一种求解Fisher最佳鉴别矢量的新算法及人脸识别

郭跃飞; 黄修武; 杨静宇

doi:10.11834/jig.19990226

学术论文与技术报告 | 浏览量 : 0 下载量: 150 CSCD: 0

PDF
导出
分享
收藏
专辑

一种求解Fisher最佳鉴别矢量的新算法及人脸识别
A Novel Algorithm Solving Fisher Optimal Discriminant Vector and Facial Recognition
1999年4卷第2期页码：95
纸质出版：1999
DOI： 10.11834/jig.19990226
稿件说明：

移动端阅览

郭跃飞, 黄修武, 杨静宇. 一种求解Fisher最佳鉴别矢量的新算法及人脸识别[J]. 中国图象图形学报, 1999,4(2):95. DOI： 10.11834/jig.19990226.

A Novel Algorithm Solving Fisher Optimal Discriminant Vector and Facial Recognition[J]. Journal of Image and Graphics, 1999, 4(2): 95. DOI： 10.11834/jig.19990226.

摘要

Fisher最佳鉴别矢量是高维模式分析中的有效方法，当训练样本数相对于特征空间的维数较小时，就成了小样本问题。为了求解小样本问题，人们提出了一系列方法并取得了的效果。但在类内距离为零的情况下民的方法均得不到最佳解，该文从理论上说明了这一点，并给一种在任何情况下都能得到最佳解的新算法，试验结果这样的推断。

Abstract

Fisher optimal discriminant vectors method is an effective method in pattern analysis of high dimension. When the number of the training samples is small compared with the dimensionality of the feature space

the problem becomes the case of a small number of samples. People have proposed many methods for solving the problem of a small number of samples

and made great progress. However

none of the previous methods can obtain the optimal solution when within-class distance equals zero. This point is illustrated in terms of theory

and a new solving method that can obtain the optimal solution in any situations is presented in this paper. The experimental result confirms our inference.