Image Denoising Based on GAN with Optimization Algorithm

doi:10.3390/electronics11152445

	Image Denoising Based on GAN with Optimization Algorithm
	Zhu, Min-Ling 1; Zhao, Liang-Liang 1; Xiao, Li 2,3
	2022-08-01
发表期刊	ELECTRONICS
卷号	11 期号:15 页码:12
摘要	Image denoising has been a knotty issue in the computer vision field, although the developing deep learning technology has brought remarkable improvements in image denoising. Denoising networks based on deep learning technology still face some problems, such as in their accuracy and robustness. This paper constructs a robust denoising network based on a generative adversarial network (GAN). Since the neural network has the phenomena of gradient dispersion and feature disappearance, the global residual is added to the autoencoder in the generator network, to extract and learn the features of the input image, so as to ensure the stability of the network. On this basis, we proposed an optimization algorithm (OA), to train and optimize the mean and variance of noise on each node of the generator. Then the robustness of the denoising network was improved through back propagation. Experimental results showed that the model's denoising effect is remarkable. The accuracy of the proposed model was over 99% in the MNIST data set and over 90% in the CIFAR10 data set. The peak signal to noise ratio (PSNR) and structural similarity (SSIM) values of the proposed model were better than the state-of-the-art models in the BDS500 data set. Moreover, an anti-interference test of the model showed that the defense capacities of both the fast gradient sign method (FGSM) and project gradient descent (PGD) attacks were significantly improved, with PSNR and SSIM values decreased by less than 2%.
关键词	image denoising GAN optimization algorithm autoencoder ResNet
DOI	10.3390/electronics11152445
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation[4202025] ; National Natural Science Foundation of China[31900979] ; Promoting the classified development of colleges and universities-the construction of the first level discipline of Computer Science and Technology[5112211036]
WOS研究方向	Computer Science ; Engineering ; Physics
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Physics, Applied
WOS记录号	WOS:000839121100001
出版者	MDPI
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19459
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xiao, Li
作者单位	1.Beijing Informat Sci & Technol Univ, Comp Sch, Beijing 100101, Peoples R China 2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100090, Peoples R China 3.Univ Chinese Acad Sci, Ningbo Huamei Hosp, Ningbo 315010, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Min-Ling,Zhao, Liang-Liang,Xiao, Li. Image Denoising Based on GAN with Optimization Algorithm[J]. ELECTRONICS,2022,11(15):12.
APA	Zhu, Min-Ling,Zhao, Liang-Liang,&Xiao, Li.(2022).Image Denoising Based on GAN with Optimization Algorithm.ELECTRONICS,11(15),12.
MLA	Zhu, Min-Ling,et al."Image Denoising Based on GAN with Optimization Algorithm".ELECTRONICS 11.15(2022):12.