Real Time Facial Expression Recognition for Online Lecture

Abstract

In order to better improve online teaching during the epidemic, teachers can adjust the teaching according to the students’ understanding. During the epidemic period, online teaching has become a basic way for teachers to teach. One big problem with online teaching is that the lecturers find it hard to see the students’ facial expressions. According to the study, the students’ facial expressions are essential for the instructor to understand the students’ understanding of the course material. There are some relevant studies on the recognition of human facial expressions. However, most of them did not consider some expressions such as “Enlightened,” “Confused,” or “Bored.” This study helps teachers to improve the quality of teaching by designing a program to provide them with students’ facial expressions. The study, implemented on students’ computers, can capture their faces from a camera, identify some common and useful facial expressions, and send them to lecturers regularly during online lectures. The main research methods used in this paper are as follows: (1) Use the face recognition algorithm provided by OpenCV to capture faces. (2) Train a convolutional neural network model to recognize the expression “Happy,” “Surprised,” “Neutral,” “Enlightened,” “Confusion,” and “Boredom.” (3) Use the message protocol EMQX to transmit the expression information. This study can successfully capture faces, and about 80% accuracy can identify expressions and successfully transmit expression information. This study contains some expressions rarely studied by others and is innovative in the field of facial expression recognition. Datasets, deep learning models, and results are available for other research teams.