CN112085700A - Automatic extraction method, system and medium for weld joint region in X-ray image - Google Patents
Automatic extraction method, system and medium for weld joint region in X-ray image Download PDFInfo
- Publication number
- CN112085700A CN112085700A CN202010761412.2A CN202010761412A CN112085700A CN 112085700 A CN112085700 A CN 112085700A CN 202010761412 A CN202010761412 A CN 202010761412A CN 112085700 A CN112085700 A CN 112085700A
- Authority
- CN
- China
- Prior art keywords
- image
- ray
- welding seam
- value
- max
- 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.)
- Pending
Links
- 238000000605 extraction Methods 0.000 title claims abstract description 22
- 238000003466 welding Methods 0.000 claims abstract description 129
- 238000000034 method Methods 0.000 claims abstract description 64
- 238000012545 processing Methods 0.000 claims abstract description 42
- 230000002146 bilateral effect Effects 0.000 claims abstract description 20
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 230000000877 morphologic effect Effects 0.000 claims description 35
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 14
- 238000003708 edge detection Methods 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000002238 attenuated effect Effects 0.000 claims description 7
- 230000005587 bubbling Effects 0.000 claims description 7
- 238000003672 processing method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 241001481710 Cerambycidae Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T7/136—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
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
-
- 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
Abstract
The invention provides an automatic extraction method, a system and a medium for a weld joint area in an X-ray image, which comprises the following steps: acquiring an X-ray original image; carrying out bilateral filtering denoising processing on the X-ray original image; detecting the edge in the horizontal direction of the denoised image by using a discrete first-order differential operator convolution method; performing opening operation processing on the edge image; and determining the position area of the welding seam according to the maximum value of the algebraic sum of the pixel values in the adjacent fixed line numbers by utilizing the size of the pixel value in the image after the on operation. The method for extracting the X-ray weld joint area disclosed by the invention has high extraction accuracy, can be applied to images with more noise, low contrast and fuzzy weld joint area edges, and is widely applied.
Description
Technical Field
The invention relates to the technical field of weld tracking, in particular to an automatic extraction method, system and medium of a weld area in an X-ray image.
Background
After the workpiece is welded, defects such as cracks, pores and incomplete penetration exist in the welding seam, and visible light cannot penetrate through the inside of an object, so that the defect detection by using an X-ray imaging method becomes an important detection means. With the development of image processing technology, the application of the X-ray imaging detection technology of objects in nondestructive detection is more and more extensive. In the X-ray image of the workpiece, the welding seam only occupies a small part of the whole image, and other areas are information-irrelevant areas. Therefore, the automatic extraction of the welding seam area is the basis of the detection and identification of the welding seam defects, and the correctness of the detection and identification of the defects is seriously influenced. However, due to the influence of objective factors such as an imaging mode of an X-ray, a welding material, a welding method and the like, the image has the problems of high noise, low contrast, fuzzy edges of a welding seam region and the like, so that the extraction of the welding seam region in the image is difficult to a certain extent, the accuracy of the extraction of the welding seam region is low, and the requirement of industrial large-scale image processing cannot be met if a method for manually marking the position of the welding seam is adopted.
The automatic extraction of the weld seam region in the X-ray image is essentially a problem of extracting a characteristic region in the image under the condition of reducing manual operation, and currently, some methods are applied to the extraction of the weld seam region, and the following methods are commonly used today:
the least square method is used for fitting the edge of a welding seam, and calculating a scale product to extract the welding seam, but the method needs to manually intercept a normal image and a defect image template during image preprocessing, is suitable for single or small-batch images, is difficult to meet the industrial large-batch requirements, and has large calculation amount during template matching, so that the automation degree and the application of the method are limited.
The optimal threshold value of the binarization processing of the radiation image is searched by utilizing a longicorn whisker optimization algorithm and a clustering idea, and the welding seam edge is extracted after binarization, but the method is suitable for the condition that the image contrast of the welding seam area is good, and when the gray value distribution of the welding seam area is close to that of the background area, the welding seam area and the background area cannot be accurately separated by utilizing a threshold value segmentation method.
The Canny operator is used for edge detection, edges are extracted by a multi-parameter threshold segmentation method based on genetic algorithm optimization, the edges are detected by searching pixel points with the maximum gradient in each row in an image, however, because the information of the edges of the welding seams in an X-ray image is fuzzy, the contrast of the welding seams is extremely low, and complete and clear boundary contour lines are difficult to form.
The fuzzy K-NN algorithm and the fuzzy C-means algorithm are used as pattern classifiers to identify each target as a welding line or a non-welding line, but the method relies on model information established by initial parameters, and the effect of welding line extraction is general when the welding line information in a test picture changes.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a method, a system and a medium for automatically extracting a weld joint region in an X-ray image.
The invention provides an automatic extraction method of a weld joint region in an X-ray image, which comprises the following steps:
step S1: acquiring an X-ray original image of a welding seam;
step S2: denoising the obtained X-ray original image to obtain a denoised image;
step S3: carrying out horizontal direction edge detection on the denoised image;
step S4: carrying out morphological processing on the edge image to remove interference information;
step S5: and acquiring the pixel value of each point in the image after morphological processing, and determining the position area of the welding line according to the maximum value of the algebraic sum of the pixel values in the adjacent fixed line number.
Preferably, the step S1:
after X-rays emitted from the X-ray source penetrate through a workpiece, attenuated ray photons are received by the digital detector, are converted into digital signals through a series of conversions, and the digital signals are amplified and subjected to A/D conversion and are output on a display in the form of digital images through computer processing, wherein the digital images are original X-ray images of welding seams.
And if the average pixel value of the weld heat affected zone is lower than the average pixel value of the background zone, performing negation operation on the X-ray original image, so that the average pixel value of the weld heat affected zone is higher than the average pixel value of the background zone.
