The Human Facial Combined Expression Recognition System
The Human Facial Combined Expression Recognition System
复制标题
DOI：
--
复制
发表时间：
2000
期刊：
影响因子：
--
通讯作者：
Jin Hui
中科院分区：
文献类型：
--
作者：
Jin Hui
人类不仅具有理性思维和逻辑推理能力，而且具有感性思维和情感。为了实现自然、智能的人机交流，必须使计算机能够理解和表达情感。本文总结了心理学领域的研究和前人的工作，提出了基于动态表情图像序列分析的组合表情识别系统。该方法将人脸看作由多个主要表情区域组成，提取表情区域的运动特征并构造特征序列。提出并实现了任意长度的人脸表情图像序列分析和组合表情识别，通过分析不同主区域各自的表情含义和表情内容，采用多特征融合的方法。
The human beings have not only rational thinking and logic reasoning ability, but also perceptual thinking and emotions. In the aim of the natural and intelligent human machine communication, it is essential to make it possible that the computer can understand and express the emotions. This paper summarizes the study in the psychology field and the former work and proposes the combined expression recognition system based on the analysis of the dynamic expression image sequences. The face is taken as being composed of several primary expression regions, in which the motion features can be extracted and constituted to eigen sequences. The analysis of the arbitrary length of image sequences of facial expressions and combined expression recognition are proposed and implemented by analyzing the respective expression meaning and the expression contents of different primary regions and using the multi feature fusion.