CN116503408B - Scanning technology-based steel structure surface defect detection method - Google Patents
Scanning technology-based steel structure surface defect detection method Download PDFInfo
- Publication number
- CN116503408B CN116503408B CN202310770671.5A CN202310770671A CN116503408B CN 116503408 B CN116503408 B CN 116503408B CN 202310770671 A CN202310770671 A CN 202310770671A CN 116503408 B CN116503408 B CN 116503408B
- Authority
- CN
- China
- Prior art keywords
- weld joint
- weld
- skeleton
- gray
- degree
- 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
Links
- 230000007547 defect Effects 0.000 title claims abstract description 72
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 40
- 239000010959 steel Substances 0.000 title claims abstract description 40
- 238000001514 detection method Methods 0.000 title claims abstract description 22
- 238000005516 engineering process Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 claims abstract description 78
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 230000004927 fusion Effects 0.000 claims abstract description 5
- 238000003466 welding Methods 0.000 claims description 69
- 238000004364 calculation method Methods 0.000 claims description 22
- 230000005856 abnormality Effects 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 18
- 239000011324 bead Substances 0.000 claims description 10
- 230000005764 inhibitory process Effects 0.000 claims description 3
- 238000007670 refining Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
Abstract
The application belongs to the technical field of image processing, and provides a steel structure surface defect detection method based on a scanning technology, which comprises the following steps: acquiring a surface image of the steel structure through a scanning technology; denoising the surface image to obtain a surface gray level image; dividing the surface gray level image by a Canny operator to obtain a weld joint framework; analyzing the weld joint skeleton to obtain a weld joint defect significance degree index; inputting the significance degree index into a visual significance detection Itti algorithm to obtain a fusion defect significance map. By the method provided by the application, the situation that the image defects cannot be identified due to the fact that the weld defects are not obvious is avoided, and the detection precision of the surface defects of the steel structure is improved.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a steel structure surface defect detection method based on a scanning technology.
Background
The steel structure is widely applied to industries such as manufacturing, building, aviation and the like, and is an important component of national economy.
In the production and use process of the steel structure, the steel structure is affected by factors such as processing equipment, production environment and the like, and defects are inevitably generated. In the use process of the steel structure, the steel materials are connected with each other generally through welding so as to realize firm connection between the steel materials, and defect characteristics such as weld fracture, uneven weld width and uneven height and the like can be generated by technical workers due to personal technical problems when welding the weld, and the defect characteristics of the weld are generally judged through a traditional image processing method, but the weld with less obvious defect characteristics is difficult to identify through the traditional image processing method.
Thus, there is a need for a method to identify welds with less pronounced surface defect characteristics.
Disclosure of Invention
The application provides a steel structure surface defect detection method based on a scanning technology, which is used for improving the steel structure surface defect detection precision.
There is provided a method for detecting surface defects of a steel structure based on a scanning technique, the method comprising:
acquiring a surface image of the steel structure through a scanning technology;
denoising the surface image to obtain a surface gray level image;
dividing the surface gray level image through a Canny operator to obtain a weld joint framework;
analyzing the weld joint skeleton to obtain a weld joint defect significance degree index;
and inputting the significance degree index into a visual significance detection Itti algorithm to obtain a fusion defect significance map.
In some embodiments of the present application, segmenting the surface grayscale image by a Canny operator to obtain a weld skeleton comprises:
dividing the surface gray level image through a Canny operator to obtain a welding line region;
refining the welding line area by a non-maximum value inhibition method to obtain a welding line framework;
and redundant lines in the weld joint framework are filtered by adopting double threshold values, so that the continuity of the weld joint framework is ensured.
