COVID-19 FACE MASK DETECTOR

Abstract

At this time, all people in the world are facing a crisis known as COVID-19. COVID-19 is a disease caused by Severe Acute Respiratory Syndrome Coronavirus 2. COVID-19 can cause respiratory system disorders, ranging from mild symptoms such as flu to lung infections, such as pneumonia, and eventually cause death. The process of spreading the COVID-19 virus itself is easy, namely through small droplets from the nose or mouth when coughing or sneezing, then spreads to surrounding objects and people. Several precautions can be taken to reduce the spread of this virus, such as social distancing, wearing masks, and washing hands frequently. But there are still many people who don't want to do that. Therefore, this thesis aims to make an application that can detect whether people are wearing masks or not from the input, such as image, video, and camera. This thesis will implement OpenCV, Keras/TensorFlow, Python, Tkinter, Computer Vision, and Deep Learning to create a COVID-19 Face Mask Detector application. The manufacture of COVID-19 Face Mask Detector application went through two phases, which are Train Mask Detector and Apply Face Mask Detector. In the first phase, the application will load the dataset image of people with masks and without a mask. Then train it to make a face mask classifier with Keras/TensorFlow and save it into a model. In the second phase, the application will load the face detector model and mask detector model. Then apply it to detect the location of the face in the input and determine whether the face is wearing a mask or not. After doing that, the application will show the input result. The application can be used in the office or at the airport via a video stream from a CCTV camera while checking the people who entered it. So it is hoped that in the future, more people can comply with wearing masks and can reduce the spread of COVID-19.