CN114708226A - Copper pipe inner wall crack detection method based on illumination influence - Google Patents
Copper pipe inner wall crack detection method based on illumination influence Download PDFInfo
- Publication number
- CN114708226A CN114708226A CN202210346872.8A CN202210346872A CN114708226A CN 114708226 A CN114708226 A CN 114708226A CN 202210346872 A CN202210346872 A CN 202210346872A CN 114708226 A CN114708226 A CN 114708226A
- Authority
- CN
- China
- Prior art keywords
- copper pipe
- brightness
- weft
- pixel point
- change function
- 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
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 title claims abstract description 116
- 229910052802 copper Inorganic materials 0.000 title claims abstract description 116
- 239000010949 copper Substances 0.000 title claims abstract description 116
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000005286 illumination Methods 0.000 title claims abstract description 24
- 230000008859 change Effects 0.000 claims abstract description 89
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000012937 correction Methods 0.000 claims description 38
- 230000000694 effects Effects 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 18
- 230000035772 mutation Effects 0.000 claims description 8
- 150000001879 copper Chemical class 0.000 claims description 3
- 230000008569 process Effects 0.000 description 8
- 229910000831 Steel Inorganic materials 0.000 description 5
- 239000010959 steel Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005498 polishing Methods 0.000 description 1
- 230000000750 progressive 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/30136—Metal
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Looms (AREA)
Abstract
The invention relates to the technical field of image processing and pipeline detection, in particular to a method for detecting cracks on the inner wall of a copper pipe based on illumination influence. Taking the central point of the copper pipe opening as the center of a circle in the copper pipe opening image, and taking the central point as the latitude line of the copper pipe opening, wherein the radius of each latitude line is different by a set number of pixels; obtaining an optimized brightness change function corresponding to each weft; correcting the brightness of the copper pipe opening image by using the optimized brightness change function, and obtaining the final brightness value of the copper pipe opening image; and (3) checking the copper pipe orifice image filtering after the brightness value of the pixel point is changed by using Gaussian filtering of different scales, and detecting cracks on the inner wall of the copper pipe. The method considers the influence of the relation between illumination influence and perspective deformation on detection, removes the illumination influence by using a brightness change function, then carries out filtering processing by considering the perspective deformation to remove clutter influence, and then carries out crack detection, thereby improving the crack detection precision.
Description
Technical Field
The invention relates to the technical field of image processing and pipeline detection, in particular to a method for detecting cracks on the inner wall of a copper pipe based on illumination influence.
Background
In life, a plurality of products have copper pipes, and along with the use of the products, the inner walls of the copper pipes in the products can generate cracks and pits. At present, the detection of cracks in the inner cavity of the steel pipe is mostly carried out by technologies such as x-ray, ultrasonic flaw detection or machine vision, and the utilization of the ray flaw detection mode not only needs expensive and heavy instruments, but also needs professional personnel to analyze detection results. The crack detection is carried out by utilizing the machine vision technology, the picture is shot by polishing one end of the copper pipe, the crack of the copper pipe is positioned through the characteristic of the crack, and compared with other methods, the method is convenient and fast to realize, but some factors cause the detection precision to become low in the detection process.
The method mainly solves the problem that the existing machine vision technology is used for detecting the cracks of the inner cavity of the steel pipe, and the detection effect of the cracks of the steel pipe is influenced by both variables without considering the characteristics of the cracks of the steel pipe under the influence of illumination and perspective; the illumination effect is mainly as follows: the illumination is polished from one side, and the illumination attenuation phenomenon exists in the copper tube along with the increase of the distance from the light source. The perspective deformation influence is mainly as follows: when the camera shoots from one end, cracks at the end close to the camera are clearer, and cracks at the end far away from the camera are reduced under the influence of perspective deformation and are easily filtered out by noise.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a method for detecting cracks on the inner wall of a copper pipe based on illumination influence, and the adopted technical scheme is as follows:
taking the central point of the copper pipe opening as the center of a circle in the copper pipe opening image, and taking the central point as the latitude line of the copper pipe opening, wherein the radius of each latitude line is different by a set number of pixels; setting a sliding window along the radius direction, wherein pixel points at the center of the window are pixel points on the weft; fitting the brightness of each pixel point in the window and the distance between the pixel point and the central point of the copper pipe orifice to obtain a brightness change function and parameters thereof;
preliminarily correcting the brightness of pixel points in the window when the sliding window slides by using a brightness change function; obtaining a correction effect evaluation value of the brightness change function according to the disorder degree of the gray value corresponding to each pixel point on the preliminary corrected weft; distributing corresponding weight values to the parameters of each brightness change function according to the correction effect evaluation values of all the brightness change functions on the weft; weighting and summing the parameters of the brightness change function by using the weight to obtain an optimized brightness change function;
correcting the brightness of pixel points in the window when the sliding window slides corresponding to the wefts by using the optimized brightness change function; adding the brightness value of the pixel point in the corrected window and the brightness average value of the unmodified copper pipe orifice image to obtain a final pixel point brightness value; and carrying out crack detection on the inner wall of the copper pipe by using the copper pipe orifice image after the brightness value of the pixel point is changed.
