Image restoration method and system based on edge restoration and content restoration

An edge image and image technology, applied in the field of image processing, can solve problems such as blurring and color differences, and achieve the effect of improving satisfaction, improving performance, and clear repair effect

Pending Publication Date: 2020-01-10
SHANDONG NORMAL UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This results in phenomena such as color differences or blurring in the image

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 edge restoration and content restoration
  • Image restoration method and system based on edge restoration and content restoration
  • Image restoration method and system based on edge restoration and content restoration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Embodiment 1, this embodiment provides an image restoration method based on edge restoration and content restoration;

[0034] Such as figure 1 As shown, image inpainting methods based on edge inpainting and content inpainting include:

[0035] S1: Preprocess the original defect image, and obtain the grayscale defect image after processing;

[0036] S2: smoothing the grayscale defect image;

[0037] S3: Extract the image mask and incomplete edge image from the smoothed grayscale defect image;

[0038] S4: The image mask, the grayscale defect image and the incomplete edge image are used as the input value of the edge generator, and the edge generator generates a complete edge structure map;

[0039] S5: The complete edge structure map and the original defect image are used as the input value of the content generator, and the content generator generates an image in which the missing area has been filled.

[0040] Utilize the present invention and other methods to repa...

Embodiment 2

[0106] Embodiment 2, this embodiment also provides an image restoration system based on edge restoration and content restoration;

[0107] Image inpainting system based on edge inpainting and content inpainting, including:

[0108]A preprocessing module, which is configured to: preprocess the original defect image, and obtain a grayscale defect image after processing;

[0109] A smoothing processing module, which is configured to: perform smoothing processing on the grayscale defect image;

[0110] An edge image extraction module configured to: extract an incomplete edge image and an image mask from the smoothed grayscale defect image;

[0111] A complete edge structure graph generation module, which is configured to: use an image mask, a gray scale defect image and an incomplete edge image as an input value of an edge generator, and the edge generator generates a complete edge structure graph;

[0112] The content filling module is configured to: use the complete edge struc...

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 restoration method and system based on edge restoration and content restoration. The image restoration method comprises the steps: carrying out the preprocessing of anoriginal defect image, and obtaining a gray defect image after processing; carrying out smoothing processing on the gray defect image; extracting incomplete edge images and image masks from the grayscale defect images subjected to smoothing processing; taking the image mask, the gray defect image and the incomplete edge image as input values of an edge generator, and generating a complete edge structure chart by the edge generator; and taking the complete edge structure diagram and the original defect image as input values of a content generator, wherein the content generator generates an image of which the missing area is filled. Compared with a traditional method, the image restoration method is more comprehensive in consideration, and practice proves that the method is effective to anactual data set.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, in particular to an image restoration method and system based on edge restoration and content restoration. Background technique [0002] The statements in this section merely mention background art related to the present disclosure and do not necessarily constitute prior art. [0003] Image inpainting refers to filling in the missing or blank image, and it can also remove unwanted target objects in the image. The research of image completion technology is a research topic of great significance in computer vision and computer graphics. For images with loss areas, since we do not know the specific form of the original image, we can only generate as many pixels as possible that can achieve authenticity and credibility to fill in the loss. Because of this, image restoration is actually to analyze the image according to human's own visual rules, and then repair the missing image. ...

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
CPCG06T2207/20081G06T2207/20084G06T5/77G06T5/70
Inventor 秦茂玲杨胜男
Owner SHANDONG NORMAL 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