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

Image segmentation method based on multi-kernel local information FCM algorithm

A technology of image segmentation and local information, applied in image analysis, image data processing, calculation, etc., can solve the problems of FILCM algorithm pollution, etc., and achieve the effect of increasing resistance to variation and robustness, accurate image segmentation, and accurate clustering results

Inactive Publication Date: 2017-06-13
HEFEI UNIV OF TECH
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the deficiencies in the prior art above, the present invention proposes an image segmentation method based on the multi-core local information FCM algorithm, in order to avoid the problem that FCM is sensitive to noise points and the FILCM algorithm is polluted in the neighborhood pixels, and at the same time It can find the most suitable weight value and return the size of the current membership value, thereby improving the reliability and convergence of the algorithm, thereby improving the accuracy of image segmentation

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-kernel local information FCM algorithm
  • Image segmentation method based on multi-kernel local information FCM algorithm
  • Image segmentation method based on multi-kernel local information FCM algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In this embodiment, an image segmentation method based on the multi-core local information FCM algorithm is performed according to the following steps:

[0041] Step 1. For an image with n pixels, let X={x 1 ,x 2 ,...,x j ,...,x n} represents the pixel set of the image, x j Indicates the jth pixel; 1≤j≤n, n is the number of pixels; optimally divide the pixel set X, so that the objective function value J shown in formula (1) is the smallest:

[0042]

[0043] In formula (1), i represents the i-th category, c represents the number of categories divided, and 1≤i≤c, u ij represents the jth pixel x j The membership degree value of the i-th class, and U={u ij | i＝1,2,…,c；j＝1,2,…,n} represents the membership matrix; 0≤u ij ≤1; Indicates that the j-th pixel belongs to the m-th power of the membership degree of the i-th class, and m is a weighted index, indicating the degree of clustering fuzziness; P ij is a balance factor, reflecting the spatial information from ...

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 segmentation method based on a multi-kernellocal information FCM algorithm. The image segmentation method is characterized by including the steps that 1, optimal division is carried out on a pixel set, so that the value of a target function is made minimum; 2, an initial membership grade matrix and an initialized clustering center are obtained; 3, a membership grade value and the clustering center are obtained through iteration; 4, a target function after a weight index is introduced is obtained. The image segmentation method can accurately avoid that an FCM is sensitive to noise points, and in implementation of a common kernel method, selection of a kernel function is not determined, meanwhile can find the most appropriate weight value and a current membership grade value to improve the reliability and astringency of the algorithm, is applied to image segmentation, and can achieve a good image segmentation effect.

Description

technical field [0001] The invention belongs to an algorithm for data classification in the field of data mining, in particular to a fuzzy c-means clustering algorithm of multi-core local information, which is applied to image segmentation. Background technique [0002] Clustering is a very important branch of unsupervised pattern recognition. The ultimate goal of clustering is to make the distance between similar pixels as small as possible and to make the distance between different pixels as large as possible. In this way, data can be distinguished. , categorical data. Image processing is an important part of computer vision. Fuzzy clustering is used to meet the needs of two aspects. First, the subjectivity of human vision makes images suitable for processing by fuzzy means. Second, the lack of training pixel images requires unsupervised The analysis of fuzzy clustering in the field of image processing is the most widely used image segmentation, which is equivalent to uns...

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): G06T7/10
Inventor 唐益明赵跟陆胡相慧任福继丰刚永
Owner HEFEI UNIV OF 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