Preferably, the step S2:
the denoising processing method is bilateral filtering, and the airspace information and the value domain information of the pixel points are considered simultaneously when the noise is removed, namely the weight coefficients of the filter are determined by the space geometric distance and the pixel difference value together.
Preferably, the domain kernel calculation formula of the filter is as follows:
wherein i and j are the number of rows and columns of the current convolved pixel, k and l are the number of rows and columns of the neighborhood pixel, and σdIs the standard deviation of the gaussian function;
the value domain kernel calculation formula of the filter is as follows:
wherein v isi,jIs the ith line of the original image,Pixel value of j-th column, vk,lIs the pixel value, σ, of the k-th row and l-th column of the original imagerIs the standard deviation of the bilateral filter.
The defined domain kernel is multiplied by the value domain kernel to obtain a filter weighting coefficient w as follows:
preferably, in the step S3, a discrete first order differential operator is used to perform convolution method to detect the horizontal direction edge of the object in the image;
the convolution operator is:
the pixel values of the image in the ith row and the jth column after convolution are calculated as follows:
v′i,j=vi-1,j+1+2vi,j+1+vi+1,j+1-vi-1,j-1-vi,j-1-vi+1,j-1
preferably, the morphological operation used in step S4 is an on operation, and the on operation structural element is a rectangle.
Preferably, the step S5 specifically includes: acquiring the pixel value of each point in the image after morphological processing, and counting the algebraic sum of the pixel values of all points in each row; adding the pixel values in the adjacent fixed line numbers to obtain a series of algebraic sums; and obtaining the maximum value of the series of algebraic sums by using a bubbling sorting method, wherein the image line number corresponding to the maximum value is the position of the upper edge of the welding seam, and thus, the welding seam position area is determined.
Preferably, the step S5 includes:
step S501: acquiring the pixel value of each point in the image after the morphological open operation, and counting the algebraic sum of the pixel values of all points in each row, wherein the numerical sum of all pixels in the ith row is as follows:
wherein m and n are respectively the number of rows and columns of the whole image;
for the convenience of observation, the pixels in the image obtained in step S4 are projected in the horizontal direction, and the added value of each line of pixels in the image is displayed;
step S502: calculating the numerical sum of all pixels from the ith row to the i + t rowiAnd then:
wherein the value of i is an integer, i is more than 0 and less than m-t, and t is the number of rows in the image occupied by the welding seam generally;
step S503: sum is obtained according to the bubble sorting method1,sum2,……,summ-tMedian maximum summaxAssume that at the i-thmaxTaking the maximum sum in line timemaxThe position of the welding seam in the image is set as the ithmaxGo to imax+ t rows.
In order to avoid the loss of welding seam edge data caused in the image processing process, the size h of a unilateral error interval can be set manually, and the ith position of the welding seam in the image is finally determinedmaxH to imax+ t + h rows, and the position of the welding seam can be marked in the X-ray original image;
step S504: because the contrast of the welding seam and the background in the X-ray original image is not obviously distinguished, the contrast condition of the welding seam area is improved by adopting a histogram normalization method, and the pixel value o of a certain point of the welding seam area in the image is outputi,jThe following were used:
wherein the gray scale range of the welding seam area in the original image is [ v ]min,vmax]The gray level range of the weld region in the output image is set to [ o ]min,omax],vi,jIs the pixel value of the ith row and the jth column of the X-ray original image.
The invention provides an automatic extraction system of a weld joint region in an X-ray image, which comprises the following modules:
module S1: acquiring an X-ray original image of a welding seam;
module S2: denoising the obtained X-ray original image to obtain a denoised image;
module S3: carrying out horizontal direction edge detection on the denoised image;
module S4: carrying out morphological processing on the edge image to remove interference information;
module S5: acquiring a pixel value of each point in the image after morphological processing, and determining a welding seam position area according to the maximum value of the algebraic sum of the pixel values in the adjacent fixed line number;
the module S1:
after X-rays emitted from the X-ray source penetrate through a workpiece, attenuated ray photons are received by the digital detector, are converted into digital signals through a series of conversions, and the digital signals are amplified and subjected to A/D conversion and are output on a display in the form of digital images through computer processing, wherein the digital images are original X-ray images of welding seams.
If the average pixel value of the weld heat affected zone is lower than the average pixel value of the background zone, performing negation operation on the X-ray original image to enable the average pixel value of the weld heat affected zone to be higher than the average pixel value of the background zone;
the module S2:
the denoising processing method is bilateral filtering, and the airspace information and the value range information of the pixel points are considered simultaneously when the noise is removed, namely the weight coefficients of the filter are determined by the space geometric distance and the pixel difference value;
the definition domain kernel calculation formula of the filter is as follows:
wherein i and j are the number of rows and columns of the current convolved pixel, k and l are the number of rows and columns of the neighborhood pixel, and σdIs the standard deviation of the gaussian function;
the value domain kernel calculation formula of the filter is as follows:
wherein v isi,jIs the pixel value of the ith row and the jth column of the original image, vk,lIs the pixel value, σ, of the k-th row and l-th column of the original imagerIs the standard deviation of the bilateral filter.
The defined domain kernel is multiplied by the value domain kernel to obtain a filter weighting coefficient w as follows:
in the module S3, a convolution method is performed by using a discrete first-order differential operator to detect a horizontal edge of an object in an image;
the convolution operator is:
the pixel values of the image in the ith row and the jth column after convolution are calculated as follows:
v′i,j=vi-1,j+1+2vi,j+1+vi+1,j+1-vi-1,j-1-vi,j-1-vi+1,j-1
the morphological operation used in the block S4 is an on operation, and the on operation structural element is a rectangle.
