Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image segmentation method based on multi-level region synthesis

A technology of image segmentation and hierarchical segmentation, which is applied in the fields of image processing and computer vision, can solve the problems of segmentation layer selection dependence, inability to guarantee optimal selection, and subjectivity, so as to reduce the number of regional nodes, reduce the difficulty of discrimination, and reduce the amount of calculation. Effect

Active Publication Date: 2018-03-23
SOUTHWEST JIAOTONG UNIV
View PDF9 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing problems include: firstly, the image may contain multiple targets, and their optimal segmentation may appear in different segmentation levels; secondly, the selection of segmentation level depends on the threshold setting of experts, which is not only cumbersome but also has subjective differences
It can directly replace expert threshold setting and reduce manual workload, but it cannot guarantee optimal selection for each individual goal

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 segmentation method based on multi-level region synthesis
  • Image segmentation method based on multi-level region synthesis
  • Image segmentation method based on multi-level region synthesis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The specific implementation steps are as follows:

[0038] Step 1: Obtain a segmentation result with a tree structure through the existing multi-level segmentation algorithm. Expand the segmentation results (such as binary tree or hypermetric contour map) according to the segmentation level, and obtain n single-level segmentation images from bottom to top S={s 1 ,s 2 ,...,s n}, where the number of regions contained in each segmentation result satisfies |s 1 |2 |n |;

[0039] Step 2: The first global segmentation hierarchical combination.

[0040] Step 2.1: Select part of the segmentation hierarchy in S for region synthesis. with l 1 For a fixed step size, select k from low to high in the global hierarchy 1 Segmentation result in Calculate S 1 Five quantitative features of each segmented image region in .

[0041] (i) Color consistency feature f within the region intra_lab , reflecting the histogram distribution of the image area in the Lab color space, def...

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

An image segmentation method based on multi-level region synthesis includes the steps of firstly, obtaining multi-level segmentation results by using an existing multi-level image segmentation algorithm; secondly, performing synthesis in a global level range: selecting multiple segmentation results of an image from a low level to a high level, respectively calculating image region characteristicsof each level, performing unified quantitative description of the multiple characteristics, establishing a synthesized model of multi-level image segmentation, and performing the optimal combination of the segmentation regions by using a multi-label graph cutting method; thirdly, according to the global-level synthesized results, selecting a local level range and performing a second synthesis by using a multi-label graph cutting model; and fourthly, subjecting the level labels by the second synthesis to regional mapping to obtain a final image segmentation result. The image segmentation methodbased on the multi-level region synthesis in the invention selects the region with high target segmentation quality from the multiple segmentation levels and realizes adaptive selection; uses less regional features to calculate the segmentation quality and reduces the number of regional nodes involved in the calculation, with the used optimized combination model having a better optimization effect.

Description

technical field [0001] The invention relates to the technical fields of computer vision and image processing, in particular to multi-level image segmentation technology, in particular to an image segmentation method based on multi-level area synthesis. Background technique [0002] Image segmentation refers to the process of extracting meaningful target areas in the image. The targets contained in the image have the characteristics of multi-level (scale), that is, the same target can be represented as several areas with different numbers according to the different levels of detail and semantics. The multi-level image segmentation method can obtain different levels of image segmentation results, and express them in a tree structure, forming a multi-level image content expression with the relationship between the upper and lower levels. Extracting target areas at different levels can adapt to computer vision tasks for different purposes, improve processing accuracy and efficie...

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): G06T7/11G06T7/187G06T7/162
CPCG06T7/11G06T7/162G06T7/187G06T2207/20161
Inventor 彭博孙昊李天瑞
Owner SOUTHWEST JIAOTONG 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
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