| 基于2D-FrFT多阶次特征融合的人脸表情识别方法 |
| |
| 引用本文： | 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(1): 109-112 |
| |
| 作者姓名： | 穆晓敏 张嗣思 齐林 |
| |
| 作者单位： | 郑州大学信息工程学院,河南郑州,450001 |
| |
| 基金项目： | 国家自然科学基金资助项目(61071211);河南省自然科学研究计划资助项目(2010A510013) |
| |
| 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.
|
| 关 键 词： | 表情识别 2D-FrFT 特征融合 典型相关分析 |
Human Emotion Recognition Using Fused 2D-Fractional Fourier Transform Features Based on CCA |
| |
| MU Xiao-min , ZHANG Si-si , QI Lin. Human Emotion Recognition Using Fused 2D-Fractional Fourier Transform Features Based on CCA[J]. Journal of Zhengzhou University: Eng Sci, 2012, 33(1): 109-112 |
| |
| Authors: | MU Xiao-min ZHANG Si-si QI Lin |
| |
| Affiliation: | (School of Information Engineening School,Zhengzhou University,Zhengzhou 450001,China) |
| |
| Abstract: | In this paper,we explored an approach for recognizing human emotional state from fused 2D-FrFT features based on Canonical Correlation Analysis(CCA).This approach is mainly based on the correlation between different orders in 2D-FrFT.First,the visual features are extracted by 2D-FrFT,and two orders are choser which achieve the highest recognition rate for feature fusion through CCA.Then we send the fused features into the multi-classifier based on SVM.The feasibility of the recognition approach we proposed has been tested and the experimental results sufficiently demonstrate the effectiveness of the proposed approach. |
| |
| Keywords: | emotion recognition 2D-FrFT feature fusion CCA |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
