CN112053368A - Welding seam center identification method and system for sheet welding - Google Patents

Welding seam center identification method and system for sheet welding Download PDF

Info

Publication number
CN112053368A
CN112053368A CN201910897761.4A CN201910897761A CN112053368A CN 112053368 A CN112053368 A CN 112053368A CN 201910897761 A CN201910897761 A CN 201910897761A CN 112053368 A CN112053368 A CN 112053368A
Authority
CN
China
Prior art keywords
determining
image
gray
pixel
center
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.)
Granted
Application number
CN201910897761.4A
Other languages
Chinese (zh)
Other versions
CN112053368B (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

Images

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 method and a system for identifying the center of a welding seam for welding a thin plate. Firstly, acquiring a sheet surface image shot by a linear array CCD (charge coupled device) and converting the sheet surface image into a gray image; determining an optimal segmentation threshold according to the gray value of the gray image; carrying out binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarization image; determining a plurality of connected domains according to the pixel values of the binary image, and determining the 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 domain. The method for identifying the center of the welding line can be used in an embedded system, can stably realize the identification of the center of the welding line with higher precision, and can effectively improve the welding efficiency, precision and accuracy when being used for automatically welding thin plates.

Description

Welding seam center identification method and system for sheet welding
Technical Field
The invention relates to the technical field of welding automation, in particular to a method and a system for identifying the center of a welding seam for welding a thin plate.
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 severe, the automation of welding seam tracking can reduce the labor intensity of welding workers and improve the welding quality. 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, regarding the identification and detection of the position of a welding seam, the welding research of medium plate steel generally used for groove welding is more, and the welding research of thin plates smaller than 5mm is less. Meanwhile, most of the welding seam center identification and detection algorithms are realized based on a PC (personal computer), so that the cost is high, and the application requirements of different occasions are difficult to meet. The current recognition algorithm for the weld joint center also has the defects of low recognition accuracy, poor robustness and the like.
Disclosure of Invention
The invention aims to provide a method and a system for identifying a weld center for welding a thin plate, which are used for solving the problems that the existing method for identifying and detecting the weld center is only suitable for welding medium-thickness steel plates, and has high cost, low identification accuracy and poor robustness.
In order to achieve the purpose, the invention provides the following scheme:
a weld center identification method for thin plate welding, the method comprising:
acquiring a sheet surface image shot by a linear array CCD;
converting the sheet surface image into a grayscale image;
determining an optimal segmentation threshold according to the gray value of the gray image;
carrying out binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarization image;
determining a plurality of connected domains according to the pixel values of the binary image;
determining a gray value corresponding to the central point of each connected domain;
and determining a welding line region and a welding line center according to the gray value corresponding to the central point of the connected domain.
Optionally, the determining an optimal segmentation threshold according to the gray value of the gray image specifically includes:
acquiring a segmentation threshold; the segmentation threshold is 0 to 255;
dividing the gray level image into a white foreground area and a black background area according to the segmentation threshold;
calculating the inter-class variance corresponding to the white foreground area and the black background area;
determining the segmentation threshold that maximizes the inter-class variance as an optimal segmentation threshold.
Optionally, the calculating the inter-class variance corresponding to the white foreground region and the black background region specifically includes:
counting the number of total pixels in the gray image, the number of pixels occupied by the white foreground region and the number of pixels occupied by the black background region;
determining the proportion of the white foreground area and the pixel mean value of the white foreground area according to the number of the pixel points occupied by the white foreground area;
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 image according to the total pixel number in the gray image;
and determining the inter-class variance according to the proportion of the white foreground area, the proportion of the black background area, the pixel mean value of the white foreground area, the pixel mean value of the black background area and the pixel mean value of the gray level 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 binary image, and forming a connected domain by the pixel points with the pixel values being continuously 1, thereby generating a plurality of connected domains.
Optionally, the determining the weld zone 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 the center of the weld joint;
and determining a communication domain corresponding to the central point corresponding to the maximum gray value as a welding seam region.
A weld center identification system for thin plate welding, the system comprising:
the thin plate image acquisition module is used for acquiring a thin plate surface image shot by the linear array CCD;
the image conversion module is used for converting the sheet surface image into a gray 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 binarization image;
a connected domain determining module, configured to determine a plurality of connected domains according to pixel values of the binarized image;
the connected domain central point gray value determining module is used for determining a gray value corresponding to the central point of each connected domain;
and the welding seam center identification module is used for determining a welding seam area and a welding seam center according to the gray value corresponding to the center point of the connected domain.
Optionally, the optimal segmentation threshold determining module specifically includes:
a division threshold acquisition unit configured to acquire a division threshold; the segmentation threshold is 0 to 255;
the area dividing unit is used for dividing the gray level image into a white foreground area and a black background area according to the segmentation threshold;
the inter-class variance calculating unit is used for calculating the inter-class variance corresponding to the white foreground area and the black background area;
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:
a pixel point counting subunit, configured to count the number of total pixel points in the grayscale image, the number of pixel points occupied by the white foreground region, and the number of pixel points occupied by the black background region;
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 pixels occupied by the white foreground region;
