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

Digital Image Restoration Method Based on Weight-guided Filtering

A digital image, guided filtering technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as difficulty in distinguishing edge areas and texture areas, effect limitations of damaged image repair, and inaccurate priority calculation methods. , to achieve the effect of wide application prospect and accurate digital image restoration effect

Active Publication Date: 2020-08-14
TIANJIN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

And in the process of image restoration, only the confidence item and data item of the image are considered. In some cases, it is difficult to effectively distinguish the edge area and the texture area only based on these two factors, that is, the calculation method of the priority is not accurate enough. Causes limited effect on repair of broken images

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
  • Digital Image Restoration Method Based on Weight-guided Filtering
  • Digital Image Restoration Method Based on Weight-guided Filtering
  • Digital Image Restoration Method Based on Weight-guided Filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] The digital image restoration algorithm based on the weight-guided filtering of the present invention mainly consists of three parts: edge-preserving filtering of the damaged image to be repaired, calculation of the change degree of the damaged image before and after filtering, and improvement of the priority calculation function. The specific steps and principles are as follows:

[0019] 101: Edge-preserving filtering of the damaged image to be repaired;

[0020] For the damaged image I to be repaired, edge-preserving filtering is performed based on weight-guided filtering to obtain the filtered damaged image I f :

[0021]

[0022]

[0023]

[0024]

[0025]

[0026] Where j is the pixel centered on i, and the size is ω i Any pixel in the window, |ω i | is the window ω i The number of pixels within; ω j is a window composed of j as the center pixel and neighboring pixels, |ω j | is the window ω j The number of pixels within; k is ω i with ω j A...

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 relates to a digital image repair method based on weight-guided filtering, which includes: performing image filtering on a damaged image I to be repaired in a weight-guided filtering-based manner to obtain a filtered damaged image I f ; Calculate the degree of change A of the pixel brightness value of the damaged image to be repaired before and after filtering and index it; Repair the damaged area of ​​the damaged image I to be repaired, and mark its corresponding target block as the block to be repaired ω(p * ); using the similarity measure function in the digital image repair algorithm based on sample blocks to find the block to be repaired ω(p * ) of the optimal matching block ω(q * ), complete ω(p * ); using the confidence item update function in the digital image repair algorithm based on sample blocks to complete the block to be repaired ω(p * ) The confidence terms of all pixels in the area are updated, and ω(p * ) area is removed from the damaged area to complete the repair of the damaged image I to be repaired.

Description

technical field [0001] The invention belongs to the field of computer image restoration and can be used for cultural relics protection, film and television special effect production and the like. Background technique [0002] Digital image repair technology is a research hotspot in the field of image processing. It mainly realizes the automatic repair of damaged images through related repair algorithms. It is mainly used in the repair of old photos, film and television special effects, scratch removal, digital watermarking and other fields. significance and research value. [0003] At present, digital image restoration technology is mainly aimed at image restoration of small areas and image restoration of large areas, and image restoration of small areas is usually based on a partial differential equation model. Compared with the restoration of small areas, the commonly used digital image restoration algorithm at this stage is a large-area digital image restoration method b...

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): G06T5/00G06T5/20
CPCG06T5/20G06T2207/10004G06T5/77
Inventor 朱程涛李锵滕建辅
Owner TIANJIN UNIV
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