Hyperspectral Mixed Noise Removal By <inline-formula><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula>-Norm-Based Subspace Representation
This article introduces a new hyperspectral image (HSI) denoising method that is able to cope with additive mixed noise, i.e., mixture of Gaussian noise, impulse noise, and stripes, which usually corrupt hyperspectral images in the acquisition process. The proposed method fully exploits a compact an...
| 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/9040508/ |
| _version_ | 1818438366021025792 |
|---|---|
| author | Lina Zhuang Michael K. Ng |
| author_facet | Lina Zhuang Michael K. Ng |
| author_sort | Lina Zhuang |
| collection | DOAJ |
| description | This article introduces a new hyperspectral image (HSI) denoising method that is able to cope with additive mixed noise, i.e., mixture of Gaussian noise, impulse noise, and stripes, which usually corrupt hyperspectral images in the acquisition process. The proposed method fully exploits a compact and sparse HSI representation based on its low-rank and self-similarity characteristics. In order to deal with mixed noise having a complex statistical distribution, we propose to use the robust ℓ<sub>1</sub> data fidelity instead of using the ℓ<sub>1</sub> data fidelity, which is commonly employed for Gaussian noise removal. In a series of experiments with simulated and real datasets, the proposed method competes with state-of-the-art methods, yielding better results for mixed noise removal. |
| first_indexed | 2024-12-14T17:39:25Z |
| format | Article |
| id | doaj.art-255cde5519864dec83b46ec9077c0344 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-14T17:39:25Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-255cde5519864dec83b46ec9077c03442022-12-21T22:52:53ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352020-01-01131143115710.1109/JSTARS.2020.29798019040508Hyperspectral Mixed Noise Removal By <inline-formula><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula>-Norm-Based Subspace RepresentationLina Zhuang0https://orcid.org/0000-0002-9622-6535Michael K. Ng1https://orcid.org/0000-0001-6833-5227Department of Mathematics, Hong Kong Baptist University (HKBU), Hong KongDepartment of Mathematics, The University of Hong Kong, Hong KongThis article introduces a new hyperspectral image (HSI) denoising method that is able to cope with additive mixed noise, i.e., mixture of Gaussian noise, impulse noise, and stripes, which usually corrupt hyperspectral images in the acquisition process. The proposed method fully exploits a compact and sparse HSI representation based on its low-rank and self-similarity characteristics. In order to deal with mixed noise having a complex statistical distribution, we propose to use the robust ℓ<sub>1</sub> data fidelity instead of using the ℓ<sub>1</sub> data fidelity, which is commonly employed for Gaussian noise removal. In a series of experiments with simulated and real datasets, the proposed method competes with state-of-the-art methods, yielding better results for mixed noise removal.https://ieeexplore.ieee.org/document/9040508/High-dimensional datahyperspectral destripinghyperspectral restorationlow-rank representationnonlocal patchself-similarity |
| spellingShingle | Lina Zhuang Michael K. Ng Hyperspectral Mixed Noise Removal By <inline-formula><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula>-Norm-Based Subspace Representation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing High-dimensional data hyperspectral destriping hyperspectral restoration low-rank representation nonlocal patch self-similarity |
| title | Hyperspectral Mixed Noise Removal By <inline-formula><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula>-Norm-Based Subspace Representation |
| title_full | Hyperspectral Mixed Noise Removal By <inline-formula><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula>-Norm-Based Subspace Representation |
| title_fullStr | Hyperspectral Mixed Noise Removal By <inline-formula><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula>-Norm-Based Subspace Representation |
| title_full_unstemmed | Hyperspectral Mixed Noise Removal By <inline-formula><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula>-Norm-Based Subspace Representation |
| title_short | Hyperspectral Mixed Noise Removal By <inline-formula><tex-math notation="LaTeX">$\ell _1$</tex-math></inline-formula>-Norm-Based Subspace Representation |
| title_sort | hyperspectral mixed noise removal by inline formula tex math notation latex ell 1 tex math inline formula norm based subspace representation |
| topic | High-dimensional data hyperspectral destriping hyperspectral restoration low-rank representation nonlocal patch self-similarity |
| url | https://ieeexplore.ieee.org/document/9040508/ |
| work_keys_str_mv | AT linazhuang hyperspectralmixednoiseremovalbyinlineformulatexmathnotationlatexell1texmathinlineformulanormbasedsubspacerepresentation AT michaelkng hyperspectralmixednoiseremovalbyinlineformulatexmathnotationlatexell1texmathinlineformulanormbasedsubspacerepresentation |