Design and Implementation of a Student Expression Detection System in Experimental Teaching Classroom
In response to the difficulty in monitoring the learning effectiveness of students in experimental teaching classrooms,the SE Attention Mechanism and improved spatial pyramid pooling are introduced into YOLOv5.A student expression detection system based on low-quality laboratory videos is designed,achieving high-precision recognition of facial expressions of students in experimental classrooms.The experimental results show that after adding the SE Attention Mechanism module,the recognition accuracy of the model reaches 89%.After adding improved pyramid pooling,the model recognition accuracy reaches 94%.The system combines Deep Learning technology with laboratory classroom teaching quality evaluation practice,innovates the experimental teaching classroom quality evaluation mode,and can provide reference basis for teachers to adjust the experimental classroom teaching mode.
国家科技期刊平台
NSTL
万方数据
