Super-resolution image reconstruction method based on progressive deep residual network

Abstract

The invention provides a super-resolution image reconstruction method based on a progressive deep residual network, and the method mainly comprises the following steps: (1) selecting a training data set and a test data set, carrying out the rotating and scaling of a training data set image, and expanding the training data set image; (2) carrying out down-sampling processing on the obtained training data set image; (3) respectively cutting the original training data set image and the low-resolution image in the step 2 into image blocks; (4) taking the original image block and the low-resolutionimage block corresponding to the same position in the step (3) as a high-resolution / low-resolution sample pair, and generating a training data set file with a format of HDF5; (5) establishing a progressive deep residual network; (6) training a progressive deep residual network; and (7) inputting the low-resolution image into the progressive deep residual network model, and outputting to obtain areconstructed high-resolution image.

Description

technical field [0001] The invention belongs to the technical field of image digital processing, and relates to a super-resolution image reconstruction method based on a progressive deep residual network. Background technique [0002] With the continuous advancement of image and video digital processing technology, people always expect higher quality images. The factors affecting image quality are mainly divided into two parts. One is objective factors such as inaccurate focus, artificial jitter, and object movement in the process of generating images in the early stage; the other is possible noise signal processing and under-sampling effects during image transmission and storage. image quality degradation. An important indicator for evaluating image quality is image resolution. The higher the resolution, the greater the pixel density of the image, the greater the number of pixels per unit area, the more detailed information provided, and the better the image quality. [...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the problems existing in the prior art, and to provide a super-resolution image reconstruction method based on a progressive deep residual network, which can solve the problems caused by the existing method because the reconstructed image is only up-sampled once. A large amount of image detail information is lost, and a clear high-resolution image can still be reconstructed under a large zoom factor

Images