摘要
首先对人脸表情的特点进行分析,给出了表情空间的定性描述.在此基础上,提出了一种兼有离散情感空间模型和连续情感空间模型特点的新的表情空间模型.为了验证该模型的合理性,利用Gabor小波特征和主分量分析方法结合混合高斯模型在人脸表情数据库JAFFE上进行了实验.对不同表情的分布规律进行了实验分析,实现了对表情空间的定性/定量描述.实验结果表明,提出的人脸表情空间模型能够对日常人脸表情进行恰当的表达.
The nature of facial expressions was analyzed and a qualitative description of the corresponding facial expression space was presented. And then a new facial expression space model was proposed with the characteristics of both the discrete affective space model and continuous affective space model. To validate the rationality of the model, experiments were eonducted on a facial expression database JAFFE using the Gaussian mixture model based on the Gabor wavelet and principal component analysis. The distribution of different expressions is analyzed and the qualitative and quantitative description of the facial expression space is accomplished. The experimental results show that the proposed model can rationally represent daily facial expressions.
关键词
表情分析
表情识别
表情空间模型
混合高斯模型
facial expression analysis
facial expression recognition
expression space model
Gaussian mixture model
