Gray-scale image edge detection method based on pulse coupling neural network

A pulse-coupled neural and gray-scale image technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of widening and discontinuity of borders, achieve the effect of increasing processing speed and overcoming widening of edges

Inactive Publication Date: 2015-12-02
JIANGXI NORMAL UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a gray-scale image edge detection method based on pulse-coupled neural network, which solves the problem that the detected boundary may change due to the existence of noise and blurring in the actual application of the existing edge detection method. wide or breaks at certain points

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
  • Gray-scale image edge detection method based on pulse coupling neural network
  • Gray-scale image edge detection method based on pulse coupling neural network
  • Gray-scale image edge detection method based on pulse coupling neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The beneficial effects of the present invention will be described in detail below in conjunction with the examples, aiming to help readers better understand the essence of the present invention, but not to limit the implementation and protection scope of the present invention.

[0027] First, construct a single-layer two-dimensional, locally connected pulse-coupled neural network, in which the number of neurons is equal to the number of pixels in the grayscale image, and the neurons correspond to and connect to each pixel one by one, and are connected to the adjacent neurons at the same time. Connection, the constructed model is as follows:

[0028] f jk [i]=S jk +F jk [i-1]·e αF +V F ·(M*Y[i-1]) jk

[0029] L jk [i]=L jk [i-1]·e αL +V L ·(K*Y[i-1]) jk ,

[0030] In the formula, K and M are connection weight matrices, * means convolution operation, Y is the information of neuron firing or not, αL and αF are time decay constants, V L and V F is the connecti...

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 gray-scale image edge detection method based on a pulse coupling neural network, and the method achieves the edge detection of a gray-scale image through employing the pulse propagation and connection characteristics of the pulse coupling neural network and the gray-scale saltation principle of the edge of the gray-scale image, can directly achieve the effective detection and extraction of the edge of a 256-color gray-scale image, overcomes the conditions that a detected edge becomes wide or is cracked in a noise environment, and greatly improves the processing speed. Therefore, the technology of video recognition achieved based on the above reaches a national advanced level.

Description

technical field [0001] The invention relates to a grayscale image edge detection method, in particular to a grayscale image edge detection method based on a pulse-coupled neural network. Background technique [0002] The existing edge detection method is to investigate the change of gray level in the specific neighborhood of each pixel of the image, and detect the edge according to the corresponding first-order or second-order directional derivative change law. Product algorithm to achieve. [0003] The derivative operator has the function of highlighting the change of gray level. Applying the derivative operator to the image, the calculated value at the point with a large change in gray level is relatively high. Therefore, these derivative values ​​can be used as the boundary strength of the corresponding point, and by setting the threshold method , to extract the boundary point set, the first derivative and is the simplest derivative operator, they respectively calculate ...

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): G06T7/00
Inventor 杨智勇
Owner JIANGXI 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