Preferably, the brightness variation function is specifically:
ldrk＝Ark*dqrk+Brkwherein, ldrkExpressing a brightness change function corresponding to the kth pixel point on the r-th weft; a. therkAnd BrkA parameter representing a luminance variation function; dqrkThe distance between the pixel point in the sliding window and the center point of the copper nozzle is represented.
Preferably, the preliminary correction of the brightness of the pixel point in the window when the sliding window slides by using the brightness change function specifically comprises:
Xlq＝Ldq-dq*Ark
wherein, XlqRepresenting the brightness value of the q-th pixel point in the sliding window after preliminary correction; ldqThe luminance value of the q-th pixel point in the sliding window is represented when the preliminary correction is not carried out; dqRepresenting the distance between the q-th pixel point in the sliding window and the central point of the copper pipe orifice; a. therkAnd expressing the parameter of the corresponding brightness change function of the kth pixel point on the r-th weft.
Preferably, the degree of grayscale value clutter is specifically:
wherein Cy is the disorder degree of the gray value corresponding to each pixel point of the r-th weft; pqAnd representing the probability that the gray value of the q-th pixel point in the sliding window appears in the neighborhood after the brightness of the q-th pixel point in the sliding window is preliminarily corrected.
Preferably, the correction effect evaluation value is in a negative correlation with an average of degrees of gradation value disorder corresponding to each pixel point.
Preferably, the weight of the pixel corresponding to the brightness change function parameter is specifically:
wherein, WrkRepresenting the weight of the parameter of the kth brightness change function of the kth weft; drkThe correction effect evaluation value corresponding to the kth brightness change function of the kth weft is shown; n represents the number of r-th weft pixels, DrnIndicating the correction effect evaluation value corresponding to the nth brightness change function on the r-th weft
Preferably, the optimized brightness variation function is specifically:
Ldr＝Ar*d+Br
wherein, LdrRepresenting the optimized brightness change function of the r-th weft; a. therAnd BrA parameter representing the optimized luminance variation function; d represents the distance from the pixel point in the window to the central point of the copper pipe orifice when the sliding window slides on the r-th weft.
Preferably, the final pixel brightness value is:
wherein, QlrWhen the sliding window slides on the r-th weft, the final brightness value of the pixel points in the window is obtained; ldrThe brightness value of the pixel points in the window when the pixel points are not corrected when the sliding window slides on the r-th weft is represented; a. therA parameter representing the optimized luminance variation function of the r-th weft; drThe distance between a pixel point in the window and the center point of the copper pipe orifice is shown when the sliding window slides on the r-th weft;
the mean value of the brightness of the image of the copper nozzle when the image is not corrected is obtained.
Preferably, before the crack detection of the inner wall of the copper pipe is performed by using the copper pipe opening image after the brightness value of the pixel point is changed, the method further includes: determining Gaussian filter kernels with different scales according to the ratio of the pixel perimeter of each weft to the pixel perimeter of the copper pipe orifice hole, and filtering the copper pipe orifice image after the brightness value of the pixel point changes;
preferably, the crack detection is specifically: and processing the filtered copper pipe opening image to obtain a local gray value mutation connected domain, wherein if the gray average value of the pixel points of the local gray value mutation connected domain is smaller than the gray average value of the pixel points of the adjacent region, the local gray value mutation connected domain is a crack region.
