Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Non-local mean image denoising method combined with structure information

A non-local mean and structure information technology, applied in the field of image processing, can solve the problems of image pseudo texture, lack of consistency of gray values, poor edge preservation effect, etc., to eliminate pseudo texture, improve edge preservation effect, and clear edge Effect

Active Publication Date: 2013-04-17
XIDIAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Obviously this is counterintuitive, each pixel has a similar gray value to its surrounding neighbors, but the non-local mean method does not take advantage of this, making the gray value of the pixel and its surrounding pixels lack consistency, resulting in denoising Pseudo-texture phenomenon appears in the smooth part of the final image
Moreover, the non-local mean method does not distinguish between image edges and smooth parts, and uses the same similarity measurement method for all pixels, that is, a square window is made with the pixel to be estimated as the center and searched as a similar window, which will result in edge preservation poor effect

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Non-local mean image denoising method combined with structure information
  • Non-local mean image denoising method combined with structure information
  • Non-local mean image denoising method combined with structure information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] refer to figure 1 , the specific implementation steps of the present invention are as follows:

[0024] Step 1, input the test image, add Gaussian white noise to it, and get the noise image.

[0025] The input image is Figure 2 The eight grayscale images shown are: the lena image shown in 2(a), the barbara image shown in 2(b), the boat image shown in 2(c), and the boat image shown in 2(d) The peppers graph shown in 2(e), the zelda graph shown in 2(f), the lighthouse graph shown in 2(g), the couple graph shown in 2(h), each The size of the image is 512×512, the gray level is 256, three experiments are done for each image, and the standard deviations of the added Gaussian white noise are σ=20, σ=35, σ=50 respectively.

[0026] by figure 2( The experiment of the lena map shown in a) is taken as an example, and Gaussian white noise with standard deviation σ=35 is added to the image to obtain the noise image 4(b) of the lena map.

[0027] Step 2, perform two-dimension...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a non-local mean image denoising method combined with structure information, and the method provided by the invention is mainly used for solving the problem of pseudo image traces generated after the non-local means deonising. The non-local mean image denoising method comprises the following steps: (1) inputting an image to be denoised; (2) carrying out two-dimensional stationary wavelet transformation and inverse transformation on the image to obtain a reconstructed image; (3) extracting the structure information of the image by means of primal sketch to obtain a sideridge sketch of the image, and dividing the reconstructed image into a smooth region and a structure region; (4) forming a square window with a pixel as the center in the smooth region so as to search similar pixels, and calculating the similarity weights to re-estimate all of the pixels in the window; (5) forming a window with a pixel as a center along the structure direction of the structure region to search the similar pixels, and calculating the similarity weights to re-estimate all of the pixels in the window; and (6) combining the re-estimation results of the pixels in the smooth regionand the structure region to obtain a final denoised image. The method can be used for natural image denoising.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to an image denoising method, and can be used for denoising natural images. Background technique [0002] Image denoising has always been an important problem in the image processing community. Due to the imperfection of image acquisition equipment, problems in the process of acquisition and transmission, and the interference of some unavoidable natural phenomena, the image data will be polluted by noise. Therefore, image denoising has become a commonly used image preprocessing method in order to improve image quality and image recognizability. Image denoising methods are mainly divided into spatial domain and frequency domain methods. The former does not need to transform the image, and directly denoises the image pixels, such as the classic mean filter, anisotropic filter and bilateral filter. The latter needs to transform the image into the frequency domain first, and then ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00
Inventor 刘芳郝红侠焦李成王爽侯彪戚玉涛尚荣华武杰马文萍王伟伟于昕
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com