Joint Sparse Local Linear Discriminant Analysis for Feature Dimensionality Reduction of Hyperspectral Images

Although linear discriminant analysis (LDA)-based subspace learning has been widely applied to hyperspectral image (HSI) classification, the existing LDA-based subspace learning methods exhibit several limitations: (1) They are often sensitive to noise and demonstrate weak robustness; (2) these meth...

Full description

Saved in:
Bibliographic Details
Main Authors: Cong-Yin Cao, Meng-Ting Li, Yang-Jun Deng, Longfei Ren, Yi Liu, Xing-Hui Zhu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/16/22/4287
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267087342141440
author Cong-Yin Cao
Meng-Ting Li
Yang-Jun Deng
Longfei Ren
Yi Liu
Xing-Hui Zhu
author_facet Cong-Yin Cao
Meng-Ting Li
Yang-Jun Deng
Longfei Ren
Yi Liu
Xing-Hui Zhu
author_sort Cong-Yin Cao
collection DOAJ
description Although linear discriminant analysis (LDA)-based subspace learning has been widely applied to hyperspectral image (HSI) classification, the existing LDA-based subspace learning methods exhibit several limitations: (1) They are often sensitive to noise and demonstrate weak robustness; (2) these methods ignore the local information inherent in data; and (3) the number of extracted features is restricted by the number of classes. To address these drawbacks, this paper proposes a novel joint sparse local linear discriminant analysis (JSLLDA) method by integrating embedding regression and locality-preserving regularization into the LDA model for feature dimensionality reduction of HSIs. In JSLLDA, a row-sparse projection matrix can be learned, to uncover the joint sparse structure information of data by imposing a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mrow><mn>2</mn><mo>,</mo><mn>1</mn></mrow></msub></semantics></math></inline-formula>-norm constraint. The <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mrow><mn>2</mn><mo>,</mo><mn>1</mn></mrow></msub></semantics></math></inline-formula>-norm is also employed to measure the embedding regression reconstruction error, thereby mitigating the effects of noise and occlusions. A locality preservation term is incorporated to fully leverage the local geometric structural information of the data, enhancing the discriminability of the learned projection. Furthermore, an orthogonal matrix is introduced to alleviate the limitation on the number of acquired features. Finally, extensive experiments conducted on three hyperspectral image (HSI) datasets demonstrated that the performance of JSLLDA surpassed that of some related state-of-the-art dimensionality reduction methods.
format Article
id doaj-art-28a706bf2b5345a1bbcbf98aaaeaa203
institution OA Journals
issn 2072-4292
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-28a706bf2b5345a1bbcbf98aaaeaa2032025-08-20T01:53:56ZengMDPI AGRemote Sensing2072-42922024-11-011622428710.3390/rs16224287Joint Sparse Local Linear Discriminant Analysis for Feature Dimensionality Reduction of Hyperspectral ImagesCong-Yin Cao0Meng-Ting Li1Yang-Jun Deng2Longfei Ren3Yi Liu4Xing-Hui Zhu5College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaKey Laboratory of Computational Optical Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaAlthough linear discriminant analysis (LDA)-based subspace learning has been widely applied to hyperspectral image (HSI) classification, the existing LDA-based subspace learning methods exhibit several limitations: (1) They are often sensitive to noise and demonstrate weak robustness; (2) these methods ignore the local information inherent in data; and (3) the number of extracted features is restricted by the number of classes. To address these drawbacks, this paper proposes a novel joint sparse local linear discriminant analysis (JSLLDA) method by integrating embedding regression and locality-preserving regularization into the LDA model for feature dimensionality reduction of HSIs. In JSLLDA, a row-sparse projection matrix can be learned, to uncover the joint sparse structure information of data by imposing a <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mrow><mn>2</mn><mo>,</mo><mn>1</mn></mrow></msub></semantics></math></inline-formula>-norm constraint. The <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msub><mi>L</mi><mrow><mn>2</mn><mo>,</mo><mn>1</mn></mrow></msub></semantics></math></inline-formula>-norm is also employed to measure the embedding regression reconstruction error, thereby mitigating the effects of noise and occlusions. A locality preservation term is incorporated to fully leverage the local geometric structural information of the data, enhancing the discriminability of the learned projection. Furthermore, an orthogonal matrix is introduced to alleviate the limitation on the number of acquired features. Finally, extensive experiments conducted on three hyperspectral image (HSI) datasets demonstrated that the performance of JSLLDA surpassed that of some related state-of-the-art dimensionality reduction methods.https://www.mdpi.com/2072-4292/16/22/4287hyperspectral image (HSI)dimensionality reductionlinear discriminant analysisembedding regression regularization
spellingShingle Cong-Yin Cao
Meng-Ting Li
Yang-Jun Deng
Longfei Ren
Yi Liu
Xing-Hui Zhu
Joint Sparse Local Linear Discriminant Analysis for Feature Dimensionality Reduction of Hyperspectral Images
Remote Sensing
hyperspectral image (HSI)
dimensionality reduction
linear discriminant analysis
embedding regression regularization
title Joint Sparse Local Linear Discriminant Analysis for Feature Dimensionality Reduction of Hyperspectral Images
title_full Joint Sparse Local Linear Discriminant Analysis for Feature Dimensionality Reduction of Hyperspectral Images
title_fullStr Joint Sparse Local Linear Discriminant Analysis for Feature Dimensionality Reduction of Hyperspectral Images
title_full_unstemmed Joint Sparse Local Linear Discriminant Analysis for Feature Dimensionality Reduction of Hyperspectral Images
title_short Joint Sparse Local Linear Discriminant Analysis for Feature Dimensionality Reduction of Hyperspectral Images
title_sort joint sparse local linear discriminant analysis for feature dimensionality reduction of hyperspectral images
topic hyperspectral image (HSI)
dimensionality reduction
linear discriminant analysis
embedding regression regularization
url https://www.mdpi.com/2072-4292/16/22/4287
work_keys_str_mv AT congyincao jointsparselocallineardiscriminantanalysisforfeaturedimensionalityreductionofhyperspectralimages
AT mengtingli jointsparselocallineardiscriminantanalysisforfeaturedimensionalityreductionofhyperspectralimages
AT yangjundeng jointsparselocallineardiscriminantanalysisforfeaturedimensionalityreductionofhyperspectralimages
AT longfeiren jointsparselocallineardiscriminantanalysisforfeaturedimensionalityreductionofhyperspectralimages
AT yiliu jointsparselocallineardiscriminantanalysisforfeaturedimensionalityreductionofhyperspectralimages
AT xinghuizhu jointsparselocallineardiscriminantanalysisforfeaturedimensionalityreductionofhyperspectralimages