Weighted Schatten <i>p</i>-Norm Low Rank Error Constraint for Image Denoising
Traditional image denoising algorithms obtain prior information from noisy images that are directly based on low rank matrix restoration, which pays little attention to the nonlocal self-similarity errors between clear images and noisy images. This paper proposes a new image denoising algorithm base...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/23/2/158 |
id |
doaj-fbddc80edf91403d8005fa407f030b28 |
---|---|
record_format |
Article |
spelling |
doaj-fbddc80edf91403d8005fa407f030b282021-01-28T00:06:38ZengMDPI AGEntropy1099-43002021-01-012315815810.3390/e23020158Weighted Schatten <i>p</i>-Norm Low Rank Error Constraint for Image DenoisingJiucheng Xu0Yihao Cheng1Yuanyuan Ma2College of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, ChinaTraditional image denoising algorithms obtain prior information from noisy images that are directly based on low rank matrix restoration, which pays little attention to the nonlocal self-similarity errors between clear images and noisy images. This paper proposes a new image denoising algorithm based on low rank matrix restoration in order to solve this problem. The proposed algorithm introduces the non-local self-similarity error between the clear image and noisy image into the weighted Schatten <i>p</i>-norm minimization model using the non-local self-similarity of the image. In addition, the low rank error is constrained by using Schatten <i>p</i>-norm to obtain a better low rank matrix in order to improve the performance of the image denoising algorithm. The results demonstrate that, on the classic data set, when comparing with block matching 3D filtering (BM3D), weighted nuclear norm minimization (WNNM), weighted Schatten <i>p</i>-norm minimization (WSNM), and FFDNet, the proposed algorithm achieves a higher peak signal-to-noise ratio, better denoising effect, and visual effects with improved robustness and generalization.https://www.mdpi.com/1099-4300/23/2/158image denoisinglow rank representationweighted schatten p-normlow rank error constraint |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jiucheng Xu Yihao Cheng Yuanyuan Ma |
spellingShingle |
Jiucheng Xu Yihao Cheng Yuanyuan Ma Weighted Schatten <i>p</i>-Norm Low Rank Error Constraint for Image Denoising Entropy image denoising low rank representation weighted schatten p-norm low rank error constraint |
author_facet |
Jiucheng Xu Yihao Cheng Yuanyuan Ma |
author_sort |
Jiucheng Xu |
title |
Weighted Schatten <i>p</i>-Norm Low Rank Error Constraint for Image Denoising |
title_short |
Weighted Schatten <i>p</i>-Norm Low Rank Error Constraint for Image Denoising |
title_full |
Weighted Schatten <i>p</i>-Norm Low Rank Error Constraint for Image Denoising |
title_fullStr |
Weighted Schatten <i>p</i>-Norm Low Rank Error Constraint for Image Denoising |
title_full_unstemmed |
Weighted Schatten <i>p</i>-Norm Low Rank Error Constraint for Image Denoising |
title_sort |
weighted schatten <i>p</i>-norm low rank error constraint for image denoising |
publisher |
MDPI AG |
series |
Entropy |
issn |
1099-4300 |
publishDate |
2021-01-01 |
description |
Traditional image denoising algorithms obtain prior information from noisy images that are directly based on low rank matrix restoration, which pays little attention to the nonlocal self-similarity errors between clear images and noisy images. This paper proposes a new image denoising algorithm based on low rank matrix restoration in order to solve this problem. The proposed algorithm introduces the non-local self-similarity error between the clear image and noisy image into the weighted Schatten <i>p</i>-norm minimization model using the non-local self-similarity of the image. In addition, the low rank error is constrained by using Schatten <i>p</i>-norm to obtain a better low rank matrix in order to improve the performance of the image denoising algorithm. The results demonstrate that, on the classic data set, when comparing with block matching 3D filtering (BM3D), weighted nuclear norm minimization (WNNM), weighted Schatten <i>p</i>-norm minimization (WSNM), and FFDNet, the proposed algorithm achieves a higher peak signal-to-noise ratio, better denoising effect, and visual effects with improved robustness and generalization. |
topic |
image denoising low rank representation weighted schatten p-norm low rank error constraint |
url |
https://www.mdpi.com/1099-4300/23/2/158 |
work_keys_str_mv |
AT jiuchengxu weightedschattenipinormlowrankerrorconstraintforimagedenoising AT yihaocheng weightedschattenipinormlowrankerrorconstraintforimagedenoising AT yuanyuanma weightedschattenipinormlowrankerrorconstraintforimagedenoising |
_version_ |
1724320285359865856 |