Noise-robustness image similarity distinguishing method

Abstract

The invention discloses a noise-robustness image similarity distinguishing method, and belongs to the field of digital image processing. By the noise-robustness image similarity distinguishing method, images with large noises can be matched with accurate image blocks, the image matching accuracy is improved, and image processing methods such as image stitching and image denoising which are based on block matching can be implemented. A noise-robustness similarity distinguishing function is established by a low-rank matrix decomposition theory which is rapidly developed recently, influences of irregular disturbance such as noises on similarity distinguishing are eliminated, and distinguishing effectiveness under the condition of large noises can be guaranteed.

Description

technical field [0001] The invention belongs to the field of digital image processing, especially for the problem of matching and similarity evaluation of image blocks obtained under the condition of large noise. The low-rank matrix decomposition theory is used to transform the similarity judgment of image blocks into the rank characteristics of the matrix, and specifically relates to A Noise-Robust Image Similarity Discrimination Method. Background technique [0002] As a basic method in the field of image processing, image block matching technology has important applications in the fields of image stitching, image denoising, etc. Among them, image block similarity discrimination is a key theoretical part of image block matching. Generally, the image similarity discrimination method refers to a class of functions that can quantify the degree of similarity between two image regions, and select the most similar image region in the two frames of images that conforms to the hab...

AI Technical Summary

Problems solved by technology

However, under the condition of noise or extremely noise, the existence of noise will bring great disturbance to the image signal, even subversive influence, thus seriously affecting the similarity judgment

According to the low-rank theory, due to rich local regularity, global symmetry, repeated textures, redundant sampling, etc., there will be low-rank characteristics in visual data such as images and videos.

Images