Adversarial Gaussian Denoiser for Multiple-Level Image Denoising
Image denoising is a challenging task that is essential in numerous computer vision and image processing problems. This study proposes and applies a generative adversarial network-based image denoising training architecture to multiple-level Gaussian image denoising tasks. Convolutional neural netwo...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/9/2998 |
id |
doaj-d93e9df9bbde4ee09376cd655a35bd54 |
---|---|
record_format |
Article |
spelling |
doaj-d93e9df9bbde4ee09376cd655a35bd542021-04-24T23:02:52ZengMDPI AGSensors1424-82202021-04-01212998299810.3390/s21092998Adversarial Gaussian Denoiser for Multiple-Level Image DenoisingAamir Khan0Weidong Jin1Amir Haider2MuhibUr Rahman3Desheng Wang4School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaDepartment of Intelligent Mechatronics Engineering, Sejong University, Seoul 05006, KoreaDepartment of Electrical Engineering, Polytechnique Montreal, Montreal, QC H3T 1J4, CanadaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, ChinaImage denoising is a challenging task that is essential in numerous computer vision and image processing problems. This study proposes and applies a generative adversarial network-based image denoising training architecture to multiple-level Gaussian image denoising tasks. Convolutional neural network-based denoising approaches come across a blurriness issue that produces denoised images blurry on texture details. To resolve the blurriness issue, we first performed a theoretical study of the cause of the problem. Subsequently, we proposed an adversarial Gaussian denoiser network, which uses the generative adversarial network-based adversarial learning process for image denoising tasks. This framework resolves the blurriness problem by encouraging the denoiser network to find the distribution of sharp noise-free images instead of blurry images. Experimental results demonstrate that the proposed framework can effectively resolve the blurriness problem and achieve significant denoising efficiency than the state-of-the-art denoising methods.https://www.mdpi.com/1424-8220/21/9/2998image denoisingresidual learning image denoising (RLID), direct image denoising (DID)convolutional neural networks (CNNs), generative adversarial network (GAN) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Aamir Khan Weidong Jin Amir Haider MuhibUr Rahman Desheng Wang |
spellingShingle |
Aamir Khan Weidong Jin Amir Haider MuhibUr Rahman Desheng Wang Adversarial Gaussian Denoiser for Multiple-Level Image Denoising Sensors image denoising residual learning image denoising (RLID), direct image denoising (DID) convolutional neural networks (CNNs), generative adversarial network (GAN) |
author_facet |
Aamir Khan Weidong Jin Amir Haider MuhibUr Rahman Desheng Wang |
author_sort |
Aamir Khan |
title |
Adversarial Gaussian Denoiser for Multiple-Level Image Denoising |
title_short |
Adversarial Gaussian Denoiser for Multiple-Level Image Denoising |
title_full |
Adversarial Gaussian Denoiser for Multiple-Level Image Denoising |
title_fullStr |
Adversarial Gaussian Denoiser for Multiple-Level Image Denoising |
title_full_unstemmed |
Adversarial Gaussian Denoiser for Multiple-Level Image Denoising |
title_sort |
adversarial gaussian denoiser for multiple-level image denoising |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-04-01 |
description |
Image denoising is a challenging task that is essential in numerous computer vision and image processing problems. This study proposes and applies a generative adversarial network-based image denoising training architecture to multiple-level Gaussian image denoising tasks. Convolutional neural network-based denoising approaches come across a blurriness issue that produces denoised images blurry on texture details. To resolve the blurriness issue, we first performed a theoretical study of the cause of the problem. Subsequently, we proposed an adversarial Gaussian denoiser network, which uses the generative adversarial network-based adversarial learning process for image denoising tasks. This framework resolves the blurriness problem by encouraging the denoiser network to find the distribution of sharp noise-free images instead of blurry images. Experimental results demonstrate that the proposed framework can effectively resolve the blurriness problem and achieve significant denoising efficiency than the state-of-the-art denoising methods. |
topic |
image denoising residual learning image denoising (RLID), direct image denoising (DID) convolutional neural networks (CNNs), generative adversarial network (GAN) |
url |
https://www.mdpi.com/1424-8220/21/9/2998 |
work_keys_str_mv |
AT aamirkhan adversarialgaussiandenoiserformultiplelevelimagedenoising AT weidongjin adversarialgaussiandenoiserformultiplelevelimagedenoising AT amirhaider adversarialgaussiandenoiserformultiplelevelimagedenoising AT muhiburrahman adversarialgaussiandenoiserformultiplelevelimagedenoising AT deshengwang adversarialgaussiandenoiserformultiplelevelimagedenoising |
_version_ |
1721510921955704832 |