Manual surveillance of whether people are wearing a mask or not is not only costly but also a risky process. In this present world, which is being hit by the Coronavirus pandemic, the risk of spread of virus is exponentially high when people are not wearing mask. Thus, the automation of the process of detection of people not wearing mask had become a necessity. Our project uses deep learning techniques to determine whether a person is wearing a mask or not. Our proposed system identifies the mask violators automatically which reduces the risk of transmission of virus and also makes it easier for the authority to monitor the mask violators and take action against them without being put at risk of transmitting the virus. We use MobileNetV2 architecture to efficiently achieve best accuracy which is the key to our system. We were able to achieve accuracy of 99.22% after training the model. Detecting and tracking the face mask is the main aim of the project.