| 一种基于Gabor小波特征的人脸表情识别新方法 |
| |
| 引用本文： | 罗飞,王国胤,杨勇. 一种基于Gabor小波特征的人脸表情识别新方法[J]. 计算机科学, 2009, 36(1): 181-183 |
| |
| 作者姓名： | 罗飞 王国胤 杨勇 |
| |
| 作者单位： | 重庆邮电大学计算机科学与技术研究所,重庆,400065;重庆邮电大学计算机科学与技术研究所,重庆,400065;西南交通大学信息科学与技术学院,成都,610031 |
| |
| 基金项目： | 重庆市自然科学基金，重庆市计算机网络与通信重点实验室开放基金 |
| |
| 摘 要： | 近来,表情识别成为人机交互研究的热点.将Gabor小波变换与2DPCA结合提出了一种表情识别的新方法.首先对静态灰度表情图片进行预处理,然后对其进行Gabar小波变换,通过2DPCA进行降维,根据Gabor不同尺度不同方向的变换结果训练不同的分类器,由校验集得到分类器权值,通过隶属度函数将各个分类结果模糊化,实现了分类器集成和表情特征数据的融合.实验证明了Gabor小渡与2DPCA结合在表情识别中的有效性,以及基于Gabor小波模糊分类器集成的方法能够进一步提高识别率.
|
| 关 键 词： | 表情识别 表情特征提取 Gabor小波 2DPCA 模糊分类 |
| 收稿时间： | 2008-05-02 |
New Approach for Facial Expression Recognition Based on Gabor Features |
| |
| LUO Fei,WANG Guo-yin,YANG Yong. New Approach for Facial Expression Recognition Based on Gabor Features[J]. Computer Science, 2009, 36(1): 181-183 |
| |
| Authors: | LUO Fei WANG Guo-yin YANG Yong |
| |
| Affiliation: | Institute of Computer Science and Technology;Chongqing University of Posts and Telecommunications;Chongqing 400065;China;School of Information Science & Technology;Southwest Jiaotong University;Chengdu 610031;China |
| |
| Abstract: | In recent years,facial expression analysis is becoming a research hotspot in human-computer interaction.A novel facial expression recognition method was proposed based on the Gabor wavelet transformation and two-dimensional principal component analysis (2DPCA).Features of expression images were extracted with Gabor wavelet and 2DPCA.The classifiers on different scales and orientations of Gabor wavelet were designed.The weight of each classifier was discussed.The classification result of each classifier was ... |
| |
| Keywords: | 2DPCA |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
