Novel hybrid integrated Pix2Pix and WGAN model with Gradient Penalty for binary images denoising

This paper introduces a novel approach to image denoising that leverages the advantages of Generative Adversarial Networks (GANs). Specifically, we propose a model that combines elements of the Pix2Pix model and the Wasserstein GAN (WGAN) with Gradient Penalty (WGAN-GP). This hybrid framework seeks...

Full description

Saved in:
Bibliographic Details
Main Authors: Luca Tirel, Ali Mohamed Ali, Hashim A. Hashim
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Systems and Soft Computing
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772941924000516
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850249409536720896
author Luca Tirel
Ali Mohamed Ali
Hashim A. Hashim
author_facet Luca Tirel
Ali Mohamed Ali
Hashim A. Hashim
author_sort Luca Tirel
collection DOAJ
description This paper introduces a novel approach to image denoising that leverages the advantages of Generative Adversarial Networks (GANs). Specifically, we propose a model that combines elements of the Pix2Pix model and the Wasserstein GAN (WGAN) with Gradient Penalty (WGAN-GP). This hybrid framework seeks to capitalize on the denoising capabilities of conditional GANs, as demonstrated in the Pix2Pix model, while mitigating the need for an exhaustive search for optimal hyperparameters that could potentially ruin the stability of the learning process. In the proposed method, the GAN’s generator is employed to produce denoised images, harnessing the power of a conditional GAN for noise reduction. Simultaneously, the implementation of the Lipschitz continuity constraint during updates, as featured in WGAN-GP, aids in reducing susceptibility to mode collapse. This innovative design allows the proposed model to benefit from the strong points of both Pix2Pix and WGAN-GP, generating superior denoising results while ensuring training stability. Drawing on previous work on image-to-image translation and GAN stabilization techniques, the proposed research highlights the potential of GANs as a general-purpose solution for denoising. The paper details the development and testing of this model, showcasing its effectiveness through numerical experiments. The dataset was created by adding synthetic noise to clean images. Numerical results based on real-world dataset validation underscore the efficacy of this approach in image-denoising tasks, exhibiting significant enhancements over traditional techniques. Notably, the proposed model demonstrates strong generalization capabilities, performing effectively even when trained with synthetic noise.
format Article
id doaj-art-c5cbe80a2d95426baafc506174ef936a
institution OA Journals
issn 2772-9419
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Systems and Soft Computing
spelling doaj-art-c5cbe80a2d95426baafc506174ef936a2025-08-20T01:58:30ZengElsevierSystems and Soft Computing2772-94192024-12-01620012210.1016/j.sasc.2024.200122Novel hybrid integrated Pix2Pix and WGAN model with Gradient Penalty for binary images denoisingLuca Tirel0Ali Mohamed Ali1Hashim A. Hashim2Department of Computer, Control, and Management, University of Rome, Via Ariosto, Rome, ItalyDepartment of Mechanical and Aerospace Engineering, Carleton University, Ottawa, ON, Canada, K1S-5B6Department of Mechanical and Aerospace Engineering, Carleton University, Ottawa, ON, Canada, K1S-5B6; Corresponding author.This paper introduces a novel approach to image denoising that leverages the advantages of Generative Adversarial Networks (GANs). Specifically, we propose a model that combines elements of the Pix2Pix model and the Wasserstein GAN (WGAN) with Gradient Penalty (WGAN-GP). This hybrid framework seeks to capitalize on the denoising capabilities of conditional GANs, as demonstrated in the Pix2Pix model, while mitigating the need for an exhaustive search for optimal hyperparameters that could potentially ruin the stability of the learning process. In the proposed method, the GAN’s generator is employed to produce denoised images, harnessing the power of a conditional GAN for noise reduction. Simultaneously, the implementation of the Lipschitz continuity constraint during updates, as featured in WGAN-GP, aids in reducing susceptibility to mode collapse. This innovative design allows the proposed model to benefit from the strong points of both Pix2Pix and WGAN-GP, generating superior denoising results while ensuring training stability. Drawing on previous work on image-to-image translation and GAN stabilization techniques, the proposed research highlights the potential of GANs as a general-purpose solution for denoising. The paper details the development and testing of this model, showcasing its effectiveness through numerical experiments. The dataset was created by adding synthetic noise to clean images. Numerical results based on real-world dataset validation underscore the efficacy of this approach in image-denoising tasks, exhibiting significant enhancements over traditional techniques. Notably, the proposed model demonstrates strong generalization capabilities, performing effectively even when trained with synthetic noise.http://www.sciencedirect.com/science/article/pii/S2772941924000516Image enhancementGenerative adversarial networkImage denoisingBinary images
spellingShingle Luca Tirel
Ali Mohamed Ali
Hashim A. Hashim
Novel hybrid integrated Pix2Pix and WGAN model with Gradient Penalty for binary images denoising
Systems and Soft Computing
Image enhancement
Generative adversarial network
Image denoising
Binary images
title Novel hybrid integrated Pix2Pix and WGAN model with Gradient Penalty for binary images denoising
title_full Novel hybrid integrated Pix2Pix and WGAN model with Gradient Penalty for binary images denoising
title_fullStr Novel hybrid integrated Pix2Pix and WGAN model with Gradient Penalty for binary images denoising
title_full_unstemmed Novel hybrid integrated Pix2Pix and WGAN model with Gradient Penalty for binary images denoising
title_short Novel hybrid integrated Pix2Pix and WGAN model with Gradient Penalty for binary images denoising
title_sort novel hybrid integrated pix2pix and wgan model with gradient penalty for binary images denoising
topic Image enhancement
Generative adversarial network
Image denoising
Binary images
url http://www.sciencedirect.com/science/article/pii/S2772941924000516
work_keys_str_mv AT lucatirel novelhybridintegratedpix2pixandwganmodelwithgradientpenaltyforbinaryimagesdenoising
AT alimohamedali novelhybridintegratedpix2pixandwganmodelwithgradientpenaltyforbinaryimagesdenoising
AT hashimahashim novelhybridintegratedpix2pixandwganmodelwithgradientpenaltyforbinaryimagesdenoising