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

A Rotor Winding Image Detection Method Fusing Regional Distribution Characteristics and Edge Scale Angle Information

A technology of regional distribution and image detection, applied in image analysis, image data processing, instruments, etc., can solve the problems of long calculation time of standard template and fluctuation of similarity value, so as to improve detection accuracy, strong accuracy and reduce interference. effect of factors

Active Publication Date: 2022-07-19
SOUTHEAST UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Aiming at the problem that the similarity value fluctuates when the image to be tested is matched with different template images, this paper proposes a rotor winding image detection method that combines regional distribution characteristics and edge scale angle information, which effectively avoids the randomness of the template selection. The impact of detection accuracy, but also avoid the problem of too many standard templates and long calculation time

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 Rotor Winding Image Detection Method Fusing Regional Distribution Characteristics and Edge Scale Angle Information
  • A Rotor Winding Image Detection Method Fusing Regional Distribution Characteristics and Edge Scale Angle Information
  • A Rotor Winding Image Detection Method Fusing Regional Distribution Characteristics and Edge Scale Angle Information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] A rotor winding image detection method that fuses regional distribution characteristics and edge scale angle information, as shown in Figure 1, specifically includes the following steps:

[0039] S1: Perform a grayscale preprocessing operation on the image to be tested, that is, convert the color image into a grayscale image, and then enter the filtering preprocessing operation, which means that the median filtering method is used to denoise the grayscale image of the image to be tested, and finally threshold preprocessing is performed. In the processing operation, the iterative method is used to adaptively calculate the threshold value, and the filtered grayscale image is binarized with this threshold value, so as to complete the image preprocessing of the winding area, and the image to be tested becomes a binary image, such as figure 2 in (a) and figure 2 As shown in (b) of , figure 2 (a) is the image preprocessing map of the present invention, taking the winding ...

Embodiment 2

[0045] The difference between this embodiment and Embodiment 1 is that: the S2 includes the following steps:

[0046] S21: Calculate the similarity of the spatial distribution characteristics of the contour of the winding area between the image to be tested and the template;

[0047]S22: Relevance retrieval is performed on the template image based on the regional distribution characteristics;

[0048] For the template retrieval algorithm based on the distribution characteristics of contour regions, it is necessary to perform correlation retrieval on the template image based on the regional distribution characteristics.

[0049]

[0050] in: H k (J) is the number of contour sampling points distributed in the Jth block region, and N is the number of regional blocks divided by the distribution descriptor;

[0051] S23: Select the origin, divide and mark the image space into modules;

[0052] S24: Count the contour sampling points of the winding area on each module interva...

Embodiment 3

[0055] The difference between this embodiment and the above-mentioned embodiment is that the morphological description of the scale and angle information of the contour in the S3 is as follows, for any point e on the contour edge i (x i ,y i ) and the contour centroid O 0 (x 0 ,y 0 ) to form the vector r i , the polar radius is defined as is the scale information, any point e on the edge of the contour i (x i ,y i ) can be defined as a vector with the point gradient The included angle θ i , which is the angle information, θ i Calculated as follows

[0056]

[0057] It can be seen that the angle θ i is calculated not by absolute coordinates, but by the vector r i The relative coordinates of the base. In this way, the information statistics of the scale and angle based on the centroid are established. figure 2 In the figure (c) as an example, the histogram statistics of the angle and scale of the edge points in the winding area are as follows: Figure 5 i...

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 rotor winding image detection method that fuses regional distribution characteristics and edge scale angle information, comprising step 1: respectively performing grayscale, filtering and threshold preprocessing operations on the image to be measured, so as to complete the winding area image Preprocessing, the image to be tested becomes a binary image; Step 2: Calculate the similarity of the spatial distribution characteristics of the contour of the winding area between the image to be tested and the template, so as to carry out template retrieval; Step 3: Through the edge of the contour of the image to be detected The relative angle information between the vector formed by the sampling point and the centroid of the contour of the area and the gradient vector at the point and the calculation of the scale information of the vector itself, realize the description of the contour shape; Step 4: Calculate the image to be measured by the Babbitt distance The similarity of the angle and scale distribution information between the template and the template is used to realize the detection of the image to be tested, which effectively avoids the influence of the accidental template selection on the detection accuracy, shortens the detection time and improves the detection accuracy.

Description

[0001] Field of study [0002] The invention relates to a digital image processing and visual detection method, and provides a detection method for the winding shape at the rotor hook, in particular to a rotor winding image detection method which integrates regional distribution characteristics and edge scale angle information. Background technique [0003] With the continuous improvement of the level of industrial automation and intelligence in my country, motors, as key products that can convert electrical energy into mechanical energy, are widely used in large-scale electromechanical equipment in industry, agriculture and other fields, and even in elevators, refrigerators, air conditioners and other general purpose As the equipment goes out, the demand for the rotor, which is the core component of the motor rotating system, is also increasing. [0004] In the rotor production process, the hooks need to be surrounded by copper wires. Due to the irregular operation and the lim...

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): G06T7/00G06V10/30G06K9/62G06V10/74
CPCG06T7/0004G06V10/30G06F18/22
Inventor 张小国朱亚旋贾友彬陈刚
Owner SOUTHEAST UNIV
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