Customized Human Mask-Face Recognition using Computer Vision

looking at the present problem of coronavirus disease, it has been advised by World Health Organization to take preventive measures to safeguard ourselves. One of the main preventive measures taken by the government and WHO is to wear a face mask while traveling outside along with social distancing. On the other hand, identifying a person with a facemask is also challenging. To overcome such situations there has been an urgent requirement for the technology to step forward. The proposed work has been implemented to overcome the situation and able to recognize a person behind the mask as well. In this work, haar cascade is used for locating the coordinates of pixels of face & mouth and abstracting the pixels of face & mouth from an image. The process of identifying starts by taking an input of the image from the default camera in the RGB format and is converted to a greyscale for fast processing of the image. The proposed work with still images and also with live video streaming with an accuracy of 90%.