The module S5 specifically includes: acquiring the pixel value of each point in the image after morphological processing, and counting the algebraic sum of the pixel values of all points in each row; adding the pixel values in the adjacent fixed line numbers to obtain a series of algebraic sums; obtaining the maximum value of the series of algebraic sums by using a bubbling sorting method, wherein the number of image lines corresponding to the maximum value is the position of the upper edge of the welding seam, and thus, determining the position area of the welding seam;
the module S5 includes:
a module S501: acquiring the pixel value of each point in the image after the morphological open operation, and counting the algebraic sum of the pixel values of all points in each row, wherein the numerical sum of all pixels in the ith row is as follows:
wherein m and n are respectively the number of rows and columns of the whole image;
for the convenience of observation, the pixels in the image obtained by the module S4 are projected in the horizontal direction, and the added value of each line of pixels in the image can be displayed;
a module S502: calculating the numerical sum of all pixels from the ith row to the i + t rowiAnd then:
wherein the value of i is an integer, i is more than 0 and less than m-t, and t is the number of rows in the image occupied by the welding seam generally;
a block S503: sum is obtained according to the bubble sorting method1,sum2,……,summ-tMedian maximum summaxAssume that at the i-thmaxTaking the maximum sum in line timemaxThe position of the welding seam in the image is set as the ithmaxGo to imax+ t rows.
In order to avoid the loss of welding seam edge data caused in the image processing process, the size h of a unilateral error interval can be set manually, and the ith position of the welding seam in the image is finally determinedmaxH to imax+ t + h rows, and the position of the welding seam can be marked in the X-ray original image;
a module S504: because the contrast distinction between the welding seam and the background in the X-ray original image is not obvious, the histogram normalization method is adopted to improve the contrast condition of the welding seam areaThen outputting the pixel value o of a certain point of the welding seam area in the imagei,jThe following were used:
wherein the gray scale range of the welding seam area in the original image is [ v ]min,vmax]The gray level range of the weld region in the output image is set to [ o ]min,omax],vi,jIs the pixel value of the ith row and the jth column of the X-ray original image.
According to the present invention, there is provided a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of any one of the above-mentioned methods for automatically extracting a weld region in an X-ray image.
Compared with the prior art, the invention has the following beneficial effects:
the method can obviously inhibit the interference of noise and improve the accuracy of automatically acquiring the welding seam region, so that the method can be applied to X-ray images with more noise, low contrast, fuzzy welding seam region edges and more similar gray value distribution of the welding seam region and a background region, and can obtain better accuracy and robustness.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a flow chart of an automated method for extracting a weld region in an X-ray image according to the present invention;
FIG. 2 is an X-ray raw image of a weld used in an embodiment of the present invention;
FIG. 3 is an image obtained after bilateral filtering denoising processing is performed on FIG. 2 according to an embodiment of the present invention;
FIG. 4 is an image obtained by convolution with the first order differential operator of FIG. 3 according to an embodiment of the present invention;
FIG. 5 is an image obtained by performing an open operation on the image of FIG. 4 according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating an image obtained by projecting the pixels in FIG. 5 in the horizontal direction according to an embodiment of the present invention;
FIG. 7 is an image of the weld locations indicated in FIG. 2 according to an embodiment of the present invention;
fig. 8 is an image obtained by histogram normalization of the weld region in fig. 7 according to an embodiment of the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
The invention provides an automatic extraction method of a weld joint region in an X-ray image, which comprises the following steps:
step S1: acquiring an X-ray original image of a welding seam;
step S2: denoising the obtained X-ray original image to obtain a denoised image;
step S3: carrying out horizontal direction edge detection on the denoised image;
step S4: carrying out morphological processing on the edge image to remove interference information;
step S5: and acquiring the pixel value of each point in the image after morphological processing, and determining the position area of the welding line according to the maximum value of the algebraic sum of the pixel values in the adjacent fixed line number.
Specifically, the step S1:
after X-rays emitted from the X-ray source penetrate through a workpiece, attenuated ray photons are received by the digital detector, are converted into digital signals through a series of conversions, and the digital signals are amplified and subjected to A/D conversion and are output on a display in the form of digital images through computer processing, wherein the digital images are original X-ray images of welding seams.
And if the average pixel value of the weld heat affected zone is lower than the average pixel value of the background zone, performing negation operation on the X-ray original image, so that the average pixel value of the weld heat affected zone is higher than the average pixel value of the background zone.
Specifically, the step S2:
the denoising processing method is bilateral filtering, and the airspace information and the value domain information of the pixel points are considered simultaneously when the noise is removed, namely the weight coefficients of the filter are determined by the space geometric distance and the pixel difference value together.
Specifically, the domain kernel calculation formula of the filter is as follows:
wherein i and j are the number of rows and columns of the current convolved pixel, k and l are the number of rows and columns of the neighborhood pixel, and σdIs the standard deviation of the gaussian function;
the value domain kernel calculation formula of the filter is as follows:
wherein v isi,jIs the pixel value of the ith row and the jth column of the original image, vk,lIs the pixel value, σ, of the k-th row and l-th column of the original imagerIs the standard deviation of the bilateral filter.
The defined domain kernel is multiplied by the value domain kernel to obtain a filter weighting coefficient w as follows:
specifically, in step S3, a discrete first order differential operator is used to perform convolution method to detect the horizontal direction edge of the object in the image;
the convolution operator is:
the pixel values of the image in the ith row and the jth column after convolution are calculated as follows:
v′i,j=vi-1,j+1+2vi,j+1+vi+1,j+1-vi-1,j-1-vi,j-1-vi+1,j-1
specifically, the morphological operation used in step S4 is an on operation, and the on operation structural element is a rectangle.
Specifically, the step S5 specifically includes: acquiring the pixel value of each point in the image after morphological processing, and counting the algebraic sum of the pixel values of all points in each row; adding the pixel values in the adjacent fixed line numbers to obtain a series of algebraic sums; and obtaining the maximum value of the series of algebraic sums by using a bubbling sorting method, wherein the image line number corresponding to the maximum value is the position of the upper edge of the welding seam, and thus, the welding seam position area is determined.
