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

Image repairing method based on rotation and scale change

A technology of scale transformation and repair method, applied in image enhancement, image data processing, instruments, etc., can solve problems such as failure to find the optimal matching block, unsatisfactory repair effect, etc., to achieve energy optimization, space expansion, and optimized search The effect of the result

Inactive Publication Date: 2015-01-14
TIANJIN UNIV
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In the process of realizing the present invention, the inventor found that the existing method is limited to the translation space. When the image has rotation and scale transformation, it is impossible to find the accurate optimal matching block, and the restoration effect is not ideal.

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
  • Image repairing method based on rotation and scale change
  • Image repairing method based on rotation and scale change
  • Image repairing method based on rotation and scale change

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the implementation manners of the present invention will be further described in detail below.

[0030] 101: Divide the image into a damaged area (the area to be repaired, which is also the target area) T and an information source area (pixel effective area) S, and then down-sample the image into a 5-level Gaussian pyramid model, and perform iterative processing;

[0031] Wherein, there are multiple methods for downsampling, all of which are well known to those skilled in the art. This method adopts references Wexler Y, Shechtman E, Irani M.Space-time completion of video[J].IEEE Transactions on Pattern Analysis and Machine The downsampling method mentioned in Intelligence, 2007, 29(3):463-476 downsamples the image. After downsampling, 15 iterations are used for the top-level image, and the number of iterations decreases by 3 for each subsequent level. The specific number o...

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 image repairing method based on rotation and scale change and relates to the field of computer image processing. The method includes the steps that images are divided into a damage region and an information source region, the images are sampled as a five-level Gaussian pyramid model, and iteration processing is conducted; rotation and scale space expansion is achieved through an expanded energy function; the images of all layers are searched for optimal matching blocks from the image of the top layer of a pyramid; the minimum mean square errors between the current optimal matching blocks and effective pixel parts in target blocks are calculated, the optimal matching blocks are updated, and search results are optimized; after the optimal matching blocks of all the target blocks are found, information filling is conducted. Due to the fact that rotation and scale parameters are introduced for space expansion and energy optimization, the method can be applied for image repair, and for other algorithms needing the block matching process, the method can be used for achieving corresponding space expansion and optimizing search results.

Description

technical field [0001] The invention relates to the field of computer image processing, in particular to an image restoration method based on rotation and scale transformation. Background technique [0002] Digital image restoration technology is an important research topic in the field of computer vision. Its main research content is how to use the known information in the image to fill the damaged area, and finally ensure the natural and reasonable effect of the repaired image. This technology has important significance and research value in the fields of subtitles, stains, scratches removal, old photo restoration, film and television special effects, and cultural relics protection. [0003] The classic algorithm of digital image restoration is the restoration algorithm based on sample blocks proposed by Criminisi et al. This algorithm uses confidence function and structural function to determine the priority function of restoration, which can realize the automatic restora...

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
Inventor 何凯郑欢张丽莹吴春芳王新磊
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