基于改进的并行特征融合人脸表情识别 |
| |
引用本文: | 罗飞,王国胤,杨勇,李振静. 基于改进的并行特征融合人脸表情识别[J]. 广西大学学报(自然科学版), 2009, 34(5) |
| |
作者姓名: | 罗飞 王国胤 杨勇 李振静 |
| |
作者单位: | 重庆邮电大学,计算机科学与技术学院,重庆,400065;重庆邮电大学,计算机科学与技术学院,重庆,400065;西南交通大学,信息科学与技术学院,四川,成都,610031 |
| |
基金项目: | 国家自然科学基金资助项目,重庆市杰出青年科学基金 |
| |
摘 要: | 基于信息融合理论和线性鉴别分析,提出了一种改进的并行特征融合人脸表情识别方法.该方法首先将不同表征下的人脸表情特征利用复向量组合起来,构成复特征向量,然后利用具有不同权重的最大散度差鉴别分析方法进行进一步的复特征提取.在不同样本库、不同类型特征融合下的实验结果表明,该方法在优化投影轴和避免"小样本"问题的同时得到了满意的识别结果.
|
关 键 词: | 表情识别 特征融合 最大散度差鉴别分析 |
Facial expression recognition based on improved parallel features fusion |
| |
Abstract: | An improved maximum scatter difference discriminate criterion method based on information fusion theory is proposed in emotion recognition. Firstly, the complex feature vectors of different features are computed. Then, complex features are extracted by the maximum scatter difference discriminate criterion of different weight. Experiment results with different samples and features show the efficiency of the method and it can avoid the "Small Sample Size" and "inferior" problems. The correct recognition rate is further improved by the proposed feature fusion method. |
| |
Keywords: | expression recognition feature fusion maximum scatter difference discriminate criterion |
本文献已被 万方数据 等数据库收录! |
|