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

Shaking table ore zoning image segmentation method based on krill optimization algorithm

An image segmentation and optimization algorithm technology, applied in the field of image processing, can solve problems such as slow convergence speed, achieve the effects of improving speed and accuracy, improving real-time performance, and saving labor

Active Publication Date: 2016-08-10
KUNMING UNIV OF SCI & TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the basic krill optimization algorithm still has the problem tha

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
  • Shaking table ore zoning image segmentation method based on krill optimization algorithm
  • Shaking table ore zoning image segmentation method based on krill optimization algorithm
  • Shaking table ore zoning image segmentation method based on krill optimization algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Example 1: see figure 1 , taking the zoning images of tin ore belts formed on the shaker bed taken from Datun Concentrator of Yunnan Tin Industry Group as an example, use VC++ software to write programs to analyze the concentrate, middle ore and tailings ore belts of tin ore For segmentation, the method and specific steps adopted are as follows:

[0029] (1) Carry out gray-scale processing to the colored shaker ore belt zoning image, and convert the colored shaker ore belt zoning image into a grayscale image;

[0030] (2) Initialization of individual krill: set parameters, foraging speed V f =0.02, the maximum diffusion speed D max =0.005, maximum moving speed N max = 0.01, the maximum number of iterations iter_max = 30 and the number of krill M = 25; the maximum inertia weight ω max =0.9, the minimum value of inertia weight ω min =0.1; generate M krill individuals evenly distributed in the gray histogram space of the shaker ore belt zoning image [0,255];

[0031]...

Embodiment 2

[0041] Example 2: see figure 1 , utilizing VC++ software to segment the concentrate, sub-concentrate, middle ore and tailings ore belts of the tin ore formed on the shaker bed, the method and steps adopted are the same as in Example 1, wherein the maximum number of iterations is 40:

[0042] (1) Carry out gray-scale processing to the colored shaker ore belt zoning image, and convert the colored shaker ore belt zoning image into a grayscale image;

[0043] (2) Initialization of individual krill: set parameters, foraging speed V f =0.02, the maximum diffusion speed D max =0.005, maximum moving speed N max = 0.01, the maximum number of iterations iter_max = 30 and the number of krill M = 25; the maximum inertia weight ω max =0.9, the minimum value of inertia weight ω min =0.1; generate M krill individuals evenly distributed in the gray histogram space of the shaker ore belt zoning image [0,255];

[0044] (3) Using the formula H(t of Kapur entropy 1 ,t 2 ,t 3 )=H 1 +H 2 ...

Embodiment 3

[0054] Embodiment 3: see figure 1 , the concentrate, sub-concentrate, middle ore and tailings ore belts of tin ore are segmented, the method and steps adopted are the same as in Example 1, and the maximum number of iterations is 40, wherein Kapur entropy H(t 1 ,t 2 ,t 3 )=H 1 +H 2 +H 3 +H 4 , to calculate the fitness function value of krill individual, after iterating steps (4), (5), (6) for 40 times, by maximizing the fitness function value, the maximum value of the fitness function is found 15.3772825987, and the search The optimal threshold value of the ore belt image [118,150,181], according to the searched optimal threshold, the shaker ore belt is segmented, so that the tin ore belt is divided into concentrate, secondary concentrate, medium ore and tailings There are four mine belts.

[0055] Using Kapur entropy to calculate the fitness function value of krill individuals, when the number of iterations is 40, the fitness function values ​​of 25 krill are respective...

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 a shaking table ore zoning image segmentation method based on a krill optimization algorithm, belonging to the image processing field. The shaking table ore zoning image segmentation method comprises steps of converting a colorized shaking table ore zoning image to a gray level image, performing initialization on the krill, calculating a fitness function value of the krill, arranging the krill, updating an inertial weight with the change of the inertial times, calculating a motion vector, a foraging motion vector and a physical dispersion motion vector of the krill, updating the positions of the krill, calculating the fitness function value of krill individuals, finding the krill having the optimal fitness function value through the optimization of the fitness function after a certain iteration time is satisfied, wherein the position corresponding to the krill is an optimal threshold of the shaking table ore zoning image, and performing segmentation on the shaking table ore zoning image according to the optimal threshold. The shaking table ore zoning image segmentation method performs updating on the inertia weight with the change of the iteration times, is faster and more accurate in searching the optimal threshold value through the algorithm, and is applicable to the segmentation of the shaking table ore zoning image.

Description

technical field [0001] The invention relates to an image segmentation method of a rocking table ore zone based on a krill optimization algorithm, and belongs to the technical field of image processing. Background technique [0002] At present, in the shaker beneficiation in our country, most of them use the naked eye to observe the change of the shaker ore zone and manually divide the shaker ore zone. This method has waste of labor, poor real-time performance, and Disadvantages such as low accuracy and low metal recovery rate. In order to overcome its shortcomings, the image segmentation of the rocking table ore belt zoning based on digital image processing technology is proposed. It does not need manual intervention, and the image segmentation technology is directly used to segment the shaking table ore belt zoning image in real time. The image segmentation method is key technologies. At present, there are many image segmentation methods. Considering the need for real-tim...

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): G06T7/00G06Q50/02
CPCG06Q50/02G06T7/0004G06T2207/30108
Inventor 和丽芳郭思哲黄宋魏童雄郝鹏宇司绪张元元
Owner KUNMING UNIV OF SCI & 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