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

Image edge detection method based on adaptive differential evolution

A differential evolution and image edge technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as insufficient search capabilities, achieve the effects of enhancing search capabilities, improving efficiency, and overcoming insufficient search capabilities

Active Publication Date: 2021-02-19
JIANGXI UNIV OF SCI & TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

To a certain extent, it overcomes the shortcomings of traditional differential evolution in the design of convolution kernels for image edge detection.

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 edge detection method based on adaptive differential evolution
  • Image edge detection method based on adaptive differential evolution
  • Image edge detection method based on adaptive differential evolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0043]Present embodiment in conjunction with accompanying drawing, the specific implementation steps of the present invention are as follows:

[0044] Step 1, the user inputs the training image OIM, and inputs the reference edge image RIM of the training image OIM;

[0045] Step 2, user input such as figure 1 The test image TIM shown;

[0046] Step 3, the user inputs the population size NP=30, the maximum number of iterations GMAX=35;

[0047] Step 4, setting scaling factor F=0.5;

[0048] Step 5, set the variation adjustment factor CA ki =0.9, then set the backup hybridization probability BCR ki =0.9, where subscript ki=1,2,...,NP;

[0049] Step 6, set current algebra G=0;

[0050] Step 7: Randomly generate NP individuals to form a population EP={X 1 ,X 2 ,...,X ki ,...,X NP}, where X ki ={X ki,1 ,X ki,2 ,...,X ki,pj ,...,X ki,HD} is the kith individual in the population, and the subscript ki=1,2,...,NP; each individual in the population stores HD convolution k...

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 edge detection method based on adaptive differential evolution. According to the method, the convolution kernel coefficient of image edge detection is designed by applying adaptive differential evolution, and then image edge detection is realized by utilizing the designed convolution kernel coefficient. In adaptive differential evolution, each individual stores a designed convolution kernel coefficient. In each generation of evolution operation, a mutation strategy is adaptively selected according to a mutation regulation factor to execute the mutation operation, Gaussian distribution is utilized to improve the adaptability of the hybridization probability, and the search capability of differential evolution is enhanced, so that the efficiency of image edgedetection is improved.

Description

technical field [0001] The invention relates to the field of digital image processing, in particular to an image edge detection method based on adaptive differential evolution. Background technique [0002] Edge detection is an important digital image processing method, which plays a very important role in image segmentation and image feature extraction. In order to realize image edge detection, technicians usually use given convolution kernel coefficients to perform convolution operations on digital images. Commonly used convolution kernels are: Sobel convolution kernel, Roberts convolution kernel and Prewitt convolution kernel. These commonly used convolution kernels have achieved certain results in edge detection of many images. However, since these convolution kernels are designed for general image edge detection. Therefore, when these commonly used convolution kernels are applied to image edge detection in specific scenes, they often focus on unimportant edge informa...

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): G06T7/13G06N3/00
CPCG06T7/13G06N3/006G06T2207/20081
Inventor 向传娇郭肇禄尹宝勇周才英张文生
Owner JIANGXI 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