人机交互中的人脸表情识别研究进展  

The Research Advance of Facial Expression Recognition in Human Computer Interaction

作　　者：薛雨丽[1] 毛峡[1] 郭叶[1] 吕善伟[1] 

机构地区：[1]北京航空航天大学电子信息工程学院,北京100191

出　　处：《中国图象图形学报》2009年第5期764-772,共9页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60572044);国家高技术研究发展计划(863计划)项目(2006AA01Z135);高等学校博士学科点专项科研基金项目(20070006057)

摘　　要：随着人机交互与情感计算技术的快速发展,人脸表情识别已成为人们研究的热点。为了阐明人机交互中人脸表情识别的研究方向及进展,该文从人脸表情数据库、表情特征提取、表情分类方法、鲁棒的表情识别、精细的表情识别、混合表情识别、非基本表情识别等方面对人脸表情识别的研究现状进行了分析。最后总结了人脸表情识别研究的热点及趋势,同时指出了人脸表情识别研究存在的局限性,并对人脸表情识别的发展进行了展望。Along with the rapid progress of the technologies in human computer interaction and affective computing, facial expression recognition has been actively researched. To clarify the research direction and development of facial expression recognition in human computer interaction, the research states of facial expression recognition are analyzed from the aspects of facial expression database, facial feature extraction, facial expression classification methods, robust facial expression recognition, fine-graded facial expression recognition, mixed facial expression recognition, and non-basic facial expression recognition. Finally, the study hotspots and trends of facial expression recognition are concluded, the limits in facial expression recognition are pointed out, and the expectation of the development of facial expression recognition is given.

关 键 词：表情识别 情感表情 人脸表情数据库 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]