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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.