Specifically, the step S5 includes:
step S501: acquiring the pixel value of each point in the image after the morphological open operation, and counting the algebraic sum of the pixel values of all points in each row, wherein the numerical sum of all pixels in the ith row is as follows:
wherein m and n are respectively the number of rows and columns of the whole image;
for the convenience of observation, the pixels in the image obtained in step S4 are projected in the horizontal direction, and the added value of each line of pixels in the image is displayed;
step S502: calculating the numerical sum of all pixels from the ith row to the i + t rowiAnd then:
wherein the value of i is an integer, i is more than 0 and less than m-t, and t is the number of rows in the image occupied by the welding seam generally;
step S503: sum is obtained according to the bubble sorting method1,sum2,……,summ-tMedian maximum summaxAssume that at the i-thmaxTaking the maximum sum in line timemaxThe position of the welding seam in the image is set as the ithmaxGo to imax+ t rows.
In order to avoid the loss of welding seam edge data caused in the image processing process, the size h of a unilateral error interval can be set manually, and the ith position of the welding seam in the image is finally determinedmaxH to imax+ t + h rows, and the position of the welding seam can be marked in the X-ray original image;
step S504: because the contrast of the welding seam and the background in the X-ray original image is not obviously distinguished, the contrast condition of the welding seam area is improved by adopting a histogram normalization method, and the pixel value o of a certain point of the welding seam area in the image is outputi,jThe following were used:
wherein the gray scale range of the welding seam area in the original image is [ v ]min,vmax]The gray level range of the weld region in the output image is set to [ o ]min,omax],vi,jIs the pixel value of the ith row and the jth column of the X-ray original image.
The invention provides an automatic extraction system of a weld joint region in an X-ray image, which comprises the following modules:
module S1: acquiring an X-ray original image of a welding seam;
module S2: denoising the obtained X-ray original image to obtain a denoised image;
module S3: carrying out horizontal direction edge detection on the denoised image;
module S4: carrying out morphological processing on the edge image to remove interference information;
module S5: acquiring a pixel value of each point in the image after morphological processing, and determining a welding seam position area according to the maximum value of the algebraic sum of the pixel values in the adjacent fixed line number;
the module S1:
after X-rays emitted from the X-ray source penetrate through a workpiece, attenuated ray photons are received by the digital detector, are converted into digital signals through a series of conversions, and the digital signals are amplified and subjected to A/D conversion and are output on a display in the form of digital images through computer processing, wherein the digital images are original X-ray images of welding seams.
If the average pixel value of the weld heat affected zone is lower than the average pixel value of the background zone, performing negation operation on the X-ray original image to enable the average pixel value of the weld heat affected zone to be higher than the average pixel value of the background zone;
the module S2:
the denoising processing method is bilateral filtering, and the airspace information and the value range information of the pixel points are considered simultaneously when the noise is removed, namely the weight coefficients of the filter are determined by the space geometric distance and the pixel difference value;
the definition domain kernel calculation formula of the filter is as follows:
wherein i and j are the number of rows and columns of the current convolved pixel, k and l are the number of rows and columns of the neighborhood pixel, and σdIs the standard deviation of the gaussian function;
the value domain kernel calculation formula of the filter is as follows:
wherein v isi,jIs the pixel value of the ith row and the jth column of the original image, vk,lIs the pixel value, σ, of the k-th row and l-th column of the original imagerIs the standard deviation of the bilateral filter.
The defined domain kernel is multiplied by the value domain kernel to obtain a filter weighting coefficient w as follows:
in the module S3, a convolution method is performed by using a discrete first-order differential operator to detect a horizontal edge of an object in an image;
the convolution operator is:
the pixel values of the image in the ith row and the jth column after convolution are calculated as follows:
v′i,j=vi-1,j+1+2vi,j+1+vi+1,j+1-vi-1,j-1-vi,j-1-vi+1,j-1
the morphological operation used in the block S4 is an on operation, and the on operation structural element is a rectangle.
The module S5 specifically includes: acquiring the pixel value of each point in the image after morphological processing, and counting the algebraic sum of the pixel values of all points in each row; adding the pixel values in the adjacent fixed line numbers to obtain a series of algebraic sums; obtaining the maximum value of the series of algebraic sums by using a bubbling sorting method, wherein the number of image lines corresponding to the maximum value is the position of the upper edge of the welding seam, and thus, determining the position area of the welding seam;
the module S5 includes:
a module S501: acquiring the pixel value of each point in the image after the morphological open operation, and counting the algebraic sum of the pixel values of all points in each row, wherein the numerical sum of all pixels in the ith row is as follows:
wherein m and n are respectively the number of rows and columns of the whole image;
for the convenience of observation, the pixels in the image obtained by the module S4 are projected in the horizontal direction, and the added value of each line of pixels in the image can be displayed;
a module S502: calculating the numerical sum of all pixels from the ith row to the i + t rowiAnd then:
wherein the value of i is an integer, i is more than 0 and less than m-t, and t is the number of rows in the image occupied by the welding seam generally;
a block S503: sum is obtained according to the bubble sorting method1,sum2,……,summ-tMedian maximum summaxAssume that at the i-thmaxTaking the maximum sum in line timemaxThe position of the welding seam in the image is set as the ithmaxGo to imax+ t rows.
