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

A method of image restoration

A repair method and image technology, applied in the field of image repair technology, can solve the problems that affect the robust repair effect, the pixel confidence does not consider the matching error, ignore the principle of similarity, etc., to prevent continuous expansion, high robustness, good effect

Inactive Publication Date: 2006-02-08
BEIHANG UNIV
View PDF0 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method has a better repair effect, but there are still some problems: first, in step (b), the color information is simply used to measure the similarity; second, in step (b), the filling order is simply based on the priority level to determine, while ignoring the principle of similarity; third, in step (c), the influence of matching error is not considered in the calculation of pixel confidence
These issues affect the robustness of the method and the final inpainting effect, because it cannot effectively prevent a common problem in the texture synthesis process - the spread of misinformation

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 method of image restoration
  • A method of image restoration
  • A method of image restoration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] First, define some symbols such as figure 1 Shown: Image I to be repaired; area Ω is the area to be repaired (area to be filled), called the target area, specified by the user, and its shape is not subject to any restrictions; Ω refers to the edge line of the current unfilled area, with the repair Ω keeps changing; Φ is the known part (I-Ω) in the image, which is the sampling space filling the Ω area, called the source area; P and Q are any two points on Ω, Ψ p , Ψq are the edge patches (Patches) centered on P and Q respectively, and w is the edge patch window size. Apparently, as the restoration progresses, the region Φ expands continuously, while Ω becomes smaller, and Ω also changes accordingly.

[0020] Next, some related concepts and methods are introduced:

[0021] 1. Edge patch: such as figure 1 Shown Ψ p , Ψq surface, with a point on the edge as the center, is the unit of known information expansion. The window size of the edge patch, such as figure 1 ...

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 an image restoring method which dose automatically restoring course after user enters into the restored area. The automatically restoring course uses the edge side as the unit of primary iteration packing and then iterates the following four steps until packs all the restored area: first step, computing all the precedent degree of the edge; second step, ascertaining the packing edge side of the current iteration by the precedent degree and the similarity degree criterion; third step, adopting line synthesis method and expends the known line and structure information; fourth step, updating the synthetic picture element ascertain value of the current iteration side.

Description

technical field [0001] The invention belongs to the technical fields of computer virtual reality and computer graphics, and in particular relates to an image restoration technology—reconstruction of damaged images and removal of objects on the images. Background technique [0002] In general, image restoration is an art in itself. As early as the renaissance period, the phenomenon of severed heads and short arms had already appeared in ancient sculptures. Therefore, sculptors not only created their own works, but also repaired ancient sculptures. As introduced by G. Emile-Male. "The Restorer's Handbook of Easel Painting" in Document 1. Van Nostrand Reinhold, New York, 1976. Our country is a country rich in cultural relics. In order to permanently protect precious cultural relics resources, we have to reproduce the original appearance of ancient calligraphy and paintings or old photos. Chinese ancient calligraphy and paintings are often printed with collector's seals, or cr...

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
Inventor 赵沁平齐越沈旭昆李便茹
Owner BEIHANG 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