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

Image restoration method based on edge generation

A repair method and image technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of blurring generated images and fixed repairing areas.

Active Publication Date: 2020-04-21
UNIV OF SCI & TECH BEIJING +1
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide an image repair method based on edge generation to solve the problem of fixed repair area and blurred image in the prior art

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 based on edge generation
  • Image restoration method based on edge generation
  • Image restoration method based on edge generation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] like figure 1 As shown, the image restoration method based on edge generation provided by the embodiment of the present invention includes:

[0049] S101, acquiring training set images, processing the images, generating defect images, and extracting edge contours of the defect images; wherein, the training set images are real images;

[0050] S102, constructing an edge generation network and a content generation network, wherein each of the edge generation network and the content generation network corresponds to a discrimination network, the discrimination network is used to judge the authenticity of the content generated by the generation network, and the content generation network adopts a U-Net structure;

[0051] S103, in the training phase: input the defect image and the extracted edge profile to train the edge generation network, input the image edge features generated by the trained edge generation network, the texture information of the defect image extracted by ...

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 provides an image restoration method based on edge generation, which can effectively solve the problems of fixed restoration area and blurred generated image in image restoration. The method comprises the steps that a defect image is generated, and the edge contour of the defect image is extracted; an edge generation network and a content generation network are constructed, wherein the content generation network adopts a U-Net structure; in the training stage, a defect image and an extracted edge contour are input to train an edge generation network, and image edge features generated by the trained edge generation network, texture information of the defect image extracted by the trained texture generation network and the defect image are input to train a content generation network; and in the restoration stage, the edge features of the to-be-restored image generated by the edge generation network, the texture information of the to-be-restored image extracted by the texture generation network and the to-be-restored image are input into the trained content generation network, and then original appearance restoration of the image is acheived. The invention relates to thefield of artificial intelligence and image processing.

Description

technical field [0001] The invention relates to the fields of artificial intelligence and image processing, in particular to an image restoration method based on edge generation. Background technique [0002] Image inpainting technology is an important branch of computer vision, which belongs to the interdisciplinary problems of deep learning and image processing. Image inpainting refers to a technology that uses the information of known areas of the image to repair some missing pixels. It is currently widely used in the fields of image redundant target removal, public security criminal investigation facial restoration, and biomedical images. [0003] The image restoration method in the prior art has the problem that the restoration area is fixed and the generated image is blurred. Contents of the invention [0004] The technical problem to be solved by the present invention is to provide an image repair method based on edge generation, so as to solve the problems in the ...

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): G06T5/00G06T7/13G06T7/181G06T7/44G06N3/04G06N3/08
CPCG06T7/13G06T7/181G06T7/44G06N3/08G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/20192G06N3/045G06T5/77
Inventor 林福宏刘娟娟周成成陆月明许海涛安建伟
Owner UNIV OF SCI & TECH BEIJING
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