The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Imej hiperspektral (HSI) umumnya terdedah kepada pelbagai hingar, seperti Gaussian dan hingar jalur. Baru-baru ini, banyak algoritma denoising telah dicadangkan untuk memulihkan HSI. Walau bagaimanapun, pendekatan tersebut tidak boleh menggunakan maklumat spektrum dengan cekap dan mengalami kelemahan penyingkiran hingar jalur. Di sini, kami mencadangkan kaedah penguraian tensor dengan dua kekangan berbeza untuk mengeluarkan bunyi campuran daripada HSI. Untuk kiub HSI, kami mula-mula menggunakan penguraian nilai tunggal tensor (t-SVD) untuk mengekalkan maklumat peringkat rendah HSI dengan berkesan. Memandangkan sifat kesinambungan spektrum HSI, kami mereka bentuk kekangan kelancaran mudah dengan menggunakan regularisasi Tikhonov untuk penguraian tensor untuk meningkatkan prestasi denoising. Selain itu, kami juga mereka bentuk kekangan jumlah variasi (TV) satu arah baharu untuk menapis hingar jalur daripada HSI. Strategi ini akan mencapai prestasi yang lebih baik untuk mengekalkan butiran imej berbanding model TV asal. Kaedah yang dibangunkan dinilai pada kedua-dua HSI bising sintetik dan sebenar, dan menunjukkan hasil yang menggalakkan.
Zhen LI
Beijing Institute of Technology
Baojun ZHAO
Beijing Institute of Technology
Wenzheng WANG
Beijing Institute of Technology,Peking University
Baoxian WANG
Shijiazhuang
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Zhen LI, Baojun ZHAO, Wenzheng WANG, Baoxian WANG, "Hyperspectral Image Denoising Using Tensor Decomposition under Multiple Constraints" in IEICE TRANSACTIONS on Fundamentals,
vol. E104-A, no. 6, pp. 949-953, June 2021, doi: 10.1587/transfun.2020EAL2099.
Abstract: Hyperspectral images (HSIs) are generally susceptible to various noise, such as Gaussian and stripe noise. Recently, numerous denoising algorithms have been proposed to recover the HSIs. However, those approaches cannot use spectral information efficiently and suffer from the weakness of stripe noise removal. Here, we propose a tensor decomposition method with two different constraints to remove the mixed noise from HSIs. For a HSI cube, we first employ the tensor singular value decomposition (t-SVD) to effectively preserve the low-rank information of HSIs. Considering the continuity property of HSIs spectra, we design a simple smoothness constraint by using Tikhonov regularization for tensor decomposition to enhance the denoising performance. Moreover, we also design a new unidirectional total variation (TV) constraint to filter the stripe noise from HSIs. This strategy will achieve better performance for preserving images details than original TV models. The developed method is evaluated on both synthetic and real noisy HSIs, and shows the favorable results.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020EAL2099/_p
Salinan
@ARTICLE{e104-a_6_949,
author={Zhen LI, Baojun ZHAO, Wenzheng WANG, Baoxian WANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Hyperspectral Image Denoising Using Tensor Decomposition under Multiple Constraints},
year={2021},
volume={E104-A},
number={6},
pages={949-953},
abstract={Hyperspectral images (HSIs) are generally susceptible to various noise, such as Gaussian and stripe noise. Recently, numerous denoising algorithms have been proposed to recover the HSIs. However, those approaches cannot use spectral information efficiently and suffer from the weakness of stripe noise removal. Here, we propose a tensor decomposition method with two different constraints to remove the mixed noise from HSIs. For a HSI cube, we first employ the tensor singular value decomposition (t-SVD) to effectively preserve the low-rank information of HSIs. Considering the continuity property of HSIs spectra, we design a simple smoothness constraint by using Tikhonov regularization for tensor decomposition to enhance the denoising performance. Moreover, we also design a new unidirectional total variation (TV) constraint to filter the stripe noise from HSIs. This strategy will achieve better performance for preserving images details than original TV models. The developed method is evaluated on both synthetic and real noisy HSIs, and shows the favorable results.},
keywords={},
doi={10.1587/transfun.2020EAL2099},
ISSN={1745-1337},
month={June},}
Salinan
TY - JOUR
TI - Hyperspectral Image Denoising Using Tensor Decomposition under Multiple Constraints
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 949
EP - 953
AU - Zhen LI
AU - Baojun ZHAO
AU - Wenzheng WANG
AU - Baoxian WANG
PY - 2021
DO - 10.1587/transfun.2020EAL2099
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E104-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2021
AB - Hyperspectral images (HSIs) are generally susceptible to various noise, such as Gaussian and stripe noise. Recently, numerous denoising algorithms have been proposed to recover the HSIs. However, those approaches cannot use spectral information efficiently and suffer from the weakness of stripe noise removal. Here, we propose a tensor decomposition method with two different constraints to remove the mixed noise from HSIs. For a HSI cube, we first employ the tensor singular value decomposition (t-SVD) to effectively preserve the low-rank information of HSIs. Considering the continuity property of HSIs spectra, we design a simple smoothness constraint by using Tikhonov regularization for tensor decomposition to enhance the denoising performance. Moreover, we also design a new unidirectional total variation (TV) constraint to filter the stripe noise from HSIs. This strategy will achieve better performance for preserving images details than original TV models. The developed method is evaluated on both synthetic and real noisy HSIs, and shows the favorable results.
ER -