In order to avoid the loss of welding seam edge data caused in the image processing process, the size h of a unilateral error interval can be set manually, and the ith position of the welding seam in the image is finally determinedmaxH to imax+ t + h rows, and the position of the welding seam can be marked in the X-ray original image;
a module S504: because the contrast of the welding seam and the background in the X-ray original image is not obviously distinguished, the contrast condition of the welding seam area is improved by adopting a histogram normalization method, and the pixel value o of a certain point of the welding seam area in the image is outputi,jThe following were used:
wherein the gray scale range of the welding seam area in the original image is [ v ]min,vmax]The gray level range of the weld region in the output image is set to [ o ]min,omax],vi,jIs the pixel value of the ith row and the jth column of the X-ray original image.
According to the present invention, there is provided a computer-readable storage medium storing a computer program, wherein the computer program is executed by a processor to implement the steps of any one of the above-mentioned methods for automatically extracting a weld region in an X-ray image.
The present invention will be described more specifically below with reference to preferred examples.
Preferred example 1:
the invention aims to provide an automatic extraction method of a weld joint region in an X-ray image, and solves the technical problem of how to improve the automatic extraction accuracy of the weld joint region.
In order to achieve the above purpose, the invention provides the following technical scheme:
an automatic extraction method of a weld joint region in an X-ray image comprises the following steps:
s1, acquiring an X-ray original image of a welding seam;
s2, denoising the X-ray original image;
s3, carrying out horizontal direction edge detection on the denoised image;
s4, performing morphological processing on the edge image to remove interference information;
and S5, acquiring the pixel value of each point in the morphologically processed image, and determining the position area of the welding line according to the maximum value of the algebraic sum of the pixel values in the adjacent fixed line numbers.
Preferably, in step S1, if the average value of the pixels in the weld heat affected zone is lower than the average value of the pixels in the background area, performing an inversion operation on the X-ray original image so that the average value of the pixels in the weld heat affected zone is higher than the average value of the pixels in the background area;
preferably, the denoising method used in step S2 is bilateral filtering, that is, the size of each weight coefficient of the filter is determined by the spatial geometric distance and the pixel difference;
preferably, in step S3, the method for detecting the horizontal edge of the object in the image is to use a discrete first-order differential operator to perform convolution to obtain an image containing edge information in the horizontal direction in the original image;
preferably, the morphological operation used in step S4 is an on operation, and the on operation structural element is a rectangle, the horizontal dimension of the rectangle is 1/64 of the horizontal dimension of the image resolution, and the vertical dimension of the rectangle is 1 pixel;
preferably, the step S5 specifically includes: acquiring the pixel value of each point in the image after morphological open operation, and counting the algebraic sum of the pixel values of all points in each row; adding the pixel values in the adjacent fixed line numbers to obtain a series of algebraic sums; obtaining the maximum value of the series of algebraic sums by using a bubbling sorting method, wherein the number of image lines corresponding to the maximum value is the position of the upper edge of the welding seam, and thus, determining the position area of the welding seam; after the welding seam position area is obtained, if the contrast in the welding seam position area is not obvious, histogram normalization transformation is carried out on pixel values of the welding seam position area, and the distribution range of the gray values of the welding seam area is enlarged so as to improve the contrast.
Preferred example 2:
the principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, an embodiment of the present invention provides an automatic extraction method of a weld region in an X-ray image, which may include the following steps:
step S1: acquiring an X-ray original image of a welding seam;
in practical application, after X-rays emitted from the X-ray source pass through a workpiece, attenuated ray photons are received by the digital detector, and are converted into digital signals through a series of conversions, and the digital signals are amplified and subjected to A/D conversion, processed by a computer, and output on a display in the form of digital images, namely X-ray original images of welding seams, as shown in FIG. 2. And if the average pixel value of the weld heat affected zone is lower than the average pixel value of the background zone, performing negation operation on the X-ray original image, so that the average pixel value of the weld heat affected zone is higher than the average pixel value of the background zone, and the weld heat affected zone is displayed more brightly and better accords with the observation characteristics of human eyes.
Step S2: carrying out bilateral filtering denoising processing on the X-ray original image;
the noise generated in the process of generating, transmitting and recording the image signal can interfere the visual effect of the image and the subsequent data processing, so that the noise is removed by using a bilateral filtering method, and the noise of the target image is suppressed under the condition of keeping the detail characteristics of the image as much as possible. And (3) simultaneously considering the spatial information and the value domain information of the pixel points during bilateral filtering, namely the magnitude w of each weight coefficient of the filter is determined by the definition domain kernel and the value domain kernel together and is the product of the definition domain kernel and the value domain kernel.
The domain kernel calculation formula of the filter is as follows:
wherein i and j are the number of rows and columns of the current convolved pixel, k and l are the number of rows and columns of the neighborhood pixel, and σdIs the standard deviation of the gaussian function.
The value domain kernel calculation formula of the filter is as follows:
wherein v isi,jIs the pixel value of the ith row and the jth column of the original image, vk,lIs the pixel value, σ, of the k-th row and l-th column of the original imagerIs the standard deviation of the bilateral filter.
The defined domain kernel is multiplied by the value domain kernel to obtain a filter weighting coefficient w as follows:
the image denoised using the bilateral filter is shown in fig. 3.
Step S3: carrying out horizontal direction edge detection on the denoised image;
performing edge detection on the image by using a convolution method of a first-order discrete differential operator to obtain edge information of the image in the horizontal direction, wherein the convolution operator is as follows:
the pixel values of the image in the ith row and the jth column after convolution are calculated as follows:
v′i,j=vi-1,j+1+2vi,j+1+vi+1,j+1-vi-1,j-1-vi,j-1-vi+1,j-1
the image obtained by the convolution is shown in fig. 4.
Step S4: performing morphological opening operation processing on the image obtained in the step S3;
the opening operation is to perform the processes of firstly corroding and then expanding the image, the corrosion and expansion processes adopt the same structural elements, wherein the structural elements are selected from rectangles, the horizontal dimension of the rectangle is 1/64 of the horizontal dimension of the image resolution, the vertical dimension of the rectangle is 1 pixel, and the image obtained after the opening operation processing is shown in fig. 5.
