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

Criminisi image restoration method based on textures and edge features

A technology of edge features and repair methods, applied in image enhancement, image analysis, image data processing, etc., to achieve good repair effects

Inactive Publication Date: 2014-04-02
HANGZHOU DIANZI UNIV
View PDF2 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the problems of priority confusion and automatic priority calculation caused by the difference between texture structure and edge structure, the present invention provides a priority calculation method based on texture and edge features, which can enhance the priority model in the priority model. Discrimination ability for structural parts, thus improving image restoration quality of Criminisi 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
  • Criminisi image restoration method based on textures and edge features
  • Criminisi image restoration method based on textures and edge features
  • Criminisi image restoration method based on textures and edge features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In this embodiment flow chart as figure 1 shown.

[0028] The first step: the image block ψ to be repaired p along n p direction, such that ψ p It is divided into two blocks of uniform size, and then averages the known pixels of the two blocks (denoted as E 1 (p) and E 2 (p)), variance (denoted as F 1 (p) and F 2 (p)), and the normalized mean difference δE(p)=(E 1 (p)-E 2 (p)) / α and variance difference δF(p)=(F 1 (p)-F 2 (p)) / α. Among them, α is a normalization parameter (take 255 in the grayscale image). The normalized mean difference and variance difference can effectively judge whether the damaged area is in the edge, texture or smooth area. Such as figure 2 As shown, the block to be repaired is first divided into block 1 and block 2 with uniform size, and the mean and variance of the known pixels of the two blocks are calculated respectively, and then the mean difference and variance difference are obtained through formula (1).

[0029] The second ste...

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 criminisi image restoration method based on textures and edge features. A difference factor which enhances the discrimination capability for a structural part is introduced in a priority model to optimize priority calculation through analyzing texture structure features and edge structure features. The Criminisi image restoration method disclosed by the invention can effectively restrain priority repair of texture parts, and prevent the texture part from extending excessively to an edge part to result in image linear structural failure.

Description

technical field [0001] The invention belongs to the technical field of digital image restoration, and in particular relates to a Criminisi image restoration method based on texture and edge features. Background technique [0002] The current image inpainting technology is divided into two categories: one is digital image inpainting (inpainting) technology for repairing small scale, such as the BSCB model, the inpainting algorithm based on the overall variation proposed by Chan et al. and the inpainting algorithm based on the curvature-driven diffusion model. algorithm. This type of algorithm has a good repair effect when repairing small-scale damaged images, but often produces blurring when repairing images with large damaged areas. The other is an image completion technology used to fill in large pieces of missing information in an image—an image restoration technology based on texture synthesis. Among them, the sample-based image restoration algorithm proposed by Crimini...

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): G06T7/00G06T5/00
Inventor 唐向宏任澍康佳伦李齐良
Owner HANGZHOU DIANZI UNIV
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