期刊文献+

智慧学习环境中基于面部表情的情感分析 被引量:66

Emotion Analysis Based on Facial Expression Recognition in Smart Learning Environment
下载PDF
导出
摘要 情感与认知加工之间存在着密不可分的联系,学习过程中的情感状态对学习效果有一定的影响。在智慧学习环境中实现学习者情感分析,有利于促进智慧学习的发生。表情作为人类情感表达的主要方式,其中蕴含了大量有关内心情感变化的信息,通过面部表情人们可以推断内心微妙的情感状态。目前,人脸检测技术已经实现了从复杂背景中定位人脸,分类算法也相对成熟,因此表情识别的研究工作主要集中在表情特征提取上,而现有研究基本上都是基于人脸与表情的混合特征进行的识别,这产生了较大的干扰。在表情识别时,理想情况是将个体相关的人脸特征和与个体无关的表情特征相分离。依据心理学家Ekman提出的FACS(面部表情编码系统)构建的智慧学习环境下基于面部表情识别的情感分析框架,通过特征分解将个体特征及表情特征分解到不同的子空间,在表情子空间中进行表情识别,从而排除个体特征对表情识别的干扰。经JAFFE表情库的验证,表情识别结果比较理想,已在三维虚拟学习平台Magic Learning的师生情感交互子系统上实现了基于面部表情的学习者情感识别及情感干预。 Emotion has many relative connections with cognition. Affective states in learning have certaininfluence on learning effect. Learners' emotion analysis in smart learning environment is beneficial to smartlearning. At present, locating human face in complex background has already been actualized by face detectivetechnology, and some available algorithms have also been applied to expression classification. Hence, the researchinto expression feature extraction has become the major issue in the expression recognition area. The featureextracted by existing methods is the combination of individual's facial feature and expressional feature, whichgreatly obstruct the expression recognition. In an optimal situation, the related individual facial feature can beseparated during the process of expression recognition. According to FACS(Facial Action Coding System) proposedby Ekman, a famous psychologist, we constructed an emotion analysis framework based on facial expressionrecognition in smart learning environment. We used feature decomposition method to decompose the facial featureand the expressional feature into face subspace and expression subspace respectively. After that, expressionrecognition will be done in the expression subspace and the interference of facial features will be eliminated.Experimental results on JAFFE database suggest that our method is effective. Facial expression recognition foremotional intervention has been performed in Magic Learning, which is an emotional interaction subsystem betweenlearners and virtual teachers in 3D virtual learning environment.
出处 《现代远程教育研究》 CSSCI 2015年第2期96-103,共8页 Modern Distance Education Research
基金 北京自然科学基金"三维虚拟教学环境中虚拟教师和教学过程建模的研究"(4102030) 中央高校基本科研业务费专项资金资助项目"自发性课堂学习情感的视觉建模与计算"(2014KJJCA15)
关键词 智慧学习环境 表情识别 表情特征 情感分析 情感干预 Smart Learning Environment Facial Expression Recognition Facial Expression Feature Emotion Analysis Emotion Intervention
  • 相关文献

参考文献26

二级参考文献193

共引文献1745

同被引文献850

引证文献66

二级引证文献790

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部