Cover Image

An ℓ0-overlapping group sparse total variation for impulse noise image restoration

Total variation (TV) based methods are effective models in image restoration. For eliminating impulse noise, an effective way is to use the ℓ1-norm total variation model. However, the TV image restoration always yields staircase artifacts, especially in high-density noise levels. Additionally, the ℓ...

Full description

Saved in:
Bibliographic Details
Main Authors: Yin, Mingming, Adam, Tarmizi, Paramesran, Raveendran, Hassan, Mohd. Fikree
Format: Article
Published: Elsevier B.V. 2022
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://eprints.utm.my/104116/
http://dx.doi.org/10.1016/j.image.2021.116620
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.104116
record_format eprints
spelling my.utm.1041162024-01-17T01:14:16Z http://eprints.utm.my/104116/ An ℓ0-overlapping group sparse total variation for impulse noise image restoration Yin, Mingming Adam, Tarmizi Paramesran, Raveendran Hassan, Mohd. Fikree QA75 Electronic computers. Computer science Total variation (TV) based methods are effective models in image restoration. For eliminating impulse noise, an effective way is to use the ℓ1-norm total variation model. However, the TV image restoration always yields staircase artifacts, especially in high-density noise levels. Additionally, the ℓ1-norm tends to over penalize solutions and is not robust to outlier characteristics of impulse noise. In this paper, we propose a new total variation model to effectively remove the staircase effects and eliminate impulse noise. The proposed model uses the ℓ0-norm data fidelity to effectively remove the impulse noise while the overlapping group sparse total variation (OGSTV) acts as a regularizer to eliminate the staircase artifacts. Since the proposed method requires solving an ℓ0-norm and an OGSTV optimization problem, a formulation using the mathematical program with equilibrium constraints (MPEC) and the majorization–minimization (MM) method are respectively used together with the alternating direction method of multipliers (ADMM). Experiments demonstrate that our proposed model performs better than several state-of-the-art algorithms such as the ℓ1 total generalized variation, ℓ0 total variation, and the ℓ1 overlapping group sparse total variation in terms of the peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM). Elsevier B.V. 2022-03 Article PeerReviewed Yin, Mingming and Adam, Tarmizi and Paramesran, Raveendran and Hassan, Mohd. Fikree (2022) An ℓ0-overlapping group sparse total variation for impulse noise image restoration. Signal Processing: Image Communication, 102 (NA). pp. 1-15. ISSN 0923-5965 http://dx.doi.org/10.1016/j.image.2021.116620 DOI:10.1016/j.image.2021.116620
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Yin, Mingming
Adam, Tarmizi
Paramesran, Raveendran
Hassan, Mohd. Fikree
An ℓ0-overlapping group sparse total variation for impulse noise image restoration
description Total variation (TV) based methods are effective models in image restoration. For eliminating impulse noise, an effective way is to use the ℓ1-norm total variation model. However, the TV image restoration always yields staircase artifacts, especially in high-density noise levels. Additionally, the ℓ1-norm tends to over penalize solutions and is not robust to outlier characteristics of impulse noise. In this paper, we propose a new total variation model to effectively remove the staircase effects and eliminate impulse noise. The proposed model uses the ℓ0-norm data fidelity to effectively remove the impulse noise while the overlapping group sparse total variation (OGSTV) acts as a regularizer to eliminate the staircase artifacts. Since the proposed method requires solving an ℓ0-norm and an OGSTV optimization problem, a formulation using the mathematical program with equilibrium constraints (MPEC) and the majorization–minimization (MM) method are respectively used together with the alternating direction method of multipliers (ADMM). Experiments demonstrate that our proposed model performs better than several state-of-the-art algorithms such as the ℓ1 total generalized variation, ℓ0 total variation, and the ℓ1 overlapping group sparse total variation in terms of the peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM).
format Article
author Yin, Mingming
Adam, Tarmizi
Paramesran, Raveendran
Hassan, Mohd. Fikree
author_facet Yin, Mingming
Adam, Tarmizi
Paramesran, Raveendran
Hassan, Mohd. Fikree
author_sort Yin, Mingming
title An ℓ0-overlapping group sparse total variation for impulse noise image restoration
title_short An ℓ0-overlapping group sparse total variation for impulse noise image restoration
title_full An ℓ0-overlapping group sparse total variation for impulse noise image restoration
title_fullStr An ℓ0-overlapping group sparse total variation for impulse noise image restoration
title_full_unstemmed An ℓ0-overlapping group sparse total variation for impulse noise image restoration
title_sort ℓ0-overlapping group sparse total variation for impulse noise image restoration
publisher Elsevier B.V.
publishDate 2022
url http://eprints.utm.my/104116/
http://dx.doi.org/10.1016/j.image.2021.116620
_version_ 1789424381379739648
score 13.211869

Similar Items