the background area parameter calculating subunit is used for determining the proportion of the black background area and the pixel average value of the black background area according to the number of the pixel points occupied by the black background area;
the gray level image pixel mean value calculating subunit is used for determining the pixel mean value of the gray level image according to the total pixel point number in the gray level image;
and the inter-class variance calculating subunit is used for determining the inter-class variance according to the proportion of the white foreground area, the proportion of the black background area, the pixel mean of the white foreground area, the pixel mean of the black background area and the pixel mean 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 binary image and forming the pixel points with the pixel values continuously being 1 into a connected domain, thereby generating a plurality of connected domains.
Optionally, the weld center identification module specifically includes:
the welding seam 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 welding seam center;
and the welding seam region identification unit is used for determining a communication domain corresponding to the central point corresponding to the maximum gray value as a welding seam region.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention provides a method and a system for identifying the center of a welding seam for welding a thin plate, wherein the method comprises the steps of firstly, acquiring a thin plate surface image shot by a linear array CCD (charge coupled device) and converting the thin plate surface image into a gray image; determining an optimal segmentation threshold according to the gray value of the gray image; carrying out binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarization image; determining a plurality of connected domains according to the pixel values of the binary image, and determining the 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 domain. The method for identifying the center of the welding line can be used in an embedded system, can stably realize the identification of the center of the welding line with higher precision, and can effectively improve the welding efficiency, precision and accuracy when being used for automatically welding thin plates.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a method for identifying the center of a weld for welding thin plates according to the present invention;
fig. 2 is a structural diagram of a weld center identification system for thin plate welding according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a method and a system for identifying a weld center for welding a thin plate, which are used for solving the problems that the existing method for identifying and detecting the weld center is only suitable for welding medium-thickness steel plates, and has high cost, low identification accuracy and poor robustness.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flowchart of a weld center identification method for thin plate welding according to the present invention. Referring to fig. 1, the method for identifying the center of a weld for welding a thin plate provided by the invention specifically includes:
step 101: and acquiring a sheet surface image shot by the linear array CCD.
The welding seam center identification method is based on a structured light vision sensing system formed by a linear array CCD (Charge Coupled Device) and is used for welding seam center identification during sheet welding. The linear array CCD is used for shooting a surface image of the thin plate during thin plate welding.
Step 102: and converting the sheet surface image 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 quantity gray signal, and calculating an optimal segmentation threshold by using a maximum inter-class variance method, which comprises the following specific steps of:
(a) acquiring a segmentation threshold; and dividing the gray level image into a white foreground area and a black background area according to the segmentation threshold.
Initializing a segmentation threshold T, wherein the segmentation threshold is 0 to 255. Dividing the gray level image into a white foreground region f according to the segmentation threshold TAAnd black backgroundRegion fBTwo parts.
The gray signal f (1, j), j belongs to M and is the jth pixel point in the gray image; and M is the set of all pixel points in the gray level image.
(b) Counting the total number N of pixel points in the gray image and the number N of pixel points occupied by the white foreground areaAAnd the number N of the pixel points occupied by the black background areaB。
(c) And determining the proportion of the white foreground area and the pixel mean value of the white foreground area according to the number of the pixel points occupied by the white foreground area.
The proportion P of the white foreground areaAThe calculation formula of (2) is as follows:
Figure BDA0002210837920000051
the white foreground area pixel mean value UAThe calculation formula of (2) is as follows:
Figure BDA0002210837920000052
wherein A is a pixel point set of the white foreground region; f (1, j) is the j-th pixel point in the gray 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 areaBThe calculation formula of (2) is as follows:
Figure BDA0002210837920000061
the pixel mean value U of the black background areaBThe calculation formula of (2) is as follows:
Figure BDA0002210837920000062
and B is a pixel point set of the black background area.
(e) And determining the pixel mean value of the gray image according to the total pixel number in the gray image.
The gray scaleThe calculation formula of the pixel mean value U of the image is as follows:
Figure BDA0002210837920000063
wherein M is a set of pixel points of the gray scale image.
(f) And determining the inter-class variance according to the proportion of the white foreground area, the proportion of the black background area, the pixel mean value of the white foreground area, the pixel mean value of the black background area and the pixel mean value of the gray level image.
The between-class variance θTThe calculation formula of (2) is as follows: thetaT＝PA×(UA-U)2+PB×(UB-U)2. Wherein P isAIs the proportion of the white foreground region, PBIs the proportion of the black background area, UAIs the mean value of the pixels of the white foreground region, UBAnd U is the pixel mean value of the black background area, and U is the pixel mean value of the gray level image.
(g) Determining the segmentation threshold that maximizes the inter-class variance as an optimal segmentation threshold.
Traversing the segmentation threshold T from 0 to 255, and simultaneously repeating the steps (a) - (f) to find out the inter-class variance thetaTThe 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 binarization image.
And performing binarization processing on the gray level image according to the optimal segmentation threshold, specifically: setting all pixel points with the gray values larger than the optimal segmentation threshold value in the gray image as 1, and setting all pixel points with the gray values smaller than the optimal segmentation threshold value as 0, so as to realize image binarization and generate the binarized image. And filtering the binary image to eliminate interference.
Step 105: and determining a plurality of connected domains according to the pixel values of the binary image.
And traversing all pixel points in the binary image, and forming a connected domain by a plurality of pixel points with the pixel values being continuously 1, thereby generating a plurality of connected domains.