Step S5: determining the position of a welding seam according to the pixel value of the image after the opening operation, and the specific steps are as follows:
A) acquiring the pixel value of each point in the image after the morphological open operation, and counting the algebraic sum of the pixel values of all points in each row, wherein the numerical sum of all pixels in the ith row is as follows:
where m and n are the number of rows and columns of the whole image, vi,jThe pixel values of the image after the on operation are in the ith row and the jth column.
For the convenience of observation, the pixels in the image obtained in step S4 are projected in the horizontal direction, and the magnitude of the added value of each line of pixels in the obtained image is displayed, as shown in fig. 6.
B) Calculating the numerical sum of all pixels from the ith row to the i + t rowiAnd then:
wherein the value of i is an integer, i is more than 0 and less than m-t, and t is the number of rows in the image occupied by the welding seam.
C) Sum is obtained according to the bubble sorting method1,sum2,……,summ-tMedian maximum summaxAssume that at the i-thmaxTaking the maximum sum in line timemaxThe position of the welding seam in the image is set as the ithmaxGo to imax+ t rows.
In order to avoid the loss of welding seam edge data caused in the image processing process, the size h of a unilateral error interval can be set manually, and the ith position of the welding seam in the image is finally determinedmaxH to imax+ t + h, the weld position may be marked in the X-ray raw image, as shown in fig. 7.
D) Because the contrast of the welding seam and the background in the X-ray original image is not obviously distinguished, the contrast condition of the welding seam area is improved by adopting a histogram normalization method, and the pixel value o of a certain point of the welding seam area in the image is outputi,jThe following were used:
wherein the gray scale range of the welding seam area in the original image is [ v ]min,vmax]The gray level range of the weld region in the output image is set to [ o ]min,omax],vi,jFig. 8 shows an image obtained by histogram normalization of pixel values in the ith row and the jth column of an X-ray original image.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
In the description of the present application, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the present application and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present application.
Those skilled in the art will appreciate that, in addition to implementing the systems, apparatus, and various modules thereof provided by the present invention in purely computer readable program code, the same procedures can be implemented entirely by logically programming method steps such that the systems, apparatus, and various modules thereof are provided in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. An automatic extraction method of a weld joint region in an X-ray image is characterized by comprising the following steps:
step S1: acquiring an X-ray original image of a welding seam;
step S2: denoising the obtained X-ray original image to obtain a denoised image;
step S3: carrying out horizontal direction edge detection on the denoised image;
step S4: carrying out morphological processing on the edge image to remove interference information;
step S5: and acquiring the pixel value of each point in the image after morphological processing, and determining the position area of the welding line according to the maximum value of the algebraic sum of the pixel values in the adjacent fixed line number.
2. The method for automatically extracting a weld region in an X-ray image according to claim 1, wherein the step S1:
after X-rays emitted from the X-ray source penetrate through a workpiece, attenuated ray photons are received by the digital detector, are converted into digital signals through a series of conversions, and the digital signals are amplified and subjected to A/D conversion and are output on a display in the form of digital images through computer processing, wherein the digital images are original X-ray images of welding seams.
And if the average pixel value of the weld heat affected zone is lower than the average pixel value of the background zone, performing negation operation on the X-ray original image, so that the average pixel value of the weld heat affected zone is higher than the average pixel value of the background zone.
3. The method for automatically extracting a weld region in an X-ray image according to claim 1, wherein the step S2:
the denoising processing method is bilateral filtering, and the airspace information and the value domain information of the pixel points are considered simultaneously when the noise is removed, namely the weight coefficients of the filter are determined by the space geometric distance and the pixel difference value together.
4. The method for automatically extracting the weld joint area in the X-ray image as claimed in claim 3, wherein the definition domain kernel calculation formula of the filter is as follows:
wherein i and j are the number of rows and columns of the current convolved pixel, k and l are the number of rows and columns of the neighborhood pixel, and σdIs the standard deviation of the gaussian function;
the value domain kernel calculation formula of the filter is as follows:
wherein v isi,jIs the pixel value of the ith row and the jth column of the original image, vk,lIs the pixel value, σ, of the k-th row and l-th column of the original imagerIs the standard deviation of the bilateral filter.
The defined domain kernel is multiplied by the value domain kernel to obtain a filter weighting coefficient w as follows:
5. the method for automatically extracting the weld joint region in the X-ray image as claimed in claim 1, wherein in step S3, the horizontal direction edge of the object in the image is detected by using a discrete first order differential operator to perform convolution method;
the convolution operator is:
the pixel values of the image in the ith row and the jth column after convolution are calculated as follows:
v′i,j=vi-1,j+1+2vi,j+1+vi+1,j+1-vi-1,j-1-vi,j-1-vi+1,j-1
6. the method according to claim 1, wherein the morphological operation used in step S4 is an open operation, and the structural element of the open operation is a rectangle.
7. The method for automatically extracting the weld joint region in the X-ray image according to claim 1, wherein the step S5 specifically includes: acquiring the pixel value of each point in the image after morphological processing, and counting the algebraic sum of the pixel values of all points in each row; adding the pixel values in the adjacent fixed line numbers to obtain a series of algebraic sums; and obtaining the maximum value of the series of algebraic sums by using a bubbling sorting method, wherein the image line number corresponding to the maximum value is the position of the upper edge of the welding seam, and thus, the welding seam position area is determined.
