Method for reconstructing single-image super-resolution based on double-layer model

Abstract

The invention discloses a method for reconstructing a single-image super-resolution based on a double-layer model. The method comprises the following steps: (1) using the L0 gradient minimizing method and a HoG operator to generate K training clusters, then training corresponding dictionary pairs of the clusters, (2) selecting a geometrical dictionary pair corresponding to a low-resolution image block for testing in a self-adapting mode according to the HoG operator, solving a high-resolution line detail image corresponding to a low-resolution image, (3) using the L0 gradient minimizing method to solve a high-resolution edge structure image corresponding to the low-resolution image for testing, (4) adding the solved high-resolution line detail image to the high-resolution edge structure image to obtain an initial high-resolution image, and (5) carrying out global restriction and local restriction on the initial high-resolution image to obtain a final high-resolution image. According to the method for reconstructing the single-image super-resolution based on the double-layer model, a reconstructed image contour is clear, detail information is abundant, and quality of the reconstructed image is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image super-resolution reconstruction method, which can be used for super-resolution reconstruction of various natural images. Background technique [0002] Image super-resolution reconstruction can be regarded as an inverse problem of recovering a high-resolution image from one or more low-resolution images. It is widely used in television imaging and other aspects. At present, scholars at home and abroad have done a lot of research work to solve the inverse problem of image super-resolution reconstruction, and proposed many classic algorithms, which can be mainly divided into three categories: interpolation-based, reconstruction-based and learning-based methods, based on The method of interpolation and reconstruction will produce ringing, block effect and image over-smoothing in the process of image reconstruction, and the quality of the reconstructed image will be s...

AI Technical Summary

Problems solved by technology

However, the high-resolution images obtained by this method lack detailed information, and the edges of the images are blurred; after that, Yang et al. proposed to use a sparse representation method to achieve super-resolution reconstruction, first collect the training library (high-low resolution images), and then Train a common dictionary pair (high-low resolution dictionary), and then use this pair of dictionaries to reconstruct a given low resolution image

This method uses the same processing for different components in the image such as edges and textures, which tends to cause the reconstructed image to tend to be blurred in details and edges

Images