Furthermore, the same label is set for all the pixel points in any connected domain, and the starting point and the end point of each connected domain are stored in the array. And averaging the gray values of the starting point and the end 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 central point of each connected domain is read and stored into the corresponding array.
Step 106: and determining the gray value corresponding to the central point of each connected domain.
Step 107: and determining a welding line region and a welding line center according to the gray value corresponding to the central point of the connected domain.
And determining the center point of the communication domain corresponding to the maximum value of the gray value according to the gray value corresponding to the center point of each communication domain, wherein the communication domain where the center point of the gray value corresponds to is the welding seam region, the starting point and the ending point of the communication domain are the left and right boundaries of the welding seam, and the center point of the communication domain is the center position of the welding seam. Determining the center point corresponding to the maximum gray value in the gray values corresponding to the center points of the connected domains as the center of the weld joint; and the communication domain corresponding to the central point corresponding to the maximum gray value is a welding seam region.
The method for identifying the center of the welding line can be used in an embedded system, can stably realize the identification of the center of the welding line with higher precision, and can effectively improve the welding efficiency, precision and accuracy when being used for automatically welding thin plates.
Based on the method for identifying the center of the welding seam provided by the invention, the invention also provides a system for identifying the center of the welding seam for welding thin plates, and referring to fig. 2, the system comprises:
a thin plate image obtaining module 201, configured to obtain a thin plate surface image captured by a linear array CCD;
an image conversion module 202, configured to convert the sheet surface image into a grayscale image;
an optimal segmentation threshold determination module 203, configured to determine an optimal segmentation threshold according to the gray-level value of the gray-level image;
a binarization module 204, configured to perform binarization processing on the grayscale image according to the optimal segmentation threshold value, and generate a binarized image;
a connected component determining module 205, configured to determine a plurality of connected components according to the 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 welding seam center identification module 207 is used for determining a welding seam area and a welding seam 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 division threshold acquisition unit configured to acquire a division threshold; the segmentation threshold is 0 to 255;
the area dividing unit is used for dividing the gray level image into a white foreground area and a black background area according to the segmentation threshold;
the inter-class variance calculating unit is used for calculating the inter-class variance corresponding to the white foreground area and the black background area;
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 counting subunit, configured to count the number N of total pixel points in the grayscale image and the number N of pixel points occupied by the white foreground regionAAnd the number N of the pixel points occupied by the black background areaB；
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 pixels occupied by the white foreground region; the method specifically comprises the following steps: according to the number N of the pixel points occupied by the white foreground areaABy the formula
Figure BDA0002210837920000081
Determining the proportion P of the white foreground areaA(ii) a According to the number N of the pixel points occupied by the white foreground areaABy the formula
Figure BDA0002210837920000082
Determining the white foreground region pixel mean UA(ii) a Wherein A is a pixel point set of the white foreground region; f (1, j) is the jth pixel point in the gray image;
the background area parameter calculating subunit is used for determining the proportion of the black background area and the pixel average value of the black background area according to the number of the pixel points occupied by the black background area; the method specifically comprises the following steps: according to the number N of the pixel points occupied by the black background areaBBy the formula
Figure BDA0002210837920000083
Determining the proportion P of the black background areaB(ii) a According to the number N of the pixel points occupied by the black background areaBBy the formula
Figure BDA0002210837920000085
Determining the mean value U of the pixels in the black background areaB(ii) a B is a pixel point set of the black background area;
a gray image pixel mean value calculating subunit, configured to adopt a formula according to the total number N of pixel points in the gray image
Figure BDA0002210837920000084
Determining a pixel mean value U of the gray level image; wherein M is a pixel point set of the gray level image;
an inter-class variance calculating subunit, configured to calculate the ratio P of the white foreground region according to the ratioAThe proportion P of the black background areaBThe pixel mean value U of the white foreground areaAThe pixel mean value U of the black background areaBAnd the pixel mean value U of the gray level image adopts a formula thetaT＝PA×(UA-U)2+PB×(UB-U)2Determining the between-class variance θT。
The connected domain determining module 205 specifically includes:
and the connected domain determining unit is used for traversing all pixel points in the binary image and forming the pixel points with the pixel values continuously being 1 into a connected domain, thereby generating a plurality of connected domains.
The weld center identification module 207 specifically includes:
the welding seam 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 welding seam center;
a weld zone identification unit for determining the connected zone corresponding to the central point corresponding to the maximum gray value as a weld zone
Compared with the existing welding seam center identification and detection method, the welding seam center identification method and the welding seam center identification system for sheet welding at least have the following advantages:
1. the method and the system for identifying the center of the welding line are applied to the field of thin plate welding, and make up for the defects of welding automation in the field.
2. The method and the system for identifying the weld center provided by the invention can be applied to an upper computer and can also be transplanted to an embedded system for use, so that the cost of a welding device is reduced, and the realization of welding automation is facilitated.
3. The method and the system for identifying the weld centers improve the resolution and the precision of weld identification by adopting a maximum between-class variance algorithm and a connected domain statistical mode, reduce the number of data operations while ensuring the data precision, and improve the speed of identifying and processing the weld centers.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims (10)

