Glowworm swarm optimization method-based image multi-threshold segmentation method

A firefly, multi-threshold technology, applied in the field of image processing, can solve the problems of long time consumption and low segmentation accuracy, and achieve the effect of fast segmentation and high segmentation threshold accuracy.

Inactive Publication Date: 2018-01-16
SHAANXI NORMAL UNIV
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing image threshold segmentation methods include the threshold segmentation method based on the graph theory, the maximum entropy automatic threshold method, etc., but there are problems such as low segmentation accuracy and long time-consuming

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 swarm optimization method-based image multi-threshold segmentation method
  • Glowworm swarm optimization method-based image multi-threshold segmentation method
  • Glowworm swarm optimization method-based image multi-threshold segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Taking a color image of the MSRA salient target data set as an example, the number is 1_56_56055, the steps of the image multi-threshold method based on the firefly swarm optimization method are as follows:

[0054] (1) Image preprocessing and determining the number of image thresholds

[0055] figure 1 A flowchart of this embodiment is given. exist figure 1 , read in the image and convert it to grayscale to get a grayscale image, see figure 2 , perform median filter processing, denoising processing, and obtain a grayscale histogram, see image 3 ,exist image 3 The middle abscissa is the gray value, and the ordinate is the number of pixels. Points (9, 741), points (82, 1511), and points (118, 2953) are peaks, and the height of the peaks is higher than the baseline 738. Determine The number of peaks is 3, and the number D of the obtained image threshold is 2; the grayscale image is processed by a first-level wavelet transform, and the obtained grayscale image is t...

Embodiment 2

[0087] Taking a color image of the MSRA salient target data set as an example, the number is 1_56_56055, the steps of the image multi-threshold method based on the firefly swarm optimization method are as follows:

[0088] In this embodiment, steps (1) and (2) are the same as in Embodiment 1.

[0089] In the parameter setting step 1) of step (3), the maximum number of iterations M of the firefly swarm optimization method is 100, the iteration count m is 1-100, the population size G of fireflies is 50, and the firefly count i is 1-50, The firefly count j is 1-50 and j≠i, the step size S is 15, the number of fireflies in the neighborhood α is 42, the neighborhood change rate β is 0.5, the fluorescein volatilization factor h is 0.8, and the fitness function extraction ratio γ is 0.8, the maximum decision radius r max is 140, the initial fluorescence brightness L of fireflies 0 30, the initial induction radius r 0 is 70, and the firefly decision radius is r i , the position of...

Embodiment 3

[0092] Taking a color image of the MSRA salient target data set as an example, the number is 1_56_56055, the steps of the image multi-threshold method based on the firefly swarm optimization method are as follows:

[0093] In this embodiment, steps (1) and (2) are the same as in Embodiment 1.

[0094] In the parameter setting step 1) of step (3), the maximum number of iterations M of the firefly swarm optimization method is 300, the iteration count m is 1-300, the population size G of fireflies is 150, and the firefly count i is 1-150, The firefly count j is 1-150 and j≠i, the step size S is 17, the number of fireflies in the neighborhood α is 49, the neighborhood change rate β is 0.9, the fluorescein volatilization factor h is 0.99, and the fitness function extraction ratio γ is 0.99, the maximum decision radius r max is 150, the initial fluorescence brightness L of fireflies 0 35, the initial induction radius r 0 is 75, and the firefly decision radius is r i , the positi...

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

A glowworm swarm optimization method-based image multi-threshold segmentation method is composed of the steps of pre-processing an image, determining the number of the image thresholds, setting an objective function, using a glowworm swarm optimization method to search an optimal threshold and carrying out the image multi-threshold segmentation, and concretely comprises reading a color image and carrying out the gray processing to obtain a gray histogram of the image, according to the number of the peak values of the histogram of the image, automatically determining the number of the segmentation thresholds, randomly distributing the initial positions of the glowworms within an image gray value range, determining the fitness function value and the fluorescent brightness value at the position of each glowworm, searching the glowworms having the largest fluorescent brightness values within the decision radius of each glowworm and comparing, updating the positions and the decision radiuses, after iteration, finding out a globe optimal segmentation threshold, and carrying out the multi-threshold segmentation on the gray image after the first-order Wavelet transform. Compared with the prior art, the method of the present invention has the advantages of being fast in segmentation speed and high in segmentation threshold precision, etc., and can be used for the color image and gray image segmentation.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to image multi-threshold segmentation. Background technique [0002] With the rapid development of computer technology, digital image processing, as one of its branches, is more and more widely used in image compression processing, biometrics, medical image processing and other fields. Image segmentation is a key step in image analysis. It refers to the process of separating the target part of interest from the background by selecting the corresponding segmentation principle according to the characteristics of the image. The quality of the segmentation result will directly affect the subsequent image processing. Common image segmentation methods include region growth method, edge detection method, threshold method, etc. Among them, the image threshold segmentation method is a classic segmentation method, the process is simple and easy to implement, by observing the gray his...

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): G06T7/136G06T5/40G06T5/20G06T5/00G06N3/00
Inventor 马苗陶丽丽杨楷芳郑玮鸽
Owner SHAANXI NORMAL UNIV
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