AI-Based Low-Cost Real-Time Face Mask Detection and Health Status Monitoring System for COVID-19 Prevention

Abstract

The outbreak of COVID-19 had brought a great challenge for the World Health Organization (WHO) in preventing the spreading of SARS-CoV-2. The Ministry of Health (MOH) of Malaysia introduced the MySejahtera mobile application for health monitoring and contact tracing. Wearing a face mask in public areas had been made compulsory by the Government. The overhead cost incurred in hiring the extra manpower to ensure all the visitors wear a face mask, check-in through MySejahtera and the status in MySejahtera is healthy before entering a premise. A low-cost solution is urgently needed to reduce the heavy overhead cost. An AI-Based Low-Cost Real-Time Face Mask Detection and Health Status Monitoring System (AFMHS) is proposed to perform real-time detection for the face mask and MySejahtera Check-In tickets by using artificial intelligence. MobileNetV2 was used for the detection and recognition of face and face masks. YOLOv3 was used for the detection of the region of interest for the MySejahtera Check-In ticket to locate the health and vaccination status of the visitor. Optical character recognition (OCR) is a technique that is used to detect the text captured in an image and encode the recognized text. OCR is implemented to recognize the text extracted from the ticket. Tesseract is used as the OCR engine in AFMHS. Raspberry-Pi-4B (Raspberry Pi Generation 4 Model B) with 4 GB RAM is used as the processing unit of AFMHS. The total cost of the AFMHS is only USD220. Extensive experimental tests were carried out to evaluate the performance of AFMHS. The optimum operation setup conditions are proposed to achieve 100% accuracy. The optimum operating distance for the face mask detector and MySejahtera Check-In ticket detector are 1.5m and 15cm respectively.