Method for judging convex figure shape similarity in digital image

A technology of geometric graphics and digital images, applied in character and pattern recognition, instruments, computer parts, etc., can solve problems such as high computational complexity, reduced reliability of recognition, and limited application range

Active Publication Date: 2016-06-15
珠海金智维信息科技有限公司
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (1) The geometric shape recognition method proposed by the "Research on the Key Issues of Plane Geometric Figure Retrieval" published in the "Journal of Peking University (Natural Science Edition)" and the foreign Hough transform can only be used for specific Identify a regular geometric shape to limit its application range;
[0007] (2) The recognition method of geometric shape represented by "relative moment and its application in geometric shape recognition" published in "Chinese Journal of Image and Graphics" needs to calculate high-order Hu invariant moments, so , the computational complexity is very high;
[0008] (3) The recognition method of geometric figure shape, represented by the "fast recognition algorithm of geometric figure based on chain code feature" published in "Jilin University Journal (Natural Science Edition)", is due to the use of statistical features of aggregated figure shape or Approximate features, resulting in the loss of some key features of the original geometric shape, so the reliability of recognition will be reduced

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 judging convex figure shape similarity in digital image
  • Method for judging convex figure shape similarity in digital image
  • Method for judging convex figure shape similarity in digital image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] This embodiment illustrates the effectiveness of the GCT transformation on closed convex shapes.

[0078] Include the following steps:

[0079] S1, yes figure 2 The closed convex shape shown in the GCT transformation

[0080] (1) adopt the form of digital image to preserve the convex geometric figure shape, suppose the coordinates of the boundary point of the convex geometric figure shape in the digital image to be (x 1 ,y 1 ), (x 2 ,y 2 ), (x 3 ,y 3 ),..., (x n ,y n ); Find the coordinates of the center point of the convex geometric figure (x 0 ,y 0 );

[0081] x 0 ,y 0 Calculated using the following formula:

[0082] x 0 = 1 n Σ i = 1 i = n x i , y 0 =...

Embodiment 2

[0088] This embodiment illustrates the effectiveness of GCT transformation for non-closed convex shapes.

[0089] The basic steps are as in Example 1. This example differs from Example 1 in that the convex geometry of this example is non-closed, so each ray is obtained at the center point (x 0 ,y 0 ) is the ray direction of the starting point and the coordinates of the intersection with the convex geometric figure on the opposite direction. In this step, since the ray may not have an intersection with the non-closed convex geometric figure, in this case, change the intersection point to find The closest to the ray, and the center point (x 0 ,y 0 ) is the coordinates of the nearest discrete point of the convex geometric shape.

[0090] For any non-closed convex shape, such as Figure 4 As shown, it is a typical non-closed convex shape. Here, k is taken as 180, and the non-closed convex geometric shape starts from the ray parallel to the x-axis, passes through its center p...

Embodiment 3

[0093] This example illustrates that for any two similar closed convex geometric figures Ω 1 , Ω 2 , it can be judged that they are similar by this method. Two similar closed convex geometric figures have the shape of Image 6 shown.

[0094] Include the following steps:

[0095] S1, with reference to Embodiment 1, use GCT transformation (take the k value as 360 here) to generate Ω respectively 1 , Ω 2 The complex plane eigenvector F of 1 , F 2 ;

[0096] S2, respectively calculate their complex plane eigenvectors F 1 , F 2 The intensity sequence M 1 , M 2 and phase sequence S 1 , S 2 , using the following formula to calculate:

[0097] M 1 = ( a 1 , 1 2 + b ...

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 provides a method for judging the convex figure shape similarity in a digital image. The method comprises the steps of S1, for any two convex figure shapes omega 1 and omega 2 that are subjected to similarity judgment, respectively figuring out the complex plane feature vectors of the two convex figure shapes based on GCT transformation and recording the complex plane feature vectors thereof as F1 and F2; calculating the intensity sequences and the phase sequences thereof and respectively recording the intensity sequences and the phase sequences as M1, S1, M2 and S2; judging the similarity between the phase sequence S1 and the phase sequence S2; calculating according to img file='DDA0000901986470000011.TIF' wi='131' he='65', img file='DDA0000901986470000012.TIF' wi='1938' he='99', and img file='DDA0000901986470000013.TIF' wi='1123' he='98'; when delta is larger than 0.2, judging that the two convex figure shapes are not similar; S3, judging the similarity between the intensity sequence M1 and the intensity sequence M2; calculating according to img file='DDA0000901986470000014.TIF' wi='918' he='94', img file='DDA0000901986470000015.TIF' wi='1907' he='99', and img file='DDA0000901986470000016.TIF' wi='579' he='97'; when eta is larger than 0.2, judging that the two convex figure shapes are not similar; otherwise, judging that the two convex figure shapes are similar. The method is simple to realize and low in time complexity. The identification accuracy of the method is up to more than 90%.

Description

technical field [0001] The invention relates to a method for judging the shape similarity of convex geometric figures in digital images. technical background [0002] Pattern recognition is an important and active research field in computer science, which is widely used in image analysis, machine vision and object recognition and other application fields. For example, in the application of self-driving cars, a self-driving car obtains digital images of the road conditions in the direction of the car through the camera installed on the self-driving car, and preprocesses the images, including smoothing, denoising, enhancement, and object finding Boundary, etc. Once the boundary of the object in the digital image is obtained, the next step is to determine the type of object to determine the way and direction of driving: if there is a person or a wall in front, then the car must stop immediately; car, then the car must also slow down and so on. Any object has a boundary, the b...

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
IPC IPC(8): G06K9/62
CPCG06F18/22
Inventor 吴绍根
Owner 珠海金智维信息科技有限公司
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