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

Image set unsupervised co-segmentation method based on deformable graph structure representation

A technology of structural representation and image set, applied in the field of image segmentation and computer vision, can solve problems such as difficulty in providing relevance

Inactive Publication Date: 2014-04-02
BEIHANG UNIV
View PDF1 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Large-scale superpixels only provide fuzzy features, and it is generally difficult to provide clear correlations

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 set unsupervised co-segmentation method based on deformable graph structure representation
  • Image set unsupervised co-segmentation method based on deformable graph structure representation
  • Image set unsupervised co-segmentation method based on deformable graph structure representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0036] figure 1 The overall processing flow of the unsupervised co-segmentation method for image sets based on deformable graph structure representation is given.

[0037]This paper invents an unsupervised co-segmentation method for image sets based on deformable graph structure representation. The main steps are as follows:

[0038] 1. Create an inner image for each image in the atlas

[0039] (1) Input the original atlas with a unified size of 256*256 pixels. The original image is segmented using SLIC superpixels. Denote as P={p 1 ,p 2 ...p n}. The number of splits is 80 and the degree of compaction is 10. Such as figure 2 shown. Features are extracted using CIE Lab or FREAK descriptors for each superpixel.

[0040] (2) For each image, use the center of the superpixel as the vertex and use Delaunay triangulation to form a two-dime...

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 set unsupervised co-segmentation method based on deformable graph structure representation. The method is divided into the following four steps: firstly, superpixel segmentation is carried out on each graph in a graph set and a descriptor is extracted; secondly, an inner graph based on a Biharmonic distance is built for each picture, specifically, a two-dimensional image is stretched as a three-dimensional grid, and a Laplacian matrix is established on the three-dimensional grid according to a Riemann flow pattern space manner; thirdly, a deformable hypergraph which includes all superpixel in the graph set is established after the inner graph is established and the Biharmonic distance is calculated in a descriptor space(characteristic space); fourthly, clustering ideas considering connectivity are used, and an energy function which comprises the inner graph, the hypergraph and segmentation size constraints is established. Optimization is carried out by using the expectation maximization algorithm to obtain a final co-segmentation result. The algorithm partly uses CPU(Central Processor Unit) parallelism with CPU parallelism, the co-segmentation method has excellent segmentation accuracy and efficiency performance for the large-scale graph set.

Description

technical field [0001] The invention relates to the technical field of image segmentation in the field of computer vision, in particular to an image set unsupervised co-segmentation method based on a deformable graph structure representation. It co-segments the thermal diffusion information of image superpixels. Background technique [0002] Image segmentation technology (segmentation foreground) is a basic technology in the field of computer vision, and it has been a research hotspot because of its wide application. However, there has been no robust and mature method for non-learning and unsupervised automatic segmentation technology. The main reason is that it is difficult to automatically analyze and define appropriate constraints for various atlases with unpredictable characteristics. Since the concept of co-segmentation was first proposed in 2006, co-segmentation technology has attracted the attention of many scholars. The idea is that when an object appears at the sa...

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): G06T7/00
Inventor 赵沁平马际洲李帅郝爱民
Owner BEIHANG 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