This project will try to address the novel challenge of detecting whether a person is using a face mask or not by developing a face mask detection and alert system. The system will first detect the face in an image or in a live video and then it will predict whether that face in the image or video has a face mask or not. As this is a classification problem, we will build a Convolutional Neural Network to classify whether a face has a mask on it or not. This classification neural network model will be trained on a public dataset containing images with masks, without masks and improper masks. Finally, the trained model will be used against a live feed from a webcam or CCTV to predict whether the person is wearing a face mask or not. This project will also implement an alert system that will send an alert to the authorities if the person is not wearing the face mask. The alert can be in the form of an email or voice prompt or both.
Dataset link 1: https://makeml.app/datasets/mask
Dataset link 2: https://doi.org/10.1016/j.smhl.2020.100144
Dataset link 3: https://github.com/chandrikadeb7/Face-Mask-Detection/tree/master/dataset