In some embodiments of the present application, analyzing the weld skeleton to obtain a weld defect significance level indicator includes:
gray value of pixel point of weld joint skeletonIn the region of the weld skeleton in the longitudinal direction thereofThe maximum value in the gray values of the pixel points is differenced to obtain the gray offset of the weld joint framework；
According to the gray level offset of the weld joint frameworkAnd weld seam skeleton seam widthCalculating to obtain the width offset of the welding seam；
Obtaining the shadow gray level of the weld joint framework according to the gray values of the pixel points of the weld joint areas on the upper side and the lower side of the weld joint framework；
According to the width deviation of the welding lineAnd the degree of shade gray of the weld skeletonObtaining the width and height offset of the weld joint framework；
A gray scale run matrix method is adopted, and gray scale values of each pixel point in the neighborhood of the pixel points of the weld joint skeleton are calculated to obtain a gray scale run matrix;
according to the gray scale run matrix, calculating and obtaining the fracture degree of the welding joint；
Height deviation according to seam width of weld joint frameworkAnd degree of weld joint fractureObtaining the weld joint skeleton pixelDegree of abnormality at a point；
According to the degree of abnormality at the pixel points of the weld joint frameworkObtaining the defect significance degree index of the welding line。
In some embodiments of the application, the weld skeleton gray scale offsetThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe gray scale offset of the weld joint skeleton at each pixel point,representing the longitudinal direction of the pixel points of the weld joint skeletonThe gray value of the largest pixel among the gray values,representing the first weld joint skeletonGray values at the individual pixel points.
In some embodiments of the application, the weld width offsetThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe weld width offset at each pixel point,representing the first weld joint skeletonThe gray scale offset of the weld joint skeleton at each pixel point,representing the first weld joint skeletonAbsolute value of the difference between the slit width at each pixel point and the average slit width.
In some embodiments of the application, the weld skeleton shading gray levelThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe degree of shade gray of the weld skeleton at each pixel point,representing the first weld joint skeletonThe sum of gray values of pixels in the weld area upwards from each pixel,representing the first weld joint skeletonAnd the gray value sum of the pixels in the weld joint area with the downward pixels.
In some embodiments of the application, the weld backbone seam width height offsetThe calculation method comprises the following steps:
in the method, in the process of the application,representing the first weld joint skeletonThe seam width and height offset of the weld joint skeleton at each pixel point,representing the first weld joint skeletonThe weld width offset at each pixel point,representing the first weld joint skeletonThe degree of shade gray of the weld skeleton at each pixel point,weld joint skeleton shadow gray scale for representing pixel points on weld joint skeletonAnd (5) a degree average value.
In some embodiments of the application, the weld joint fracture degreeThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe degree of weld joint fracture at each pixel point,is thatIs a matrix of gray scale run lengths of (c),representing the gray level in the 5x5 neighborhood,representing the direction alongIs used for the maximum run length of the (c) code,representing the direction alongThe sum of all elements in the gray run length matrix above.
In some embodiments of the application, the degree of abnormality at the weld skeleton pixel pointsThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe degree of abnormality at each pixel point,representing the first weld joint skeletonThe seam width and height offset of the weld joint skeleton at each pixel point,representing the first weld joint skeletonThe degree of weld joint fracture at each pixel point.
In some embodiments of the application, the weld defect significance level indicatorThe calculation method of (1) is as follows:
in the method, in the process of the application,the index of the significance degree of the weld defect is shown,representing the first weld joint skeletonDegree of abnormality at each pixel point.
As can be seen from the above embodiments, the scanning technology-based steel structure surface defect detection method provided by the embodiment of the present application has the following beneficial effects:
according to the application, the significance detection is carried out according to the characteristic of the width and height deviation of the welding seam and the fracture degree of the welding seam joint of the pixel points on the welding seam framework, the image defect characteristic which is not easy to be identified by a machine is analyzed, and on the basis that the brightness, the color and the direction of the Itti algorithm are fused together to form a defect significance map, the index of the significance degree of the welding seam defect is added as an index, and the index of the significance degree of the welding seam defect is fused together to form the defect significance map, so that the welding seam defect on the surface of the steel structure image is more significantly represented. The condition that image defects cannot be identified due to unobvious weld defects is avoided, and the detection precision of the surface defects of the steel structure is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings that are needed in the embodiments will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a basic flow diagram of a method for detecting surface defects of a steel structure based on a scanning technique according to an embodiment of the present application;
FIG. 2 is a schematic flow diagram of a method for obtaining a weld skeleton according to an embodiment of the present application;
fig. 3 is a basic flow chart of a method for obtaining a defect significance level index of a weld according to an embodiment of the present application.
Detailed Description
In order to make the technical solution of the present application better understood by those skilled in the art, the technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The following describes in detail a method for detecting a surface defect of a steel structure based on a scanning technique according to this embodiment with reference to the accompanying drawings.
