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

Pulse coupling neural network skeletal muscle image processing method based on pixel values

A technology of pulse-coupled neural and image processing, which is applied in the field of image processing and can solve problems such as difficulty in parameter setting of pulse-coupled neural networks

Inactive Publication Date: 2021-02-05
HARBIN UNIV OF SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the defects or deficiencies in the above-mentioned prior art, the present invention proposes a pulse-coupled neural network based on pixel values ​​to solve the problem of difficult parameter setting of the existing pulse-coupled neural network, including the following steps:

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
  • Pulse coupling neural network skeletal muscle image processing method based on pixel values
  • Pulse coupling neural network skeletal muscle image processing method based on pixel values
  • Pulse coupling neural network skeletal muscle image processing method based on pixel values

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0028] to combine figure 1 Shown, the present invention mainly comprises three main steps:

[0029] Step 1, solve for the amplitude V of the dynamic threshold E with connection coefficient β;

[0030] Step 2, Substitute the pixel threshold of the region of interest in the image to be processed into the target optimization formula, and the output result is the exponential attenuation factor k of the feed input f ;

[0031] Step 3, pass k f and the exponential decay factor k of the leaky product e The relationship between, solve k e...

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 provides a pulse coupling neural network skeletal muscle image processing method based on a pixel value, and the method comprises the following steps: solving the amplitude VE and connection coefficient beta of a dynamic threshold; secondly, substituting a pixel threshold value of a region of interest in an image to be processed into a target optimization formula, and taking an output result as an exponential attenuation factor kf of feed input; and finally, solving and obtaining the ke through the relationship between the kf and the exponential decay factor ke of the leakage integrator. Compared with an existing popular pulse coupling neural network scheme, the method has the advantages that fewer parameter setting times are used, and a better processing effect is obtained.

Description

technical field [0001] The invention relates to the field of image processing, and particularly designs a pulse-coupled neural network skeletal muscle image processing method based on pixel values. Background technique [0002] Pulse-coupled neural network has developed rapidly in image processing fields such as image segmentation, image shadow removal, image fusion, feature extraction, and pattern recognition. Currently, standard pulse-coupled neural networks are often simplified to reduce computational complexity while preserving essential properties of the visual cortex. [0003] Since the pulse-coupled neural network method inherits the characteristics of the mammalian visual cortex, the model parameters represent the properties of neurons. The main problem with PCNN methods is that it is difficult to establish the relationship between neuron properties and image results. This difficulty is due to the abstraction of network parameters in pulse-coupled neural networks. ...

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): G06T7/00G06T7/10
CPCG06T7/0012G06T2207/20084G06T2207/30008G06T7/10
Inventor 王沫楠王海滨
Owner HARBIN 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