| 一种改进的典型相关分析方法及其应用 |
| |
| 引用本文： | 陈才扣,彭倩倩,孙强强,黄建平. 一种改进的典型相关分析方法及其应用[J]. 系统仿真学报, 2010, 22(2) |
| |
| 作者姓名： | 陈才扣 彭倩倩 孙强强 黄建平 |
| |
| 作者单位： | 1. 扬州大学计算机科学与工程系,扬州,225009;南京理工大学计算机科学与工程系,南京,210094
2. 扬州大学计算机科学与工程系,扬州,225009 |
| |
| 基金项目： | 国家自然科学基金(60875004); 江苏省自然科学基金(BK2009184) |
| |
| 摘 要： | 传统典型相关分析准则函数在界定同组特征矢量中各元素之间不相关时采用乘法运算,易出现无法保证两组特征矢量同时达到同组元素协方差意义下最小的问题。为解决这一问题,提出了一种改进的典型相关分析方法,对典型相关准则函数分母部分进行修正,将其中的乘法改成加法,对该方法进行推导得到投影矫正系数,该系数对两组特征矢量特征方程进行调整,保证两组特征矢量同时达到同组元素协方差意义下最小。该方法有效地改善了融合效果、提高了人脸识别的正确率。在ORL和Yale人脸数据库上的实验结果都验证了其有效性。
|
| 关 键 词： | 特征融合 典型相关分析 准则函数改进 人脸识别 |
Improved Canonical Correlation Analysis Method and Its Application |
| |
| CHEN Cai-kou,,PENG Qian-qian,SUN Qiang-qiang,HUANG Jian-ping. Improved Canonical Correlation Analysis Method and Its Application[J]. Journal of System Simulation, 2010, 22(2) |
| |
| Authors: | CHEN Cai-kou PENG Qian-qian SUN Qiang-qiang HUANG Jian-ping |
| |
| Affiliation: | CHEN Cai-kou1,2,PENG Qian-qian1,SUN Qiang-qiang1,HUANG Jian-ping1 (1.Information Engineering College,Yangzhou Univeristy,Yangzhou 225009,China,2.Computer Science , Technology College,Nanjing University of Science , Technology,Nanjing 210094,China) |
| |
| Abstract: | The traditional canonical correlation analysis criterion in defining function of the same group on the correlation between the elements use the multiplication operation,and it is an easy problem that it can't guarantee the two groups can be in smallest covariance of the same group of elements at the same time.To solve this problem,an improved canonical correlation analysis was proposed which made an amendment in the denominator of the criteria,it would change the multiplication to the addition,it had a proj... |
| |
| Keywords: | feature fusion canonical correlation analysis improved discrminant criterion face recognition |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
