Real-Time Deep Learning Face Mask Detection Model During COVID-19

Juyal, A.; Joshi, A.

COVID-19 pandemic has affected the whole world not only physically but also financially. Thousands of people have died due to this COVID-19 (Coronavirus) epidemic, and still the whole world is struggling to prevent this epidemic. Initially, the government had only an option to stop this epidemic and that was to declare complete lockdown. But during this time phase of lockdown, many people became unemployed. To stop this scenario and for the sake of employment and other financial economy, our government has decided to unlock various sectors. This unlock phase has increased the risk of outbreak of COVID-19 so to avoid risk and to stop spreading of this pandemic disease, the government has issued some important guidelines to be followed mandatorily by each individual during this unlock process. The face mask is one of the compulsory guidelines issued by the government. Wearing a face mask may reduce the chances of spreading corona virus. Many people roaming in public places without wearing a face mask. To monitor such kind of people at a time is not easy manually. So in this paper, we are proposing deep learning-based model that can automatically detect person wearing a mask or not. In this method, a model convolutional neural network (CNN) was trained over thousands of images to detect whether a person wearing a mask or not. Proposed model achieved 93.36 validation accuracy and 98.71 training accuracy. This model can be helpful to stop spreading of coronavirus in such organizations where human interaction is necessary for smooth functioning like hospitals, colleges, gyms, supermarkets. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.