| 面向脸部表情识别的Gabor特征选择方法 |
| |
| 引用本文： | 姚伟,孙正兴,张岩. 面向脸部表情识别的Gabor特征选择方法[J]. 计算机辅助设计与图形学学报, 2008, 20(1): 79-84 |
| |
| 作者姓名： | 姚伟 孙正兴 张岩 |
| |
| 作者单位： | 南京大学计算机软件新技术国家重点实验室,南京,10093;南京大学计算机软件新技术国家重点实验室,南京,10093;南京大学计算机软件新技术国家重点实验室,南京,10093 |
| |
| 基金项目： | 国家自然科学基金 , 国家高技术研究发展计划(863计划) , 教育部跨世纪优秀人才培养计划 |
| |
| 摘 要： | 针对人脸表情识别中Gabor特征向量的高维度信息冗余问题,提出了一个2层Gabor特征选择方法.该方法首先利用改进方差比率作为评估特征的区分能力对高维向量进行过滤,然后对过滤得到的特征子集进行AdaBoost特征选择,以挑选出最具区分度的特征,从而降低了Gabor特征的表示维度.实验结果验证了所提方法的有效性,在训练时间和识别性能两者之间取得了较好的平衡.
|
| 关 键 词： | 表情识别 Gabor特征 特征选择 方差率 AdaBoost 支持向量机 |
| 收稿时间： | 2007-05-10 |
| 修稿时间： | 2007-07-31 |
Optimal Gabor Feature for Facial Expression Recognition |
| |
| Yao Wei,Sun Zhengxing,Zhang Yan. Optimal Gabor Feature for Facial Expression Recognition[J]. Journal of Computer-Aided Design & Computer Graphics, 2008, 20(1): 79-84 |
| |
| Authors: | Yao Wei Sun Zhengxing Zhang Yan |
| |
| Abstract: | In order to reduce the curse of dimensionality of Gabor features in facial expression recognition, a two-level feature selection algorithm is developed. Firstly, the original Gabor features are pre-optimized according to the augmented variance ratio to represent the distinguish ability of each feature. Then, the most informative Gabor features are obtained with AdaBoost feature selection algorithm from the preoptimized subset. As a result, the dimension of features is effectively reduced. Experimental results prove the effectiveness of the proposed method, by achieving a balance between training time and recognition rate. |
| |
| Keywords: | facial expression recognition Gabor feature feature selection variance ratio AdaBoost SVM |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
