Multi-view teaching expression recognition method and system in classroom environment

Abstract

The invention discloses a multi-view teaching expression recognition method and system in a classroom environment. The method comprises the following steps: acquiring a long-wave infrared multi-view expression image sequence of a teacher in a classroom in class; preprocessing the long-wave infrared multi-view expression image sequences respectively; inputting the preprocessed long-wave infrared multi-view expression images into a trained expression recognition model to obtain expression results of the teacher in class; the teaching emotional state of the teacher is determined according to the teaching expression change of the teacher in the classroom, and the teaching emotional state of the whole class is counted, so that service is provided for classroom teaching evaluation intelligentization. The method can improve the accuracy of teacher expression recognition in the classroom environment, can be used for analyzing the classroom emotion and emotion of the teacher, and promotes the refinement and individuation of classroom evaluation.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and more specifically relates to a method and system for multi-view teaching expression recognition in a classroom environment. Background technique [0002] The teacher's teaching emotional state is an important means to measure the enthusiasm of teachers in the classroom, and it can provide more intelligent services for the intelligent evaluation of classroom teaching. Facial expression is one of the most common signals for human beings to express their inner emotions and intentions. Teachers' facial expressions are an effective form of expression for teachers' emotional state in teaching. Applying facial expression recognition technology to teachers' teaching status detection ensures the fairness and accuracy of evaluation to a certain extent. The difficulties in facial expression recognition are: ①The facial image is not clear, and the image pixels are low due to other factors (l...

AI Technical Summary

Problems solved by technology

First of all, the image is directly input into the convolution module, which destroys the internal information of the image and cannot accurately capture the shallow information of the image.

Secondly, the lighting changes of the learning environment, too strong or too weak light will lead to the loss of facial details, and sometimes shadows will be generated, which will affect the recognition results

Images