GAN image processing method and system

Abstract

The application discloses a GAN image processing method and system. The method comprises the steps of receiving random noise, and generating a generative image by using a generative network based on an improved LSGAN; receiving a real image, and performing image gradient transformation of different degrees on the real image and the generative image respectively to obtain a transformed image set; and inputting transformed images in the transformed image set respectively into channels of a multi-channel convolutional network of a discrimination network, and extracting and fusing features to obtain an output result. In this application, the random noise is input to the generative network to generate the generative image, then the real image is received, the image gradient transformation of different degrees are respectively performed on the real image and the generative image to obtain the transformed image set, the transformed images in the transformed image set are input respectively into the channels of the multi-channel convolutional network of the discrimination network, extraction and fusion of features are performed to obtain the output result, the network is allowed to have a good generalization ability, the phenomenon of gradient disappearance avoided, and more realistic pictures with higher quality can be output.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to a GAN image processing method and system. Background technique [0002] GAN (Generative Adversarial Nets, Generative Adversarial Nets) is inspired by the two-person zero-sum game in game theory. Since Ian Goodfellow published the paper Generative Adversarial Nets in 2014, the Generative Adversarial Nets has attracted wide attention. The new favorite in the field of machine learning. [0003] In the prior art, GAN can be a discriminator that uses the sigmoid cross-entropy loss function as a classifier. However, this loss function may be prone to gradient disappearance during the learning process. The GAN model training is unstable and the generalization ability is not good. It is difficult to Convergence and other issues. Contents of the invention [0004] In view of this, the purpose of the present invention is to provide a GAN image processing method and system to imp...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, GAN can be a discriminator that uses the sigmoid cross-entropy loss function as a classifier. However, this loss function may be prone to gradient disappearance during the learning process. The GAN model training is unstable and the generalization ability is not good. It is difficult to Convergence and other issues

Images