Titre :

A global variational filter for restoring noised images with gamma multiplicative noise

Auteur(s) :

Diffellah, Nacira [Auteur]
University of Biskra Mohamed Khider
Baarir, Zine-Eddine [Auteur]
University of Biskra Mohamed Khider
Derraz, Foued [Auteur]
Université Aboubekr Belkaid - University of Belkaïd Abou Bekr [Tlemcen]
Tahleb Ahmed, Abdelmalik [Auteur]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - Département Opto-Acousto-Électronique - UMR 8520 [IEMN-DOAE]

Titre de la revue :

ENGINEERING TECHNOLOGY & APPLIED SCIENCE RESEARCH

Pagination :

4188-4195

Éditeur :

EOS ASSOC

Date de publication :

2019-06

ISSN :

2241-4487

Mot(s)-clé(s) en anglais :

multiplicative gamma noise
restoration
regularization
data fitting
total variation
MAP estimation
proximal operator
PSNR
SSIM
VSNR

Discipline(s) HAL :

Sciences de l'ingénieur [physics]

Résumé en anglais : [en]

In this paper, we focus on a globally variational method to restore noisy images corrupted by multiplicative gamma noise. The problem is assumed as a regularization problem in total variation (TV) framework with data fitting ...
Lire la suite >In this paper, we focus on a globally variational method to restore noisy images corrupted by multiplicative gamma noise. The problem is assumed as a regularization problem in total variation (TV) framework with data fitting term which is deduced by maximizing the a-posteriori probability density (MAP estimation). We need to evaluate the proximal operator of a data fitting term then we numerically adapt the Douglas-Rachford (DR) splitting method to solve the problem. Real images with different levels of noise were used. To validate the effectiveness of the proposed method, the proposed method was compared with other variational models. Our method shows effective noise suppression, excellent edge preservation. Measures of image quality such as PSNR (peak signal-to-noise ratio), VSNR (visual signal-to-noise ratio) and SSIM (structural similarity index) explain the proposed model's good performance.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Institut d'Électronique, de Microélectronique et de Nanotechnologie (IEMN) - UMR 8520

Source :

Harvested from HAL