CN112053368B - Weld joint center identification method and system for sheet welding - Google Patents

Weld joint center identification method and system for sheet welding Download PDF

Info

Publication number
CN112053368B
CN112053368B CN201910897761.4A CN201910897761A CN112053368B CN 112053368 B CN112053368 B CN 112053368B CN 201910897761 A CN201910897761 A CN 201910897761A CN 112053368 B CN112053368 B CN 112053368B
Authority
CN
China
Prior art keywords
gray
image
determining
pixel
region
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910897761.4A
Other languages
Chinese (zh)
Other versions
CN112053368A (en
Inventor
李冰
杨旭
何煊
张妍
翟永杰
苑朝
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
North China Electric Power University
Original Assignee
North China Electric Power University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by North China Electric Power University filed Critical North China Electric Power University
Priority to CN201910897761.4A priority Critical patent/CN112053368B/en
Publication of CN112053368A publication Critical patent/CN112053368A/en
Application granted granted Critical
Publication of CN112053368B publication Critical patent/CN112053368B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30152—Solder
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

The invention discloses a weld center identification method and a weld center identification system for sheet welding. Firstly, acquiring a sheet surface image shot by a linear array CCD and converting the sheet surface image into a gray image; determining an optimal segmentation threshold according to the gray value of the gray image; performing binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarized image; determining a plurality of connected domains according to the pixel values of the binarized image, and determining a gray value corresponding to the central point of each connected domain; and determining a welding seam area and a welding seam center according to the gray value corresponding to the central point of the connected area. The weld center recognition method can be used in an embedded system, can stably realize high-precision weld center recognition, and can effectively improve welding efficiency, precision and accuracy when being used for automatic welding of thin plates.

