Scholarlink

Art style recognition is a key challenge in the field of digital humanities. This study proposes an innovative approach based on deep learning, achieving an accuracy of 93.8% by optimizing the ResNet50 model. The developed system excels in single-image recognition and batch processing, with average recognition times of 0.21 s and 0.18 s, respectively. The extended art piece era classifier achieves an accuracy of 87.5%, with an average error of 8.7 years. A personalized art learning recommendation system built on these technologies significantly enhances user learning outcomes, increasing daily learning time by 51%. These achievements provide innovative tools for art education, promoting the intelligent development of art appreciation and research.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on the Application of Deep Learning Models in Art Education Image Recognition

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Shihui Jin

摘要

Art style recognition is a key challenge in the field of digital humanities. This study proposes an innovative approach based on deep learning, achieving an accuracy of 93.8% by optimizing the ResNet50 model. The developed system excels in single-image recognition and batch processing, with average recognition times of 0.21 s and 0.18 s, respectively. The extended art piece era classifier achieves an accuracy of 87.5%, with an average error of 8.7 years. A personalized art learning recommendation system built on these technologies significantly enhances user learning outcomes, increasing daily learning time by 51%. These achievements provide innovative tools for art education, promoting the intelligent development of art appreciation and research.