Color Face Images Recognition Based on Quaternion Kernel Discriminant Analysis

被引：0

作者：

Jing, Xiao-Yuan ^{[1
,2
]}

Tang, Hui ^{[1
,2
]}

Yao, Yong-Fang ^{[1
,2
]}

Zhang, Ji-Wei ^{[1
,2
]}

机构：

[1] Nanjing Univ Posts & Telecommun, Sch Automat, Nanjing, Jiangsu, Peoples R China

[2] Zhongxing Commun Co, Nanjing Res & Dev Ctr, Nanjing, Peoples R China

来源：

2011 3RD WORLD CONGRESS IN APPLIED COMPUTING, COMPUTER SCIENCE, AND COMPUTER ENGINEERING (ACC 2011), VOL 4 | 2011年 / 4卷

关键词：

Color image; quaternion matrix; correlation; kernel discriminant analysis;

D O I：

暂无

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper proposed a color component fusion technique based on quaternion. Quaternion is a more general measurement than real value and complex value and has many neat properties. In our approach, each color image is representd as a quaternion, whose three complex components are the R, G and B component images respectively. Then quaternion based nonlinear discriminant analysis using kernel tricks is presented to extract nonlinear features of color images. Experimental results validate the effectiveness of our proposed approach.

引用

页码：53 / +

页数：3

共 16 条

[1]

[Anonymous], 1998, 24 CVC

[2] Color clustering and learning for image segmentation based on neural networks [J].