Agent-driven multi-objective evolutionary fuzzy clustering method based on preference information

A fuzzy clustering method and multi-objective evolution technology, applied in the field of image processing, can solve the problems of low calculation efficiency and long time consumption of the algorithm, and achieve better segmentation effect, reduce time cost, and improve evolution efficiency

Pending Publication Date: 2021-11-30
XIAN UNIV OF POSTS & TELECOMM
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to address the above-mentioned deficiencies in the prior art, and propose an agent-driven multi-objective evolutionary fuzzy clustering method based on preference info

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
  • Agent-driven multi-objective evolutionary fuzzy clustering method based on preference information
  • Agent-driven multi-objective evolutionary fuzzy clustering method based on preference information
  • Agent-driven multi-objective evolutionary fuzzy clustering method based on preference information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] Refer to attached figure 1 , an agent-driven multi-objective evolutionary fuzzy clustering method based on preference information proposed by the present invention, which generally includes the following steps:

[0059] Step A. Input the image to be segmented and set the initial parameter values.

[0060] Input the image I to be divided;

[0061] Set initial parameter values: population size E=50, fuzzy index m=2, maximum iteration number of fine search TF max =50, the threshold σ=0.3, the reference point is (0.1,0.9), the maximum number of iterations of rough search TC max =20, the crossover probability is 0.9, the mutation probability is 0.1, the coefficient β=0.3 to control the dimension of the coarse search space, the weight factor χ=0.5 to control the image region information, and the number of reference vectors v=40;

[0062] Step B: Apply the multi-objective evolutionary fuzzy clustering method based on reference points and preference angles guided by coarse a...

Embodiment 2

[0080] Refer to attached figure 1 , the method proposed by the present invention specifically includes the following steps:

[0081] Step 1: Input the image I to be segmented, and set the initial parameter values: population size E=50, fuzzy index m=2, maximum iteration number TF of fine search max =50, the threshold σ=0.3, the reference point is (0.1,0.9), the maximum number of iterations of rough search TC max =20, the crossover probability is 0.9, the mutation probability is 0.1, the coefficient β=0.3 to control the dimension of the coarse search space, the weight factor χ=0.5 to control the image region information, and the number of reference vectors v=40;

[0082] Step 2: Use Latin hypercube sampling to obtain the initial population X, and encode the chromosomes in the population;

[0083] Step 3: Decode each encoded chromosome to obtain a column vector, calculate the fitness function value Y corresponding to each chromosome, specifically calculate the global fuzzy com...

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 agent-driven multi-objective evolutionary fuzzy clustering method based on preference information, and mainly solves the problems that the existing color image segmentation performance is not ideal and the calculation cost is high. The scheme comprises the steps of inputting a to-be-segmented image and setting an initial parameter value; constructing a fitness function fusing image region information, introducing a thickness agent model, and designing a multi-objective evolution clustering framework based on a dominating relation of a reference point and a preference angle to obtain a non-dominating solution set; constructing a clustering effectiveness index by using information entropy of a fuzzy membership function, and selecting an optimal chromosome from the non-dominated solution set by using the index to decode the optimal chromosome so as to obtain an optimal clustering center; updating the global membership matrix by using the optimal clustering center, and obtaining a classification result of the pixel points according to a maximum membership principle. For an image with a complex background and a low contrast ratio, the image segmentation effect can be effectively improved, and the consumed time is short; the method can be used for natural image recognition.

Description

technical field [0001] The invention belongs to the field of image processing, and further relates to a fuzzy clustering image segmentation method, specifically an agent-driven multi-objective evolutionary fuzzy clustering method based on preference information, which can be used for natural image recognition. Background technique [0002] Image segmentation is to divide the image into several disjoint regions according to features such as grayscale, color, texture and geometric shape, so that the features show similarity in the same region and obvious differences between different regions. Image segmentation algorithms mainly include threshold-based segmentation algorithms, cluster-based segmentation algorithms, edge detection-based segmentation algorithms, and convolutional neural network-based weakly supervised learning segmentation algorithms. Common clustering methods can be mainly divided into K-means clustering algorithm, fuzzy clustering algorithm, density-based clus...

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): G06K9/62G06K9/34G06N3/00
CPCG06N3/006G06F18/23Y02T10/40
Inventor 赵凤刘非凡刘汉强
Owner XIAN UNIV OF POSTS & TELECOMM
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