8. The method for automatically extracting the weld zone in the X-ray image according to claim 7, wherein the step S5 includes:
step S501: acquiring the pixel value of each point in the image after the morphological open operation, and counting the algebraic sum of the pixel values of all points in each row, wherein the numerical sum of all pixels in the ith row is as follows:
wherein m and n are respectively the number of rows and columns of the whole image;
for the convenience of observation, the pixels in the image obtained in step S4 are projected in the horizontal direction, and the added value of each line of pixels in the image is displayed;
step S502: calculating the numerical sum of all pixels from the ith row to the i + t rowiAnd then:
wherein the value of i is an integer, i is more than 0 and less than m-t, and t is the number of rows in the image occupied by the welding seam generally;
step S503: sum is obtained according to the bubble sorting method1,sum2,……,summ-tMedian maximum summaxAssume that at the i-thmaxTaking the maximum sum in line timemaxThe position of the welding seam in the image is set as the ithmaxGo to imax+ t rows.
In order to avoid the loss of welding seam edge data caused in the image processing process, the size h of a unilateral error interval can be set manually, and the ith position of the welding seam in the image is finally determinedmaxH to imax+ t + h rows, and the position of the welding seam can be marked in the X-ray original image;
step S504: because the contrast of the welding seam and the background in the X-ray original image is not obviously distinguished, the contrast condition of the welding seam area is improved by adopting a histogram normalization method, and the pixel value o of a certain point of the welding seam area in the image is outputi,jThe following were used:
wherein the gray scale range of the welding seam area in the original image is [ v ]min,vmax]The gray level range of the weld region in the output image is set to [ o ]min,omax],vi,jIs the pixel value of the ith row and the jth column of the X-ray original image.
9. An automatic extraction system of a weld joint area in an X-ray image is characterized by comprising the following modules:
module S1: acquiring an X-ray original image of a welding seam;
module S2: denoising the obtained X-ray original image to obtain a denoised image;
module S3: carrying out horizontal direction edge detection on the denoised image;
module S4: carrying out morphological processing on the edge image to remove interference information;
module S5: acquiring a pixel value of each point in the image after morphological processing, and determining a welding seam position area according to the maximum value of the algebraic sum of the pixel values in the adjacent fixed line number;
the module S1:
after X-rays emitted from the X-ray source penetrate through a workpiece, attenuated ray photons are received by the digital detector, are converted into digital signals through a series of conversions, and the digital signals are amplified and subjected to A/D conversion and are output on a display in the form of digital images through computer processing, wherein the digital images are original X-ray images of welding seams.
If the average pixel value of the weld heat affected zone is lower than the average pixel value of the background zone, performing negation operation on the X-ray original image to enable the average pixel value of the weld heat affected zone to be higher than the average pixel value of the background zone;
the module S2:
the denoising processing method is bilateral filtering, and the airspace information and the value range information of the pixel points are considered simultaneously when the noise is removed, namely the weight coefficients of the filter are determined by the space geometric distance and the pixel difference value;
the definition domain kernel calculation formula of the filter is as follows:
wherein i and j are the number of rows and columns of the current convolved pixel, k and l are the number of rows and columns of the neighborhood pixel, and σdIs the standard deviation of the gaussian function;
the value domain kernel calculation formula of the filter is as follows:
wherein v isi,jIs the pixel value of the ith row and the jth column of the original image, vk,lIs the pixel value, σ, of the k-th row and l-th column of the original imagerIs the standard deviation of the bilateral filter.
The defined domain kernel is multiplied by the value domain kernel to obtain a filter weighting coefficient w as follows:
in the module S3, a convolution method is performed by using a discrete first-order differential operator to detect a horizontal edge of an object in an image;
the convolution operator is:
the pixel values of the image in the ith row and the jth column after convolution are calculated as follows:
v′i,j=vi-1,j+1+2vi,j+1+vi+1,j+1-vi-1,j-1-vi,j-1-vi+1,j-1
the morphological operation used in the block S4 is an on operation, and the on operation structural element is a rectangle.
The module S5 specifically includes: acquiring the pixel value of each point in the image after morphological processing, and counting the algebraic sum of the pixel values of all points in each row; adding the pixel values in the adjacent fixed line numbers to obtain a series of algebraic sums; obtaining the maximum value of the series of algebraic sums by using a bubbling sorting method, wherein the number of image lines corresponding to the maximum value is the position of the upper edge of the welding seam, and thus, determining the position area of the welding seam;
the module S5 includes:
a module S501: acquiring the pixel value of each point in the image after the morphological open operation, and counting the algebraic sum of the pixel values of all points in each row, wherein the numerical sum of all pixels in the ith row is as follows:
wherein m and n are respectively the number of rows and columns of the whole image;
for the convenience of observation, the pixels in the image obtained by the module S4 are projected in the horizontal direction, and the added value of each line of pixels in the image can be displayed;
a module S502: calculating the numerical sum of all pixels from the ith row to the i + t rowiAnd then:
wherein the value of i is an integer, i is more than 0 and less than m-t, and t is the number of rows in the image occupied by the welding seam generally;
a block S503: sum is obtained according to the bubble sorting method1,sum2,……,summ-tMedian maximum summaxAssume that at the i-thmaxTaking the maximum sum in line timemaxThe position of the welding seam in the image is set as the ithmaxGo to imax+ t rows.
