Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images

Image denoising and image super-resolution reconstruction are two important techniques for image processing. Deep learning is used to solve the problem of image denoising and super-resolution reconstruction in recent years, and it usually has better results than traditional methods. However, image d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Size Li, Pengjiang Qian, Xin Zhang, Aiguo Chen
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Telecommunication TK5101-6720
Acceso en línea:	https://doaj.org/article/d0e7158d6ed340ea8169fdb17d50c3ec
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d0e7158d6ed340ea8169fdb17d50c3ec
record_format	dspace
spelling	oai:doaj.org-article:d0e7158d6ed340ea8169fdb17d50c3ec2021-11-15T01:20:16ZResearch on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images1875-905X10.1155/2021/5184688https://doaj.org/article/d0e7158d6ed340ea8169fdb17d50c3ec2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/5184688https://doaj.org/toc/1875-905XImage denoising and image super-resolution reconstruction are two important techniques for image processing. Deep learning is used to solve the problem of image denoising and super-resolution reconstruction in recent years, and it usually has better results than traditional methods. However, image denoising and super-resolution reconstruction are studied separately by state-of-the-art work. To optimally improve the image resolution, it is necessary to investigate how to integrate these two techniques. In this paper, based on Generative Adversarial Network (GAN), we propose a novel image denoising and super-resolution reconstruction method, i.e., multiscale-fusion GAN (MFGAN), to restore the images interfered by noises. Our contributions reflect in the following three aspects: (1) the combination of image denoising and image super-resolution reconstruction simplifies the process of upsampling and downsampling images during the model learning, avoiding repeated input and output images operations, and improves the efficiency of image processing. (2) Motivated by the Inception structure and introducing a multiscale-fusion strategy, our method is capable of using the multiple convolution kernels with different sizes to expand the receptive field in parallel. (3) The ablation experiments verify the effectiveness of each employed loss measurement in our devised loss function. And our experimental studies demonstrate that the proposed model can effectively expand the receptive field and thus reconstruct images with high resolution and accuracy and that the proposed MFGAN method performs better than a few state-of-the-art methods.Size LiPengjiang QianXin ZhangAiguo ChenHindawi LimitedarticleTelecommunicationTK5101-6720ENMobile Information Systems, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Telecommunication TK5101-6720
spellingShingle	Telecommunication TK5101-6720 Size Li Pengjiang Qian Xin Zhang Aiguo Chen Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images
description	Image denoising and image super-resolution reconstruction are two important techniques for image processing. Deep learning is used to solve the problem of image denoising and super-resolution reconstruction in recent years, and it usually has better results than traditional methods. However, image denoising and super-resolution reconstruction are studied separately by state-of-the-art work. To optimally improve the image resolution, it is necessary to investigate how to integrate these two techniques. In this paper, based on Generative Adversarial Network (GAN), we propose a novel image denoising and super-resolution reconstruction method, i.e., multiscale-fusion GAN (MFGAN), to restore the images interfered by noises. Our contributions reflect in the following three aspects: (1) the combination of image denoising and image super-resolution reconstruction simplifies the process of upsampling and downsampling images during the model learning, avoiding repeated input and output images operations, and improves the efficiency of image processing. (2) Motivated by the Inception structure and introducing a multiscale-fusion strategy, our method is capable of using the multiple convolution kernels with different sizes to expand the receptive field in parallel. (3) The ablation experiments verify the effectiveness of each employed loss measurement in our devised loss function. And our experimental studies demonstrate that the proposed model can effectively expand the receptive field and thus reconstruct images with high resolution and accuracy and that the proposed MFGAN method performs better than a few state-of-the-art methods.
format	article
author	Size Li Pengjiang Qian Xin Zhang Aiguo Chen
author_facet	Size Li Pengjiang Qian Xin Zhang Aiguo Chen
author_sort	Size Li
title	Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images
title_short	Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images
title_full	Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images
title_fullStr	Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images
title_full_unstemmed	Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images
title_sort	research on image denoising and super-resolution reconstruction technology of multiscale-fusion images
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/d0e7158d6ed340ea8169fdb17d50c3ec
work_keys_str_mv	AT sizeli researchonimagedenoisingandsuperresolutionreconstructiontechnologyofmultiscalefusionimages AT pengjiangqian researchonimagedenoisingandsuperresolutionreconstructiontechnologyofmultiscalefusionimages AT xinzhang researchonimagedenoisingandsuperresolutionreconstructiontechnologyofmultiscalefusionimages AT aiguochen researchonimagedenoisingandsuperresolutionreconstructiontechnologyofmultiscalefusionimages
_version_	1718428897227309056

Research on Image Denoising and Super-Resolution Reconstruction Technology of Multiscale-Fusion Images

Ejemplares similares