基于图像分析的教育视觉情感识别  

The Recognition and Application of Educational Emotion Based on Image Analysis

作　　者：马晓玲[1] 郭胜男 吴永和[2] MA Xiao-ling;GUO Sheng-nan;WU Yong-he(Department of Information Management,East China Normal University,Shanghai,China 200062;Faculty of Education,East China Normal University,Shanghai,China 200062)

机构地区：[1]华东师范大学信息管理系,上海200062 [2]华东师范大学教育技术系,上海200062

出　　处：《现代教育技术》2020年第2期118-121,共4页Modern Educational Technology

基　　金：国家新闻出版署教育内容产品互联网传播与营销重点实验室开放课题“基于学习分析的用户学习能力模型构建”(项目编号：14108-412312-19023);认知智能国家重点实验室智能教育开放课题“基于大数据的学生学习行为分析及教学干预研究”(项目编号：14108-412321-19364)资助

摘　　要：情感识别是情感计算的基础,为了促进视觉情感识别技术与教育的深度融合,文章定义了教育视觉情感识别的概念,随后从技术视角分析了面部表情识别和肢体动作识别的三方面内容,即特征提取方法、分类器算法和常用数据库。此外,文章构建了双模态教育视觉情感识别模型,以解决单一模态的情感特征不能充分表达学习者学习情感信息的问题。期望这种更全面的模型,能为未来教育领域学习者情感识别研究提供参考。Emotion recognition is the basis of emotion calculation.In order to promote the deep integration of visual emotion recognition technology and education,the paper first defined the concept of educational visual emotion recognition.From the technical perspective,the three aspects of facial expression recognition and limb movement recognition were analyzed,which were feature extraction method,classifier algorithm and common emotion database.Then the dual-modal educational visual emotion recognition model was constructed to solve the problem that single-modal emotion feature could not fully express the learners’emotional information.It was expected that this more comprehensive model could provide reference value for future study of emotion recognition in the education field.

关 键 词：视觉情感识别 机器学习 双模态分析 

分 类 号：G40-057[文化科学—教育学原理]