[1]穆晓敏,张嗣思,齐林..基于2D-FrFT多阶次特征融合的人脸表情识别方法[J].郑州大学学报(工学版),2012,33(01):109-112.[doi:10.3969/j.issn.1671-6833.2012.01.027]
　MU Xiaomin,ZHANG Sisi,QI Lin.Human Emotion Recognition Using Fused 2D-Fractional FourierTransform Features Based on CCA[J].Journal of Zhengzhou University (Engineering Science),2012,33(01):109-112.[doi:10.3969/j.issn.1671-6833.2012.01.027]
点击复制

基于2D-FrFT多阶次特征融合的人脸表情识别方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
33卷
期数:
2012年01期
页码:
109-112
栏目:
出版日期:
2012-01-10

文章信息/Info

Title:
Human Emotion Recognition Using Fused 2D-Fractional FourierTransform Features Based on CCA
作者:
穆晓敏; 张嗣思; 齐林.
郑州大学信息工程学院,河南郑州,450001, 郑州大学信息工程学院,河南郑州,450001, 郑州大学信息工程学院,河南郑州,450001
Author(s):
MU Xiaomin; ZHANG Sisi; QI Lin
School of information Engineening School, Zhengzhou University, Zhengzhou 450001. China
关键词:
表情识别;  2D-FrFT;  特征融合;  典型相关分析
Keywords:
emotion recognition; 2D-FrFT;  feature fusion;  CCA
分类号:
TN91
DOI:
10.3969/j.issn.1671-6833.2012.01.027
摘要:
提出一种二维分数阶傅里叶域(2D-FrFT)多阶次特征融合分类算法.该方法充分利用分数阶傅里叶域不同阶次下表情特征之间的相关性,选取两个阶次的表情特征,利用典型相关分析法( Canonical Correlation Analysis,CCA)进行特征融合,并通过基于支持向量机(Support Vector Machine,SVM)的多层次分类机制进行人脸表情识别.仿真实验结果表明,采用多阶次特征融合算法后提高了平均识别率,降低了表情特征维数,减小了计算量.
Abstract:
In this. paper, we explored an approach for recognizing human cmotional state from fused 2D-FrF’Tfealures based on Canonical Correlation Analysis ( CCA). This approach is mainly based on the correlation be-tween different orders in 2D-FrF’T. First, the visual features are extracted by 2D-FrFT, and two orders arechoser which achieve the highest recognition rate for feature fusion through CCA, Then we send the fused fea.tures into the multi-classifier based on SVM. The feasibility of the recognition approach we proposed has beentested and the experimental results sufficiently demonstrate the effectiveness of the proposed approach.
更新日期/Last Update: 1900-01-01