Image super-resolution method and system

Abstract

The invention discloses an image super-resolution method comprising the following steps of: acquiring an original image, up-sampling the original image to obtain an initial result; filtering the sampled initial result by using a plurality of impact filter waves to obtain an intermediate result; and carrying out reconstruction constraint on the intermediate result to obtain a high-resolution image. Image space information and strength information are simultaneously considered in the up-sampling algorithm, and current pixels are smoothed by using a bilateral filtering method; the impact filter waves can enhance the edge of the image; and finally reconstruction is carried out to obtain the high-resolution image. Therefore, the generated high-resolution image has smooth transition and can effectively avoid obvious boundary flaws. In addition, the invention provides an image super-resolution system.

Description

【Technical field】 [0001] The invention relates to image processing technology, in particular to an image super-resolution method and system. 【Background technique】 [0002] Image super-resolution algorithms have many important applications in the multimedia field, such as playing low-resolution videos on high-resolution hardware devices. Although there are many super-resolution algorithms, the super-resolution problem has not been well solved. The generation of low-resolution images can be considered to be obtained by smoothing and downsampling of high-resolution images, so a low-resolution image can be used to reconstruct a corresponding high-resolution image. This algorithm is called image super-resolution algorithm. Traditional image super-resolution methods can be divided into three categories: interpolation-based, reconstruction-based, and learning-based. [0003] However, in these traditional image super-resolution methods, the interpolation-based algorithm does not ...

AI Technical Summary

Problems solved by technology

[0003] However, in these traditional image super-resolution methods, the interpolation-based algorithm does not introduce high-frequency information from the high-resolution image, so the final high-resolution image is too smooth and there are jagged flaws at the edge of the image; the disadvantage of the reconstruction-based method is the artificially imposed The image prior is not necessarily suitable for any image, so high-resolution images often have many defects, such as ringing effects; the time complexity of learning-based algorithms is relatively high

Also, due to insufficient training samples, high-frequency artifacts often appear in the results based on learning algorithms

[0004] Therefore, none of the above three traditional image super-resolution methods can solve the problem of image boundary defects well.

Images