Description

Weld joint center identification method and system for sheet welding
Technical Field
The invention relates to the technical field of welding automation, in particular to a weld joint center identification method and system for sheet welding.
Background
With the development of industry and material science, the welding automation technology has become an indispensable metal hot working technology. Because the welding environment is very bad, the automation of the weld tracking is realized, the labor intensity of welding workers can be reduced, and the welding quality is improved. The rapid development of sensor technology and intelligent control methods provides a material and technical basis for the realization of weld tracking.
In the current welding automation scheme, the recognition and detection of the weld joint position are carried out, so that the welding research of the medium steel plate for groove welding is more, and the welding research for the thin plate with the thickness smaller than 5mm is less. Meanwhile, the weld center recognition and detection algorithm is mostly realized based on a PC, so that the cost is high, and the application requirements of different occasions are difficult to meet. The existing recognition algorithm for the weld center has the defects of low recognition accuracy, poor robustness and the like.
Disclosure of Invention
The invention aims to provide a weld center identification method and a weld center identification system for sheet welding, which are used for solving the problems that the existing weld center identification and detection method is only suitable for welding medium steel plates, and is high in cost, low in identification accuracy and poor in robustness.
In order to achieve the above object, the present invention provides the following solutions:
a method of weld center identification for sheet welding, the method comprising:
acquiring a sheet surface image shot by a linear array CCD;
converting the sheet surface image into a gray scale image;
determining an optimal segmentation threshold according to the gray value of the gray image;
performing binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarized image;
determining a plurality of connected domains according to the pixel values of the binarized image;
determining a gray value corresponding to a center point of each connected domain;
and determining a welding seam area and a welding seam center according to the gray value corresponding to the center point of the connected area.
Optionally, the determining the optimal segmentation threshold according to the gray value of the gray image specifically includes:
obtaining a segmentation threshold value; the segmentation threshold is 0 to 255;
dividing the gray image into a white foreground region and a black background region according to the segmentation threshold;
calculating the inter-class variance corresponding to the white foreground region and the black background region;
the segmentation threshold that maximizes the inter-class variance is determined to be the optimal segmentation threshold.
Optionally, the calculating the inter-class variance corresponding to the white foreground area and the black background area specifically includes:
counting the total pixel points in the gray level image, the number of the pixel points occupied by the white foreground region and the number of the pixel points occupied by the black background region;
determining the proportion of the white foreground region and the pixel mean value of the white foreground region according to the number of the pixel points occupied by the white foreground region;
determining the proportion of the black background area and the pixel mean value of the black background area according to the number of the pixel points occupied by the black background area;
determining the pixel mean value of the gray level image according to the total pixel point number in the gray level image;
and determining the inter-class variance according to the proportion of the white foreground region, the proportion of the black background region, the pixel mean value of the white foreground region, the pixel mean value of the black background region and the pixel mean value of the gray image.
Optionally, the determining a plurality of connected domains according to the pixel values of the binarized image specifically includes:
and traversing all pixel points in the binarized image, and forming a connected domain by pixel points with pixel values of continuous 1, so as to generate a plurality of connected domains.
Optionally, the determining the weld area and the weld center according to the gray value corresponding to the center point of the connected domain specifically includes:
determining a central point corresponding to the maximum gray value in the gray values corresponding to the central points of the connected domains as a welding seam center;
and determining the connected domain corresponding to the central point corresponding to the maximum gray value as a welding line region.
A weld center identification system for sheet welding, the system comprising:
the sheet image acquisition module is used for acquiring a sheet surface image shot by the linear array CCD;
an image conversion module for converting the sheet surface image into a gray scale image;
the optimal segmentation threshold determining module is used for determining an optimal segmentation threshold according to the gray value of the gray image;
the binarization module is used for carrying out binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarized image;
the connected domain determining module is used for determining a plurality of connected domains according to the pixel values of the binarized image;
the gray value determining module is used for determining the gray value corresponding to the center point of each connected domain;
and the weld joint center identification module is used for determining a weld joint region and a weld joint center according to the gray value corresponding to the center point of the connected region.
Optionally, the optimal segmentation threshold determining module specifically includes:
a segmentation threshold acquisition unit configured to acquire a segmentation threshold; the segmentation threshold is 0 to 255;
the region dividing unit is used for dividing the gray image into a white foreground region and a black background region according to the dividing threshold value;
an inter-class variance calculating unit, configured to calculate an inter-class variance corresponding to the white foreground region and the black background region;
an optimal segmentation threshold determination unit configured to determine the segmentation threshold that maximizes the inter-class variance as an optimal segmentation threshold.
Optionally, the inter-class variance calculating unit specifically includes:
the pixel point statistics subunit is used for counting the total number of pixel points in the gray level image, the number of pixel points occupied by the white foreground area and the number of pixel points occupied by the black background area;
the foreground region parameter calculating subunit is used for determining the proportion of the white foreground region and the pixel mean value of the white foreground region according to the number of the pixel points occupied by the white foreground region;
the background area parameter calculation subunit is used for determining the proportion of the black background area and the pixel mean value of the black background area according to the number of the pixel points occupied by the black background area;
a gray image pixel mean value calculating subunit, configured to determine a pixel mean value of the gray image according to the total number of pixel points in the gray image;
and the class variance calculating subunit is used for determining the class variance according to the proportion of the white foreground region, the proportion of the black background region, the pixel mean value of the white foreground region, the pixel mean value of the black background region and the pixel mean value of the gray level image.
