Coronamask: A Face Mask Detector for Real-Time Data

Abstract

COVID – 19 (2019 novel coronavirus) which started in China had spread all over the world rapidly. It is the worst health crisis the whole world has suffered after World War II. Many precautionary measures have been indicated by the World Health Organisation (WHO) like to maintain social distancing, wear masks, wash hands with soap for 20 seconds and many more. Wearing masks in public places is quite an effective measure to stay protected from this pandemic. There is very few research done for detecting face masks. This paper contributes to the welfare of human beings and proposes CoronaMask, a highly effective face mask detector. The proposed model uses the deep learning convolutional neural network (CNN) algorithm as a base for detecting faces. In this study, the dataset has been created which consists of 1238 images which are divided into two classes as “mask” and “no_mask”. This model also takes live streaming videos as input and detects faces which are wearing masks and which are not wearing a mask. The convolutional neural network is trained on the dataset and it gives 95% of accuracy. CoronaMask, a two-phase face mask detector works in identifying masks in images and also in real-time video streams.