Image segmentation method based on improved genetic algorithm

An improved genetic algorithm and image segmentation technology, which is applied in the field of visible light target detection and image segmentation, can solve the problems of losing the original information of the image and slow speed, and achieve the effect of slow solution and speed improvement

Inactive Publication Date: 2018-12-14
昆山智易知信息科技有限公司 +2
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the standard genetic algorithm SGA is used to segment the target image with a complex background, the speed will be slow and the original information of the image will be lost.

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
  • Image segmentation method based on improved genetic algorithm
  • Image segmentation method based on improved genetic algorithm
  • Image segmentation method based on improved genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The technical solutions and effects of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0040] refer to figure 1 , the implementation steps of the present invention are as follows:

[0041] Step 1, input RGB color image and process it.

[0042] 1a) will be as figure 2 The RGB color image shown is used as the input original image;

[0043] 1b) Use the weighted average algorithm 0.2989R+0.5870G+0.1140B to process each pixel of the original image into a grayscale point, and generate the grayscale image pic of the original image.

[0044] Step 2, generate a population according to the genetic algorithm and initialize it.

[0045] 2a) In the original grayscale image pic, randomly select 1 / 4 pixels of the total number of pixels to form individuals of the initial population p, and define the pixel values ​​corresponding to these individuals as individual values;

[0046] 2b) According to the pixel value rang...

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 image segmentation method based on an improved genetic algorithm, which mainly solves the problem that the segmentation precision is not enough and the original informationof the image is lost when the prior art segments the target image under the complex background. The scheme includes: 1, processing the input color RGB image into a gray scale image pic; 2, generatingan initial population p, and treating all individual in that population p; 3, summing up the individual value in population p and using the result as the parameter to construct the improved individualfitness function; 4, using the improved individual fitness function as the fitness function in genetic algorithm, and obtaining the threshold g of the best segmentation image by iterative operation on the individual in the population; 5. performing target image segmentation by using the b segmentation threshold. The invention can be used for visible light target detection in a complex background.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image segmentation method, which can be used for visible light target detection under complex backgrounds. Background technique [0002] With the rapid development of information technology marked by computer technology, the degree of digitalization of human society is getting higher and higher. At the same time, the technology and means of dealing with digital objects are constantly being updated. Image is the light information transmitted or reflected by an object, and the impression or cognition formed in the brain through the human visual system. As an information carrier, it has the characteristics of intuition, convenience, easy understanding and perception, etc. that other information carriers do not have. . [0003] In engineering, a digital image is defined as an image that can be stored and processed by a computer. Using computers and other eq...

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): G06T7/136G06N3/12G06N3/00
CPCG06N3/006G06N3/126G06T2207/10024G06T7/136
Inventor 李林刘思成姬红兵张文博臧博
Owner 昆山智易知信息科技有限公司
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