[1]陈子健,朱晓亮.基于面部表情的学习者情绪自动识别研究——适切性、现状、现存问题和提升路径[J].远程教育杂志,2019,(04):064-72.[doi:10.15881/j.cnki.cn33-1304/g4.2019.04.008]
 Zhu Xiaoliang,Chen Zijian.Research on Automatic Emotion Recognition for Students based on Facial Expression: Relevance, Research Situation, Existing Problems and Development Strategies[J].Distance Education Journal,2019,(04):064-72.[doi:10.15881/j.cnki.cn33-1304/g4.2019.04.008]
点击复制

基于面部表情的学习者情绪自动识别研究——适切性、现状、现存问题和提升路径()
分享到:

《远程教育杂志》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年04期
页码:
064-72
栏目:
前沿探索
出版日期:
2019-07-10

文章信息/Info

Title:
Research on Automatic Emotion Recognition for Students based on Facial Expression: Relevance, Research Situation, Existing Problems and Development Strategies
作者:
陈子健;朱晓亮
1.华中师范大学 国家数字化学习工程技术研究中心,湖北武汉 430079;2.贵州财经大学 信息学院,贵州贵阳 550025
Author(s):
Zhu Xiaoliang; Chen Zijian
1.National Engineering Research Center for E-learning, Central China Normal University, Wuhan Hubei 430079; 2. Information Institute, Guizhou University of Finance and Economics, Guiyang Guizhou 550025
关键词:
面部表情识别情绪识别学习者情绪计算机视觉深度学习
Keywords:
Facial Expression Recognition Emotion Recognition Emotion of Learners Computer Visual Deep Learning
分类号:
G40-05
DOI:
10.15881/j.cnki.cn33-1304/g4.2019.04.008
文献标志码:
A
摘要:
面部表情是表达情绪的主要通道,也是用于情绪识别的一种重要信号。以计算机视觉、人工智能、情感计算等新兴技术为支撑,计算机可以通过识别学习者外显的面部表情来判断学习者内隐的情绪状态,从而获取识别、理解学习者情绪的能力。基于面部表情的学习者情绪识别需要在对不同情绪表征方法进行对比分析的基础上,确定适用的情绪表征方法,并对基于面部表情的学习者情绪识别的适切性进行论证。作为面部表情识别流程中的核心环节,面部表情特征提取方法分为传统的计算机视觉方法和深度学习方法两大类。梳理不同特征提取算法的特点及局限性,可以为探索适合学习者面部表情识别的特征提取算法提供借鉴,并推动学习者面部表情识别研究的有效发展和应用。当前,学习者情绪面部表情识别相关研究仍存在一些问题,需从多种路径提升对学习者情绪面部表情识别的研究,包括:大规模的自然的学习者情绪面部表情数据库的共建共享,融合多种特征识别学习者情绪面部表情,结合人工设计和自动学习两种方法提取面部表情特征。
Abstract:
The facial expression is the main channel for expressing emotion and an important signal for emotion recognition. Supported by computer vision, artificial intelligence, affective computing, and other emerging technologies, the computer can estimate the emotion of students by the means of recognizing the facial expressions of learners. It makes computers have the ability of recognizing the emotion of learners. To realize the recognition of learners’ emotion based on facial expressions, firstly, it is necessary to determine the representation methods based on the comparative analysis of different emotional representation methods, then demonstrate the suitability of learners’ emotion recognition based on facial expression. As the core of facial expression recognition process, the extraction methods of facial expression features can be divided into traditional computer vision methods and deep learning methods.The pros and cons of different feature extraction algorithms can provide useful reference for finding the appropriate feature extraction algorithm for student facial expression recognition, and promote the effective development and application of learners facial expression recognition research.Finally, the existing problems in the related researches were pointed out, and the proposals to promote researches on learner facial expression recognition were presented, including co-construction and sharing of the large-scale natural learner facial expression database, recognizing the learner facial expression based on multimodal features, and extracting features of learner facial expressions with feature descriptors and feature learning.

备注/Memo

备注/Memo:
基金项目:本文系教育部人文社会科学研究规划基金项目(编号:18YJAZH152);国家重点研发计划项目(项目编号:2018YFB1004500,课题编号:2018YFB1004504);中央高校基本科研业务费专项资金(编号:CCNU18TS005);贵州财经大学校级科研基金项目(编号:2018XYB09)的研究成果。
更新日期/Last Update: 1900-01-01