Student Evaluation Using Face Emotion Recognition

Computer Engineering

Student Evaluation Using Face Emotion Recognition" is introduced in this system. Many students in the institute do not mentally attend lectures, and as a result, they do not grasp the concepts of the lecture. For this implementation, OpenCV technology and the Convolution Neural Network (CNN) Machine Learning Algorithm is used. This framework is built on deep learning technology, which can greatly improve teaching and learning interactivity. To get the picture frame sequence, first separate the video stream. Then, after extracting the valid data with the classroom analysis module, mark the face section with the Mask CNN model. And the eigenvalue of the face is obtained through the Exception framework. The Haar cascade is then used to analyze the students' facial expressions. It also prevents recognition of lectures caused by lack office representation. Using this system the teachers can grasp the classroom atmosphere in real time, to facilitate the adjustment of the teaching strategy in time. The outcomes of empirical experiments indicate that the proposed method performs well. In addition, the method increases teaching efficiency, allowing students to have a much more positive learning experience and satisfaction. Students who respond quickly to questions about their comprehension during a lecture will learn more quickly.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.