Please use this identifier to cite or link to this item: http://dlib.scu.ac.ir/handle/Hannan/516926
Title: Unsupervised Band Selection Using Block-Diagonal Sparsity for Hyperspectral Image Classification
Authors: Jingyu Wang;Ke Zhang;Pei Wang;Kurosh Madani;Christophe Sabourin
Year: 2017
Publisher: IEEE
Abstract: In order to alleviate the negative effect of curse of dimensionality, band selection is a crucial step for hyperspectral image (HSI) processing. In this letter, we propose a novel unsupervised band selection approach to reduce the dimensionality for hyperspectral imagery. In order to obtain the most representative bands, the correlation matrix computed from the original HSI is used to describe the correlation characteristics among bands, while the block-diagonal structure is measured to segment all bands into a series of subspace. After applying the spectral clustering algorithm, the optimal combination of band is finally selected. To verify the effectiveness and superiority of the proposed band selection method, experiments have been conducted on three widely used real-world hyperspectral data. The results have shown that the proposed method outperforms other methods in HSI classification application.
URI: http://dl.kums.ac.ir/handle/Hannan/516926
volume: 14
issue: 11
More Information: 2062,
2066
Appears in Collections:2017

Files in This Item:
File Description SizeFormat 
8049336.pdf804.82 kBAdobe PDFThumbnail
Preview File
Title: Unsupervised Band Selection Using Block-Diagonal Sparsity for Hyperspectral Image Classification
Authors: Jingyu Wang;Ke Zhang;Pei Wang;Kurosh Madani;Christophe Sabourin
Year: 2017
Publisher: IEEE
Abstract: In order to alleviate the negative effect of curse of dimensionality, band selection is a crucial step for hyperspectral image (HSI) processing. In this letter, we propose a novel unsupervised band selection approach to reduce the dimensionality for hyperspectral imagery. In order to obtain the most representative bands, the correlation matrix computed from the original HSI is used to describe the correlation characteristics among bands, while the block-diagonal structure is measured to segment all bands into a series of subspace. After applying the spectral clustering algorithm, the optimal combination of band is finally selected. To verify the effectiveness and superiority of the proposed band selection method, experiments have been conducted on three widely used real-world hyperspectral data. The results have shown that the proposed method outperforms other methods in HSI classification application.
URI: http://dl.kums.ac.ir/handle/Hannan/516926
volume: 14
issue: 11
More Information: 2062,
2066
Appears in Collections:2017

Files in This Item:
File Description SizeFormat 
8049336.pdf804.82 kBAdobe PDFThumbnail
Preview File
Title: Unsupervised Band Selection Using Block-Diagonal Sparsity for Hyperspectral Image Classification
Authors: Jingyu Wang;Ke Zhang;Pei Wang;Kurosh Madani;Christophe Sabourin
Year: 2017
Publisher: IEEE
Abstract: In order to alleviate the negative effect of curse of dimensionality, band selection is a crucial step for hyperspectral image (HSI) processing. In this letter, we propose a novel unsupervised band selection approach to reduce the dimensionality for hyperspectral imagery. In order to obtain the most representative bands, the correlation matrix computed from the original HSI is used to describe the correlation characteristics among bands, while the block-diagonal structure is measured to segment all bands into a series of subspace. After applying the spectral clustering algorithm, the optimal combination of band is finally selected. To verify the effectiveness and superiority of the proposed band selection method, experiments have been conducted on three widely used real-world hyperspectral data. The results have shown that the proposed method outperforms other methods in HSI classification application.
URI: http://dl.kums.ac.ir/handle/Hannan/516926
volume: 14
issue: 11
More Information: 2062,
2066
Appears in Collections:2017

Files in This Item:
File Description SizeFormat 
8049336.pdf804.82 kBAdobe PDFThumbnail
Preview File