The embodiment of the invention at least has the following beneficial effects: the crack detection precision is reduced due to the fact that large light differences exist in different areas in the inner wall image of the steel pipe, the brightness of pixel points of the inner wall image of the copper pipe is corrected by constructing brightness change functions of the different areas, the influence of the light differences is reduced, and the crack detection precision is improved; meanwhile, considering the influence of perspective deformation on the detection of the crack image of the copper pipe, Gaussian filter kernels with different scales are used for filtering cracks distributed in the copper pipe (cracks far away from a camera), and the detection precision is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a schematic view of the weft of the copper nozzle of the present invention;
fig. 3 is a schematic view showing the position of the sliding window of the present invention on the r-th weft.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, a method, its specific implementation, structure, features and effects according to the present invention are described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The concrete scheme of the copper pipe inner wall crack detection method based on the illumination influence is concretely described below by combining the attached drawings.
Example 1
The present invention is directed to the following scenarios: aiming at a longer cylindrical copper pipe, a point light source device is fixed above a camera, an image of the inner wall of the copper pipe is collected just over the center of a hole of the copper pipe, and cracks on the inner wall of the copper pipe are identified and positioned by processing the image.
Referring to fig. 1, a flowchart illustrating steps of a method for detecting cracks on an inner wall of a copper pipe based on illumination according to an embodiment of the present invention is shown, where the method includes the following steps:
the method comprises the following steps: taking the central point of the copper pipe opening as the center of a circle in the copper pipe opening image, and taking the central point as the latitude line of the copper pipe opening, wherein the radius of each latitude line is different by a set number of pixels; setting a sliding window along the radius direction, wherein pixel points at the center of the window are pixel points on the weft; and fitting the brightness of each pixel point in the window and the distance between the pixel point and the central point of the copper pipe orifice to obtain a brightness change function and parameters thereof.
Acquiring a copper pipe orifice image, and performing graying to obtain a copper pipe orifice grayscale image; and the copper pipe orifice image is converted into HSV color space, which specifically comprises the following steps: the light source equipment is fixed above the camera, so that the light source can be projected into the copper pipe to assist in acquiring clear copper pipe opening images. And adjusting the angle of the camera to enable the optical center of the camera to coincide with the center of the copper pipe orifice. Since the light source is projected into the copper tube from one end of the copper tube, the phenomenon of brightness attenuation along with the increase of the distance from the light source occurs, and in the embodiment, a brightness change model needs to be constructed according to the brightness characteristics, so that the color space needs to be converted, and the brightness characteristics need to be extracted. And converting the copper pipe orifice image from an RGB color space into an HSV space, and extracting the copper pipe orifice brightness image in the HSV color space.
In this embodiment, a brightness change function is constructed based on brightness characteristics of each region in a brightness image of a copper pipe opening, and the brightness change function is used to eliminate the illumination influence of the image of the inner wall of the copper pipe, and the specific process is as follows:
as shown in fig. 2, based on the gray level image of the copper pipe orifice, a copper pipe circular hole 100 is detected by hough transform, and different radiuses are cut out at intervals of a set number of pixels along the radius direction of the circular hole with the center point of the copper pipe orifice as the center of the circle, preferably, the implementation is set at intervals of 4 pixels; and making circles concentric with the circular holes of the copper pipes according to different radiuses, wherein the circles with different radiuses are the wefts 101 of the copper pipe openings.
As shown in fig. 3, after the latitude lines are segmented from the gray level image of the copper pipe orifice, marking the corresponding coordinate position of the latitude lines on the brightness image of the copper pipe orifice to obtain the latitude lines in the brightness image of the copper pipe orifice; based on the latitude lines in the copper pipe orifice brightness image, calculating brightness change functions corresponding to different pixel points of the latitude lines: taking the r-th weft 200 on the copper tube brightness image as an example, a set of all pixel points { jw } on the r-th weft on the brightness image is obtainedr1，jwr2，...，jwrmStarting from the k-th pixel point 201 on the weft, a sliding window 202 with the dimension 1 x 5 is arranged, the sliding step length of the sliding window is 1, all pixels on the weft are traversed by sliding along the weft, and the function of the sliding window is to solve the brightness change function of the pixel point on the r-th weft along the radius direction.
