Published Paper Details:

The recent COVID-19 virus outbreak has caused a global health crisis. According to the World Health Organization (WHO), one of the effective protection measures is to wear a face mask in public areas. The COVID-19 pandemic enforced the governments across the world to impose lockdowns to prevent virus transmission. Reports indicate that wearing facemasks at workplace clearly reduces the risk of virus transmission. Therefore, we built a face mask detector with computer vision using Python, OpenCV, Tensor Flow and Keras. In our proposed system we use live video streaming. We train the system to detect the faces of the registered people at a particular workplace. The main aim here is to identify whether a person on the live video stream is wearing a face mask or not. If it detects a person who is not wearing a mask, then it sends an alert message stating the same. This method attains an accuracy of up to 95.77%. We use the mobile net model to detect the presence of masks correctly without causing over-fitting.