Optionally, the connected domain determining module specifically includes:
and the connected domain determining unit is used for traversing all pixel points in the binarized image, and forming a connected domain by the pixel points with the pixel values of 1 continuously, so as to generate a plurality of connected domains.
Optionally, the weld center identification module specifically includes:
the weld joint center identification unit is used for determining a center point corresponding to the maximum gray value in the gray values corresponding to the center points of the connected domains as a weld joint center;
and the weld joint region identification unit is used for determining the connected region corresponding to the central point corresponding to the maximum gray value as the weld joint region.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a weld center identification method and a system for welding a sheet, wherein the method comprises the steps of firstly acquiring a sheet surface image shot by a linear array CCD and converting the sheet surface image into a gray level image; determining an optimal segmentation threshold according to the gray value of the gray image; performing binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarized image; determining a plurality of connected domains according to the pixel values of the binarized image, and determining a gray value corresponding to the central point of each connected domain; and determining a welding seam area and a welding seam center according to the gray value corresponding to the central point of the connected area. The weld center recognition method can be used in an embedded system, can stably realize high-precision weld center recognition, and can effectively improve welding efficiency, precision and accuracy when being used for automatic welding of thin plates.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for identifying a weld center for sheet welding provided by the present invention;
fig. 2 is a block diagram of a bead center recognition system for sheet welding according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a weld center identification method and a weld center identification system for sheet welding, which are used for solving the problems that the existing weld center identification and detection method is only suitable for welding medium steel plates, and is high in cost, low in identification accuracy and poor in robustness.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Fig. 1 is a flowchart of a method for identifying a weld center for welding a sheet according to the present invention. Referring to fig. 1, the method for identifying a weld center for welding a sheet according to the present invention specifically includes:
step 101: and acquiring a sheet surface image shot by the linear array CCD.
The weld center recognition method is based on a structured light vision sensing system consisting of linear array CCD (Charge Coupled Device ) and is used for weld center recognition during sheet welding. The linear array CCD is used for shooting the sheet surface image during sheet welding.
Step 102: the sheet surface image is converted into a gray scale image.
Step 103: and determining an optimal segmentation threshold according to the gray value of the gray image.
Converting a voltage signal output by the linear array CCD into a digital gray level signal, and calculating an optimal segmentation threshold value by using a maximum inter-class variance method, wherein the method comprises the following specific steps of:
(a) Obtaining a segmentation threshold value; and dividing the gray image into a white foreground region and a black background region according to the segmentation threshold.
A segmentation threshold T is initialized, which takes on values from 0 to 255. Dividing the gray image into white foreground regions f according to the segmentation threshold T A And a black background area f B Two parts.
In the invention, gray signals f (1, j), j epsilon M are the j pixel points in the gray image; m is the set of all pixel points in the gray image.
(b) Counting the total number N of pixel points in the gray level image and the number N of pixel points occupied by the white foreground region A And the number N of the pixel points occupied by the black background area B 。
(c) And determining the proportion of the white foreground region and the pixel mean value of the white foreground region according to the number of the pixel points occupied by the white foreground region.
The proportion P of the white foreground region A The calculation formula of (2) is as follows:
the pixel mean value U of the white foreground region A The calculation formula of (2) is as follows:wherein A is a pixel point set of the white foreground region; f (1, j) is the j-th pixel point in the gray scale image.
(d) And determining the proportion of the black background area and the pixel mean value of the black background area according to the number of the pixel points occupied by the black background area.
The proportion P of the black background area B The calculation formula of (2) is as follows:
the pixel mean value U of the black background area B The calculation formula of (2) is as follows:wherein B is the pixel point set of the black background area.
(e) And determining the pixel mean value of the gray level image according to the total pixel point number in the gray level image.
The calculation formula of the pixel mean value U of the gray image is as follows:wherein M is the pixel point set of the gray scale image.
(f) And determining the inter-class variance according to the proportion of the white foreground region, the proportion of the black background region, the pixel mean value of the white foreground region, the pixel mean value of the black background region and the pixel mean value of the gray image.
The inter-class variance theta T The calculation formula of (2) is as follows: θ T ＝P A ×(U A -U) 2 +P B ×(U B -U) 2 . Wherein P is A P being the proportion of the white foreground region B U is the proportion of the black background area A For the pixel mean value of the white foreground region, U B And U is the pixel mean value of the gray image.
(g) The segmentation threshold that maximizes the inter-class variance is determined to be the optimal segmentation threshold.
Traversing the segmentation threshold T from 0 to 255 while repeating the steps (a) - (f) above to find the inter-class variance θ T The maximum segmentation threshold T is the optimal segmentation threshold.
Step 104: and carrying out binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarized image.
And carrying out binarization processing on the gray level image according to the optimal segmentation threshold, wherein the binarization processing comprises the following steps of: and setting all pixels with gray values larger than the optimal segmentation threshold value in the gray image as 1, setting all pixels with gray values smaller than the optimal segmentation threshold value as 0, realizing image binarization, and generating the binarized image. And filtering the binarized image to eliminate interference.
Step 105: and determining a plurality of connected domains according to the pixel values of the binarized image.
Traversing all pixel points in the binarized image, and forming a connected domain by a plurality of pixel points with pixel values of 1 continuously, so as to generate a plurality of connected domains.
Further, the invention sets the same reference numerals for all pixel points in any one connected domain, and stores the start point and the end point of each connected domain into an array. And taking the average value of the gray values of the starting point and the ending point of each connected domain to obtain the central point of each connected domain and storing the central point into a corresponding array. In addition, the gray value corresponding to the center point of each connected domain is read and stored in a corresponding array.
