Real-Time Face Mask Detection in Mass Gathering to reduce COVID-19 Spread

Abstract

The outbreak of Covid 19 (coronavirus) pandemic has become one of the lethal health crises worldwide. So far no effective and completely curable vaccine or any alternative has been provided to stop this transmission. This virus gets transmitted from a person when they sneeze or when they speak also in the form of respiratory droplets. According to leading and well known scientists, wearing face masks and maintaining six feet of social distance are the most substantial protections to limit the virus’s spread. In the proposed model we have used the Convolutional Neural Network(CNN) algorithm of Deep Learning(DL) to ensure efficient real-time mask detection. We have divided the system in two parts – 1. Train Face Mask Detector 2. Apply Face Mask Detector for better understanding. This is a real time application which is used to discover or detect the person who is wearing a mask at proper position or not. The system has achieved an accuracy of 99% after being trained with the dataset, which contains around 2500 images of width and height 224×224. This type of model just needs to be integrated with a camera and the rest of the detection will be performed, like at airports, offices, railway stations, malls etc., to check whether a government guidelines are properly being followed or not.