Local rank priori based single-image super-resolution reconstruction method

Abstract

The invention provides a local rank priori based single-image super-resolution reconstruction method. The method is characterized by comprising the following steps: performing the learning method to obtain local priori information of a high-resolution image; limiting a local rank of the high-resolution image to be reconstructed through minimum energy functions according to the priori information; converting the minimum energy functions into a reconstruction model under the limitation of the local rank. According to the method, a local and non-local combined optimization model is proposed according to the non-local characteristics of the image; a local-rank-base optimized weight calculation method is also proposed for obtaining higher non-local weight. With the adoption of the method, the high-resolution image with more details can be reconstructed well by utilizing the reconstruction model; in addition, the flaws of a reconstructed image can be reduced, and the side edge of the image can be sharpened.

Description

technical field [0001] The invention belongs to the technical field of computer image processing, and relates to a method for super-resolution reconstruction of a single image. Background technique [0002] In the process of acquiring visual images, there are many factors that cause the degradation of image quality. The influencing factors include: system aberration, defocus, air disturbance and the existence of noise. Therefore, in many digital image applications, people expect images with high resolution. Image super-resolution refers to recovering a high-resolution image from a low-resolution image or image sequence. It has a wide range of applications in computer vision, satellite remote sensing, astronomy, biomedical imaging, civil security and other fields. There are two ways to increase image resolution: improving hardware conditions and image processing. If we start from improving hardware facilities, we can do two aspects of work: 1. Improve the physical charact...

AI Technical Summary

Problems solved by technology

However, the disadvantage of this approach is that increasing the chip area will lead to a decrease in the charge transfer rate, and reducing the size of the pixel will reduce the amount of light received by the unit pixel, thereby increasing the impact of shot noise on the imaging unit, which in turn will lead to a decrease in the quality of the imaging image. A sharp decline

[0003] However, the effect of sparse representation-based methods places high demands on the image library used for dictionary training

If the selected training image library is not good, the reconstructed high-resolution image will have artifacts, and the edges and details will not be sharp and prominent

Images