Step 106: and determining a gray value corresponding to the central point of each connected domain.
Step 107: and determining a welding seam area and a welding seam center according to the gray value corresponding to the center point of the connected area.
And determining the center point of the connected domain corresponding to the maximum gray value according to the gray value corresponding to the center point of each connected domain, wherein the connected domain where the maximum gray value is located is the welding seam region, the starting point and the end point of the connected domain are the left and right boundaries of the welding seam, and the center point of the connected domain is the center position of the welding seam. Namely, determining a central point corresponding to the maximum gray value in gray values corresponding to the central points of the connected domains as a welding seam center; and the connected domain corresponding to the center point corresponding to the maximum gray value is a welding line region.
The weld center recognition method can be used in an embedded system, can stably realize high-precision weld center recognition, and can effectively improve welding efficiency, precision and accuracy when being used for automatic welding of thin plates.
Based on the weld center recognition method provided by the invention, the invention also provides a weld center recognition system for sheet welding, and referring to fig. 2, the system comprises:
a sheet image acquisition module 201, configured to acquire a sheet surface image captured by the linear array CCD;
an image conversion module 202 for converting the sheet surface image into a gray scale image;
an optimal segmentation threshold determining module 203, configured to determine an optimal segmentation threshold according to a gray value of the gray image;
a binarization module 204, configured to perform binarization processing on the gray-scale image according to the optimal segmentation threshold value, to generate a binarized image;
a connected domain determining module 205, configured to determine a plurality of connected domains according to pixel values of the binarized image;
a connected domain center point gray value determining module 206, configured to determine a gray value corresponding to a center point of each connected domain;
and the weld center identification module 207 is configured to determine a weld region and a weld center according to the gray value corresponding to the center point of the connected domain.
The optimal segmentation threshold determining module 203 specifically includes:
a segmentation threshold acquisition unit configured to acquire a segmentation threshold; the segmentation threshold is 0 to 255;
the region dividing unit is used for dividing the gray image into a white foreground region and a black background region according to the dividing threshold value;
an inter-class variance calculating unit, configured to calculate an inter-class variance corresponding to the white foreground region and the black background region;
an optimal segmentation threshold determination unit configured to determine the segmentation threshold that maximizes the inter-class variance as an optimal segmentation threshold.
The inter-class variance calculating unit specifically includes:
a pixel point statistics subunit, configured to count the total number N of pixel points in the gray level image and the number N of pixel points occupied by the white foreground region A And the number N of the pixel points occupied by the black background area B ；
The foreground region parameter calculating subunit is used for determining the proportion of the white foreground region and the pixel mean value of the white foreground region according to the number of the pixel points occupied by the white foreground region; the method comprises the following steps: according to the number N of the pixel points occupied by the white foreground region A Using the formulaDetermining the proportion P of the white foreground region A The method comprises the steps of carrying out a first treatment on the surface of the According to the number N of the pixel points occupied by the white foreground region A Adopts the formula->Determining the pixel mean value U of the white foreground region A The method comprises the steps of carrying out a first treatment on the surface of the Wherein A is a pixel point set of the white foreground region; f (1, j) is the j-th pixel point in the gray scale image;
the background area parameter calculation subunit is used for determining the proportion of the black background area and the pixel mean value of the black background area according to the number of the pixel points occupied by the black background area; the method comprises the following steps: according to the number N of the pixel points occupied by the black background area B Using the formulaDetermining the proportion P of the black background area B The method comprises the steps of carrying out a first treatment on the surface of the According to the number N of the pixel points occupied by the black background area B Adopts the formula->Determining the pixel mean value U of the black background area B The method comprises the steps of carrying out a first treatment on the surface of the B is a pixel point set of the black background area;
a gray image pixel mean value calculating subunit, configured to use a formula according to the total number N of pixel points in the gray imageDetermining a pixel mean value U of the gray image; wherein M is a pixel point set of the gray level image;
an inter-class variance calculating subunit for calculating the proportion P of the white foreground region A The proportion P of the black background area B The pixel mean value U of the white foreground region A The pixel mean value U of the black background area B And the pixel mean value U of the gray level image adopts the formula theta T ＝P A ×(U A -U) 2 +P B ×(U B -U) 2 Determining an inter-class variance θ T 。
The connected domain determining module 205 specifically includes:
and the connected domain determining unit is used for traversing all pixel points in the binarized image, and forming a connected domain by the pixel points with the pixel values of 1 continuously, so as to generate a plurality of connected domains.
The weld center identification module 207 specifically includes:
the weld joint center identification unit is used for determining a center point corresponding to the maximum gray value in the gray values corresponding to the center points of the connected domains as a weld joint center;
a weld region identification unit, configured to determine that a connected region corresponding to the center point corresponding to the maximum gray value is a weld region
Compared with the existing weld center identification and detection method, the weld center identification method and system for sheet welding have at least the following advantages:
1. the weld center identification method and the system provided by the invention are applied to the field of sheet welding, and make up for the defect of welding automation in the field.
2. The weld center identification method and the weld center identification system provided by the invention can be applied to an upper computer, can be transplanted to an embedded system for use, are beneficial to reducing the cost of a welding device and are beneficial to realizing welding automation.
3. The weld center recognition method and the system provided by the invention adopt the maximum inter-class variance algorithm and the connected domain statistical mode to improve the resolution and the accuracy of weld recognition, reduce the number of data operations while guaranteeing the accuracy of data, and improve the processing speed of weld center recognition.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.