The pixel point of window central point position is the pixel point on the weft, acquires the distance between each pixel point and the copper pipe mouth central point in the sliding window: { d1rk，d2rk，...，d5rkAnd simultaneously obtaining the brightness value of each pixel: { ld1rk，ld2rk，...，ld5rk-composition of distance-luminance set: { (d 1)rk，ld1rk)，(d2rk，ld2rk)，...，(d5rk，ld5rk) }; and obtaining a brightness change function corresponding to the kth pixel point according to each value in the distance-brightness set. Copper pipe orifice imageThe change rule of the brightness in the small area can be regarded as a linear change relation, so the function formula is as follows:
ldrk＝Ark*dqrk+Brk
ldrkexpressing a brightness change function corresponding to the kth pixel point on the r-th weft; a. therkAnd BrkProcessing the value in the distance-brightness set of each pixel in the sliding window by a least square method to obtain the parameter of the function; dqrkRepresenting the distance between a pixel point in the sliding window and the central point of the copper pipe orifice, and the distance is an independent variable of a brightness change function; therefore, the light variation function of the kth point of the r-th weft can be obtained. And obtaining a brightness change function and parameters thereof corresponding to each pixel point on the r-th weft through a sliding window.
Step two: preliminarily correcting the brightness of pixel points in the window when the sliding window slides by using a brightness change function; obtaining a correction effect evaluation value of the brightness change function according to the disorder degree of the gray value corresponding to each pixel point on the preliminary corrected weft; distributing corresponding weight values to the parameters of each brightness change function according to the correction effect evaluation values of all the brightness change functions on the weft; and carrying out weighted summation on the parameters of the brightness change function by using the weight to obtain the optimized brightness change function.
Because the distances between the pixel points on the same weft and the light source are equal, the change rate of the brightness on the same weft should be the same, however, the brightness change function corresponding to each pixel point obtained by using the sliding window has unicity, and the description precision of the change relation of the brightness of the pixel point along with the distance between the pixel point and the central point of the copper pipe orifice according to the brightness change function obtained by the pixel point is not known to be higher, namely, the brightness change function corresponding to one pixel point is not necessarily suitable for the brightness change of other pixel points on the same weft, so the brightness change function corresponding to each pixel point needs to be optimized by the principle that the gray value disorder degree of the pixel points in the sliding window and the pixel points in the neighborhood thereof is lower after the initial brightness correction is carried out. And the brightness change functions corresponding to the pixel points on the same weft are unified into the optimized brightness change function. The specific optimization process is as follows:
taking the luminance change function corresponding to the kth pixel point of the r-th weft as an example, preliminarily correcting the luminance of the pixel point in the window when the sliding window slides on the r-th weft:
Xlq＝Ldq-dq*Ark
wherein, XlqRepresenting the brightness value of the q-th pixel point in the sliding window after preliminary correction; ldqThe luminance value of the q-th pixel point in the sliding window is represented when the preliminary correction is not carried out; dqRepresenting the distance between the q-th pixel point in the sliding window and the central point of the copper pipe orifice; a. therkAnd expressing the parameter of the corresponding brightness change function of the kth pixel point on the r-th weft.
And (3) performing an analogy on a brightness initial correction process by using the brightness of the kth pixel point on the r-th weft corresponding to the brightness change function, and performing initial correction on the brightness of the pixel point in the window when the sliding window slides on the r-th weft by using other brightness change functions obtained on the same weft to obtain a corresponding correction result.
And (4) graying the copper pipe orifice image subjected to the preliminary brightness correction, and analyzing based on the grayed image. Analyzing the preliminarily corrected grey scale image of the copper pipe orifice, acquiring 24 neighborhood pixel points of each pixel point on the r-th weft, and calculating the probability of the grey scale value of the pixel point in the sliding window appearing in the 24 neighborhood:
wherein, fqThe frequency of the gray value of the q-th pixel point in the sliding window appearing in the 24-neighborhood after the initial correction.
Calculating the gray value disorder degree corresponding to each pixel point on the r-th weft by using the entropy of the gray value of the pixel point in the sliding window:
wherein Cy is the degree of disorder of the gray value corresponding to each pixel point of the r-th weft; pqAnd the probability that the gray value of the q-th pixel point in the sliding window appears in the 24 neighborhoods after the brightness of the q-th pixel point is preliminarily corrected is represented.
