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

Infinitesimal normalized cut method for image segmentation

A technology of image segmentation and normalization, which is applied to instruments, character and pattern recognition, computer components, etc., and can solve problems such as high computational complexity

Active Publication Date: 2006-10-04
XIAMEN PRIMA TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, some scientists have applied the method of graph theory to image segmentation, and proposed the normalized cut (Normalized Cut) image segmentation method. This algorithm is suitable for different image scenarios, but its computational complexity is huge. For grayscale images with a word length of more than 128×128 bits, it is configured on a machine with Intel Pentium IV, CPU 2G, 256M RAM, and Matlab6.5 , the calculation time is more than five minutes, for the 256X256, 8bit grayscale image, it crashes due to the limitation of the machine memory

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
  • Infinitesimal normalized cut method for image segmentation
  • Infinitesimal normalized cut method for image segmentation
  • Infinitesimal normalized cut method for image segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Specific embodiments of the present invention will be described in detail below.

[0038] Image segmentation is also a clustering process, which gathers regions with certain characteristic consistency into one region, that is, clusters the pixels in the image. We can regard the entire image as an undirected graph, which is composed of vertices and edges connecting vertices. The vertices represent the positions of pixels, and the edges represent the strength of the connection between vertices. The value of the edges between pixels can also be expressed As a measure that two vertices have some kind of feature consistency, that is to measure whether two vertices should be clustered into the same region. Let G=(V, E), G represents the undirected graph, V represents the vertex set of the undirected graph, and E represents the edge between the vertices in the undirected graph G. Divide the undirected graph G into two disjoint regions A and B, satisfying AB=V and A⌒B=Φ, and ...

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 related minimal normalization image segmentation method comprises: 1) reducing dimension to the target image; 2) taking minimal normalization segmentation to obtain the low-dimension segmentation boundary; 3) taking additional sampling, reconstructing an image with same dimension as the target; 4) connecting the discontinuous segmentation boundary to obtain the required segmentation boundary. This invention has acceptable time and space complexity and wide application.

Description

technical field [0001] The invention relates to an image segmentation method, in particular to an image segmentation method using normalized cut in graph theory. Background technique [0002] In computer vision, multimedia retrieval, multimedia nonlinear editing and object-oriented video coding, automatic and semi-automatic segmentation of video objects at the semantic level is a fundamental problem with wide application. In computer vision, object segmentation at the semantic level can obtain an intermediate description of the scene. It needs to fuse local and global descriptions of images and videos such as chromaticity, texture, and motion field in the image. Successful video object segmentation is further image coding, Fundamentals of scene understanding and pattern recognition. For example, the segmentation of video objects must be obtained in the extensive research on surveillance scene understanding. The surveillance scene understanding system can automatically deter...

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): G06K9/34
Inventor 贾天旭田东红苏钟人
Owner XIAMEN PRIMA TECH
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