Mask and Emotion: Computer Vision in the Age of COVID-19

Abstract

Computer vision systems since the early 1960s have undergone a long evolution and are widely used in various fields, in particular, in education for the implementation of immersive educational resources. When developing computer vision systems for educational purposes, it is advisable to use the computer vision libraries based on deep learning (in particular, implementations of convolutional neural networks). Computer vision systems can be used in education both under normal and pandemic conditions. The changes in the education industry caused by the COVID-19 pandemic have affected the classic educational applications of computer vision systems, modifying existing ones and giving rise to new ones, including social distancing, face mask recognition, intrusion detection in universities and schools, and vandalism prevention, recognition of emotions on faces with and without masks, attendance monitoring. Developed on the basis of Microsoft Cognitive Toolkit and deployed in the Microsoft Azure cloud, a prototype computer vision system integrates emotion recognition of students and detection of violations of the mask regime, additionally providing the ability to determine gender, smile intensity, average age, makeup, glasses, hair color, etc. with a high degree of reliability.