And calculating to obtain the degree of disorder of the gray value corresponding to the pixel point on the weft when the brightness change function corresponding to the kth pixel point performs preliminary brightness correction, wherein the correction effect evaluation value of the brightness change function is as follows:
wherein D isrkThe correction effect evaluation value corresponding to the kth brightness change function of the kth weft is shown; n is the number of pixel points on the r-th weft, CynAnd the degree of disorder of the gray value corresponding to the nth pixel point of the N pixel points on the r-th weft. The correction effect evaluation value and the mean value of the confusion degree of the gray value corresponding to each pixel point form a negative correlation relationship, and meanwhile, the correction effect evaluation value of the brightness change function corresponding to other pixel points on the r-th latitude line is obtained.
The weight value according to the brightness change function parameter of the kth pixel point is as follows:
wherein, WrkRepresenting the weight of the parameter of the kth brightness change function of the kth weft; drkThe correction effect evaluation value corresponding to the kth brightness change function of the kth weft is shown; n represents the number of r-th weft pixels, DrnAnd the correction effect evaluation value corresponding to the nth brightness change function on the r-th latitude line is shown.
Similarly, the weight W of the brightness change function parameter corresponding to each pixel point on the r-th weft is obtainedrnObtaining the parameter A of the brightness change function corresponding to the optimized r-th weft by using the weight of each brightness change function parameter and the parameter of the brightness change functionrAnd Br. Then A isrAnd BrThe method specifically comprises the following steps:
wherein, WrnThe weight value of the nth brightness change function parameter on the r-th weft is calculated; a. thernAnd BrnA parameter representing the nth brightness variation function on the r-th weft; n represents N brightness change functions on the r-th weft.
Obtaining an optimized brightness change function, namely a brightness change function corresponding to the r-th weft:
Ldr＝Ar*d+Br
step three: correcting the brightness of the pixel points in the window when the sliding window slides corresponding to the weft by using the optimized brightness change function; adding the brightness value of the pixel point in the corrected window and the brightness average value of the unmodified copper pipe orifice image to obtain a final pixel point brightness value; and carrying out crack detection on the inner wall of the copper pipe by using the copper pipe orifice image after the brightness value of the pixel point is changed.
The final brightness correction process is illustrated by taking the r-th weft as an example: finally correcting the brightness value of a pixel point in a window when the sliding window slides on the r-th weft by using the brightness change function after the optimization of the r-th weft to obtain the distance between the pixel point in the window and the central point of the copper pipe orifice, and substituting the optimized brightness change function to obtain the brightness difference value A between the pixel point and the central point of the copper pipe orificerD, the corrected brightness value is:
Xlr＝Ldr-Ard
wherein, XlrWhen the sliding window slides on the r-th weft, the corrected brightness value of the pixel points in the window; ldrWhen the sliding window slides on the r-th weft, the pixel points in the window are not correctedA luminance value of time; a. therA parameter representing the optimized luminance variation function of the r-th weft; drAnd the distance between the pixel point in the window and the center point of the copper pipe orifice is shown when the sliding window slides on the r-th weft.
After the brightness correction is performed on the r-th weft in the copper pipe opening image, the final brightness value of the pixel point in the sliding window is as follows:
wherein, QlrWhen the sliding window slides on the r-th weft, the final brightness value of the pixel points in the window is obtained; ldrThe brightness value of the pixel points in the window when the pixel points are not corrected when the sliding window slides on the r-th weft is represented; a. therA parameter representing the optimized luminance variation function of the r-th weft; drThe distance between a pixel point in the window and the center point of the copper pipe orifice is shown when the sliding window slides on the r-th weft;
the average value of the brightness of the copper pipe opening image when not corrected is added to prevent the image from being too dark.
And (3) performing brightness correction on other wefts in the copper pipe opening image by analogy with the brightness correction process of the r-th weft, and obtaining the final brightness value of the copper pipe opening image to obtain the copper pipe opening image suitable for crack detection.
