An image super-resolution reconstruction method

Abstract

The invention discloses an image super-resolution reconstruction method. The method comprises the following steps: making a learning sample set; Learning and training: a single-frame model of the convolutional neural network is adopted as a recurrent network module, a super-resolution mapping model of a recurrent neural network mode comprising N + 1 recurrent network modules is constructed, and inthe training process, a single lowest-resolution image is input into each recurrent network module in the super-resolution mapping model for single-time training; Replacing a low-resolution picture and repeatedly carrying out the single training; Carrying out single training for multiple times; And reconstruction: inputting the low-resolution image to be reconstructed into the trained super-resolution mapping model to obtain a high-resolution image. According to the method, the model is guided to learn low-frequency and high-frequency information of the image at the same time by adding the output error items related to the blurred image in the performance indexes, so that the image super-resolution reconstruction result can give consideration to reliability and details; And meanwhile, thestorage space can be greatly saved through the super-resolution mapping model in a cyclic network form.

Description

technical field [0001] The invention belongs to the technical field of software and relates to image processing technology, in particular to an image super-resolution reconstruction method. Background technique [0002] Image super-resolution reconstruction technology is a means of generating high-resolution images from low-resolution images, and has great application value in medical images, satellite photography, security monitoring and other fields. Super-resolution reconstruction techniques can be divided into three categories: interpolation-based methods, model-based methods, and learning-based methods. Among them, the learning-based method is the current mainstream direction, especially with the continuous development of deep learning technology and convolutional neural network, the image quality of super-resolution reconstruction is also improving. It learns image features and a low-resolution to high-resolution mapping model through a large number of pairs of low-re...

AI Technical Summary

Problems solved by technology

This method relies too much on the sample library without introducing some basic principles of human cognition to images. However, due to the complexity and diversity of images, it is difficult for the sample library to ensure sufficient distribution in various image details. In this case The model trained in the next step should also emphasize the sharpness of the image, that is, it is exactly the same as the original image, and it is easy to cause obvious errors in supplementary pixels.

Images