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

Image fusion method based on algebraic multigrid and watershed segmentation

A watershed segmentation, multi-grid technology, applied in the field of image fusion, can solve the problem of limited block and can not fundamentally solve the block effect and other problems

Active Publication Date: 2018-05-04
CHONGQING UNIV OF POSTS & TELECOMM
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Although this method adopts the adaptive block method, the block is still limited. For example, the image can only be divided into four blocks on average at the beginning, which cannot fundamentally solve the problem of block effect.

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 fusion method based on algebraic multigrid and watershed segmentation
  • Image fusion method based on algebraic multigrid and watershed segmentation
  • Image fusion method based on algebraic multigrid and watershed segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] S11. Reconstruct at least two source images by using algebraic multigrid to obtain a reconstructed image of each source image respectively;

[0060] S21. Obtain an average image according to the source image, that is, average two or more source images to obtain an average image;

[0061] S31. Using a watershed image segmentation method to perform region segmentation on the mean image to obtain several segmented regions;

[0062] S41. For each segmented area, calculate the value of the mean square error of each source image and the reconstructed image of each source image, that is, calculate the source image corresponding to the boundary according to the segmented boundary of the segmented area The value of the mean square error between the area and the reconstructed image area corresponding to the boundary; compare the value of the mean square error, calculate the sharpness of each segmented area, mark the source image source of the segmented area, and obtain the defini...

Embodiment 2

[0066] Steps S22-S52 are the same as steps S2-S5, for details, refer to the description of steps S2-S5; S12 of this embodiment and S11 (or S1) of Embodiment 1 have the following improvements:

[0067] S12. Reconstruct at least two source images by using an algebraic multigrid to obtain a reconstructed image of each source image respectively; image 3 shown, including the following steps:

[0068] Step 101: Initially Ω 0 , AU=F, do several iterations on this grid, and project the error to Ω 1 .

[0069] Step 102: According to A 1 u 1 =F 1 , and then do several iterations to project the error to the next level of grid.

[0070] Step 103: Continue to iteratively solve, and finally in the coarse grid Ω m , get A m u m =F m , F m =Ω m -C m ;A m is the coefficient matrix sequence, U m is the system of equations in the cyclic process of algebraic multigrid; the coarser coarse mesh Ω of algebraic multigrid m+1 =C m is the finer coarse mesh Ω m A true subset of .

[...

Embodiment 3

[0074] Steps S13-S33 are the same as steps S12-S32, please refer to the description of steps S12-S32 for details;

[0075] Step S43, using the watershed image segmentation method to segment the mean image to obtain several segmented areas including:

[0076] Use the Sobel operator to find the gradient image of the mean image;

[0077] The basic operations of morphology are expansion and erosion. The opening operation of B on A is A○B, and the closing operation is A·B, expressed as is an expansion operation, □ is an erosion operation, and the obtained gradient image is smoothed by using the expansion operation and the erosion operation;

[0078] The gradient image is segmented using the watershed segmentation method, and the two source images are divided into several different areas. Among them, the principle of the watershed image segmentation method is as follows: Image 6 shown.

[0079] The idea of ​​the watershed algorithm comes from the topography of geodesy. The bas...

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 fusion method based on algebraic multigrid and watershed segmentation. The method comprises the following steps that two or a plurality of images of the same scene butdifferent focuses are processed to obtain one synthetical image with rich information; an algebraic multigrid method is used for rebuilding a source image to obtain a rebuilt image; a mean value image is segmented into different regions by a watershed image segmentation method; the mean square error of the source image and the rebuilt image of the region is calculated according to the segmented image region; the clear degree is judged; a region definition decision image is generated; the picture clear and fuzzy boundary is obtained according to the region definition decision image; the imagefusion is performed according to the boundary. Compared with a multiresolution image fusion method, the image fusion method provided by the invention has the advantages that each target region of a fusion image is directly selected from a clear region in the source image; the image definition loss caused by image change is avoided.

Description

technical field [0001] The invention relates to the field of image fusion, in particular to an image fusion method based on algebraic multigrid and watershed segmentation. Background technique [0002] The current image fusion method based on algebraic multigrid, such as multi-focus fusion method using algebraic multigrid (Journal of University of Electronic Science and Technology of China, 2015, Huang Ying, Xie Mei, Li Weisheng, Gao Jingsong), the main steps of this method are 1) Use the AMG method to reconstruct the source image; 2) Divide the reconstructed image block into 4 blocks, calculate the MSE between the reconstructed result of each block and the corresponding original block, if the difference between the two source images is greater than a certain threshold, Then directly select the corresponding picture to enter the fusion result; 3) If the difference between the two source images is less than a certain threshold, then determine whether to include clear blocks a...

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): G06T5/50G06T7/11G06T7/155G06T7/174
CPCG06T5/50G06T2207/20152G06T2207/20221G06T7/11G06T7/155G06T7/174
Inventor 黄颖谢蓉
Owner CHONGQING UNIV OF POSTS & TELECOMM
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