Controlling spread of COVID-19 through Facial Mask Detection using Deep Learning

Abstract

The corona virus disease continues to spread across the world. The health, humanitarian and socio-Economic policies adopted by countries will determine the speed and strength of the recovery. The coordinated global effort is required to support countries that currently do not have enough finance social policy. Reports indicate that wearing face mask reduces the risk of transmission. This encourages exploring face mask detection technology to monitor people wearing masks in public places. Most recent and advanced face mask detection approaches are designed using deep learning. In this research work, proposed a model to find out people who are not wearing face mask in the public areas that are monitored with cameras. A deep learning-based model called Faster R-CNN is trained on the face-mask-detection and maskedFace-net datasets that consists of people with masks, without masks and improper masks are collected from different sources. The goal of this work is to identify whether the person in a given image is wearing face mask or not wearing face mask. If the person is wearing face mask, this work will also verify the improper face mask. This research work anticipate that the proposed model will achieve high accuracy on differentiating people with mask and without mask and that it will be useful to reduce the spread of this communicative disease.