GAN image denoising algorithm fused with improved residual network

Abstract

The invention provides a GAN image denoising algorithm fused with an improved residual network. The GAN image denoising algorithm comprises: S1, preprocessing a data set image; S2, extracting features of the noisy image by a generator to generate a de-noised image; S3, judging the input image by the discriminator, and outputting a judgment result; and S4, performing alternate iteration training on the processes according to a loss function. Compared with a traditional residual network, the multi-layer residual feature extraction network creatively used in the invention retains the advantages of the original residual network, that is, the problem of gradient disappearance or explosion caused by a single-stack convolutional neural network is solved, meanwhile, the multi-layer residual feature extraction network also realizes the extraction of deep-level features and shallow-level detail feature information of the input picture, and the residual network used in the invention also reduces model network parameters. According to the invention, the dual-channel discriminator construction model is used, so that the discrimination capability of the discriminator can be well improved, the generator G can be well trained, and a picture with a better denoising effect can be generated.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a target image denoising algorithm based on a generative confrontation network. Background technique [0002] In recent years, the rapid progress of image processing technology has attracted continuous attention in the application fields of medical imaging, satellite remote sensing and intelligent monitoring. In the applications in the above fields, image acquisition technology is required, but in the process of image acquisition and transmission, the images will be polluted or even damaged to varying degrees, and the use of high-quality images is the premise of all image processing technologies. Therefore, how to remove the pollution and damage to the greatest extent during image collection and transportation without damaging the image information, so as to restore the ideal high-quality lossless image has become a hot issue in various fields. . [0003] In order to...

AI Technical Summary

Problems solved by technology

However, the generator model of the DeblurGAN algorithm only uses a 9-layer residual network structure. Although this design reduces the model network parameters very well, it tends to reduce the receptive field of the generator model, so that the entire generator cannot fully extract the image. Detailed features, resulting in the loss of detailed texture of the generated image, which ultimately affects the reconstruction effect of the image

Images