Fig. 1 is a basic flow chart of a method for detecting a surface defect of a steel structure based on a scanning technique according to an embodiment of the present application, as shown in fig. 1, the method specifically includes the following steps:
s100: and acquiring and obtaining a surface image of the steel structure through a scanning technology.
And (3) carrying out high-speed scanning imaging on the surface of the steel structure by using a linear sensor and an image processor which move at high speed through a surface scanning camera, and acquiring and obtaining a surface image of the steel structure, namely a surface RGB space image of the steel structure.
S200: and denoising the surface image to obtain a surface gray level image.
And denoising pretreatment is carried out on the obtained surface image of the steel structure, so that the influence caused by noise and partial external interference is eliminated, and the accuracy of subsequent analysis is enhanced. In order to remove noise while retaining boundary information, the application selects median filtering to perform denoising processing on the image, and an implementer can also adopt other denoising methods. And converting the acquired RGB image of the steel structure surface into a steel structure surface gray scale image.
S300: and dividing the surface gray level image through a Canny operator to obtain a weld joint framework.
The welding level and the technique of each worker are different, the height and the width deviation of the welding seam welded by one worker are also different, and the difference is difficult to judge whether the welding seam quality is qualified by a manual detection method, so that the welding seam quality needs to be analyzed by adopting an image processing technology.
The defects in the surface image of the steel structure are various, and particularly, poor weld joint formation caused by different welding methods of welding workers is mainly represented by three bad states of poor joints, inconsistent seam widths and inconsistent seam heights. If these defect states are detected only manually, the evaluation results are easily affected by subjective factors. In view of this, the present application builds a severity index for three features at the weld by three bad conditions of weld formation to evaluate if the weld should be more significant.
Fig. 2 is a basic flow chart of a method for obtaining a weld bead skeleton according to an embodiment of the present application, as shown in fig. 2, in some embodiments of the present application, a weld bead skeleton is obtained by segmenting a surface gray image by a Canny operator, including:
s301: dividing the surface gray level image by a Canny operator to obtain a welding seam region;
s302: refining the welding line area by a non-maximum value inhibition method to obtain a welding line framework;
s303: and redundant lines in the weld joint framework are filtered by adopting double threshold values, so that the continuity of the weld joint framework is ensured.
S400: and analyzing the weld joint framework to obtain the weld joint defect significance degree index.
The weld defect significance degree index of each pixel point is obtained by analyzing three characteristics of the weld width deviation degree of each pixel point on the weld skeleton, the weld width height deviation degree of the weld skeleton and the fracture degree of the weld joint。
Fig. 3 is a basic flow chart of a method for obtaining a defect significance level index of a weld, which is provided by an embodiment of the present application, as shown in fig. 3, in some embodiments of the present application, a weld skeleton is analyzed to obtain a defect significance level index of the weld, including the following steps:
s401: gray value of pixel point of weld joint skeletonIn the region of the weld skeleton in the longitudinal direction thereofThe maximum value of the gray values of the pixel points is differenced to obtainTo the gray level offset of the weld joint framework。
Assume that the number of pixel points on the weld skeleton isThe number of the two-dimensional space-saving type,representing the first weld joint skeletonGray values of individual pixels. By welding the first joint on the frameworkTaking a pixel point as an example, assume that the first pixel point is on a welding line frameworkThe longitudinal axis direction of each pixel point is provided withA pixel point, for the first on the weld joint frameworkGray value of each pixel pointAccording to the pixel point and the welding line framework area in the longitudinal directionThe maximum value in the gray values of the pixel points is differed, the width direction of the weld joint framework is defined as the longitudinal direction, and the first weld joint framework is obtainedWeld joint skeleton gray scale offset at each pixel point. Further, the gray level offset of the weld joint frameworkThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe gray scale offset of the weld joint skeleton at each pixel point,representing the longitudinal direction of the pixel points of the weld joint skeletonThe gray value of the largest pixel among the gray values,representing the first weld joint skeletonGray values at the individual pixel points.
Gray scale offset of weld joint frameworkReflecting whether each pixel point on the weld skeleton is the center of the weld width, ifThe larger the pixel points of the weld joint skeleton are, the larger the center of the offset weld joint width is, which indicates that the weld joint width is uneven and the quality of the weld joint width is poor; otherwise, the weld joint width is uniform, and the seam width quality is good.
