Super-resolution image reconstruction method and device, medium and computing equipment

Abstract

The invention provides a super-resolution image reconstruction method and device, a medium and computing equipment. The method comprises the steps that the brightness image and the color image of an original image are extracted; up-sampling processing is performed on the brightness image so as to obtain a first brightness image; the first brightness image is inputted to N layers of convolutional neutral networks which are obtained pre-training and used for outputting high-frequency images, N layers of convolutional forward processing is performed on the first brightness image in the N layers of convolutional neutral networks and a first high-frequency image is obtained, wherein N is an integer greater than 3; the first brightness image is fused with the first high-frequency image so as toobtain a second brightness image; and the second brightness image is fused with the color image so as to obtain the super-resolution image of the original image. The super-resolution image of the original image obtained through reconstruction can include more image details so that the super-resolution image effect is great.

Description

Technical field [0001] The present invention relates to the technical field of image processing, in particular to a super-resolution image reconstruction method, device, medium and computing equipment. Background technique [0002] At present, the image super-resolution reconstruction technology refers to the digital image processing technology that produces high-resolution and high-quality images from one or more low-resolution and low-quality images. The resolution of a digital image here refers to the spatial resolution of the image, that is, the number of pixels per inch of the image, and the unit of resolution is dpi (dots per inch). It is not difficult to understand that the greater the resolution, the greater the amount of image information and the clearer the image. Obtaining higher-resolution images from low-resolution images is a "out of nothing" process, that is, to estimate more information from the existing information. [0003] As a method that can significantly imp...

AI Technical Summary

Problems solved by technology

[0006] The present invention provides a super-resolution image reconstruction method, device, medium and computing equipment, which are used to solve the problem that the super-resolution image reconstructed by the non-uniform interpolation method in the prior art has poor effect, and the obtained super-resolution image has The jagged effect and the blurred super-resolution image cannot meet the actual needs

Images