Claims (8)

1. A method for identifying a weld center for sheet welding, the method comprising:
acquiring a sheet surface image shot by a linear array CCD;
converting the sheet surface image into a gray scale image;
determining an optimal segmentation threshold according to the gray value of the gray image;
performing binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarized image;
determining a plurality of connected domains according to the pixel values of the binarized image;
determining a gray value corresponding to a center point of each connected domain;
determining a welding seam area and a welding seam center according to the gray value corresponding to the center point of the connected area; and determining a central point corresponding to the maximum gray value in the gray values corresponding to the central points of the connected domains as a welding seam center, wherein the connected domain corresponding to the central point corresponding to the maximum gray value is a welding seam region.
2. The weld center identification method according to claim 1, wherein the determining an optimal segmentation threshold according to the gray value of the gray image specifically comprises:
obtaining a segmentation threshold value; the segmentation threshold is 0 to 255;
dividing the gray image into a white foreground region and a black background region according to the segmentation threshold;
calculating the inter-class variance corresponding to the white foreground region and the black background region;
the segmentation threshold that maximizes the inter-class variance is determined to be the optimal segmentation threshold.
3. The weld center identification method according to claim 2, wherein the calculating the inter-class variance corresponding to the white foreground region and the black background region specifically includes:
counting the total pixel points in the gray level image, the number of the pixel points occupied by the white foreground region and the number of the pixel points occupied by the black background region;
determining the proportion of the white foreground region and the pixel mean value of the white foreground region according to the number of the pixel points occupied by the white foreground region;
determining the proportion of the black background area and the pixel mean value of the black background area according to the number of the pixel points occupied by the black background area;
determining the pixel mean value of the gray level image according to the total pixel point number in the gray level image;
and determining the inter-class variance according to the proportion of the white foreground region, the proportion of the black background region, the pixel mean value of the white foreground region, the pixel mean value of the black background region and the pixel mean value of the gray image.
4. The weld center identification method according to claim 3, wherein the determining a plurality of connected domains according to the pixel values of the binarized image specifically includes:
and traversing all pixel points in the binarized image, and forming a connected domain by pixel points with pixel values of continuous 1, so as to generate a plurality of connected domains.
5. A weld center identification system for sheet welding, the system comprising:
the sheet image acquisition module is used for acquiring a sheet surface image shot by the linear array CCD;
an image conversion module for converting the sheet surface image into a gray scale image;
the optimal segmentation threshold determining module is used for determining an optimal segmentation threshold according to the gray value of the gray image;
the binarization module is used for carrying out binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarized image;
the connected domain determining module is used for determining a plurality of connected domains according to the pixel values of the binarized image;
the gray value determining module is used for determining the gray value corresponding to the center point of each connected domain;
the weld joint center identification module is used for determining a weld joint region and a weld joint center according to the gray value corresponding to the center point of the connected region; and determining a central point corresponding to the maximum gray value in the gray values corresponding to the central points of the connected domains as a welding seam center, wherein the connected domain corresponding to the central point corresponding to the maximum gray value is a welding seam region.
6. The weld center identification system of claim 5, wherein the optimal segmentation threshold determination module specifically comprises:
a segmentation threshold acquisition unit configured to acquire a segmentation threshold; the segmentation threshold is 0 to 255;
the region dividing unit is used for dividing the gray image into a white foreground region and a black background region according to the dividing threshold value;
an inter-class variance calculating unit, configured to calculate an inter-class variance corresponding to the white foreground region and the black background region;
an optimal segmentation threshold determination unit configured to determine the segmentation threshold that maximizes the inter-class variance as an optimal segmentation threshold.
7. The weld center identification system according to claim 6, wherein the inter-class variance calculation unit specifically includes:
the pixel point statistics subunit is used for counting the total number of pixel points in the gray level image, the number of pixel points occupied by the white foreground area and the number of pixel points occupied by the black background area;
the foreground region parameter calculating subunit is used for determining the proportion of the white foreground region and the pixel mean value of the white foreground region according to the number of the pixel points occupied by the white foreground region;
the background area parameter calculation subunit is used for determining the proportion of the black background area and the pixel mean value of the black background area according to the number of the pixel points occupied by the black background area;
a gray image pixel mean value calculating subunit, configured to determine a pixel mean value of the gray image according to the total number of pixel points in the gray image;
and the class variance calculating subunit is used for determining the class variance according to the proportion of the white foreground region, the proportion of the black background region, the pixel mean value of the white foreground region, the pixel mean value of the black background region and the pixel mean value of the gray level image.
8. The weld center identification system of claim 7, wherein the connected domain determination module specifically comprises:
and the connected domain determining unit is used for traversing all pixel points in the binarized image, and forming a connected domain by the pixel points with the pixel values of 1 continuously, so as to generate a plurality of connected domains.
CN201910897761.4A 2019-09-23 2019-09-23 Weld joint center identification method and system for sheet welding Active CN112053368B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910897761.4A CN112053368B (en) 2019-09-23 2019-09-23 Weld joint center identification method and system for sheet welding

