Chrysanthemum pool pattern geometrical information extraction method based on detection straight lines and line segments

A technology for geometric information and straight line detection, applied in character and pattern recognition, image data processing, instruments, etc., to achieve fast detection speed, effective and feasible coordinate positioning and detection methods, and high accuracy of detection results

Active Publication Date: 2020-09-01
SHANGHAI UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] With the development of early automatic detection technology, the detection methods of straight line and line segment were applied to the detection material image respectively, but the straight line and line segment can only show the overall image features and local features

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
  • Chrysanthemum pool pattern geometrical information extraction method based on detection straight lines and line segments
  • Chrysanthemum pool pattern geometrical information extraction method based on detection straight lines and line segments
  • Chrysanthemum pool pattern geometrical information extraction method based on detection straight lines and line segments

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] In this embodiment, a method for extracting geometric information of Kikuchi patterns based on detecting straight lines and line segments includes the following steps:

[0051] a. Detect straight lines and line segments on the material image, including image denoising and edge extraction; when performing edge extraction, first use the Canny operator to extract the edge, and then use the Radon transform and the cumulative probability Hough transform method to extract the edge image Lines and segments;

[0052] b. Use a two-way screening algorithm to screen and match all the detection results to obtain multiple sets of sets with the same direction and similar distances. Each set contains a matching set of a straight line and multiple line segments, and use the filtered straight line to generate the center Line and screen again to get the screened center line;

[0053] c. Use the generated and screened center line to obtain the maximum value range using the rendering algo...

Embodiment 2

[0059] This embodiment is basically the same as Embodiment 1, especially in that:

[0060] In this embodiment, the detected straight line and line segment are respectively the performance of the overall feature and the local feature in the picture of the Kikuchi pattern, so the combination of the two can realize the acquisition of a complete feature. In the step b, the detected straight line and line segment are used as the overall feature and local feature in the Kikuchi pattern picture respectively; Between distances, when the straight line is set to match a line segment, a bidirectional screening algorithm is used to obtain a set of matching sets containing a center line and multiple line segments; the bidirectional screening algorithm adopts the following two assumptions:

[0061] First, if a line segment does not have any straight line to match it, then it has a high probability of being a false line segment;

[0062] Second, if a straight line does not have any line seg...

Embodiment 3

[0071] This embodiment is basically the same as the previous embodiment, and the special features are:

[0072] In this embodiment, since the intersection point of the Kikuchi belt can be approximately considered to be on the centerline of multiple Kikuchi belts, it can be considered that the closer the distance is to the centerline, the more likely the intersection point will be found. Based on this principle, in the step c, the steps of using the rendering algorithm to generate the rendering image according to the center line and obtaining the intersection point of the Kikuchi belt are as follows:

[0073] Assume that since the intersection point of the Kikuchi belt is on the center line of multiple Kikuchi belts, the closer to the center line, the more likely to find the intersection point; design the following rendering algorithm based on the distance to the center line, where d refers to the rendering coordinates to each The distance from the centerline, v is the renderin...

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 chrysanthemum pool pattern geometrical information extraction method based on detection straight lines and line segments, and the method achieves the obtaining and drawing ofinformation in a material image through a computer image detection method. The method includes: firstly, extracting edges of an image, and carrying out straight line and line segment detection on anedge detection image; eliminating false results through a bidirectional screening algorithm to obtain a plurality of sets including a center line and a plurality of line segments, wherein the center line is obtained by combining two straight line detection results with the same angle and close distance; detecting and positioning intersection points of the chrysanthemum pool belts by utilizing a result graph obtained by applying a rendering algorithm through the generated center line; supplementing a detection result by using a turning method according to the detected intersection point and part of the single-side edge; and finally describing the pattern edge of the chrysanthemum pool through a hyperbolic curve. According to the method for detecting the patterns of the chrysanthemum pond, the patterns and the intersection points of the patterns of the material chrysanthemum pond can be detected, positioned and described, the research speed is increased, the research cost is reduced, andresearch and development of the disciplines are promoted.

Description

technical field [0001] The invention relates to a material image analysis and detection method, in particular to a material image Kikuchi pattern detection method, which is applied to the technical field of material physical property computer detection and analysis. Background technique [0002] In the study of materials science, the Kikuchi pattern can display information such as crystal structure and orientation. For material images, the location of patterns and intersections is the key to obtain these information. In the early methods, the edge of the Kikuchi zone was determined by manual delineation, but this method was inefficient and could not meet the growing research needs. Reliable detection methods were needed to automatically detect the Kikuchi image and then obtain it. Information. However, computer image technology has many methods for detecting and extracting information in images. How to choose an appropriate method and apply it to the detection of material ...

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): G06T7/00G06T7/13G06T7/155G06K9/62G06T5/00
CPCG06T7/0002G06T7/13G06T7/155G06T5/002G06F18/22
Inventor 韩越兴李睿祺王冰
Owner SHANGHAI 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