| 一种基于KCCA的小样本脸像鉴别方法 |
| |
| 引用本文： | 贺云辉,赵力,邹采荣.一种基于KCCA的小样本脸像鉴别方法[J].应用科学学报,2006,24(2):140-144. |
| |
| 作者姓名： | 贺云辉 赵力 邹采荣 |
| |
| 作者单位： | 东南大学无线电工程系, 江苏南京 210096 |
| |
| 摘 要： | 基于典型相关分析和Fisher线性鉴别分析的等价性,提出了利用核典型相关分析来抽取小样本人脸图像的非线性鉴别特征,并用其进行脸像鉴别.这样得到的非线性特征本质上等价于核Fisher非线性最佳鉴别特征.基于ORL库的实验表明,对小样本人脸图像,KCCA可以得到和广义鉴别分析近似的识别性能,其所得非线性特征明显优于FLDA的线性鉴别特征.
|
| 关 键 词： | Fisher鉴别分析 脸像鉴别 典型相关分析 核方法 小样本问题 |
| 文章编号： | 0255-8297（2006）02-0140-05 |
| 收稿时间： | 2004-11-24 |
| 修稿时间： | 2004-11-242005-05-25 |
Kernel Canonical Correlation Analysis and Application for Face Discrimination |
| |
| HE Yun-hui,ZHAO Li,ZOU Cai-rong.Kernel Canonical Correlation Analysis and Application for Face Discrimination[J].Journal of Applied Sciences,2006,24(2):140-144. |
| |
| Authors: | HE Yun-hui ZHAO Li ZOU Cai-rong |
| |
| Institution: | Department of Radio Engineering, Southeast University, Nanjing 210096, China |
| |
| Abstract: | Based on the equivalence between canonical correlation analysis(CCA) and Fisher linear discriminant analysis(FLDA),nonlinear discriminant features of face images are extracted with kernel CCA.These features are equivalent to those extracted with KFDA.Experimental results demonstrate that KCCA is similar to GDA and significantly better than FLDA. |
| |
| Keywords: | canonical correlation analysis kernel method Fisher discriminant analysis small sample size problem face image discrimination |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《应用科学学报》浏览原始摘要信息 |
| 点击此处可从《应用科学学报》下载免费的PDF全文 |