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910897761.4A CN112053368B (en) 2019-09-23 2019-09-23 Weld joint center identification method and system for sheet welding

Publications (2)

Publication Number Publication Date
CN112053368A CN112053368A (en) 2020-12-08
CN112053368B true CN112053368B (en) 2023-07-21

Family

ID=73609638

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910897761.4A Active CN112053368B (en) 2019-09-23 2019-09-23 Weld joint center identification method and system for sheet welding

Country Status (1)

Country Link
CN (1) CN112053368B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3533913A1 (en) * 1985-09-23 1987-04-02 Muenchener Apparatebau Fuer El Arrangement for nondestructive testing of welded seams
CN101358836A (en) * 2008-09-28 2009-02-04 西安理工大学 Method for recognising weld spot central position based on computer vision
JP2010054246A (en) * 2008-08-26 2010-03-11 Panasonic Electric Works Co Ltd Method for detecting joint and method for inspecting external appearance of joint using the method
CN103745475A (en) * 2014-01-22 2014-04-23 哈尔滨工业大学 Detection and positioning method used for spherical pin element
CN103759648A (en) * 2014-01-28 2014-04-30 华南理工大学 Complex fillet weld joint position detecting method based on laser binocular vision
CN106469312A (en) * 2016-09-29 2017-03-01 江苏省特种设备安全监督检验研究院 Weld seam visual identity method based on region growing label
CN108132017A (en) * 2018-01-12 2018-06-08 中国计量大学 A kind of plane welded seam Feature Points Extraction based on laser vision system
CN109514043A (en) * 2018-12-13 2019-03-26 刘堂斌 A kind of effective welding robot welding control system
CN109746597A (en) * 2017-11-08 2019-05-14 大族激光科技产业集团股份有限公司 Using method, system and the welding equipment of camera tracking weld seam
CN110021017A (en) * 2019-04-02 2019-07-16 南通大学 A method of extracting axis of a weld