S402: according to the gray level offset of the weld joint frameworkAnd weld seam skeleton seam widthCalculating to obtain the width offset of the welding seam。
By welding the first joint on the frameworkFor example, according to the first pixel on the weld skeletonWeld joint skeleton gray scale offset at each pixel pointAnd the first weld joint frameworkWeld bead skeleton seam width at individual pixel pointsCalculating to obtain the first weld joint skeletonWeld width offset at individual pixel points. Wherein, the first welding line framework isThe number of the pixel points in the welding seam framework area along the longitudinal axis direction of the position of each pixel point is the width of the welding seam frameworkLikewise, the weld bead skeleton width direction is defined herein as the longitudinal axis direction. Further, the first welding line frameworkWeld width offset at individual pixel pointsCalculation of (2)The method comprises the following steps:
in the method, in the process of the application,representing the first weld joint skeletonThe weld width offset at each pixel point,representing the first weld joint skeletonThe gray scale offset of the weld joint skeleton at each pixel point,representing the first weld joint skeletonAbsolute value of the difference between the weld skeleton seam width at each pixel point and the average weld skeleton seam width.
If it isThe larger the welding seam framework pixel point is, the farther the welding seam framework pixel point is from the highest salient point, and the larger the average width of the welding seam at the position of the welding seam framework pixel point is, the worse the quality of the welding seam width is; otherwise, the weld width quality is better.
S403: obtaining the shadow gray level of the weld joint framework according to the gray values of the pixel points of the weld joint areas on the upper side and the lower side of the weld joint framework。
And the joint height characteristic of each pixel point on the weld joint framework can be analyzed by obtaining the sum of the gray values of the pixel points on the smallest side of the weld joint framework. By welding the first joint on the frameworkFor example, according to the first pixel on the weld skeletonGray values of pixel points of welding line areas on the upper side and the lower side of each pixel point are obtained, and the first welding line skeleton is obtainedShadow gray scale of weld joint skeleton at each pixel point. Further, the shade gray level of the weld joint frameworkThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe degree of shade gray of the weld skeleton at each pixel point,representing the first weld joint skeletonThe sum of gray values of pixels in the weld area upwards from each pixel,representing the first weld joint skeletonAnd the gray value sum of the pixels in the weld joint area with the downward pixels.
If it isThe bigger the height of the pixel point of the weld joint skeleton is, the brighter the shadow part is, and the gray value is larger; otherwise, the height of the weld joint skeleton pixel point is higher.
S404: according to the width deviation of the welding lineAnd the degree of shade gray of the weld skeletonObtaining the width and height offset of the weld joint framework。
The calculation of the height of a single weld bead skeleton pixel does not allow for the assessment of weld bead height quality by calculating the degree of weld bead skeleton shadow gray scale for each weld bead skeleton pixelMean value of gray scale degree of shadow of weld joint frameworkThe square of the difference and the width deviation of the welding line are addedObtaining the width and height offset of each welding seam skeleton pixel spot welding seam. By welding the first joint on the frameworkThe first pixel point is taken as an example on a welding line frameworkSeam width and height offset of weld joint skeleton at each pixel pointThe calculation method comprises the following steps:
in the method, in the process of the application,representing the first weld joint skeletonThe seam width and height offset of the weld joint skeleton at each pixel point,representing the first weld joint skeletonThe weld width offset at each pixel point,representing the first weld joint skeletonThe degree of shade gray of the weld skeleton at each pixel point,and the average value of the shade gray level of the weld joint skeleton of the pixel points on the weld joint skeleton is represented.
If it isThe larger the welding seam framework pixel point is, the larger the deviation of the welding seam framework pixel point from the highest salient point is, and meanwhile, the larger the difference of the welding seam width of the welding seam framework pixel point is compared with the average width, the worse the quality of the welding seam width is; otherwise, the slit width quality is better.The evaluation of the pixel point height of each weld joint skeleton is shown, if the value is larger, the pixel point height of the weld joint skeleton is higher or lower than the average weld joint height, and the quality of the weld joint is poorer; otherwise, the high quality of the seam at the pixel point of the welding seam framework is indicated.Representing the width and height offset of the pixel spot weld of the weld skeleton ifThe bigger the seam is, the wider the seam width of the weld joint skeleton is, the higher the seam quality is poor; otherwise, the seam width and the seam high quality of the weld joint framework are better.
