Human Face Recognition and Temperature Measurement Based on Deep Learning for Covid-19 Quarantine Checkpoint

Abstract

The human temperature measurement system has been widely applying in hospitals and public areas during the widespread Covid-19 pandemic. However, the current systems in the quarantine checkpoint are only capable of measuring the human temperature; however, it can not combine with the identification of facial recognition, human temperature information, and wearing mask detection. In addition, in the hospitals as well as the public areas such as schools, libraries, train stations, airports, etc. facial recognition of employees combined with temperature measurement and masking will save the time check and update employee status immediately. This study proposes a method that combines body temperature measurement, facial recognition, and masking based on deep learning. Furthermore, the proposed method adds the ability to prevent spoofing between a real face and face-in-image recognition. A depth camera is used in the proposed system to measure and calculate the length between the human's face and camera to approach the best accuracy of facial recognition and anti-spoofing. Moreover, a low-cost thermal camera measures the human body temperature. The methodology and algorithm for the human face and body temperature recognition are validated through the experimental results.