Unlock instant, AI-driven research and patent intelligence for your innovation.

Structural information synthesis-based image completion method

A technology of structure information and image, applied in the field of image completion with comprehensive structure information, can solve problems such as poor repair effect and matching error, and achieve the effect of avoiding blur effect, improving effect and retaining structural information.

Inactive Publication Date: 2013-01-30
TIANJIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this algorithm eliminates the blur effect in the previous algorithm, it is easy to cause matching errors, so for the defect image with rich structural information, the restoration effect is not good.

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
  • Structural information synthesis-based image completion method
  • Structural information synthesis-based image completion method
  • Structural information synthesis-based image completion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention proposes a block-missing image repair algorithm framework based on structural information. The algorithm uses Bayesian network theory to combine the TV algorithm suitable for repairing structural information with the texture synthesis algorithm suitable for repairing texture information. Its essence is for image The feature proposes the corresponding energy objective function, and then optimizes it, and then copies the selected most matching texture block to the defect area to obtain the repaired image. This invention achieves the effect of simultaneously retaining structure information and texture information without human intervention.

[0021] The present invention is an image complement method based on comprehensive structural information, figure 1 It is an overall flow chart, specifically including the following steps:

[0022] 1. Determine the target area of ​​the image.

[0023] Such as Figure 4 As shown in , an image that has been color...

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 belongs to the technical field of image inpainting, and relates to a structural information synthesis-based image completion method, which comprises the following steps of: for an image, determining an inpainting border area; calculating the cost energy of nodes per se; calculating the correlation energy of the nodes; determining an integral target function; initializing and updating message values between every two adjacent nodes; and calculating the optimal solution of the nodes. The method has the advantages of achieving the effect of simultaneously reserving structural information and texture information without human intervention and greatly improving image inpainting effect.

Description

technical field [0001] The invention belongs to the technical field of image repair, and relates to an image complement method for integrated structural information. Background technique [0002] The background technology involved in the present invention has: [0003] (1) TV image restoration algorithm: The image restoration model based on the overall variational method was first established by Chan & Shen based on the variational principle, called the TV model, which is one of the best models based on partial differential equations to retain structural information. That is to use the diffusion equation in physics to spread the information of the known area to the area to be repaired. The TV image restoration algorithm has a better effect on small-scale damage and can effectively retain its structural information. However, if the area to be repaired is large, obvious blurring will occur, which does not conform to people's visual perception. [0004] (2) Image Completion ...

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 Patents(China)
IPC IPC(8): G06T5/00
Inventor 张怡张加万孙迪宋芸芸
Owner TIANJIN UNIV