1. A method of weld center identification for thin plate welding, the method comprising:
acquiring a sheet surface image shot by a linear array CCD;
converting the sheet surface image into a grayscale image;
determining an optimal segmentation threshold according to the gray value of the gray image;
carrying out binarization processing on the gray level image according to the optimal segmentation threshold value to generate a binarization image;
determining a plurality of connected domains according to the pixel values of the binary image;
determining a gray value corresponding to the central point of each connected domain;
and determining a welding line region and a welding line center according to the gray value corresponding to the central point of the connected domain.
2. The weld joint center identification method according to claim 1, wherein the determining an optimal segmentation threshold value according to the gray-scale value of the gray-scale image specifically comprises:
acquiring a segmentation threshold; the segmentation threshold is 0 to 255;
dividing the gray level image into a white foreground area and a black background area according to the segmentation threshold;
calculating the inter-class variance corresponding to the white foreground area and the black background area;
determining the segmentation threshold that maximizes the inter-class variance as an optimal segmentation threshold.
3. The weld center identification method according to claim 2, wherein the calculating of the inter-class variance corresponding to the white foreground region and the black background region specifically includes:
counting the number of total pixels in the gray image, the number of pixels occupied by the white foreground region and the number of pixels occupied by the black background region;
determining the proportion of the white foreground area and the pixel mean value of the white foreground area according to the number of the pixel points occupied by the white foreground area;
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 image according to the total pixel number in the gray image;
and determining the inter-class variance according to the proportion of the white foreground area, the proportion of the black background area, the pixel mean value of the white foreground area, the pixel mean value of the black background area and the pixel mean value of the gray level 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 comprises:
and traversing all pixel points in the binary image, and forming a connected domain by the pixel points with the pixel values being continuously 1, thereby generating a plurality of connected domains.
5. The weld joint center identification method according to claim 4, wherein the determining of the weld joint region and the weld joint center according to the gray value corresponding to the center point of the connected domain specifically comprises:
determining a central point corresponding to the maximum gray value in the gray values corresponding to the central points of the connected domains as the center of the weld joint;
and determining a communication domain corresponding to the central point corresponding to the maximum gray value as a welding seam region.
6. A weld center identification system for thin plate welding, the system comprising:
the thin plate image acquisition module is used for acquiring a thin plate surface image shot by the linear array CCD;
the image conversion module is used for converting the sheet surface image into a gray 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 binarization image;
a connected domain determining module, configured to determine a plurality of connected domains according to pixel values of the binarized image;
the connected domain central point gray value determining module is used for determining a gray value corresponding to the central point of each connected domain;
and the welding seam center identification module is used for determining a welding seam area and a welding seam center according to the gray value corresponding to the center point of the connected domain.
7. The weld center identification system according to claim 6, wherein the optimal segmentation threshold determination module specifically comprises:
a division threshold acquisition unit configured to acquire a division threshold; the segmentation threshold is 0 to 255;
the area dividing unit is used for dividing the gray level image into a white foreground area and a black background area according to the segmentation threshold;
the inter-class variance calculating unit is used for calculating the inter-class variance corresponding to the white foreground area and the black background area;
an optimal segmentation threshold determination unit configured to determine the segmentation threshold that maximizes the inter-class variance as an optimal segmentation threshold.
8. The weld center identification system according to claim 7, wherein the between-class variance calculation unit specifically includes:
a pixel point counting subunit, configured to count the number of total pixel points in the grayscale image, the number of pixel points occupied by the white foreground region, and the number of pixel points occupied by the black background region;
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 pixels occupied by the white foreground region;
the background area parameter calculating subunit is used for determining the proportion of the black background area and the pixel average value of the black background area according to the number of the pixel points occupied by the black background area;
the gray level image pixel mean value calculating subunit is used for determining the pixel mean value of the gray level image according to the total pixel point number in the gray level image;
and the inter-class variance calculating subunit is used for determining the inter-class variance according to the proportion of the white foreground area, the proportion of the black background area, the pixel mean of the white foreground area, the pixel mean of the black background area and the pixel mean of the gray level image.
9. The weld center identification system according to claim 8, wherein the connected component determination module specifically comprises:
and the connected domain determining unit is used for traversing all pixel points in the binary image and forming the pixel points with the pixel values continuously being 1 into a connected domain, thereby generating a plurality of connected domains.
10. The weld center identification system according to claim 9, wherein the weld center identification module specifically comprises:
the welding seam 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 welding seam center;
and the welding seam region identification unit is used for determining a communication domain corresponding to the central point corresponding to the maximum gray value as a welding seam region.
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 true CN112053368A (en) 2020-12-08
CN112053368B 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
XIAOJIA WANG等: "Groove-center detection in gas metal arc welding using a template-matching method", 《INT J ADV MANUF TECHNOL》, vol. 86, pages 2791, XP036061376, DOI: 10.1007/s00170-016-8389-7 *
欧志辉等: "基于区域连通滤波的薄板焊缝跟踪图像处理算法", 《焊接试验研究》, no. 12, pages 37 - 40 *
王伟杰等: "基于视觉传感的焊缝识别方法的研究", 《机械工程师》, no. 10, pages 18 - 20 *
程世东等: "基于CCD的埋弧焊焊缝跟踪系统数字图像处理方法", 《焊接技术》, vol. 37, no. 2, pages 34 - 36 *
龚国基: "基于主动光视觉传感的焊缝自动跟踪系统研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 2017, pages 138 - 3755 *

