Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multiplicative noise removal method based on non-local adaptive dictionary

An adaptive dictionary and multiplicative noise technology, applied in image data processing, instrumentation, computing, etc., can solve the problem of insufficient edge, detail and texture information of the image preserved by the denoising algorithm, so as to effectively remove noise and reduce work Amount, enhance the effect of removal and texture features

Active Publication Date: 2016-12-07
GUILIN UNIV OF ELECTRONIC TECH
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is that the existing denoising algorithm still has insufficient problems in retaining the edge, detail and texture information of the image, and provides a multiplicative noise removal method based on a non-local adaptive dictionary

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
  • Multiplicative noise removal method based on non-local adaptive dictionary
  • Multiplicative noise removal method based on non-local adaptive dictionary
  • Multiplicative noise removal method based on non-local adaptive dictionary

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Multiplicative noise removal methods based on non-locally adaptive dictionaries, such as figure 1 shown, including the following steps:

[0032] Step 1. Obtain a natural image in the standard image library and add noise to the image.

[0033] Obtain natural images in the standard image library. The size of the images is all 256×256, and the gray value is between 0-255. Add multiplicative noise that obeys the Gamma distribution to each standard image. The noise is divided into 3 levels, namely Visual number L=4,10,16.

[0034] Step 2, transform the noisy image into the logarithmic domain.

[0035] In order to make the image meaningful in the logarithmic domain, we adjust the gray value of the noise image to [1, 256], and then transform the multiplicative noise into additive noise through logarithmic transformation. The multiplicative noise model is: y= uv. Where y represents the observed image, u represents the original image, and v represents the multiplicative noise...

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 multiplicative noise removal method based on a non-local adaptive dictionary. The method comprises the following steps of: firstly, utilizing logarithm transformation to convert multiplicative noise into additive noise; then combining a PCA (Principal Component Analysis) sparse dictionary with an iteration shrinkage algorithm to update sparse coding, and utilizing a Newton iteration method to obtain a noise removal image in a log domain; and finally, through an exponential function and error correction, obtaining the noise removal image in a real number field. By use of the method, the edge, detail and texture information of the image can be favorably kept while noise can be effectively removed.

Description

technical field [0001] The invention relates to the technical field of digital image processing, in particular to a method for removing multiplicative noise based on a non-local adaptive dictionary. Background technique [0002] Image denoising research is to obtain high-quality images from observation images. The more traditional methods include Fourier transform, wavelet transform, linear filtering method and Wiener filtering method. In recent years, variational method and sparse representation method have been widely used. [0003] The variational method to deal with multiplicative noise was first proposed by Rudin, Lions and Osher. Under the assumption that the multiplicative noise obeys the Gamma distribution with a mean of 1, Aubert and Aujol used the maximum a posteriori estimation regularization method, and derived a denoising model (AA model) using Bayesian criterion and variational method, " G,Aujol O.AVariational Approach to Removing Multiplicative Noise[J].Sia...

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 Applications(China)
IPC IPC(8): G06T5/00
CPCG06T2207/20021G06T5/70
Inventor 陈利霞何成凤王学文李其珂杨彬
Owner GUILIN UNIV OF ELECTRONIC TECH
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
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