Design of an intelligent art appreciation teaching support system based on deep image recognition

Abstract

Art appreciation teaching is an important part of art education. However, there are many limitations in the traditional teaching mode, such as strong subjectivity in art interpretation, uneven distribution of high-quality resources and low participation of students. In recent years, the breakthrough of deep learning technology in the field of image recognition has provided a new opportunity for the intelligent development of art education. This paper puts forward a design scheme of intelligent assistant system for art appreciation teaching based on depth image recognition, aiming at empowering education equity through technology and improving teaching efficiency and quality. The system adopts hierarchical architecture, including data layer, algorithm layer, service layer and application layer, and integrates the key technologies such as the multi-task style classification model of ResNet-152 architecture, the improved Faster R-CNN visual element detection model and knowledge map construction. Through the differentiated functional design between teachers and students, the system supports real-time classroom interaction and personalized autonomous learning after class. The test results show that the system performs well in the tasks of artistic style classification, creative period identification and visual element detection, and its educational effect is significantly better than the traditional teaching mode, which can effectively improve students' artistic understanding and critical thinking ability. In addition, the teacher's user experience evaluation also shows a high degree of satisfaction, thinking that the system has significantly improved the efficiency of lesson preparation and the effect of classroom interaction. This study provides an innovative solution for the intelligent development of art education, which has important theoretical and practical value.