Also Published As

Publication number Publication date
CN112053368B (en) 2023-07-21

Similar Documents

Publication Publication Date Title
CN107941808B (en) 3D printing forming quality detection system and method based on machine vision
CN109969736B (en) Intelligent detection method for deviation fault of large carrying belt
CN101387493B (en) Shape and position dimension non-contact photoelectric detection method for pylon component hole
CN109993154B (en) Intelligent identification method for single-pointer sulfur hexafluoride instrument of transformer substation
CN109376740A (en) A kind of water gauge reading detection method based on video
CN104112269A (en) Solar cell laser-marking parameter detection method based on machine vision and system thereof
CN106407924A (en) Binocular road identifying and detecting method based on pavement characteristics
CN101315668A (en) Automatic detection method for test paper form
CN106548111A (en) A kind of Quick Response Code open defect detection method and device
CN107016394B (en) Cross fiber feature point matching method
CN110619328A (en) Intelligent ship water gauge reading identification method based on image processing and deep learning
CN115184380B (en) Method for detecting abnormity of welding spots of printed circuit board based on machine vision
CN113177924A (en) Industrial production line product flaw detection method
TW200810518A (en) System and method for boundary scan of an image
CN104123728A (en) Hough transform based round pipe detection method
CN113705564B (en) Pointer type instrument identification reading method
CN104515473A (en) Online diameter detection method of varnished wires
CN105606623A (en) Linear array camera based steel plate surface defect detection system
Ying et al. Research on an automatic counting method for steel bars' image
CN112053368A (en) Welding seam center identification method and system for sheet welding
CN112561875A (en) Photovoltaic cell panel coarse grid detection method based on artificial intelligence
CN110689926A (en) Accurate detection method for high-throughput digital PCR image droplets
CN111243006A (en) Method for measuring liquid drop contact angle and size based on image processing
CN116071692A (en) Morphological image processing-based water gauge water level identification method and system
CN115909359A (en) Capacitance character detection method based on intelligent vision

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