S405: and calculating the gray value of each pixel point in the neighborhood of the pixel point of the weld joint skeleton by adopting a gray run matrix method to obtain a gray run matrix.
In order to obtain the gray value non-uniformity around each weld joint skeleton pixel, the situation that the joint is poor and not fused around part of the weld joint skeleton pixels is possible. The gray value of each pixel point of the welding line area is mapped to the gray level of 0-4 in equal proportion and average to obtain a gray image with the gray level of 5。
For each weld skeleton pixel point in the weld region after gray level conversionAdopting a gray scale run matrix method to weld the pixel points of the skeletonAnd calculating the gray value of each pixel point in the neighborhood to obtain a gray run matrix.
S406: according to the gray scale run matrix, calculating and obtaining the fracture degree of the welding joint。
By welding the first joint on the frameworkTaking a pixel point as an example, calculating to obtain the first pixel on the weld joint framework according to the gray scale run matrixDegree of weld joint fracture at individual pixel points. Further, the first welding line frameworkDegree of weld joint fracture at individual pixel pointsThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe degree of weld joint fracture at each pixel point,is thatIs a matrix of gray scale run lengths of (c),representing the gray level in the 5x5 neighborhood,representing the direction alongIs used for the maximum run length of the (c) code,representing the direction alongThe sum of all elements in the gray run length matrix above.
Q represents the fracture degree of the weld joint, namely the uneven distribution of pixel gray levels around each weld skeleton pixel point. If it isThe larger the pixel points are, the uneven gray distribution of the pixel points around the pixel points of the current weld joint skeleton is shown, and the state that the joint defect exists in the larger probability around the pixel points of the weld joint skeleton is shown; otherwise, the state that the joint is poor in a small probability exists around the pixel point of the weld joint skeleton is indicated.
S407: height deviation according to seam width of weld joint frameworkAnd degree of weld joint fractureObtaining the degree of abnormality at the pixel points of the weld skeleton。
By welding the first joint on the frameworkFor example, according to the first pixel on the weld skeletonSeam width and height offset of weld joint skeleton at each pixel pointAnd degree of weld joint fractureObtaining a weld joint frameworkDegree of abnormality at each pixel point. Further, the first welding line frameworkDegree of abnormality at each pixel pointThe calculation method of (1) is as follows:
in the method, in the process of the application,representing the first weld joint skeletonThe degree of abnormality at each pixel point,representing the first weld joint skeletonThe seam width and height offset of the weld joint skeleton at each pixel point,representing the first weld joint skeletonThe degree of weld joint fracture at each pixel point.
In the range of 0-1. If it isThe larger the weld joint skeleton pixel point is, the seam height and seam width of the weld joint skeleton pixel point are indicated, and quality abnormality occurs in joints and the like, so that the weld joint skeleton pixel point can be provided with defects; and otherwise, the probability of defects at the pixel points of the weld joint framework is smaller.
S408: according to the degree of abnormality at the pixel points of the weld joint frameworkObtaining the defect significance degree index of the welding line。
By welding the first joint on the frameworkFor example, according to the first pixel on the weld skeletonDegree of abnormality at each pixel pointObtaining the defect significance degree index of the welding line. Further, the defect significance degree index of the welding lineThe calculation method of (1) is as follows:
in the method, in the process of the application,the index of the significance degree of the weld defect is shown,representing the first weld joint skeletonDegree of abnormality at each pixel point.
Weld defect significance level indexBy summing the degree of abnormality of the weld skeleton pixels, ifThe closer the larger the indication of theThe greater the likelihood of defects in the weld area, the more significant the need to represent that area; and conversely, the less likely the weld region is to be defective. The judgment threshold may be empirically set.
S500: inputting the significance degree index into a visual significance detection Itti algorithm to obtain a fusion defect significance map.
