Image super-resolution method based on generative adversarial network

Abstract

The invention discloses an image super-resolution method based on a generative adversarial network. The method comprises the following steps: obtaining a training data set and a verification data set;constructing an image super-resolution model, wherein the image super-resolution model comprises a generation network model and a discrimination network model; initializing weights of the establishedgenerative network model and the discriminant network model, initializing the network model, selecting an optimizer, and setting network training parameters; simultaneously training the generative network model and the discriminant network model by using a loss function until the generative network and the discriminant network reach Nash equilibrium; obtaining a test data set and inputting the test data set into the trained generative network model to generate a super-resolution image; and calculating a peak signal-to-noise ratio between the generated super-resolution image and a real high-resolution image, calculating an evaluation index of the image reconstruction quality of the generated image, and evaluating the reconstruction quality of the image. According to the method, the performance of reconstructing the super-resolution image by the network is improved by optimizing the network structure, and the problem of image super-resolution is solved.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to an image super-resolution method based on a Generative Adversarial Network (GAN). Background technique [0002] In daily production and life, images are an important information carrier, and image resolution is one of the important criteria for measuring image quality. High-resolution images contain more texture features and can provide more information, so people hope to obtain high-resolution images in production and life. However, due to the unevenness of imaging equipment and the loss of image information during network transmission, image super-resolution can be used to improve image resolution with lower cost, better effect, and easier implementation. Therefore, image super-resolution is more practical, and it is of great significance to the research of image super-resolution tasks. [0003] Image super-resolution methods are mainly divided into three types: interpolation-b...

AI Technical Summary

Problems solved by technology

The invention solves the problem of image super-resolution through an improved generative confrontation network, uses a discriminant network to supervise the generation network, and makes the generation network generate super-resolution images closer to real images

Images