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

Chaos genetic BP neural network image segmentation method based on Arnold transformation

A BP neural network and chaotic genetic technology, applied in the image segmentation field of chaotic genetic BP neural network based on Arnold transform, can solve the problems of low initial population ergodicity, poor local optimization ability, complex individual operation, etc., so as to avoid individual prematurity problems, speed up evolution, and ensure ergodic effects

Active Publication Date: 2017-11-07
HENAN NORMAL UNIV
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The invention provides a chaotic genetic BP neural network image segmentation method based on Arnold transform, aiming to solve the problem of slow convergence speed, poor local optimization ability, complex individual operation in the population and initial The problem of low population traversability

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
  • Chaos genetic BP neural network image segmentation method based on Arnold transformation
  • Chaos genetic BP neural network image segmentation method based on Arnold transformation
  • Chaos genetic BP neural network image segmentation method based on Arnold transformation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] The method of this embodiment comprises the following steps: 1) set up BP neural network; 2) obtain the initial weight value and initial threshold value of BP neural network according to the optimal solution obtained by chaotic genetic algorithm; 3) bring initial threshold value and initial weight value into In the BP neural network, the input data is used for training, and the weights and thresholds of the BP neural network are updated by the error obtained each time, and the trained BP neural network is obtained through repeated iterations; 4) image segmentation is performed using the trained BP neural network ;

[0056] The specific process of obtaining the initial weights and initial thresholds of the BP neural network based on the optimal solution obtained by the chaotic genetic algorithm is as follows:

[0057] ①Initialize population: generate population p by chaotic mapping method, divide population p into initial population x and population y to be optimized; th...

Embodiment 2

[0135] It is found in the research that the above-mentioned chaotic perturbation in the mutation process can improve the local search ability of the algorithm, but it has the following shortcomings: chaotic perturbation completely replaces the random mutation of the population and ignores the influence of the mutation rate in different evolutionary periods on the search results. Individual chaotic perturbation reduces the search efficiency, so this embodiment improves the chaotic mutation strategy:

[0136] When performing the chaotic mutation operation, the adaptive mutation is performed first, and then the fitness value of the adaptive mutation individual is calculated, the fitness value is sorted according to the high and low, and the previously preset number of individuals with higher fitness values ​​are selected as excellent individuals. Perform chaotic mutation operations on the remaining individuals according to Step1-Step4. Wherein, the preset number is preferably 10%...

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 relates to a chaos genetic BP neural network image segmentation method based on Arnold transformation. The method comprises BP neural network optimization through adoption of a chaos genetic algorithm and image segmentation by utilizing a trained neural network. The specific process of the chaos genetic algorithm is as follows: (1) a swarm is initialized, two swarms x, y are generated through chaos mapping, the small swarm x is taken as an initial swarm, and the large swarm y is standby; (2) individual fitness values in the initial swarm x are calculated; and individuals the number of which is set after the individual fitness values in the initial swarm x are replaced with individuals in the large swarm y, and fitness values of the individuals after replacement are calculated; and (3) according to the calculated individual fitness values, selection, intersection and chaotic variation operation are performed on the individuals in the initial swarm x until the fact that the maximum evolution frequency is reached or the maximum fitness is not changed, and then the algorithm stops. Ergodicity of a swarm evolution process can be effectively ensured, neural network training process is speeded up, and an image segmentation effect is enhanced.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a chaotic genetic BP neural network image segmentation method based on Arnold transformation. Background technique [0002] Image segmentation is a basic image recognition and analysis technique. It determines the quality of digital image analysis and the quality of visual information processing results, and is also a key step from image processing to image analysis. The purpose of image segmentation is to divide the image into several disjoint regions, so that each region has consistency, but the attribute characteristics between adjacent regions are obviously different. The current image segmentation methods such as image segmentation based on the threshold method are based on Morphological image segmentation, image segmentation based on fuzzy clustering, image segmentation based on neural network, image segmentation method based on support vector machine, etc. [00...

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): G06T7/11G06N3/08
CPCG06N3/084G06N3/086G06T7/11G06T2207/20081G06T2207/20084
Inventor 孙林张祥攀李敏张磊刘琳王振华王伟穆晓霞李梦莹刘琛
Owner HENAN NORMAL 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