Graying the optimized copper pipe orifice image, constructing a filtering core by utilizing a perspective relation, and performing filtering processing by utilizing the filtering core, wherein the specific process comprises the following steps of:
in order to remove noise interference, filtering processing is performed by using filtering kernels with different scales, and the pixel perimeter Zcm of the copper pipe opening and the pixel perimeter Zc of each weft are calculated, so that the deformation ratio of the pixels on the weft is:
and constructing Gaussian filter kernels with different scales by taking the deformation proportion as a filter kernel adjusting coefficient, and describing a filter kernel scale confirmation method of the filter kernels by using the r-th weft. :
cdr＝bl*β*cdm
wherein cdrExpressing the size of a Gaussian filter kernel suitable for the r-th weft and the surrounding neighborhood thereof; cdm represents the minimum filter kernel scale; beta is a Gaussian filter kernel adjustment coefficient.
The Gaussian filter kernel scale of each weft is obtained by analogy with the method. And performing filtering processing by using the Gaussian filter kernel of the determined filter kernel scale, wherein the variance of the Gaussian filter kernel is sigma.
Preferably, in this embodiment, cdm is 3, β is 0.2, and σ is 0.3.
After filtering, processing the noise-reduced copper pipe inner wall image through an LBP algorithm to obtain a local gray value mutation connected domain set Qy1，Qy2，...，Qyn。
Judging gray level mean value of local mutation connected domain
Whether or not it is smaller than the mean of the gray values of the pixels in the adjacent area
If the mean value of the abrupt change connected domain gray levels:
this region is a crack region, otherwise it is not a crack region.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And that specific embodiments have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
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.
Claims (10)
1. A copper pipe inner wall crack detection method based on illumination influence is characterized by comprising the following steps:
taking the central point of the copper pipe opening as the center of a circle in the copper pipe opening image, and taking the central point as the latitude line of the copper pipe opening, wherein the radius of each latitude line is different by a set number of pixels; setting a sliding window along the radius direction, wherein pixel points at the center of the window are pixel points on the weft; fitting the brightness of each pixel point in the window and the distance between the pixel point and the central point of the copper pipe orifice to obtain a brightness change function and parameters thereof;
preliminarily correcting the brightness of the pixel points in the window when the sliding window slides by using a brightness change function; obtaining a correction effect evaluation value of the brightness change function according to the disorder degree of the gray value corresponding to each pixel point on the weft after the initial correction; distributing corresponding weight values to the parameters of each brightness change function according to the correction effect evaluation values of all the brightness change functions on the weft; weighting and summing the parameters of the brightness change function by using the weight to obtain an optimized brightness change function;
correcting the brightness of the pixel points in the window when the sliding window slides corresponding to the weft by using the optimized brightness change function; adding the brightness value of the pixel point in the corrected window and the brightness average value of the unmodified copper pipe orifice image to obtain a final pixel point brightness value; and carrying out crack detection on the inner wall of the copper pipe by using the copper pipe orifice image after the brightness value of the pixel point is changed.
2. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence as claimed in claim 1, wherein the brightness change function is specifically as follows:
ldrk＝Ark*dqrk+Brk
wherein, ldrkExpressing a brightness change function corresponding to the kth pixel point on the r-th weft; a. therkAnd BrkA parameter representing a luminance variation function; dqrkAnd the distance between the pixel point in the sliding window and the center point of the copper nozzle is represented.
3. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence as claimed in claim 1, wherein the preliminary correction of the brightness of the pixel points in the window when the sliding window slides by using the brightness change function specifically comprises the following steps:
Xlq＝Ldq-dq*Ark
wherein, XlqRepresenting the brightness value of the q-th pixel point in the sliding window after preliminary correction; ldqThe luminance value of the q-th pixel point in the sliding window is represented when the preliminary correction is not carried out; daRepresenting the distance between the q-th pixel point in the sliding window and the central point of the copper pipe orifice; a. therkAnd expressing the parameter of the luminance change function corresponding to the kth pixel point on the r-th weft.
4. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence as claimed in claim 1, wherein the disorder degree of the gray value is specifically as follows:
wherein Cy is the disorder degree of the gray value corresponding to each pixel point of the r-th weft; pqRepresenting the probability that the gray value of the q-th pixel point in the sliding window appears in the neighborhood after the brightness of the q-th pixel point is preliminarily correctedAnd (4) rate.
5. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence as claimed in claim 1, wherein the correction effect evaluation value is in a negative correlation with the mean value of the chaos degree of the gray value corresponding to each pixel point.
6. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence as recited in claim 1, wherein the weight of the pixel corresponding to the brightness change function parameter is specifically as follows:
wherein, WrkRepresenting the weight of the parameter of the kth brightness change function of the kth weft; drkRepresenting a correction effect evaluation value corresponding to the kth brightness change function of the r-th weft; n represents the number of r-th weft pixels, DrnAnd the correction effect evaluation value corresponding to the nth brightness change function on the r-th latitude line is shown.
7. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence according to claim 1, wherein the optimized brightness change function is specifically as follows:
Ldr＝Ar*d+Br
wherein, LdrRepresenting the optimized brightness change function of the r-th weft; a. therAnd BrA parameter representing the optimized luminance variation function; d represents the distance from the pixel point in the window to the central point of the copper pipe orifice when the sliding window slides on the r-th weft.
8. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence as claimed in claim 1, wherein the final pixel brightness value is as follows:
wherein, QlrWhen the sliding window slides on the r-th weft, the final brightness value of the pixel points in the window; ldrThe brightness value of the pixel points in the window when the pixel points are not corrected when the sliding window slides on the r-th weft is represented; a. therA parameter representing the optimized luminance variation function of the r-th weft; drThe distance between a pixel point in the window and the center point of the copper pipe orifice is shown when the sliding window slides on the r-th weft;
the mean value of the brightness of the image of the copper nozzle when the image is not corrected is obtained.
9. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence as claimed in claim 1, wherein before the crack detection on the inner wall of the copper pipe is performed by using the copper pipe opening image after the brightness value of the pixel point is changed, the method further comprises the following steps: and determining Gaussian filter kernels with different scales according to the ratio of the pixel perimeter of each weft to the pixel perimeter of the copper pipe orifice hole, and filtering the copper pipe orifice image after the brightness value of the pixel point is changed.
10. The method for detecting the cracks on the inner wall of the copper pipe based on the illumination influence as claimed in claim 1, wherein the crack detection is specifically as follows: and processing the filtered copper pipe opening image to obtain a local gray value mutation connected domain, wherein if the gray average value of pixel points of the local gray value mutation connected domain is smaller than that of pixel points in an adjacent region, the local gray value mutation connected domain is a crack region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210346872.8A CN114708226A (en) | 2022-04-01 | 2022-04-01 | Copper pipe inner wall crack detection method based on illumination influence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210346872.8A CN114708226A (en) | 2022-04-01 | 2022-04-01 | Copper pipe inner wall crack detection method based on illumination influence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114708226A true CN114708226A (en) | 2022-07-05 |
Family
ID=82171849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210346872.8A Pending CN114708226A (en) | 2022-04-01 | 2022-04-01 | Copper pipe inner wall crack detection method based on illumination influence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114708226A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115272344A (en) * | 2022-09-30 | 2022-11-01 | 南通钰昇智能科技有限公司 | Ground displacement detection method based on image feature matching |
| CN116596403A (en) * | 2023-06-14 | 2023-08-15 | 常州润来科技有限公司 | Evaluation method and system for forming quality of internal threads of copper pipe |
| CN116645373A (en) * | 2023-07-27 | 2023-08-25 | 济宁名居木业有限公司 | Wood surface defect identification method |
| CN117974641A (en) * | 2024-03-28 | 2024-05-03 | 岐山县华强工贸有限责任公司 | Retarder rotor hidden crack identification method based on X-ray flaw detection |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2225980C1 (en) * | 2003-02-17 | 2004-03-20 | Ивановская государственная текстильная академия | Method for determining of filling coefficient and porosity of woven webs from computer-made image |
