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

Low rank image denoising method

An image and image matrix technology, applied in the field of image denoising, can solve the problems affecting the accuracy, sparseness, and unstable solutions of image restoration, and achieve the effects of improving accuracy, enhancing stability, and avoiding too sparse

Active Publication Date: 2018-12-21
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the current low-rank image denoising method based on sparse representation, the most commonly used method is to use the kernel norm of the matrix instead of the rank of the matrix. In the case of a low-rank matrix, it is easy to cause the solution to be too sparse, resulting in an unstable solution. , so as to affect the accuracy of image restoration

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
  • Low rank image denoising method
  • Low rank image denoising method
  • Low rank image denoising method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Such as figure 1 with image 3 As shown, the present invention provides a method for denoising a low-rank image, comprising the steps of:

[0061] 1) Input an image D containing noise;

[0062] 2) Firstly, the matrix D∈R to be restored m×n Perform singular value decomposition Get his left singular vector U=(u 1 , u 2 ,...,u m )∈R m×m , right singular vector V=(v 1 ,v 2 ,...,v m )∈R n×n and the singular value Σ r =diag(σ 1 ,σ 2 ,...,σ r );

[0063] 3) According to the definition of truncated nuclear norm Arrange the singular values ​​from small to large, remove the largest r-t singular values, and take the left singular vector F=(u 1 , u 2 ,...,u t ) T and right singular vector G=(v 1 ,v 2 ,...,v t ) T ;

[0064] 4) According to the objective function and constraints, an image denoising model based on truncated kernel norm and Frobenius norm is established,

[0065]

[0066] Where A represents the original image; E represents noise, ||E|| ...

Embodiment 2

[0099] Such as figure 2 Shown, (a) is original image, and (b) is the noise-containing image of original image, utilizes NNR, NNF, TNNR and the method for embodiment 1 to carry out denoising process to noise-containing image (b) respectively, four kinds of methods The PSNRs are 25.3, 26.1, 27.5, and 28.4 respectively, and the denoised images (c), (d), (e) and (f) are obtained respectively. According to the comparison, the image (f) obtained by the method of Example 1 The closest to the original image (a), the best denoising effect.

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 denoising method of a low-rank image, which is applied to the reconstruction of an image containing noise. By analyzing the correlation characteristics of the low-rank matrix, the denoising problem of the image is modeled as a non-linear constraint problem, and then the specific iterative steps are deduced by using an alternating direction multiplier method, thereby obtaining the image after denoising. The invention uses the truncated kernel norm to more accurately approximate the rank of the matrix and avoids the result deviation caused by the large singular value. In addition, the Frobenius norm is added to the model as a regular term, the Frobenius norm and the truncated kernel norm form an elastic network about the singular value, so that the final result is sparse and stable, so that better denoising effect can be achieved.

Description

technical field [0001] The invention belongs to the technical field of image denoising, and in particular relates to a low-rank image denoising method. Background technique [0002] Image is an important source of information, and image processing can help people understand the connotation of information. However, images are often disturbed and affected by various noises during the process of image generation and transmission, which degrades the image quality, which will have an adverse effect on subsequent image processing (such as segmentation, compression, and image understanding, etc.). There are many types of noise, such as: electrical noise, mechanical noise, channel noise and other noises. In order to suppress noise, improve image quality, and facilitate higher-level processing, image denoising preprocessing must be performed. [0003] After several years of research, there are many image denoising algorithms, but they cannot fully meet the growing application requi...

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
CPCG06T2207/10004G06T5/70
Inventor 王韦刚宋伟
Owner NANJING UNIV OF POSTS & TELECOMM
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