三维面部表情识别技术的研究进展  

Research Progress of 3D Facial Expression Recognition Technology

作　　者：魏永超[1] 庄夏[2] 傅强[2] 杜冬[1] 

机构地区：[1]中国民用航空飞行学院飞行技术与飞行安全科研基地,四川广汉618307 [2]中国民用航空飞行学院科研处,四川广汉618307

出　　处：《电讯技术》2015年第6期693-703,共11页Telecommunication Engineering

基　　金：国家自然科学基金资助项目(61079022);四川省科技基金项目(2015JY0188);中国民航飞行学院科研基金项目(Q2013-050;J2012-43)~~

摘　　要：三维采集设备的快速发展,极大推动了三维数据技术的研究。其中,以三维人脸数据为载体的三维面部表情识别研究成果不断涌现。三维面部表情识别可以极大克服二维识别中的姿态和光照变化等方面问题。对三维表情识别技术进行了系统概括,尤其针对三维表情的关键技术,即对表情特征提取、表情编码分类及表情数据库进行了总结分析,并提出了三维表情识别的研究建议。三维面部表情识别技术在识别率上基本满足要求,但实时性上需要进一步优化。相关内容对该领域的研究具有指导意义。The rapid development of three-dimensional（3D） acquisition devices has greatly promoted the researches based on dimensional data and the achievements in 3D facial expression recognition research is constantly emerging. 3D facial recognition can greatly overcome the gesture and illumination changes and other issues of two-dimensional（2D） recognition. This paper summarizes 3D facial expression recognition technologies with emphasis on analysis of the key technologies of 3 D expression, including expression fea- ture extraction, coding and database. It also gives some research suggestions about 3 D facial expression rec- ognition. 3D facial expression recognition technology can basically meet the requirements in recognition rate, but its real-time performance needs to be further optimized. The research in this paper has reference value for researchers in the field.

关 键 词：表情识别 三维人脸 表情特征 表情编码 表情数据库 研究进展 

分 类 号：TN29[电子电信—物理电子学] TP391.4[自动化与计算机技术—计算机应用技术]