Student Evaluation Model Based on Emotion Recognition through Classroom Monitoring

The improvement and perfection of higher education work relies on correct feedback from student evaluation of teaching, however, problems such as strong subjectivity and generalization of the indicator system are common in college student evaluation. Therefore, this article designs a student evaluation model based on emotion recognition through classroom monitoring. First, use classroom surveillance to collect class videos of teachers and students. After that the emotional information of teachers and students in class is captured through emotion recognition technology by calling Baidu AI Open Platform API and gesture recognition technology through improved you only watch once (YOWO) algorithm model, then entering into the database for statistics. Finally, statistical data is used to analyze teaching methods and teaching attitudes such as content mastery and enthusiasm, as well as learning effects such as student initiative and knowledge mastery, and multiple indicators of student evaluation are presented on a web page in the form of bar charts, pie charts, etc through plotting library. As a result, this model improves the objectivity and reliability of the evaluation results and provides data support for the quantification of the indicator system, which makes the evaluation results more intuitive and easy to understand.