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

A Method of Extracting Closed Edge Image Contour Based on Anisotropic Gaussian Kernel

An anisotropic, edge contour technology, used in instruments, character and pattern recognition, computer parts and other directions, can solve problems such as cross-edge fractures, unable to obtain closed image contours, etc., to achieve good positioning accuracy, positioning accuracy single edge The effect of low response and detection error rate

Inactive Publication Date: 2018-03-23
XI'AN POLYTECHNIC UNIVERSITY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for extracting closed edge image contours based on anisotropic Gaussian kernel, which solves the technical problem that the cross edge fracture caused by edge detection in the prior art cannot obtain closed image contours

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
  • A Method of Extracting Closed Edge Image Contour Based on Anisotropic Gaussian Kernel
  • A Method of Extracting Closed Edge Image Contour Based on Anisotropic Gaussian Kernel
  • A Method of Extracting Closed Edge Image Contour Based on Anisotropic Gaussian Kernel

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0043] ANDDs (anisotropic directional derivatives) represent anisotropic Gaussian kernels.

[0044] see figure 1 , the method for extracting closed edge image contour based on anisotropic Gaussian kernel of the present invention comprises the following steps:

[0045] Step 1: first read the image to be extracted into the computer;

[0046] Step 2: Convolve the image with an anisotropic Gaussian kernel and the input image on the direction angle [0, π] to smooth and filter the image. The expression of the anisotropic Gaussian kernel in the direction corresponding to the θ angle is as follows,

[0047]

[0048]

[0049] where σ is the scale parameter, ρ is the anisotropic Gaussian parameter, θ is the rotation angle, and R θ is the rotation matrix, n is the input image matrix, that is, the transpose matrix of the matrix composed of the p...

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 method for extracting the contour of a closed edge image based on an anisotropic Gaussian kernel. Using the anisotropic characteristics of the edge direction, the anisotropic Gaussian kernel with multi-directional angles is used to smooth and filter the image, and then edge detection is performed to judge the edge The structure of the contour, and finally fill or extend the edge at the break, so that there will be no edge break at the intersection edge, so as to obtain a closed image edge contour. In addition, the method for extracting the contour of a closed-edge image of the present invention also has the advantages of high noise robustness, low detection error rate, good positioning accuracy and single-edge response.

Description

technical field [0001] The invention belongs to the technical field of image feature extraction, and relates to a method for using an anisotropic Gaussian kernel to perform edge detection to obtain a closed edge image contour. Background technique [0002] Edge is the basic feature of image, contains rich visual information, and is an important research topic in the field of computer vision and pattern recognition. Obtaining complete image edges is a key step in image feature extraction. The edge detection algorithm based on differential determines the edge pixels by the maximum point of the first-order differential operator or the zero point of the second-order differential operator. However, the edge detector based on the first-order or second-order difference operator is sensitive to noise. In order to alleviate this problem, a smoothing filter is added before the image differential operation. In the prior art, the best edge detector based on the first derivative of the...

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 Patents(China)
IPC IPC(8): G06K9/46
Inventor 章为川杨婷婷顾梅花
Owner XI'AN POLYTECHNIC UNIVERSITY
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