Digital image inpainting method based on multi-window fusion

A digital image and repair method technology, applied in image enhancement, image data processing, instruments, etc., can solve problems such as deviation of repair results, and achieve the effect of wide application prospects and accurate digital image repair effect

Active Publication Date: 2020-08-14
TIANJIN UNIV
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The Criminisi algorithm is currently the most commonly used digital image restoration algorithm based on texture synthesis, but this algorithm has certain defects. It needs to fill and synthesize textures by specifying the size of the repair window. When the repair window changes, it is easy to cause repair results. There is a large deviation

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 inpainting method based on multi-window fusion
  • Digital image inpainting method based on multi-window fusion
  • Digital image inpainting method based on multi-window fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The digital image restoration algorithm based on multi-window fusion in the present invention mainly consists of three parts: digital image restoration under multi-size windows, update of image to be repaired, calculation of restoration variance information, and improvement of priority calculation function. The specific steps and principles are as follows:

[0017] 101: Setting repair windows of different sizes;

[0018] The size of the repair window is ω n ,n=1,...,N, where n is the serial number of the repaired window, and N is the number of windows. Use the Criminsi repair algorithm to repair the image I to be repaired, and the repaired image is recorded as I n :

[0019] 102: Fix window size to ω n Image I to be repaired under the damaged area and the mark of the source area;

[0020] The damaged area of ​​image I to be repaired is denoted as Ω n , the edge is recorded as Target pixel point p n for At any point on , the source area is Φ n , and satisfy t...

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 present invention relates to a multi-window fusion-based digital image repairing algorithm. The method comprises the steps of for a to-be-repaired image I, setting a repair window omega n at different sizes; in the repair window omega n, completing the repairing process of the to-be-repaired image I by adopting the Criminisi repair algorithm, and marking the repaired image to be In; calculating an updated to-be-repaired image UI, and calculating a repair variogram VI; calculating the priority of a target pixel point Pu, and changing the priority calculation mode of the target pixel point in the Criminisi repair algorithm to be the calculation mode of Pu(pu); and repairing the UI according to the Criminisi repair principle so as to obtain a final repair result IP.

Description

technical field [0001] The invention belongs to the field of computer image restoration, and relates to a digital image restoration algorithm based on multi-window fusion, which can be used for cultural relics protection, film and television special effect production and the like. Background technique [0002] Digital image restoration technology is the process of filling information missing areas in the image to be repaired. Its purpose is to restore the damaged image, and at the same time make the observer unable to detect the traces of the image being repaired. Digital image restoration technology has been used in many fields. In the photography and film industry, it is used to repair movies and restore deteriorated films. At the same time, it can also be used to remove red eyes, dates on photos, digital watermarks, etc. [0003] The current digital image restoration technology is mainly divided into two categories, one is the digital image restoration algorithm based on ...

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
CPCG06T5/001
Inventor 朱程涛李锵滕建辅
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap