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

Method for closing fracture curve in image

A technology of curves and curves in images, which is applied in the fields of image processing and computer vision, can solve problems such as connection, curve segments cannot be closed accurately, and breakpoints cannot be accurately found, so as to achieve the effect of avoiding connection

Active Publication Date: 2017-06-13
ZHEJIANG UNIV OF TECH
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In summary, the current methods for closing broken curves in images have the following deficiencies: (1) cannot accurately close curve segments with relatively large gaps; (2) cannot accurately find the corresponding breakpoints for connection , it is easy to connect with the matte when closed

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
  • Method for closing fracture curve in image
  • Method for closing fracture curve in image
  • Method for closing fracture curve in image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The specific implementation of the fracture curve closing method of the present invention will be described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0056] A method for closing a fracture curve in an image of the present invention comprises the following steps:

[0057] Step 1: Binarize the image, and through thinning, the curve existing in the image becomes a single-pixel curve. In this embodiment, the binarized image is as follows Figure 4 As shown, the thinned image is as Figure 5 shown;

[0058] Step 2: Traverse the pixels in the image to find a breakpoint of the curve, and determine a certain pixel point p as the breakpoint of the curve needs to meet one of the following conditions:

[0059] (2.1) B(p) = 1;

[0060] (2.2) B(p)=2 and C 2 (p)=1;

[0061] (2.3) B(p)=3 and the gray value of the 8 nei...

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 closing a fracture curve in an image. The method comprises the following steps of performing binarization on the image, and changing a curve existent in the image to a single-pixel curve through refinement; traversing all pixel points in the image to find a breakpoint p of the curve; storing coordinates of the breakpoint p and an extension direction of a line segment where the breakpoint p is located, and performing circular traversal, until all the pixel points in the image are traversed; and finding two breakpoints meeting a closing requirement, performing closure on the two breakpoints, performing circular closure until all closable breakpoints are closed, and drawing a quadric B-spline curve between the two breakpoints, thereby finishing the closure of the fracture curve in the image. Through the method, the fracture curve in the image is closed; and big or small fracture parts of the curve in the image can be correctly closed by selectively connecting the breakpoints, so that connection between disordered boundary and real edge of an object can be avoided, and boundary disorder is not caused while complete object edge is obtained.

Description

technical field [0001] The invention relates to the technical fields of image processing and computer vision, in particular to a method for closing broken curves in an image for closing broken curves in an image. Background technique [0002] With the continuous development of the field of computer vision, it is often necessary to obtain effective outer edge contours of objects in image processing and analysis such as image understanding and intelligent recognition and tracking. In the image detected by the traditional edge detection method, there are often broken image edges due to missing detection, so it is necessary to find a way to close these broken edges to obtain a complete object outer contour edge. [0003] Currently there are many methods for fracture curve closure in images, wherein the closer technical solution to the present invention is: literature (Zhang Linrui, Jia Yulin, Cheng Ke. Simple image closure outer edge contour extraction. Infrared and Laser Engine...

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): G06K9/46G06T7/13G06T7/181
CPCG06T2207/10004G06V10/44
Inventor 高飞汪敏倩徐云静蔡益超葛一粟卢书芳毛家发肖刚
Owner ZHEJIANG UNIV OF 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