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

MCMC sampling and threshold low-rank approximation-based image de-noising method

A low-threshold, image technology, used in image enhancement, image data processing, instruments, etc., can solve the problem of high complexity of dictionary training

Inactive Publication Date: 2016-01-20
EAST CHINA JIAOTONG UNIVERSITY
View PDF1 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to combine the advantages of the above-mentioned denoising method and address its shortcomings, and propose an image denoising method based on Markov Monte Carlo sampling and adaptive threshold low-rank approximation, combining the characteristics of non-local similarity and low-rank approximation The advantages of dealing with high-dimensional data overcome the problem of high complexity of dictionary training

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
  • MCMC sampling and threshold low-rank approximation-based image de-noising method
  • MCMC sampling and threshold low-rank approximation-based image de-noising method
  • MCMC sampling and threshold low-rank approximation-based image de-noising method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] specific implementation

[0042] Refer to the attached figure 1 , the implementation steps of the present invention are as follows:

[0043] Step 1, input a noisy image Y with N rows and M columns:

[0044] Step 2, set parameters:

[0045] Observation image Y∈R m×n , s j represents the sample point, S j means s j set, m 0 represents the number of sample points, σ s represents the spatial variance, represents the desired image, N represents the additive noise, and Ψ represents the similarity evaluation function;

[0046] Step 3, using the block histogram multiple statistical feature similarity criteria to perform Markov Monte Carlo sampling, that is, for each point s in the observed image Y j Perform an iterative operation to obtain clusters of similar matching blocks;

[0047] 3a) Initialization parameters: S j =φ, s j =s j0 , k=1;

[0048] 3b) Take points for the entire image:

[0049] According to Gaussian suggestive distribution Q ...

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 an MCMC sampling and threshold low-rank approximation-based image de-noising method. According to the method, firstly, during the denoising process, an image block is generated through the MONTE-CARLO sampling process. Secondly, based on a plurality of statistical features in a histogram, a similarity judging function that meets the condition of the Markov chain can be obtained. Thirdly, the singular value decomposition on all kinds of image block clusters is conducted and the self-adaptive threshold estimation for singular values is conducted according to the prior information corresponding to an image. Fourthly, on the basis of a decomposed low-rank structure, the image reconstruction is conducted according to the low-rank approximation algorithm, so that the de-noising purpose is realized. According to the invention, the characteristics of the similar non-local geometric structure information of images and the better treatment of high-dimensional data based on a low-rank matrix are fully utilized. Meanwhile, the defect in the prior art that the conventional non-local mean-value traversing search method is high in block-selecting complexity can be overcome. The block-selecting robustness is therefore improved. moreover, to a certain extent, the algorithm operating period is shortened.

Description

technical field [0001] The invention relates to an image denoising method based on MCMC sampling and threshold low-rank approximation, and belongs to the technical field of video image data processing. Background technique [0002] Image is the most commonly used information carrier in human activities, and has become the main way for people to obtain original information from the outside world. However, complex monitoring scenes, harsh weather conditions, changes in illumination, and the accuracy of acquisition equipment can easily cause images to be seriously polluted by noise, blurred visual effects, and difficult to distinguish target features, which will affect the subsequent processing of images and cannot meet the application environment. demand. Therefore, as an indispensable link in image preprocessing, image denoising plays a great role in subsequent image feature extraction, segmentation, compression, etc., which can make the image more realistically restored and...

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): G06T5/40
Inventor 罗晖徐瑶王玮王培东
Owner EAST CHINA JIAOTONG UNIVERSITY
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