Using a visual saliency detection Itti algorithm, wherein the Itti algorithm is a saliency target detection algorithm, and inputting a saliency degree index into the visual saliency detection Itti algorithm, namely inputting a weld defect saliency degree indexAdded to the brightnessColor ofAnd direction ofIn the comprehensive significance map evaluation of (2), obtainIs a final fusion defect saliency map. The weld defects were evaluated in this way.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
It should be noted that unless otherwise specified and limited, terms such as "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a circuit structure, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such article or apparatus. Without further limitation, the statement "comprises one … …" does not exclude that an additional identical element is present in an article or device that comprises the element. In addition, the term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (9)
1. The method for detecting the surface defects of the steel structure based on the scanning technology is characterized by comprising the following steps of:
acquiring a surface image of the steel structure through a scanning technology;
denoising the surface image to obtain a surface gray level image;
dividing the surface gray level image through a Canny operator to obtain a weld joint framework;
analyzing the weld joint skeleton to obtain a weld joint defect significance degree index;
inputting the significance degree index into a visual significance detection Itti algorithm to obtain a fusion defect significance map;
analyzing the weld joint skeleton to obtain a weld joint defect significance degree index, wherein the weld joint defect significance degree index comprises the following steps:
gray value of pixel point of weld joint skeletonAnd the weld joint skeleton area in the longitudinal directionInner->The maximum value in the gray values of the pixel points is differenced to obtain the gray offset degree of the weld joint skeleton>；
According to the gray level offset of the weld joint frameworkAnd weld skeleton seam width->Calculating to obtain the width deviation of the welding line>；
Obtaining the shadow gray level of the weld joint framework according to the gray values of the pixel points of the weld joint areas on the upper side and the lower side of the weld joint framework；
According to the width deviation of the welding lineAnd the shade gray level of the weld joint skeleton->Obtaining the seam width and height deviation of the weld joint framework>；
A gray scale run matrix method is adopted, and gray scale values of each pixel point in the neighborhood of the pixel points of the weld joint skeleton are calculated to obtain a gray scale run matrix;
according to the gray scale run matrix, calculating and obtaining the fracture degree of the welding joint；
Height deviation according to seam width of weld joint frameworkAnd degree of weld joint fracture->Obtaining the degree of abnormality +.>；
According to the degree of abnormality at the pixel points of the weld joint frameworkObtaining a weld defect significance degree index ++>。
2. The scanning technology-based steel structure surface defect detection method according to claim 1, wherein the surface gray scale image is segmented by a Canny operator to obtain a weld skeleton, comprising:
dividing the surface gray level image through a Canny operator to obtain a welding line region;
refining the welding line area by a non-maximum value inhibition method to obtain a welding line framework;
and redundant lines in the weld joint framework are filtered by adopting double threshold values, so that the continuity of the weld joint framework is ensured.
3. The scanning-technology-based steel structure surface defect detection method according to claim 1, wherein the weld bead skeleton gray scale offsetThe calculation method of (1) is as follows:
in the method, in the process of the application,indicating the%>The gray scale offset of the weld joint skeleton at each pixel point,pixel point longitudinal direction of weld joint skeleton>Gray value of the largest pixel of the gray values,/gray value of the pixel of the gray values>Indicating the%>Gray values at the individual pixel points.
4. The method for detecting surface defects of steel structure based on scanning technology as claimed in claim 1, wherein the weld width deviation degreeThe calculation method of (1) is as follows:
in the method, in the process of the application,indicating the%>Weld width offset at individual pixels, +.>Indicating the%>Gray scale offset of weld skeleton at each pixel point, < ->Indicating the%>Absolute value of the difference between the slit width at each pixel point and the average slit width.
5. The scanning-technology-based steel structure surface defect detection method according to claim 1, wherein the weld skeleton shadow gray scale degreeThe calculation method of (1) is as follows:
in the method, in the process of the application,indicating the%>The gray level of the weld skeleton shadow at each pixel point,/->Indicating the%>Weld joint area image with upward pixel pointsSum of gray values of pixels +.>Indicating the%>And the gray value sum of the pixels in the weld joint area with the downward pixels.
6. The scanning-technology-based steel structure surface defect detection method according to claim 1, wherein the weld bead skeleton seam width height offset degreeThe calculation method comprises the following steps:
in the method, in the process of the application,indicating the%>Seam width and height offset of weld joint skeleton at each pixel point, < >>Indicating the%>Weld width offset at individual pixels, +.>Indicating the%>The gray level of the weld skeleton shadow at each pixel point,/->And the average value of the shade gray level of the weld joint skeleton of the pixel points on the weld joint skeleton is represented.
