Face Mask Detection using Machine Learning Techniques

COVID-19 pandemic has bought a lot of change in our daily routine. To protect ourselves from getting infected, we need to follow certain precautions. One such safety measures are wearing a face mask. Viruses spread from one person to other respiratory droplets. When an infected person talks, shouts, sneezes or coughs, the droplets land in the mouth or nose of other people who are nearby. So, wearing a face mask over nose and mouth acts as a barrier for preventing the transmission of respiratory droplets. But many people ignore wearing a mask in public areas. It is good to have a system to identify people without masks in public places. This system, when integrated with embedded systems ensures the public safely. Our project aims to detect the people without masks on a video by developing a machine learning algorithm which identifies the person without a face mask. Machine learning is one of the techniques of Artificial Intelligence which is used for extracting valuable knowledge from large databases[1]. We collected the training sets from Kaggle, few open-source libraries and Google consisting of faces with and without a face mask. There are around 1500 images of with and without a face mask.