CN110687122A - Method and system for detecting surface cracks of ceramic tile - Google Patents
Method and system for detecting surface cracks of ceramic tile Download PDFInfo
- Publication number
- CN110687122A CN110687122A CN201910889381.6A CN201910889381A CN110687122A CN 110687122 A CN110687122 A CN 110687122A CN 201910889381 A CN201910889381 A CN 201910889381A CN 110687122 A CN110687122 A CN 110687122A
- Authority
- CN
- China
- Prior art keywords
- image
- area
- cracks
- crack
- ceramic tile
- 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
- 238000000034 method Methods 0.000 title claims abstract description 79
- 239000000919 ceramic Substances 0.000 title claims abstract description 42
- 230000007547 defect Effects 0.000 claims abstract description 42
- 238000001914 filtration Methods 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 31
- 230000011218 segmentation Effects 0.000 claims abstract description 19
- 230000000877 morphologic effect Effects 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims description 16
- 230000000694 effects Effects 0.000 claims description 6
- 230000007797 corrosion Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 8
- 239000000284 extract Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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 using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method and a system for detecting ceramic tile surface cracks, which are characterized in that an image to be detected is filtered by a rapid self-adaptive median filtering method by acquiring an image of the surface of a ceramic tile to be detected, and the image is divided into a tile head area and a texture area; carrying out image enhancement and segmentation processing on the crack defects of the tile head region by adopting a user-defined sliding filtering method to obtain a binary image of the tile head region; carrying out image enhancement and segmentation processing on the crack defects of the texture region by adopting an automatic region growing method so as to obtain a binary image of the texture region; and performing morphological operation on the binary images of the tile head area and the texture area to remove stray interference points, extracting characteristic parameters of cracks, and judging crack defects according to the extracted characteristic parameters of the cracks, so that the repeated precision and the detection efficiency of the ceramic tile surface crack detection are improved.
Description
Technical Field
The invention belongs to the field of image detection, and particularly relates to a method and a system for detecting cracks on the surface of a ceramic tile.
Background
The image detection technology is widely used in product detection at home and abroad, and is a comprehensive detection system which is formed by integrating modern advanced scientific technologies such as an image processing technology, a photoelectronic technology, a computer technology and the like on the basis of optics. The technology mainly utilizes an optical technology to image a detected substance, the image is used as a carrier for transmitting information or a detection means, and then the detection of the external characteristics of the material is realized through certain processing treatment.
At present, most methods for detecting ceramic tile surface crack defects need binarization processing on an obtained workpiece image, the requirements of the methods on a light source are strict, and the detection cost is undoubtedly greatly increased due to the expensive price of the light source; meanwhile, the electrical interference of the image acquisition device can cause the gray level image to generate various noises, so that the obtained image is easy to generate multi-ambiguity and the repeated precision of workpiece detection is seriously influenced; in addition, the image acquisition speed of the visual system also leads the time of an image processing part to be longer, and restricts the improvement of the detection efficiency. Therefore, how to solve the problem of the relationship between the detection precision of the ceramic tile surface cracks and the complexity of the detection algorithm is still a great challenge faced by the workpiece detection technology.
Disclosure of Invention
Aiming at the defects or improvement requirements in the prior art, the invention provides a method and a system for detecting the surface cracks of the ceramic tile, which are used for filtering the surface image of the ceramic tile to be detected and dividing the surface image into a tile head area and a texture area; carrying out image enhancement and segmentation processing on the tile head area, the texture area and the crack defects by adopting different methods to obtain corresponding binary images; by extracting the characteristic parameters of the cracks and judging the crack defects according to the extracted characteristic parameters of the cracks, the repeated precision and the detection efficiency of the ceramic tile surface crack detection are improved.
In order to achieve the above object, according to one aspect of the present invention, there is provided a method for detecting cracks on a surface of a ceramic tile, comprising the steps of:
s1, acquiring a surface image of a ceramic tile to be detected, filtering the image to be detected by using a rapid self-adaptive median filtering method, and dividing the filtered image into a tile head area and a texture area;
s2, carrying out image enhancement and segmentation processing on the crack defects of the tile head area by adopting a user-defined sliding filtering method to obtain a binary image of the tile head area; carrying out image enhancement and segmentation processing on the crack defects of the texture region by adopting an automatic region growing method so as to obtain a binary image of the texture region;
and S3, performing morphological operation on the binary images of the tile head area and the texture area to remove stray interference points, extracting characteristic parameters of the cracks, and judging the defects of the cracks according to the extracted characteristic parameters of the cracks.
As a further improvement of the present invention, the acquiring of the surface image of the ceramic tile to be detected specifically comprises: and acquiring the image of the surface of the ceramic tile by using a strip-shaped LED light source, a high-definition CCD camera and an image acquisition card.
