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

A Matrix Filling Image Inpainting Method Based on Graph Regularization

A technology of matrix filling and repairing method, applied in the field of image processing, can solve the problems of ignoring relationship and unsatisfactory image repairing effect, and achieve the effect of enhancing low rank, good image repairing effect, and effective repairing effect.

Active Publication Date: 2022-05-03
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although matrix filling has achieved good development, they still consider the data information from the input data set as a whole, and still ignore the relationship between each sample data in the data set, resulting in unsatisfactory image restoration 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
  • A Matrix Filling Image Inpainting Method Based on Graph Regularization
  • A Matrix Filling Image Inpainting Method Based on Graph Regularization
  • A Matrix Filling Image Inpainting Method Based on Graph Regularization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0049] Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as those of ordinary skill in the art to which the present invention generally understands, and it should also be understood that , terms such as those defined in commonly used dictionaries should be understood to have a meaning consistent with the meaning in the context of the prior art, and unless defined as herein, will not be interpreted in an idealized or overly formal meaning.

[0050] Such as figure 1 , figure 2 Shown, described a kind of matrix filling image restoration method based on graph regularization, comprises the following steps:

[0051] Step (1): the input image X to be repaired is divided into I search areas M, and each search area is divided into J image ...

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 matrix filling image restoration method based on graph regularization, comprising the following steps: Step 1: Divide the image X to be repaired into I search areas M, and divide each search area into J image blocks K; Step 2 : at M i Find p and Kth in search area j The most similar image blocks of each image block form a data matrix F; Step 3: Calculate the graph Laplacian matrix and graph regularization term of the data matrix F; Step 4: Input the data matrix F to the matrix filling algorithm based on graph regularization ; Step 5: Use the Alternate Direction Method to solve the optimization problem of the matrix filling algorithm based on graph regularization; Step 6: After completing the processing of j image blocks in the search area, restore the image of the search area by integrating the image blocks; if all search areas are processed End, skip to step 7, otherwise skip to step 2; step 7: until the complete image is recovered. The invention has the advantage of good image restoration effect.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a matrix filling image restoration method based on graph regularization. Background technique [0002] Image restoration refers to the restoration and reconstruction of damaged images or the removal of redundant objects in images. As early as the Renaissance, people began to restore some medieval artworks. The purpose was to restore the original appearance of the picture by filling some cracks. This work is called "restoration" or "retouching". M.Bertalmio proposed for the first time that many image repairs can be simplified into a mathematical expression, which can be automatically realized by computer. Image restoration is now a research hotspot in computer graphics and computer vision, and has great application value in cultural relics protection, film and television special effects production, virtual reality, and redundant object removal. [0003] With the develop...

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
CPCG06T5/005
Inventor 杨敏程雷荆晓远黄佳凯
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