7. The method for detecting surface defects of steel structures based on the scanning technology according to claim 1, wherein the degree of fracture of the weld jointThe calculation method of (1) is as follows:
in the method, in the process of the application,indicating the%>Degree of weld joint fracture at individual pixel points, +.>Is thatGray run length matrix of>Represents gray levels in the 5x5 neighborhood, < >>Indicating>Is the maximum run length of +.>Indicating>The sum of all elements in the gray run length matrix above.
8. The method for detecting surface defects of steel structures based on the scanning technique according to claim 1, wherein the degree of abnormality at the pixel points of the weld skeleton isThe calculation method of (1) is as follows:
in the method, in the process of the application,indicating the%>Degree of abnormality at each pixel, +.>Indicating the%>Seam width and height offset of weld joint skeleton at each pixel point, < >>Indicating the%>The degree of weld joint fracture at each pixel point.
9. The method for detecting surface defects of steel structures based on the scanning technique as recited in claim 1, wherein the weld defect significance level indexThe calculation method of (1) is as follows:
in the method, in the process of the application,index of significance of the weld defect, +.>Indicating the%>Degree of abnormality at each pixel point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310770671.5A CN116503408B (en) | 2023-06-28 | 2023-06-28 | Scanning technology-based steel structure surface defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310770671.5A CN116503408B (en) | 2023-06-28 | 2023-06-28 | Scanning technology-based steel structure surface defect detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116503408A CN116503408A (en) | 2023-07-28 |
| CN116503408B true CN116503408B (en) | 2023-08-25 |
Family
ID=87320608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310770671.5A Active CN116503408B (en) | 2023-06-28 | 2023-06-28 | Scanning technology-based steel structure surface defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116503408B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001011545A1 (en) * | 1999-08-09 | 2001-02-15 | Cross Match Technologies, Inc. | Calibration and correction in a fingerprint scanner |
| CN102413283A (en) * | 2011-10-25 | 2012-04-11 | 广州飒特红外股份有限公司 | Infrared chart digital signal processing system and method |
| JP2012202858A (en) * | 2011-03-25 | 2012-10-22 | Railway Technical Research Institute | Closure crack detection method of concrete surface |
| WO2014139273A1 (en) * | 2013-03-14 | 2014-09-18 | 苏州华源包装股份有限公司 | Weld seam defect detection method |
| CN105488758A (en) * | 2015-11-30 | 2016-04-13 | 河北工业大学 | Image scaling method based on content awareness |
| CN105931227A (en) * | 2016-04-14 | 2016-09-07 | 北京工业大学 | Weld surface defect feature extraction method based on image gray scale B sweeping curve |
| CN112907595A (en) * | 2021-05-06 | 2021-06-04 | 武汉科技大学 | Surface defect detection method and device |
| WO2021168733A1 (en) * | 2020-02-27 | 2021-09-02 | 京东方科技集团股份有限公司 | Defect detection method and apparatus for defect image, and computer-readable storage medium |
| CN115170570A (en) * | 2022-09-07 | 2022-10-11 | 南通睿谷纺织科技有限公司 | Fabric fuzzing and pilling detection method based on gray level run-length matrix |
| WO2022225995A1 (en) * | 2021-04-19 | 2022-10-27 | F. Hoffmann-La Roche Ag | Methods and systems for gene alteration prediction from pathology slide images |
| CN115375676A (en) * | 2022-10-24 | 2022-11-22 | 微山三利特不锈钢有限公司 | Stainless steel product quality detection method based on image recognition |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3011935B1 (en) * | 2013-10-11 | 2017-06-23 | Luceo | METHOD AND DEVICE FOR INSPECTING PACKAGING WELDINGS |
| US9959617B2 (en) * | 2016-01-28 | 2018-05-01 | Taihao Medical Inc. | Medical image processing apparatus and breast image processing method thereof |
| US11684333B2 (en) * | 2020-01-03 | 2023-06-27 | National Taiwan University | Medical image analyzing system and method thereof |
| US20230092247A1 (en) * | 2021-09-22 | 2023-03-23 | Rockwell Automation Technologies, Inc. | Automated monitoring using image analysis |
-
2023
