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

Glowworm optimization algorithm-based ore zone image segmentation method

A technology of firefly optimization and image segmentation, which is applied in the field of image processing, can solve problems such as slow convergence speed and low convergence precision, and achieve the effects of improving speed and accuracy, reducing iteration times, and efficient utilization

Inactive Publication Date: 2013-10-23
KUNMING UNIV OF SCI & TECH
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The firefly optimization algorithm is a new intelligent swarm optimization algorithm, but the basic firefly optimization algorithm has the disadvantages of slow convergence speed and low convergence accuracy in the later stage

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
  • Glowworm optimization algorithm-based ore zone image segmentation method
  • Glowworm optimization algorithm-based ore zone image segmentation method
  • Glowworm optimization algorithm-based ore zone image segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Example 1: see figure 1 , taking the tin ore image taken from the Datun Concentrator of Yunnan Tin Industry Group as an example, using VC++ software to segment the tin ore concentrate and tailings belt, the method and specific steps are as follows:

[0032] (1) Preprocessing of the ore belt image. Since the ore belt image is captured in real time during the beneficiation process, the image is easily affected by external noise. Therefore, in this step, the color ore belt image is first converted into a grayscale image; and then Then use adaptive low-pass filtering to filter the grayscale image;

[0033] (2) Firefly initialization, setting parameters: maximum number of iterations is 10, the number of fireflies N is 50, and the dynamic decision domain The initial value is 3, the perception domain radius is 5, the fluorescein renewal rate 0.6, the disappearance rate of fluorescein is 0.4, the maximum value of the step size 1, the minimum value of the step size ...

Embodiment 2

[0043] Example 2: see figure 1 , Utilize VC++ software to segment the concentrate and tailings ore belt of tin ore, the method and steps adopted are identical with embodiment 1, wherein the number of fireflies is 70:

[0044] (1) Preprocessing of the ore belt image. Since the ore belt image is captured in real time during the beneficiation process, the image is easily affected by external noise. Therefore, in this step, the color ore belt image is first converted into a grayscale image; and then Then use adaptive low-pass filtering to filter the grayscale image;

[0045] (2) Firefly initialization, setting parameters: maximum number of iterations is 20, the number of fireflies N is 70, and the dynamic decision domain The initial value is 3, the perception domain radius is 5, the fluorescein renewal rate 0.6, the disappearance rate of fluorescein is 0.4, the maximum value of the step size 1, the minimum value of the step size is 0.001; use a random function unifor...

Embodiment 3

[0055] Embodiment 3: see figure 1 , the concentrate, middle ore and tailings ore belts of tin ore are segmented, the method and steps adopted are the same as those in Example 1, wherein the largest inter-class variance is used , calculate the fitness function, through iterative steps (3), (4), (5), (6) 20 times, continuously search for the maximum value of the fitness function, and search for the optimal threshold of the ore belt image to be , the grayscale image of the ore belt is composed of pixels, and each pixel has a certain threshold, so the ore belt image is thresholded according to the optimal threshold, so that the tin ore belt is divided into concentrate, medium ore and tailings.

[0056] When the number of iterations is 20, the values ​​of 50 firefly luciferins are:

[0057]

[0058] use the maximum between-class variance , calculate the ore zone

[0059] The fitness function of the image; when the number of iterations is 20, .

[0060]

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 glowworm optimization algorithm-based ore zone image segmentation method, belonging to the technical field of image processing. The method comprises the steps: firstly, pre-treating an ore zone image, converting the colorful ore zone image into a gray level image and carrying out self-adaptive low-pass filtering treatment; uniformly distributing glowworms in a grey level histogram space of the ore zone image, updating the value of the fluorescein of each glowworm, according to local information, global information and a policy of step size self-adaptive updating along with iterations, updating local decision domain radius of the glowworms, calculating a fitness function, according to the fitness function, and searching for the global optimal solution, wherein after multiple iterations, the global optimal position is the optimal threshold value; and according to the optimal threshold value, segmenting the ore zone image. According to the method, in the moving process of the glowworm, the global information and the policy of step size self-adaptive updating along with iterations are added, the convergence speed and accuracy of the algorithm are high, the global optimization capability is strong, and the method is suitable for ore zone image segmentation.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for segmenting mine belt images by using a firefly optimization algorithm. Background technique [0002] At present, in my country's mineral processing industry, most of them use manual methods to divide ore belts, which have the disadvantages of poor real-time performance, waste of labor, and low mineral recovery rate. [0003] The mine belt segmentation based on digital image processing technology can segment the mine belt in real time without manual intervention. In the whole process, image segmentation is a key step, which can separate the mine belt. There are many image segmentation algorithms. Because different mine belts have certain differences in color and gray scale and mine belt images need to be segmented in real time, the image segmentation method based on threshold is suitable for mine belt segmentation. [0004] Among the image segmen...

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): G06T7/00G06T5/00G06N3/00
Inventor 和丽芳童雄黄宋魏宋耀莲黄斌黄靖惠
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