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

Image Processing-Based Recognition Method for Hook Tail Frame Fracture

An image processing and recognition method technology, which is applied in character and pattern recognition, instruments, calculations, etc., can solve the problem of low accuracy of hook-tail frame, achieve detection accuracy, improve detection rate and detection accuracy, and ensure detection. effect of speed

Active Publication Date: 2021-08-06
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims to solve the problem of low accuracy in existing detection methods for hook tail frame breakage

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
  • Image Processing-Based Recognition Method for Hook Tail Frame Fracture
  • Image Processing-Based Recognition Method for Hook Tail Frame Fracture
  • Image Processing-Based Recognition Method for Hook Tail Frame Fracture

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0043] Specific implementation mode one: combine figure 1 To describe this embodiment,

[0044] This embodiment is an image processing-based method for identifying the breakage of a hooktail frame, comprising the following steps:

[0045] S1. Obtain a target image containing the component to be detected; and enhance the target image to obtain an enhanced target image;

[0046] S2. Use local adaptive threshold segmentation to extract the boundary area between the pallet and the background; calculate the segmentation results in the horizontal direction and use the vertical center point of the enhanced target image as a reference to search for the upper and lower boundaries at the upper and lower ends;

[0047] Position and intercept the hooktail frame according to the position of the upper boundary or the lower boundary in the enhanced target image, as an accurately positioned and intercepted image, calculate the pixel variance of the accurately positioned and intercepted image...

specific Embodiment approach 2

[0051] This embodiment is an image processing-based method for identifying the breakage of a hooktail frame. In this embodiment, the process of enhancing the target image includes the following steps:

[0052] Normalize the target image, and then count the number of pixel values ​​in the 10 intervals with the gray value of the normalized image between 0 and 1 with a step size of 0.1, and select the upper bound of the interval with the largest number of pixel values ​​as Enhance the center of the curve; and enhance the target image according to the following formula:

[0053]

[0054] where imgval is the statistical value of the number of pixel values ​​in the interval with the normalized image step size of 0.1, F off is the upper bound of the interval corresponding to the maximum number of pixel values ​​in the statistical value, exp is the exponent with the base e, y is the power of enhancement, img normal is the normalized pixel value of the target image before enhanceme...

specific Embodiment approach 3

[0058] This embodiment is an image processing-based hook-tail frame break recognition method. In S2 of this embodiment, the segmentation results are counted in the horizontal direction and the process of finding the upper and lower boundaries at the upper and lower ends with the vertical center point of the enhanced target image includes the following steps: step:

[0059] Use the vertical center point of the enhanced target image to search for the upper and lower ends respectively, and find the position of the row where the number of white pixels in a row exceeds half the width of the enhanced target image and record it as A1, and continue to search, if there are 5 consecutive If the row satisfies the condition of exceeding half the width of the target image after enhancement, select A1 as the boundary to stop the search, otherwise continue to search;

[0060] If two lines satisfying the condition are found at the upper and lower ends at the same time, the upper and lower bou...

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 relates to an image processing-based method for recognizing the breakage of a hooktail frame, which belongs to the technical field of image detection. The invention aims to solve the problem of low accuracy in the existing detection method for hooktail frame breakage. The present invention firstly enhances the target image, uses the local adaptive threshold to extract the boundary area between the pallet and the background, calculates the segmentation results in the horizontal direction and searches for the upper and lower boundaries to obtain an accurately positioned and intercepted image, and then calculates the pixel variance in the column direction to obtain the variance Curve, traverse the pixel variance curve, find the start and end positions of the jump point of the variance curve, corresponding to the precise positioning of the intercepted image, expand the starting position by L pixels as the starting coordinates of the suspected fault area, and intercept the suspected fault area according to the obtained coordinates The subgraph of the fault area; then, based on the features extracted from the subgraph of the suspected fault area, the SVM classifier is used to identify the fault. It is mainly used for the identification of the breakage of the hooktail frame.

Description

technical field [0001] The invention belongs to the technical field of image detection, and in particular relates to a hook tail frame break recognition method. Background technique [0002] In order to ensure the safe operation of railway trains, railway inspection technicians need to inspect various components of railway trains. The traditional method is that the detection equipment takes pictures of the train or each component, and after the pictures are taken, the fault point of the train is determined by manual observation. This approach enables fault detection while the vehicle is moving without stopping. However, the fault detection method of manually inspecting images is inefficient and requires a lot of manpower, and has the disadvantages of easy fatigue, high intensity, and need for training. [0003] For faults with obvious characteristics and fixed standards, image processing can be used to identify them, which can greatly save manpower and shorten the detectio...

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): G06K9/34G06K9/46G06K9/62
CPCG06V10/26G06V10/462G06F18/214G06F18/2411
Inventor 汤岩
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
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