- 2023-06-28 CN CN202310770671.5A patent/CN116503408B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001011545A1 (en) * | 1999-08-09 | 2001-02-15 | Cross Match Technologies, Inc. | Calibration and correction in a fingerprint scanner |
| JP2012202858A (en) * | 2011-03-25 | 2012-10-22 | Railway Technical Research Institute | Closure crack detection method of concrete surface |
| CN102413283A (en) * | 2011-10-25 | 2012-04-11 | 广州飒特红外股份有限公司 | Infrared chart digital signal processing system and method |
| WO2014139273A1 (en) * | 2013-03-14 | 2014-09-18 | 苏州华源包装股份有限公司 | Weld seam defect detection method |
| CN105488758A (en) * | 2015-11-30 | 2016-04-13 | 河北工业大学 | Image scaling method based on content awareness |
| CN105931227A (en) * | 2016-04-14 | 2016-09-07 | 北京工业大学 | Weld surface defect feature extraction method based on image gray scale B sweeping curve |
| WO2021168733A1 (en) * | 2020-02-27 | 2021-09-02 | 京东方科技集团股份有限公司 | Defect detection method and apparatus for defect image, and computer-readable storage medium |
| WO2022225995A1 (en) * | 2021-04-19 | 2022-10-27 | F. Hoffmann-La Roche Ag | Methods and systems for gene alteration prediction from pathology slide images |
| CN112907595A (en) * | 2021-05-06 | 2021-06-04 | 武汉科技大学 | Surface defect detection method and device |
| CN115170570A (en) * | 2022-09-07 | 2022-10-11 | 南通睿谷纺织科技有限公司 | Fabric fuzzing and pilling detection method based on gray level run-length matrix |
| CN115375676A (en) * | 2022-10-24 | 2022-11-22 | 微山三利特不锈钢有限公司 | Stainless steel product quality detection method based on image recognition |
Non-Patent Citations (1)
| Title |
|---|
| 基于机器视觉的电机换向器质量在线检测系统开发;罗立浩;郑日荣;何小敏;许亮;;计算机测量与控制(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116503408A (en) | 2023-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102175700B (en) | Method for detecting welding seam segmentation and defects of digital X-ray images | |
| CN111667462B (en) | Automatic detection method and system for small and weak targets in welding defects | |
| CN115797358B (en) | Metal shell automatic welding defect detection method based on machine vision | |
| CN114240944B (en) | Welding defect detection method based on point cloud information | |
| JP2012002531A (en) | Crack detection method | |
| CN111724369A (en) | U-shaped welding seam detection method | |
| CN112053376A (en) | Workpiece weld joint identification method based on depth information | |
| JP2015520359A (en) | Method for evaluating the centerline of an object of arbitrary shape | |
| CN117095004B (en) | Excavator walking frame main body welding deformation detection method based on computer vision | |
| US20160321797A1 (en) | Imaging-based methods for detecting and measuring defects in extruded cellular ceramic articles | |
| JP4870016B2 (en) | Crack detection method | |
| CN115719332A (en) | Welding quality detection method | |
| US20150254830A1 (en) | Shape Inspecting Device And Shape Inspecting Method | |
| CN116468687A (en) | Scratch defect detection method and device, storage medium and electronic equipment | |
| JP4230880B2 (en) | Defect inspection method | |
| JP4893788B2 (en) | Tube extraction inspection method and apparatus for heat exchanger | |
| CN117058411B (en) | Method, device, medium and equipment for identifying edge appearance flaws of battery | |
| CN116503408B (en) | Scanning technology-based steel structure surface defect detection method | |
| CN115830021B (en) | Metal surface defect detection method for hardware machining | |
| JP2006155579A (en) | Image processing method and image processing apparatus | |
| JP4697328B2 (en) | Inspection method for heat exchanger core | |
| JP5378974B2 (en) | Tire inspection method and inspection apparatus | |
| CN116309416A (en) | Visual inspection method for surface of part | |
| CN114638822B (en) | Method and system for detecting surface quality of automobile cover plate by using optical means | |
| US11880969B2 (en) | Belt examination system and computer-readable non-transitory recording medium having stored belt examination program |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Surface defect detection method for steel structures based on scanning technology Effective date of registration: 20231225 Granted publication date: 20230825 Pledgee: Qufu sub branch of Postal Savings Bank of China Ltd. Pledgor: Qufu Yuanda Group Engineering Co.,Ltd. Registration number: Y2023980073867 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |