Bionic contour detection method based on color and gray feature fusion

A grayscale feature, contour detection technology, applied in image data processing, instrumentation, computing and other directions, can solve problems such as missing target contour information and reducing the performance of contour detection models.

Active Publication Date: 2020-05-19
GUANGXI UNIVERSITY OF TECHNOLOGY
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The bionic models that have been proposed generally consider the color information or grayscale information of the image alone, and do not consider the effective combination of the color information and grayscale information of the image, but simply use the single and double antagonism principle of color or the grayscale The central excitation-peripheral inhibition mechanism simulates a complex visual perception system, which to some extent causes the loss of target contour information, thereby reducing the performance of the contour detection model

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
  • Bionic contour detection method based on color and gray feature fusion
  • Bionic contour detection method based on color and gray feature fusion
  • Bionic contour detection method based on color and gray feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] like figure 1 Shown, the technical scheme of the present embodiment is as follows:

[0065] A bionic contour detection method based on color and grayscale feature fusion, comprising the following steps:

[0066] A. Input the image to be detected, and calculate the color features; extract the red, green, and blue components of each pixel in the image to be detected, and use the red and green components to calculate the yellow component of each pixel; preset the center Two-dimensional Gaussian function, for each pixel point, use the central two-dimensional Gaussian function to filter the red, green, blue, and yellow components of the pixel point, respectively, to obtain the filter response value of each color component of the pixel point;

[0067] Described step A specifically is:

[0068] The filter response values ​​of the various color components are as follows:

[0069] S C (x,y)=I C (x,y)*G c (x,y) (1);

[0070] where S C (x, y) represents the filter response...

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 aims at providing a bionic contour detection method based on color and gray feature fusion. The bionic contour detection method comprises the following steps of: A, inputting a to-be-detected image, carrying out the calculation of color features, extracting color components in the to-be-detected image, and carrying out filtering to obtain a filtering response value of each color component; B, calculating single antagonism response based on color features of each pixel point; C, calculating a color feature contour response value and a color feature optimal direction of each pixelpoint; D, performing gray processing on the to-be-detected image, and calculating gray features, namely, calculating a gray feature initial response value of each pixel point; E, calculating a classical optimal response value and an optimal gray feature direction of the gray feature of each pixel point; F, calculating a gray feature contour response value of each pixel point; G, calculating a final contour response value of each pixel point; H, and calculating a final contour value of each pixel point. The bionic contour detection method overcomes the defects in the prior art, and has the advantages of comprehensive operation feature and high contour recognition rate.

Description

technical field [0001] The invention relates to the field of image contour detection, in particular to a bionic contour detection method based on fusion of color and grayscale features. Background technique [0002] In the field of image contour detection, bio-inspired contour detection models are currently one of the mainstream research directions. The bionic models that have been proposed generally consider the color information or grayscale information of the image alone, and do not consider the effective combination of the color information and grayscale information of the image, but simply use the single and double antagonism principle of color or the grayscale The central excitation-peripheral inhibition mechanism simulates the complex visual perception system, which to some extent causes the loss of target contour information, thereby reducing the performance of the contour detection model. Contents of the invention [0003] The present invention aims to provide a ...

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): G06T7/13G06T7/90
CPCG06T7/13G06T7/90G06T2207/10024
Inventor 林川王瞿文泽奇万术娟潘勇才刘青正张玉薇李福章张晴王垚王蕤兴韦艳霞
Owner GUANGXI UNIVERSITY OF TECHNOLOGY
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