Image restoration method and system based on priori knowledge constraint and computer equipment

A priori knowledge and repair method technology, applied in the field of image repair, can solve the problems of artificial traces of repair effect, uncontrollable repair content, etc., and achieve good image quality

Inactive Publication Date: 2019-07-16
ZHEJIANG UNIVERSITY OF MEDIA AND COMMUNICATIONS
View PDF2 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The image restoration algorithm based on the convolutional neural network has been greatly improved on the basis of the traditional restoration algorithm

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 restoration method and system based on priori knowledge constraint and computer equipment
  • Image restoration method and system based on priori knowledge constraint and computer equipment
  • Image restoration method and system based on priori knowledge constraint and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0034] In order to make the purpose, technical solutions, and advantages of this application clearer, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the application, and not used to limit the application.

[0035] The steps in each embodiment are not necessarily executed in the order described, unless explicitly stated in this article, at least some of the steps may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily at the same time. The execution is completed but can be executed at different moments, and the execution order of these sub-steps or stages is not necessarily performed sequentially, but can be executed alternately or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0036] This application proposes an image restoration ...

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 restoration method and system based on priori knowledge constraint and computer equipment. The image restoration method comprises the steps of constructing a missingcontent generation network, wherein the missing content generation network comprises a generator used for receiving an image with a missing area and outputting a restored image, and a discriminator used for identifying a training result when the missing content generation network is trained; constructing a content constraint network, wherein the content constraint network is used for providing constraint conditions for the generator to output the restored image; training the missing content generation network by using a data set in a specified field; generating a network based on the trained missing content, and performing iterative optimization through back propagation by taking the conditional network as a constraint to obtain a hidden variable; and inputting the image with the missing region into the trained missing content generation network, and solving the restored image by combining the hidden variable of the missing content generation network.

Description

technical field [0001] This paper relates to the technical field of image restoration, and specifically relates to an image restoration method, system and computer equipment based on prior knowledge constraints. Background technique [0002] As a relatively large and popular research direction in the field of digital image processing, image restoration technology has received great attention at home and abroad. This concept was first proposed by Beralmio et al. at the Siggraph conference in 2000. The concept of image restoration The proposal of is inspired by the previous hand-painted art images, and it has been developed for nearly two decades. The shortcomings of Beralmio et al. are also more obvious. The computational complexity is large and the integrity of image restoration is not considered, and the restoration effect is relatively poor. Telea proposed a fast marching algorithm (Fast Marching Method, FMM) based on Bertalmio, and Chan proposed a method using Euler-Lagr...

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
CPCG06T5/005G06T2207/10004G06T2207/20081
Inventor 张根源
Owner ZHEJIANG UNIVERSITY OF MEDIA AND COMMUNICATIONS
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