模块2DPCA的缺陷与改进

朱明旱; 罗大庸

doi:10.11834/jig.20090117

图像分析和识别 | 浏览量 : 0 下载量: 307 CSCD: 0

PDF
导出
分享
收藏
专辑

模块2DPCA的缺陷与改进
Defects and Improvement of Modular Two-dimensional Principal Component Analysis
2009年14卷第1期页码：94
纸质出版：2009
DOI： 10.11834/jig.20090117
稿件说明：

移动端阅览

朱明旱, 罗大庸. 模块2DPCA的缺陷与改进[J]. 中国图象图形学报, 2009,14(1):94. DOI： 10.11834/jig.20090117.

ZHU Minghan, LUO Dayong. Defects and Improvement of Modular Two-dimensional Principal Component Analysis[J]. Journal of Image and Graphics, 2009, 14(1): 94. DOI： 10.11834/jig.20090117.

摘要

模块2DPCA是2DPCA的推广，在识别性能上比2DPCA更具鲁棒性。本文分析了模块2DPCA在计算训练样本总体散布矩阵和本征向量选取方面的缺陷，提出了一种改进的模块2DPCA算法。实验结果表明，改进后的算法能更好地选取本征向量，更有效地提取人脸特征。

Abstract

Modular 2DPCA is an extension of 2DPCA algorithm. The recognition performance of modular 2DPCA is more robust than that of 2DPCA.In this paper

the defects of modular 2DPCA about computing the total scatter matrix of training samples and selecting eigenvectors are analyzed. An improved modular 2DPCA algorithm is presented. Experiments show that the improved modular 2DPCA algorithm can select better eigenvectors and extract facial features more effectively.