Semisupervised Hypergraph Discriminant Learning for Dimensionality Reduction of Hyperspectral Image
Semisupervised learning is an effective technique to represent the intrinsic features of a hyperspectral image (HSI), which can reduce the cost to obtain the labeled information of samples. However, traditional semisupervised learning methods fail to consider multiple properties of an HSI, which has...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9146627/ |
id |
doaj-413b8e7938b242a9a5db8d276bd49e02 |
---|---|
record_format |
Article |
spelling |
doaj-413b8e7938b242a9a5db8d276bd49e022021-06-03T23:07:00ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01134242425610.1109/JSTARS.2020.30114319146627Semisupervised Hypergraph Discriminant Learning for Dimensionality Reduction of Hyperspectral ImageFulin Luo0https://orcid.org/0000-0002-7696-0775Tan Guo1https://orcid.org/0000-0001-9523-8094Zhiping Lin2https://orcid.org/0000-0002-1587-1226Jinchang Ren3https://orcid.org/0000-0001-6116-3194Xiaocheng Zhou4State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, ChinaSchool of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing, ChinaSchool of Electrical and Electronic Engineering, Nanyang Technological University, SingaporeDepartment of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, U.K.Key Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education, Fuzhou University, Fuzhou, ChinaSemisupervised learning is an effective technique to represent the intrinsic features of a hyperspectral image (HSI), which can reduce the cost to obtain the labeled information of samples. However, traditional semisupervised learning methods fail to consider multiple properties of an HSI, which has restricted the discriminant performance of feature representation. In this article, we introduce the hypergraph into semisupervised learning to reveal the complex multistructures of an HSI, and construct a semisupervised discriminant hypergraph learning (SSDHL) method by designing an intraclass hypergraph and an interclass graph with the labeled samples. SSDHL constructs an unsupervised hypergraph with the unlabeled samples. In addition, a total scatter matrix is used to measure the distribution of the labeled and unlabeled samples. Then, a low-dimensional projection function is constructed to compact the properties of the intraclass hypergraph and the unsupervised hypergraph, and simultaneously separate the characteristics of the interclass graph and the total scatter matrix. Finally, according to the objective function, we can obtain the projection matrix and the low-dimensional features. Experiments on three HSI data sets (Botswana, KSC, and PaviaU) show that the proposed method can achieve better classification results compared with a few state-of-the-art methods. The result indicates that SSDHL can simultaneously utilize the labeled and unlabeled samples to represent the homogeneous properties and restrain the heterogeneous characteristics of an HSI.https://ieeexplore.ieee.org/document/9146627/Dimensionality reduction (DR)graph learninghyperspectral image (HSI) classificationlocality-constrained linear codingneighborhood margin |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Fulin Luo Tan Guo Zhiping Lin Jinchang Ren Xiaocheng Zhou |
spellingShingle |
Fulin Luo Tan Guo Zhiping Lin Jinchang Ren Xiaocheng Zhou Semisupervised Hypergraph Discriminant Learning for Dimensionality Reduction of Hyperspectral Image IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Dimensionality reduction (DR) graph learning hyperspectral image (HSI) classification locality-constrained linear coding neighborhood margin |
author_facet |
Fulin Luo Tan Guo Zhiping Lin Jinchang Ren Xiaocheng Zhou |
author_sort |
Fulin Luo |
title |
Semisupervised Hypergraph Discriminant Learning for Dimensionality Reduction of Hyperspectral Image |
title_short |
Semisupervised Hypergraph Discriminant Learning for Dimensionality Reduction of Hyperspectral Image |
title_full |
Semisupervised Hypergraph Discriminant Learning for Dimensionality Reduction of Hyperspectral Image |
title_fullStr |
Semisupervised Hypergraph Discriminant Learning for Dimensionality Reduction of Hyperspectral Image |
title_full_unstemmed |
Semisupervised Hypergraph Discriminant Learning for Dimensionality Reduction of Hyperspectral Image |
title_sort |
semisupervised hypergraph discriminant learning for dimensionality reduction of hyperspectral image |
publisher |
IEEE |
series |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
issn |
2151-1535 |
publishDate |
2020-01-01 |
description |
Semisupervised learning is an effective technique to represent the intrinsic features of a hyperspectral image (HSI), which can reduce the cost to obtain the labeled information of samples. However, traditional semisupervised learning methods fail to consider multiple properties of an HSI, which has restricted the discriminant performance of feature representation. In this article, we introduce the hypergraph into semisupervised learning to reveal the complex multistructures of an HSI, and construct a semisupervised discriminant hypergraph learning (SSDHL) method by designing an intraclass hypergraph and an interclass graph with the labeled samples. SSDHL constructs an unsupervised hypergraph with the unlabeled samples. In addition, a total scatter matrix is used to measure the distribution of the labeled and unlabeled samples. Then, a low-dimensional projection function is constructed to compact the properties of the intraclass hypergraph and the unsupervised hypergraph, and simultaneously separate the characteristics of the interclass graph and the total scatter matrix. Finally, according to the objective function, we can obtain the projection matrix and the low-dimensional features. Experiments on three HSI data sets (Botswana, KSC, and PaviaU) show that the proposed method can achieve better classification results compared with a few state-of-the-art methods. The result indicates that SSDHL can simultaneously utilize the labeled and unlabeled samples to represent the homogeneous properties and restrain the heterogeneous characteristics of an HSI. |
topic |
Dimensionality reduction (DR) graph learning hyperspectral image (HSI) classification locality-constrained linear coding neighborhood margin |
url |
https://ieeexplore.ieee.org/document/9146627/ |
work_keys_str_mv |
AT fulinluo semisupervisedhypergraphdiscriminantlearningfordimensionalityreductionofhyperspectralimage AT tanguo semisupervisedhypergraphdiscriminantlearningfordimensionalityreductionofhyperspectralimage AT zhipinglin semisupervisedhypergraphdiscriminantlearningfordimensionalityreductionofhyperspectralimage AT jinchangren semisupervisedhypergraphdiscriminantlearningfordimensionalityreductionofhyperspectralimage AT xiaochengzhou semisupervisedhypergraphdiscriminantlearningfordimensionalityreductionofhyperspectralimage |
_version_ |
1721398549527134208 |