WGAN-Based Image Denoising Algorithm

Traditional image denoising algorithms are generally based on spatial domains or transform domains to denoise and smooth the image. The denoised images are not exhaustive, and the depth-of-learning algorithm has better denoising effect and performs well while retaining the original image texture det...

Full description

Saved in:
Bibliographic Details
Published in:Journal of global information management 2022-04, Vol.30 (9), p.1-20
Main Authors: Zou, XiuFang, Zhu, Dingju, Huang, Jun, Lu, Wei, Yao, Xinchu, Lian, Zhaotong
Format: Article
Language:English
Subjects:
Algorithms
Deep learning
Image enhancement
Image reconstruction
Information management
Machine learning
Neural networks
Noise
Noise reduction
Texture
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Traditional image denoising algorithms are generally based on spatial domains or transform domains to denoise and smooth the image. The denoised images are not exhaustive, and the depth-of-learning algorithm has better denoising effect and performs well while retaining the original image texture details such as edge characters. In order to enhance denoising capability of images by the restoration of texture details and noise reduction, this article proposes a network model based on the Wasserstein GAN. In the generator, small convolution size is used to extract image features with noise. The extracted image features are denoised, fused and reconstructed into denoised images. A new residual network is proposed to improve the noise removal effect. In the confrontation training, different loss functions are proposed in this paper.
ISSN:1062-7375
1533-7995
DOI:10.4018/JGIM.300821