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

Artificial immune network clustering based grayscale image segmentation method

An artificial immune network and gray-scale image technology, applied in the field of clustering and segmentation based on artificial immune network, can solve the problems of increasing the time complexity of the segmentation process, unable to ensure the optimization function, increasing the computational complexity and other problems, and achieve accurate regional consistency , good edge retention performance, and speed-up effects

Inactive Publication Date: 2015-07-22
XIDIAN UNIV
View PDF1 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method has a certain improvement effect in terms of regional consistency and edge preservation, there are still shortcomings in this method: too many evolutionary techniques are used: cloning, binary crossover and binary mutation, crossover and mutation for all data in the cluster For the crossover, after selecting a certain breakpoint, that is, a certain dimension of the clustering data, it needs to be operated separately, which increases the time complexity of the entire segmentation process and makes the segmentation speed slower. For image segmentation, the efficiency is reduced; clustering is transformed into a multi-objective optimization problem. Compared with single-objective clustering, multiple optimization functions are used. When one of the functions is guaranteed to be optimal, the rest cannot be guaranteed. The optimization function can get the optimal solution, but how to choose the compromise optimal of multiple functions increases the computational complexity

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
  • Artificial immune network clustering based grayscale image segmentation method
  • Artificial immune network clustering based grayscale image segmentation method
  • Artificial immune network clustering based grayscale image segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] In order to further improve the segmentation speed, the present invention provides a grayscale image segmentation method based on artificial immune network clustering, see figure 1 , grayscale image segmentation includes the following steps:

[0055] Step 1. Input the grayscale image to be segmented. In this example, the images applied respectively are lina image, vegetable image and rice image. See figure 2 (a), image 3 (a) and Figure 4 (a).

[0056] Step 2. Extract the texture features of the grayscale image to be segmented:

[0057] 2a) extracting the feature vector of the grayscale image to be segmented using the grayscale co-occurrence matrix method;

[0058] 2b) Use the extracted feature vector to represent each pixel of the grayscale image to be segmented.

[0059] Step 3. Generate the clustering data of the immune network to obtain the initial antigen set Ag:

[0060] 3a) Process the grayscale image to be segmented with the watershed method to obtain im...

Embodiment 2

[0090] The grayscale image segmentation method based on artificial immune network clustering is the same as embodiment 1, wherein the grayscale co-occurrence matrix method described in step 2a) includes the following steps:

[0091] 2a1) Quantize the grayscale image to be segmented into 0-255, a total of 256 grayscales;

[0092] 2a2) Select four directions in which the angle between the line connecting two pixels in the grayscale image to be segmented and the horizontal axis is 0°, 45°, 90°, and 135° in turn, and calculate the four directions of the image to be segmented according to the following formula: The gray level co-occurrence matrix of the direction:

[0093] p(i,j)=#{(x 1 ,y 1 ),(x 2 ,y 2 )∈M×N|f(x 1 ,y 1 )=r,f(x 2 ,y 2 )=s}

[0094] Among them, p(i,j) is the element value of the gray level co-occurrence matrix at the coordinate (i,j) position, # is the number of elements in the set {}, (x 1 ,y 1 ) and (x 2 ,y 2 ) is the coordinates of two pixel points w...

Embodiment 3

[0097] The grayscale image segmentation method based on artificial immune network clustering is the same as embodiment 1-2, wherein the watershed method described in 3a) processes the grayscale image to be segmented and includes the following steps:

[0098] 3a1) Obtaining the gradient map of the grayscale image to be segmented;

[0099] 3a2) Select the internal mark of the grayscale image to be segmented, that is, find the local minimum value of the grayscale image to be segmented;

[0100] 3a3) selecting the external marker of the grayscale image to be segmented, that is, the watershed transformation of the internal marker of the grayscale image to be segmented;

[0101] 3a4) Gradient correction: use the forced minimum technique to correct the gradient of the grayscale image to be segmented, so that the local minimum area only appears at the marked position of the grayscale image to be segmented;

[0102] 3a5) Watershed transformation is performed on the corrected gradient ...

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 artificial immune network clustering based grayscale image segmentation method, mainly aiming at solving the problems that the existing image segmentation technology is high in computation complexity and low in segmentation speed. The artificial immune network clustering based grayscale image segmentation method mainly comprises the following steps: (1) inputting a grayscale image to be segmented; (2) extracting the characteristics of the grayscale image to be segmented; (3) acquiring clustered data; (4) generating an initial antibody population randomly to realize initialization; (5) training optimally; (6) checking whether all antigens enter the network; (7) repeating the steps 5 and 6 for 100 times and ending the optimization training; (8) clustering; (9) generating a clustering result; and (10) outputting a segmented image. According to the artificial immune network clustering based grayscale image segmentation method, a watershed and the immune network clustering method are adopted to realize grayscale image segmentation, more image detail information is acquired, accurate region homogeneity and good edge retentivity are acquired, the segmentation speed is high, the overall segmentation precision is improved and the method can be applied to the technical field of natural grayscale image segmentation.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a grayscale image segmentation technology, in particular to a clustering and segmentation method based on an artificial immune network. The invention can be used for the segmentation of natural grayscale images to achieve the purpose of target recognition. Background technique [0002] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. At present, people mostly use methods based on cluster analysis for image segmentation. Segmenting an image with a method based on cluster analysis is to represent the pixels in the image space with corresponding feature space points, segment the feature space according to their aggregation in the feature space, and then map them back to the original image space to achieve image segmentation. the goal of. [0003] In order to...

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): G06T7/00
Inventor 李阳阳焦李成于一然马文萍尚荣华马晶晶杨淑媛侯彪屈嵘
Owner XIDIAN 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