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE3533913A1 (en) * 1985-09-23 1987-04-02 Muenchener Apparatebau Fuer El Arrangement for nondestructive testing of welded seams
JP2010054246A (en) * 2008-08-26 2010-03-11 Panasonic Electric Works Co Ltd Method for detecting joint and method for inspecting external appearance of joint using the method
CN101358836A (en) * 2008-09-28 2009-02-04 西安理工大学 Method for recognising weld spot central position based on computer vision
CN103745475A (en) * 2014-01-22 2014-04-23 哈尔滨工业大学 Detection and positioning method used for spherical pin element
CN103759648A (en) * 2014-01-28 2014-04-30 华南理工大学 Complex fillet weld joint position detecting method based on laser binocular vision
CN106469312A (en) * 2016-09-29 2017-03-01 江苏省特种设备安全监督检验研究院 Weld seam visual identity method based on region growing label
CN109746597A (en) * 2017-11-08 2019-05-14 大族激光科技产业集团股份有限公司 Using method, system and the welding equipment of camera tracking weld seam
CN108132017A (en) * 2018-01-12 2018-06-08 中国计量大学 A kind of plane welded seam Feature Points Extraction based on laser vision system
CN109514043A (en) * 2018-12-13 2019-03-26 刘堂斌 A kind of effective welding robot welding control system
CN110021017A (en) * 2019-04-02 2019-07-16 南通大学 A method of extracting axis of a weld

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
Groove-center detection in gas metal arc welding using a template-matching method;Xiaojia Wang等;《Int J Adv Manuf Technol》;第86卷;第2791–2801页 *
基于CCD的埋弧焊焊缝跟踪***数字图像处理方法;程世东等;《焊接技术》;第37卷(第2期);第34-36页 *
基于主动光视觉传感的焊缝自动跟踪***研究;龚国基;《中国优秀硕士学位论文全文数据库 信息科技辑》(第（2017）02期);I138-3755 *
基于区域连通滤波的薄板焊缝跟踪图像处理算法;欧志辉等;《焊接试验研究》(第12期);第37-40、VII页 *
基于视觉传感的焊缝识别方法的研究;王伟杰等;《机械工程师》(第10期);第18-20页 *

Also Published As

Publication number Publication date
CN112053368A (en) 2020-12-08

Similar Documents

Publication Publication Date Title
CN107203990B (en) Label breakage detection method based on template matching and image quality evaluation
CN107941808B (en) 3D printing forming quality detection system and method based on machine vision
CN103499585B (en) Based on noncontinuity lithium battery film defect inspection method and the device thereof of machine vision
Wang et al. Comparison analysis on present image-based crack detection methods in concrete structures
CN103886597B (en) Circle detection method based on edge detection and fitted curve clustering
CN109489566B (en) Lithium battery diaphragm material slitting width detection method, detection system and device
CN101387493B (en) Shape and position dimension non-contact photoelectric detection method for pylon component hole
CN111127429A (en) Water conservancy system pipe thread defect detection method based on self-training deep neural network
CN107389693A (en) A kind of printed matter defect automatic testing method based on machine vision
CN109993154A (en) The lithium sulfur type instrument intelligent identification Method of substation's simple pointer formula
CN110619328A (en) Intelligent ship water gauge reading identification method based on image processing and deep learning
CN108871185B (en) Method, device and equipment for detecting parts and computer readable storage medium
CN113177924A (en) Industrial production line product flaw detection method
CN100492396C (en) Method for identifying fabric grain image facing camara weft straightener
CN112858321A (en) Steel plate surface defect detection system and method based on linear array CCD
CN115601379A (en) Surface crack accurate detection technology based on digital image processing
CN112561875A (en) Photovoltaic cell panel coarse grid detection method based on artificial intelligence
CN109614868A (en) Automobile tire decorative pattern graph line identifying system
CN105991997A (en) Capacitive image sensor dead pixel real-time positioning method
CN104515473A (en) Online diameter detection method of varnished wires
CN104123728A (en) Hough transform based round pipe detection method
CN112053368B (en) Weld joint center identification method and system for sheet welding
CN113610054A (en) Underwater structure disease depth detection method, system and device and storage medium
CN105606623A (en) Linear array camera based steel plate surface defect detection system
CN116381053A (en) Ultrasonic detection method and system for welding metal materials

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant