Shape-adaptive non-local mean denoising method

Abstract

The invention discloses a shape-adaptive non-local mean denoising method, which mainly solves the problem of inaccurate similarity calculation during non-local mean denoising of a natural image in the prior art. The method comprises the following steps of: (1) acquiring a similar point set based on a shape-adaptive regional mean in allusion to each pixel to be estimated in an input noisy natural image; (2) respectively calculating weights of all the pixels in the set based on the block average Euclidean distance and the shape-adaptive region average Euclidean distance; (3) performing weightedaverage on all the pixels in the set according to two weights to acquire a recovery value of the current pixel; and (4) solving the recovery values of the pixels to be estimated and substituting a gray value of the original image according to the steps to acquire a denoising map of the image. The comprehensive performance of the method is superior to that of other denoising methods, and the method can be used for smoothing noise better, maintaining details such as edges, textures and the like of the natural image and denoising the natural image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a shape-adaptive non-local mean value denoising method, which can be used for denoising processing of natural images. Background technique [0002] Images are the most important means for people to understand the objective world. In digital image processing, due to the limitations of imaging methods and conditions and external interference, image signals are inevitably polluted by noise. Important information such as edges and detail features in the image are often lost in the noise, which has a great impact on the subsequent processing of the image, such as edge detection, image segmentation, image matching, etc., so it is necessary to denoise the image in the preprocessing stage. Image denoising is a widely used technology in image preprocessing. How to better preserve the texture details of images while filtering out image noise has become the central issue in the fiel...

AI Technical Summary

Problems solved by technology

Due to the good performance of this method in the field of denoising, it has attracted widespread attention from many scholars since it was proposed, but it still has the following problems: 1: The complexity of the algorithm is relatively large; 2: The accuracy of weight calculation is not good; 3: The edges and details of the image are still somewhat blurred

However, these algorithms calculate the similarity of pixels based on the Euclidean distance between square blocks. For example, the most commonly used non-local mean denoising is 7*7 blocks, which mainly reflect the structural information of pixels. , good similarity calculation results can be obtained in the smooth area of ​​the image, but the homogeneous information similarity is ignored for point targets and edge areas, and the similarity calculation based only on structural information is not accurate, so the final denoising As a result, the edge or texture information of the image is often blurred, which will lead to deviations in our subsequent analysis and processing of image details.

Images