Local and non-local combined self-adaption image denoising method

A non-local, adaptive technology, applied in the field of image processing, can solve the problems of not being able to effectively approach image edge and detail information, loss of edge and texture details, etc., to reduce the impact, maintain edge and texture details, and strong sparse capabilities Effect

Inactive Publication Date: 2013-05-01
XIDIAN UNIV
View PDF2 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that the discrete cosine transform DCT dictionary is used for image block sparse approximation. Since the dictionary is a fixed diction

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
  • Local and non-local combined self-adaption image denoising method
  • Local and non-local combined self-adaption image denoising method
  • Local and non-local combined self-adaption image denoising method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The specific implementation and effects of the present invention will be further described in detail below with reference to the accompanying drawings.

[0037] Reference figure 1 , The implementation steps of the present invention are as follows:

[0038] Step 1. Input a noisy image Y with N rows and M columns, and set the maximum number of iterations γ and the stop parameter δ. The value ranges of γ and δ are respectively 9-15 and 0.01-0.03. In this example, γ and δ The values ​​of are 12 and 0.02 respectively.

[0039] Step 2. Use the following formula to estimate the noise standard deviation σ of the noisy image Y n :

[0040] σ n = median ( abs | W | ) 0.6745 ,

[0041] Among them, W is the first layer of high-frequency coefficients obtained by wavelet decomposition of the noisy image Y, abs|·| is an absolute value operation, and median(·) is a median value operation.

[0042] Step 3. Take any pixel in the noisy image Y as the center, and...

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 local and non-local combined self-adaption image denoising method, mainly solving the problem of poor denoising effect of the prior denoising method. The method comprises the steps of: (1) inputting noisy images; (2) estimating the noise standard deviation of the noisy images; (3) extracting pixel vectors by taking any pixel of the noisy images as a center, and calculating a pixel vector non-local mean value; (4) performing the step 3 on all pixels of the noisy images; (5) clustering all of the pixel vectors and training dictionaries on each type of vector subset; (6) respectively performing self-adaption denoising on all of the pixel vectors; (7) pulling all of the denoised pixel vectors into image blocks and clustering to obtain denoised images; (8) judging if the iteration is finished, if so, outputting the denoised images, and if not so, transferring the denoised images as the noisy images into the step 2 for the next iteration. According to the method disclosed by the invention, noise of natural images containing the white Gaussian noise is effectively eliminated, and the method is available for digital image processing in the fields of medical images, video multi-media, and the like.

Description

Technical field [0001] The invention belongs to the technical field of image processing, and specifically is an adaptive image denoising method combining local and non-local, which can be used for digital image preprocessing in the fields of medical imaging, astronomical imaging, video multimedia and the like. Background technique [0002] Image denoising technology solves the problem of image quality degradation caused by various noise interference in the process of image acquisition, encoding, and transmission, and improves image quality. It is an important link and research content in image processing. [0003] Image denoising technology is roughly carried out from both the spatial domain and the transform domain. At present, the best spatial filtering methods include non-local mean filtering denoising method NLM, image denoising method KSVD under sparse representation, etc., better transform Domain filtering methods include three-dimensional block matching denoising method BM3D...

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
IPC IPC(8): G06T5/00
Inventor 王桂婷焦李成丁炜马文萍马晶晶钟桦
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap