Region merging method for threshold-restrained minimum spanning tree algorithm

A technology of generating trees and thresholds, which is applied in the field of image processing, can solve the problems of low efficiency, different merging results, and the inability to guarantee the first merging of regions, so as to improve the efficiency of merging and improve the effect of merging

Inactive Publication Date: 2012-12-05
REMOTE SENSING APPLIED INST CHINESE ACAD OF SCI
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the RAG method, the order of region merging is related to the order of marking the regions. The order of marking is different, the order of region merging is different, and the merging results are also different, and the RAG method cannot guarantee that the region with the smallest feature difference among adjacent regions will be merged first; The NNG method is an improvement to the RAG method. Although the merging result does not change with the marking order, the NNG method only ensures that the region with the smallest feature difference is first merged within the scope of the local area. The merging is not globally optimal and contains many redundant operations. ,low efficiency

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
  • Region merging method for threshold-restrained minimum spanning tree algorithm
  • Region merging method for threshold-restrained minimum spanning tree algorithm
  • Region merging method for threshold-restrained minimum spanning tree algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described in detail through the embodiments below in conjunction with the accompanying drawings.

[0023] The implementation process of the region merging method of the threshold-constrained minimum spanning tree algorithm described in the present invention is as follows: figure 1 as shown, figure 1 Consists of 4 units. The graph merging in this embodiment will use two algorithms, Boruvka and Kruskal, to construct the minimum spanning tree.

[0024] Unit 100 is a unit for performing watershed segmentation on an image.

[0025] Unit 101 is a unit for constructing a region adjacency graph. The result of the initial segmentation of the watershed obtained by the processing unit 100 is represented as a graph structure, such as figure 2 As shown, all the divided regions are regarded as the vertices of the graph, the adjacency relationship of the regions constitutes the edges of the graph, and the feature difference between adjacent r...

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 provides a region merging method for a minimum spanning tree implementing threshold restraining on 'over-segmentation' regions generated due to watershed segmentation. The method comprises the following steps: regional adjacent maps are built to a watershed segmentation result; the built maps for the threshold-restrained minimum spanning tree algorithm are combined, and the 'over-segmentation' regions are combined to form a combining result.

Description

technical field [0001] The invention relates to image processing technology, in particular to an area merging method for performing a threshold-constrained minimum spanning tree algorithm on an "over-segmented" area generated by watershed segmentation. Background technique [0002] The watershed algorithm is an image segmentation method based on mathematical morphology. Its advantages are global segmentation, boundary closure, high implementation efficiency, high accuracy, and advantages in algorithm stability and practicability. However, the watershed transformation is based on the gradient magnitude image, which is easily affected by noise, resulting in a large number of "over-segmented" regions in the results of watershed segmentation. For the "over-segmentation" problem of the watershed algorithm, image preprocessing before segmentation, that is, image filtering, is generally used, and the region after segmentation is merged to reduce "over-segmentation". Compared with ...

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): G06T7/00
Inventor 唐娉边钊
Owner REMOTE SENSING APPLIED INST CHINESE ACAD OF SCI
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