| JP2007024746A (en) * | 2005-07-20 | 2007-02-01 | Kitakyushu Foundation For The Advancement Of Industry Science & Technology | Method and device for defect detection/discrimination inside conduit |
| JP2012229928A (en) * | 2011-04-25 | 2012-11-22 | Jfe Steel Corp | Surface flaw detection method and surface flaw detection device |
| CN107220962A (en) * | 2017-04-07 | 2017-09-29 | 北京工业大学 | A kind of image detecting method and device of tunnel crackle |
| JP2018128309A (en) * | 2017-02-07 | 2018-08-16 | 大成建設株式会社 | Crack detection method |
-
2022
- 2022-04-01 CN CN202210346872.8A patent/CN114708226A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2225980C1 (en) * | 2003-02-17 | 2004-03-20 | Ивановская государственная текстильная академия | Method for determining of filling coefficient and porosity of woven webs from computer-made image |
| JP2007024746A (en) * | 2005-07-20 | 2007-02-01 | Kitakyushu Foundation For The Advancement Of Industry Science & Technology | Method and device for defect detection/discrimination inside conduit |
| JP2012229928A (en) * | 2011-04-25 | 2012-11-22 | Jfe Steel Corp | Surface flaw detection method and surface flaw detection device |
| JP2018128309A (en) * | 2017-02-07 | 2018-08-16 | 大成建設株式会社 | Crack detection method |
| CN107220962A (en) * | 2017-04-07 | 2017-09-29 | 北京工业大学 | A kind of image detecting method and device of tunnel crackle |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115272344A (en) * | 2022-09-30 | 2022-11-01 | 南通钰昇智能科技有限公司 | Ground displacement detection method based on image feature matching |
| CN115272344B (en) * | 2022-09-30 | 2023-12-08 | 山西豪正森资源环境规划设计有限公司 | Ground displacement detection method based on image feature matching |
| CN116596403A (en) * | 2023-06-14 | 2023-08-15 | 常州润来科技有限公司 | Evaluation method and system for forming quality of internal threads of copper pipe |
| CN116596403B (en) * | 2023-06-14 | 2023-12-22 | 常州润来科技有限公司 | Evaluation method and system for forming quality of internal threads of copper pipe |
| CN116645373A (en) * | 2023-07-27 | 2023-08-25 | 济宁名居木业有限公司 | Wood surface defect identification method |
| CN116645373B (en) * | 2023-07-27 | 2023-10-20 | 济宁名居木业有限公司 | Wood surface defect identification method |
| CN117974641A (en) * | 2024-03-28 | 2024-05-03 | 岐山县华强工贸有限责任公司 | Retarder rotor hidden crack identification method based on X-ray flaw detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114708226A (en) | Copper pipe inner wall crack detection method based on illumination influence | |
| CN115829883B (en) | Surface image denoising method for special-shaped metal structural member | |
| CN115330767B (en) | Method for identifying production abnormity of corrosion foil | |
| CN113362306B (en) | Packaged chip defect detection method based on deep learning | |
| CN115619793B (en) | Power adapter appearance quality detection method based on computer vision | |
| CN114219805B (en) | Intelligent detection method for glass defects | |
| CN116309600B (en) | Environment-friendly textile quality detection method based on image processing | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| CN116311079B (en) | Civil security engineering monitoring method based on computer vision | |
| CN116758057A (en) | Communication equipment defect detection method based on artificial intelligence | |
| CN116703910A (en) | Intelligent detection method for quality of concrete prefabricated bottom plate | |
| CN112381848A (en) | Anti-interference method of instrument visual reading on-line monitoring system in complex environment | |
| CN116758083A (en) | Quick detection method for metal wash basin defects based on computer vision | |
| CN115511907B (en) | Scratch detection method for LED screen | |
| CN115205297B (en) | Abnormal state detection method for pneumatic winch | |
| CN114937035B (en) | Image processing-based power transformer silicon steel sheet quality detection method and system | |
| CN115601368A (en) | Method for detecting defects of sheet metal parts of building material equipment | |
| CN114998311A (en) | Part precision detection method based on homomorphic filtering | |
| CN117541582B (en) | IGBT insulation quality detection method for high-frequency converter | |
| CN116416164B (en) | Ultraviolet light path imaging resolution optimization method | |
| CN116205923B (en) | Nondestructive testing method for internal defects of automobile hub based on X-RAY | |
| CN115049647B (en) | BV cable-based user side data feedback method and system | |
| CN115564705B (en) | Burr detection precision enhancement method and system for precision standard component | |
| CN115222735A (en) | Metal mold quality detection method based on pockmark defects | |
| CN111223074B (en) | Method for detecting top concrete defect of concrete column member |
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 |