Research on Student Classroom Attention Detection Based on Multi-Feature Fusion

With the proposal of the concept of “AI+education”, the research on learner attention has received great attention from scholars. Student classroom attention is an important aspect of educational research, which directly affects their learning status and efficiency in class, and also provides objective data support for teachers to adjust classroom rhythms and teaching methods. This paper proposes a multi-feature fusion method for attention detection based on artificial intelligence, which applies multiple features such as eye, mouth, and facial expression to determine whether students are in a state of focused learning. Compared with only detecting body posture or single facial feature detection, this method improves the accuracy of detection.