Hyperspectral Image Denoising via Correntropy-Based Nonconvex Low-Rank Approximation
Hyperspectral images (HSIs) are prone to be corrupted by various types of noise during the process of imaging and transmission, which seriously affect the subsequent HSI processing tasks. In this article, we proposed a novel low-rank-based model for HSIs denoising. On one hand, motivated by the supe...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2024-01-01
|
Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/10460099/ |
_version_ | 1797243357493198848 |
---|---|
author | Peizeng Lin Lei Sun Yaochen Wu Weiyong Ruan |
author_facet | Peizeng Lin Lei Sun Yaochen Wu Weiyong Ruan |
author_sort | Peizeng Lin |
collection | DOAJ |
description | Hyperspectral images (HSIs) are prone to be corrupted by various types of noise during the process of imaging and transmission, which seriously affect the subsequent HSI processing tasks. In this article, we proposed a novel low-rank-based model for HSIs denoising. On one hand, motivated by the superiority of nonconvex approximation to matrix rank, we construct a new nonconvex function which is tighter than some of existing rank approximated functions. On the other hand, we describe Gaussian noise and sparse noise simultaneously by introducing correntropy. In comparison with traditional model, we constrain noise in one regularization instead of separately constraining Gaussian noise and sparse noise, which indicates that the number of regularization parameters have been reduced. To optimize the proposed model, some convex analysis tools are utilized in this article. In addition, we provide theoretical analysis on the convergence of the developed algorithm. Through experiments conducted on both simulated and real HSIs, we verify the superiority of our model in enhancing the performance of mixture noise removal in HSIs. |
first_indexed | 2024-04-24T18:53:50Z |
format | Article |
id | doaj.art-3da643ec66ea4f19b472ef53892ed046 |
institution | Directory Open Access Journal |
issn | 2151-1535 |
language | English |
last_indexed | 2024-04-24T18:53:50Z |
publishDate | 2024-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
spelling | doaj.art-3da643ec66ea4f19b472ef53892ed0462024-03-26T17:47:06ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01176841685910.1109/JSTARS.2024.337346610460099Hyperspectral Image Denoising via Correntropy-Based Nonconvex Low-Rank ApproximationPeizeng Lin0https://orcid.org/0000-0002-3807-8079Lei Sun1https://orcid.org/0000-0002-1017-355XYaochen Wu2https://orcid.org/0009-0004-3876-0774Weiyong Ruan3https://orcid.org/0000-0001-7400-5443School of Systems Sciences and Engineering, Sun Yat-sen University, Guangzhou, ChinaSchool of Systems Sciences and Engineering, Sun Yat-sen University, Guangzhou, ChinaSchool of Systems Sciences and Engineering, Sun Yat-sen University, Guangzhou, ChinaSchool of Systems Sciences and Engineering, Sun Yat-sen University, Guangzhou, ChinaHyperspectral images (HSIs) are prone to be corrupted by various types of noise during the process of imaging and transmission, which seriously affect the subsequent HSI processing tasks. In this article, we proposed a novel low-rank-based model for HSIs denoising. On one hand, motivated by the superiority of nonconvex approximation to matrix rank, we construct a new nonconvex function which is tighter than some of existing rank approximated functions. On the other hand, we describe Gaussian noise and sparse noise simultaneously by introducing correntropy. In comparison with traditional model, we constrain noise in one regularization instead of separately constraining Gaussian noise and sparse noise, which indicates that the number of regularization parameters have been reduced. To optimize the proposed model, some convex analysis tools are utilized in this article. In addition, we provide theoretical analysis on the convergence of the developed algorithm. Through experiments conducted on both simulated and real HSIs, we verify the superiority of our model in enhancing the performance of mixture noise removal in HSIs.https://ieeexplore.ieee.org/document/10460099/Correntropyhyperspectral image (HSI) denoisinglow-rank presentationnonconvex approximation |
spellingShingle | Peizeng Lin Lei Sun Yaochen Wu Weiyong Ruan Hyperspectral Image Denoising via Correntropy-Based Nonconvex Low-Rank Approximation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Correntropy hyperspectral image (HSI) denoising low-rank presentation nonconvex approximation |
title | Hyperspectral Image Denoising via Correntropy-Based Nonconvex Low-Rank Approximation |
title_full | Hyperspectral Image Denoising via Correntropy-Based Nonconvex Low-Rank Approximation |
title_fullStr | Hyperspectral Image Denoising via Correntropy-Based Nonconvex Low-Rank Approximation |
title_full_unstemmed | Hyperspectral Image Denoising via Correntropy-Based Nonconvex Low-Rank Approximation |
title_short | Hyperspectral Image Denoising via Correntropy-Based Nonconvex Low-Rank Approximation |
title_sort | hyperspectral image denoising via correntropy based nonconvex low rank approximation |
topic | Correntropy hyperspectral image (HSI) denoising low-rank presentation nonconvex approximation |
url | https://ieeexplore.ieee.org/document/10460099/ |
work_keys_str_mv | AT peizenglin hyperspectralimagedenoisingviacorrentropybasednonconvexlowrankapproximation AT leisun hyperspectralimagedenoisingviacorrentropybasednonconvexlowrankapproximation AT yaochenwu hyperspectralimagedenoisingviacorrentropybasednonconvexlowrankapproximation AT weiyongruan hyperspectralimagedenoisingviacorrentropybasednonconvexlowrankapproximation |