Dimensionality reduction for hyperspectral image classification based on multiview graphs ensemble

被引：9

作者：

Chen, Puhua ^{[1
]}

Jiao, Licheng ^{[1
]}

Liu, Fang ^{[2
]}

Zhao, Jiaqi ^{[1
]}

Zhao, Zhiqiang ^{[1
]}

机构：

[1] Xidian Univ, Int Res Ctr Intelligent Percept & Computat, Key Lab Intelligent Percept & Image Understanding, Minist Educ, 2 South Taibai Rd, Xian 710071, Shaanxi, Peoples R China

[2] Xidian Univ, Sch Comp Sci & Technol, Int Res Ctr Intelligent Percept & Computat, Key Lab Intelligent Percept & Image Understanding, 2 South Taibai Rd, Xian 710071, Shaanxi, Peoples R China

来源：

JOURNAL OF APPLIED REMOTE SENSING | 2016年 / 10卷

基金：

中国国家自然科学基金;

关键词：

graph embedding; dimensionality reduction; hyperspectral image classification;

D O I：

10.1117/1.JRS.10.030501

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

Hyperspectral data are the spectral response of landcovers from different spectral bands and different band sets can be treated as different views of landcovers, which may contain different structure information. Therefore, multiview graphs ensemble-based graph embedding is proposed to promote the performance of graph embedding for hyperspectral image classification. By integrating multiview graphs, more affluent and more accurate structure information can be utilized in graph embedding to achieve better results than traditional graph embedding methods. In addition, the multiview graphs ensemble-based graph embedding can be treated as a framework to be extended to different graph-based methods. Experimental results demonstrate that the proposed method can improve the performance of traditional graph embedding methods significantly. (C) 2016 Society of Photo-Optical Instrumentation Engineers (SPIE)

引用

页数：8

共 14 条

[1] Laplacian eigenmaps for dimensionality reduction and data representation [J].