In order to avoid the loss of welding seam edge data caused in the image processing process, the size h of a unilateral error interval can be set manually, and the ith position of the welding seam in the image is finally determinedmaxH to imax+ t + h rows, and the position of the welding seam can be marked in the X-ray original image;
a module S504: because the contrast of the welding seam and the background in the X-ray original image is not obviously distinguished, the contrast condition of the welding seam area is improved by adopting a histogram normalization method, and the pixel value o of a certain point of the welding seam area in the image is outputi,jThe following were used:
wherein the gray scale range of the welding seam area in the original image is [ v ]min,vmax]The gray level range of the weld region in the output image is set to [ o ]min,omax],vi,jIs the pixel value of the ith row and the jth column of the X-ray original image.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for automated extraction of a weld region in an X-ray image according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010761412.2A CN112085700A (en) | 2020-07-31 | 2020-07-31 | Automatic extraction method, system and medium for weld joint region in X-ray image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010761412.2A CN112085700A (en) | 2020-07-31 | 2020-07-31 | Automatic extraction method, system and medium for weld joint region in X-ray image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112085700A true CN112085700A (en) | 2020-12-15 |
Family
ID=73735955
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010761412.2A Pending CN112085700A (en) | 2020-07-31 | 2020-07-31 | Automatic extraction method, system and medium for weld joint region in X-ray image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112085700A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113298738A (en) * | 2021-07-13 | 2021-08-24 | 上海航天精密机械研究所 | Automatic enhancement device and method for X-ray welding seam image |
CN113393378A (en) * | 2021-05-26 | 2021-09-14 | 浙江大华技术股份有限公司 | Image splicing method and device for photovoltaic module, electronic device and storage medium |
CN113421304A (en) * | 2021-06-21 | 2021-09-21 | 沈阳派得林科技有限责任公司 | Intelligent positioning method for industrial radiographic negative image weld bead area |
CN115511819A (en) * | 2022-09-21 | 2022-12-23 | 武汉理工大学 | X-ray weld boundary identification method, device, equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100615047B1 (en) * | 2005-03-11 | 2006-08-22 | 목포해양대학교 산학협력단 | Method for auto-detecting defect of welding position |
WO2009003702A1 (en) * | 2007-07-04 | 2009-01-08 | Thermosensorik Gmbh | Method for the automatic inspection of a welding seam using heat flow thermography |
CN108596930A (en) * | 2018-04-23 | 2018-09-28 | 西安交通大学 | It must algorithm and the morphologic ray image weld seam extracting method of mathematics based on longicorn |
CN110717872A (en) * | 2019-10-08 | 2020-01-21 | 江西洪都航空工业集团有限责任公司 | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning |
-
2020
- 2020-07-31 CN CN202010761412.2A patent/CN112085700A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100615047B1 (en) * | 2005-03-11 | 2006-08-22 | 목포해양대학교 산학협력단 | Method for auto-detecting defect of welding position |
WO2009003702A1 (en) * | 2007-07-04 | 2009-01-08 | Thermosensorik Gmbh | Method for the automatic inspection of a welding seam using heat flow thermography |
CN108596930A (en) * | 2018-04-23 | 2018-09-28 | 西安交通大学 | It must algorithm and the morphologic ray image weld seam extracting method of mathematics based on longicorn |
CN110717872A (en) * | 2019-10-08 | 2020-01-21 | 江西洪都航空工业集团有限责任公司 | Method and system for extracting characteristic points of V-shaped welding seam image under laser-assisted positioning |
Non-Patent Citations (2)
Title |
---|
朱亮;柳洪义;原培新;: "X射线焊缝底片数字化图像边缘检测方法", 中国工程机械学报, no. 03 * |
马云;王贺;张晓光;胡晓钦;张涛;: "基于形态学的焊接图像缺陷检测方法研究", 计算机测量与控制, no. 05 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113393378A (en) * | 2021-05-26 | 2021-09-14 | 浙江大华技术股份有限公司 | Image splicing method and device for photovoltaic module, electronic device and storage medium |
CN113421304A (en) * | 2021-06-21 | 2021-09-21 | 沈阳派得林科技有限责任公司 | Intelligent positioning method for industrial radiographic negative image weld bead area |
CN113298738A (en) * | 2021-07-13 | 2021-08-24 | 上海航天精密机械研究所 | Automatic enhancement device and method for X-ray welding seam image |
CN115511819A (en) * | 2022-09-21 | 2022-12-23 | 武汉理工大学 | X-ray weld boundary identification method, device, equipment and storage medium |
CN115511819B (en) * | 2022-09-21 | 2023-08-25 | 武汉理工大学 | X-ray weld boundary identification method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111292305B (en) | Improved YOLO-V3 metal processing surface defect detection method | |
CN112085700A (en) | Automatic extraction method, system and medium for weld joint region in X-ray image | |
CN107543828B (en) | Workpiece surface defect detection method and system | |
CN112598001B (en) | Automatic ship water gauge reading identification method based on multi-model fusion | |
US20090279772A1 (en) | Method and System for Identifying Defects in NDT Image Data | |
CN107230203A (en) | Casting defect recognition methods based on human eye vision attention mechanism | |
CN110415208A (en) | A kind of adaptive targets detection method and its device, equipment, storage medium | |
CN115908269B (en) | Visual defect detection method, visual defect detection device, storage medium and computer equipment | |
CN108537787B (en) | Quality judgment method for face image | |
CN109781737B (en) | Detection method and detection system for surface defects of hose | |
CN105718931B (en) | System and method for determining clutter in acquired images | |
CN115984284A (en) | X-ray hull weld image detection method for ship maintenance | |
CN116993744B (en) | Weld defect detection method based on threshold segmentation | |
CN103822932B (en) | Based on the X ray realtime graphic weld defect method for detecting of multi-scale filtering operator | |
CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
CN107644417A (en) | Foil gauge outward appearance defect detection method | |
CN113705564B (en) | Pointer type instrument identification reading method | |
CN113724322A (en) | Cargo pallet positioning method and system for unmanned forklift | |
CN110276759B (en) | Mobile phone screen bad line defect diagnosis method based on machine vision | |
CN115661110B (en) | Transparent workpiece identification and positioning method | |
JPS63236989A (en) | Foreign matter detector | |
CN115131355A (en) | Intelligent method for detecting abnormality of waterproof cloth by using data of electronic equipment | |
CN117456371B (en) | Group string hot spot detection method, device, equipment and medium | |
CN117495846B (en) | Image detection method, device, electronic equipment and storage medium | |
CN114037705B (en) | Metal fracture fatigue source detection method and system based on moire lines |
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 |