Sample block image restoration method based on layered guide strategy

A repair method and sample block technology, applied in the field of image repair, can solve problems such as difficulty in maintaining structural consistency

Active Publication Date: 2017-06-20
FUYANG NORMAL UNIVERSITY
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When the existing sample block repair methods repair large areas of image damage, it is difficult to maintain structural consistency.

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
  • Sample block image restoration method based on layered guide strategy
  • Sample block image restoration method based on layered guide strategy
  • Sample block image restoration method based on layered guide strategy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The following with attached Figure 1 to Figure 4 A sample block image restoration method based on a layered guidance strategy of the present invention is further described in detail.

[0023] A sample block image restoration method based on layered guidance strategy of the present invention, please refer to Figure 1-4 ,include:

[0024] Step 1: Perform Gaussian pyramid decomposition on the original image to be repaired to obtain multi-layer decomposed images with different resolutions. Among them, the Gaussian pyramid decomposition is a kind of multi-scale expression in the image. The pyramid decomposition of the present invention adopts sub-sampling, that is to say, the K-th layer Gaussian pyramid can obtain the K+1 layer Gaussian image through sub-sampling, and its cut-off frequency is from the previous one. The layer to the next layer is gradually increased by a factor of 2, so the Gaussian pyramid can span a large frequency range, such as figure 1 as shown, fi...

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 a sample block image restoration method based on a layered guide strategy, and the method comprises the steps: carrying out the Gaussian pyramid decomposition of a to-be-restored original image; obtaining decomposed images with different resolutions at a plurality of layers; carrying out the layer-by-layer restoration of the decomposed images according to a sequence from the top layer to the bottom layer; carrying out the restoration of the top decomposed image based on a sample block image restoration method, and obtaining a top layer image restoration result; carrying out the up-sampling of the top layer image restoration result, enabling the top layer image restoration result to be merged with a second layer decomposed image, enabling the information of a to-be-filled region in the merging result to serve as guide information, and storing the second decomposed image; repeatedly carrying out the above process till the restoration of the to-be-filled regions of all layers is completed. The method provided by the invention is wide in application range, is good in restoration effect, is high in practicality, can be suitable for the restoration of an image with large-area damages, and accords with the visual effect.

Description

technical field [0001] The invention relates to the technical field of image restoration, in particular to a sample block image restoration method based on a layered guidance strategy. Background technique [0002] Image inpainting is a practical application problem, mainly used in object hiding, restoration of cultural relics loss, removal of text or date on photos, etc. [0003] Currently, there are two most representative inpainting methods: one is the image inpainting method based on variational partial differential; the other is the technique based on sample blocks. When the existing sample block repair methods repair large areas of image damage, it is difficult to maintain structural consistency. Contents of the invention [0004] The present invention is completed in order to solve the deficiencies in the prior art. The purpose of the present invention is to provide a wide application range, good repair effect and strong practicability. A Sample Block Image Inpa...

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 Applications(China)
IPC IPC(8): G06T5/00G06T5/50
CPCG06T5/005G06T5/50G06T2207/20021G06T2207/20221
Inventor 毕学慧刘华明刘坤哲王秀友王诗兵王浩于立志韩波赵正平
Owner FUYANG NORMAL UNIVERSITY
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