Multiscale basic geometrical shape feature extraction method

A geometric shape and feature extraction technology, applied in image data processing, instruments, calculations, etc., can solve problems such as judgment errors, large calculations, and complex calculations, and achieve the effects of high speed, high precision, and low computational complexity

Inactive Publication Date: 2017-02-22
WUHAN POLYTECHNIC UNIVERSITY
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even if it is improved to a fast algorithm, there is still a large amount of calculation
[0006] (3) There is no theoretical one-to-one correspondence between the frequency-domain feature vector or moment parameters and the plane geometry, so there is a possibility of judgment error
[0007] (4) Frequency-domain feature vectors or moment parameters cannot describe the common features of a class of planar geometric shapes
[0009] Liu Hairong's doctoral thesis "Curvature Representation and Decomposition of Shape" pointed out that traditional region-based methods mainly suffer from computational complexity, and the key features of shapes disappear in some cases due to the lack of multi-scale characteristics of the algorithm.

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
  • Multiscale basic geometrical shape feature extraction method
  • Multiscale basic geometrical shape feature extraction method
  • Multiscale basic geometrical shape feature extraction method

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0061] Such as figure 1 As shown in the flow diagram of the first embodiment:

[0062] A multi-scale basic geometric shape feature extraction method, comprising the following steps:

[0063] S100: Calculating the coordinates of the center of gravity of the geometric shape defined as:

[0064]

[0065] S200: by center of gravity coordinates is the origin of the coordinates, and the shape area of ​​the geometric shape is divided by the x and y axes. The angle between the positive direction of the abscissa x and the y coordinate is θ, and θ is between 0° and 90°. The division is The four areas are s1, s2, s3 and s4;

[0066] S300: Calculate the area of ​​the four divided regions, marked as in is the total area of ​​the region;

[0067] S400: Rotate the abscissa x and ordinate y counterclockwise, execute step S300 again, the total rotation angle satisfies 180 degrees, and the area vectors of the four regions are obtained as follows:

[0068]

[0069]

[0070] ...

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 present invention provides a multiscale basic geometrical shape feature extraction method, and relates to the technology field of identifying the shape images via a computer, in particular to a plane geometrical shape feature extraction method. Areas are the important features of the shapes, a conventional area feature extraction method does not have a multiscale characteristic, so that the key features of the shapes disappear. The multiscale feature is the capability of a feature extraction algorithm of extracting the features from roughly to finely. Aiming at the above problems, the present invention provides a method of utilizing the polar coordinates similarly to extract the shape features, and by changing the included angle of an X-axis and a Y-axis from large to small, the features from rough to fine are extracted. The multiscale basic geometrical shape feature extraction method has the advantages of being fast in speed, higher in precision and lower in calculation complexity, having the multiscale feature, etc.

Description

technical field [0001] The invention relates to the technical field of computer recognition of shape images, in particular to a method for feature extraction of plane geometric shapes. Background technique [0002] Geometric shape recognition is the basic technology of graphics and image recognition in the field of pattern recognition. In artificial intelligence, computer vision, robotics, image target recognition, optical character reader (Optical Character Reader, OCR), military and other high-tech fields, geometric shape recognition technology plays a key role. Geometric shape recognition is realized based on the mathematical description method of shape features and feature information extraction technology. In the prior art, the mathematical description of graphics is mainly based on two theoretical systems. One is the Fourier descriptor theory based on integral transform, which transforms the image information from the time domain to the frequency domain, and uses 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 Applications(China)
IPC IPC(8): G06T7/41G06T7/62G06T7/66
Inventor 牟怿周龙卢亚玲陈维真赵煦
Owner WUHAN POLYTECHNIC UNIVERSITY
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