this and other relevant safety protocols, all over the world, is the reluctance and outright refusal of citizens to comply and the inability of relevant agencies to monitor and enforce compliance. This paper explores the development of a CCTV–enabled facial mask recognition software that will facilitate the monitoring and enforcement of this protocol. Such models can be particularly useful for security purposes in checking if the disease transmission is being kept in check. A constructive research methodology was adopted, where a pre-trained deep convolutionary neural network (CNN) (mostly eyes and forehead regions) used and the most probable limit (MPL) was use for the classification process. The designed method uses two datasets to train in order to detect key facial features and apply a decision-making algorithm. Experimental findings on the Real-World-Masked-Face-Dataset indicate high success in recognition. A proof of concept as well as a development base are provided towards reducing the spread of COVID-19 by allowing people to validate the face mask via their webcam. We recommend that the use of the app and to further investigate the development of highly robust detectors by training a deep learning model with respect to specified face-feature categories or to correctly and incorrectly wear mask categories.