Single image super-resolution method based on identical scale structure self-similarity and compressed sensing

Abstract

Disclosed is a single image super-resolution method based on identical scale structure self-similarity and compressed sensing. Firstly, the interpolation is performed for a low-resolution image and a quasi-high-resolution image is obtained; then, the quasi-high-resolution image is divided into quasi-high-resolution image blocks, vectors corresponding to the quasi-high-resolution image blocks serve as a training sample, a sample matrix is assembled, a K-SVD dictionary studying method is used for a solution and a dictionary is obtained; the low-resolution image is divided into low-resolution image blocks; by the aid of a down-sampling matrix, the dictionary and vectors corresponding to all low-resolution image blocks, an orthogonal matching pursuit (OMP) method is used for a solution, and vectors corresponding to high-resolution reconstruction image blocks; and finally, vectors corresponding to high-resolution reconstruction image blocks are assembled and a high-resolution reconstruction image is formed. According to the super-resolution method based on the identical scale structure self-similarity and the compressed sensing, additional information is added in the high-resolution reconstruction image through a compressed sensing frame, and the space resolution is improved.

Description

Technical field [0001] The invention belongs to a super-resolution method, in particular to a single-image super-resolution method based on self-similarity and compressed sensing of the same-scale structure. Background technique [0002] High-resolution images have a wide range of applications in many fields. However, due to the limitations of the manufacturing process and manufacturing costs of imaging equipment, there is a certain resolution limit. The super-resolution method can overcome the resolution limit problem to a certain extent, thus becoming a very effective way to improve the image resolution. The super-resolution method is a technology to obtain high-resolution images through multiple or single low-resolution images. In the process of super-resolution realization, the process of obtaining high-resolution images from low-resolution images is called the reconstruction process. The reconstructed high-resolution image is called the high-resolution reconstructed image. ...

AI Technical Summary

Problems solved by technology

The disadvantage of this dictionary learning sample selection method is that in order to make various image blocks can be well expressed under the dictionary, the size of the dictionary must be large and the efficiency of dictionary learning cannot be guaranteed; in addition, when the image library When the image in the image cannot provide the accurate additional information required by the low-resolution image, the effect of the high-resolution reconstructed image cannot be guaranteed

The super-resolution method based on self-similarity of image structure utilizes similar image blocks in the image, and only uses the low-resolution image itself without the image library, which makes the additional information used in the reconstruction process accurate, but Since such methods need to traverse and search for similar image blocks, the computational efficiency is not high

The super-resolution method based on compressed sensing and the super-resolution method based on image structure self-similarity have their own advantages and disadvantages, and there is no super-resolution method that effectively combines these two methods

Images