As a further improvement of the present invention, the fast adaptive median filtering method specifically comprises:
performing a first filtering process, i.e. calculating a1 ═ Zmed-ZminAnd a2 ═ Zmed-Zmax；
If A1>0 and A2<0, then jump to the second filtering process; otherwise, increasing the size of the window;
if the increased size is not greater than SmaxRepeating the first filtering process; otherwise, output Zmed；
The second filtering process is as follows: calculation of B1 ═ Zxy-ZminAnd B2 ═ Zxy-Zmax；
If B1>0, and B2<0, then output Zxy(ii) a Otherwise output Zmed；
Wherein S isxy: the central point of the area is the y-th row and x-th column pixel points in the image; zmin：SxyThe smallest gray value; zmax：SxyThe medium and maximum gray scale values; zmed：SxyThe median of all gray values; zxy: expressing the gray value of the pixel point of the ith row and the xth column in the image; smax：SxyThe maximum window size allowed.
As a further improvement of the invention, the image enhancement and segmentation processing of the crack defect of the tile head region by adopting a user-defined sliding filtering method specifically comprises the following steps:
the self-defined filter is of a double-window structure, the size of a self-defined filter template is 15 multiplied by 7, and the self-defined filter template specifically comprises the following steps:
h0＝[h1h2h1]T
wherein h is1A first window of custom filter template size 1 x 4; h is2A second window of custom filter template size 1 × 7; h is0A certain column of the filter template is defined by users;
s＝[1 … 1]15
h(m,n)＝h0×s
wherein s is a certain line of the custom filter template, and the size of s is 1 × 15; h (m, n) is the custom filter template.
As a further improvement of the invention, the image enhancement and segmentation processing of the crack defect of the texture region by adopting an automatic region growing method specifically comprises the following steps:
scanning the texture area by adopting a 21 x 21 window, and if the pixel value of the central point is smaller than a preset multiple of the window mean value, taking the central point as a seed point;
calculating an absolute value E of a difference between the seed point and the eight-neighborhood pixel value, wherein the pixel coordinate of E smaller than a preset threshold value T can be marked as the seed point, otherwise, the pixel coordinate can not be marked as the seed point; repeating the marked new seed points in sequence; when no new mark point appears, repeating the operation on the next seed point until the seed points all finish growing;
and extracting all the mark points, namely finishing automatic region growth, and obtaining an enhanced effect image of the texture region and a divided binary image.
As a further improvement of the present invention, step S3 specifically includes: performing morphological operation on the binary image obtained in the step S2, wherein the morphological operation comprises a first corrosion operation and a second corrosion operation, performing characteristic parameter extraction on the image T (x, y) obtained after the morphological operation, and calculating the area A of a connected region of the upper singular point 1 in the obtained image T (x, y)sAspect ratio BaNamely:
wherein T (x, y) is a cracked pixel point, I is a crack area, and AsIs the total area of the cracks, NxThe longest length of the crack, NyMaximum width of crack region, BsIs the aspect ratio;
when A issArea greater than detection accuracy, and BsIf the length-width ratio is larger than the detection precision, representing that a certain defect exists on the detected image, and classifying the crack grade according to the calculated characteristic parameters; otherwise, it represents no defect on the detected image.
To achieve the above object, according to another aspect of the present invention, there is provided a ceramic tile surface crack detection system comprising at least one processing unit, and at least one memory unit, wherein the memory unit stores a computer program which, when executed by the processing unit, causes the processing unit to perform the steps of the above method.
Generally, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:
the invention relates to a method and a system for detecting ceramic tile surface cracks, which are characterized in that the surface image of a ceramic tile to be detected is filtered and divided into a tile head area and a texture area; carrying out image enhancement and segmentation processing on the tile head area, the texture area and the crack defects by adopting different methods to obtain corresponding binary images; by extracting the characteristic parameters of the cracks and judging the crack defects according to the extracted characteristic parameters of the cracks, the repeated precision and the detection efficiency of the ceramic tile surface crack detection are improved.
According to the method and the system for detecting the ceramic tile surface cracks, the image denoising is carried out through the rapid self-adaptive median filtering, the following noise can be effectively removed, the edge of the processed image is clear, namely, the image details are effectively protected, and experimental results show that the method is high in filtering speed and can well meet the requirements of site real-time performance.
According to the method and the system for detecting the cracks on the surface of the ceramic tile, the self-defined sliding filtering method is adopted to carry out image enhancement and segmentation on the crack defects in the tile head area, so that the cracks in the tile head area are completely extracted, most of the cracks in the tile head area are horizontally long and narrow, and the contrast ratio between the defects and the background area is low. After custom filtering, the defect contrast is significantly increased, making the crack defect region more obvious. Compared with the traditional image detection algorithm, the method not only improves the contrast of the image, but also can effectively enhance the edge details of the workpiece defect and well preserve the image characteristics of the crack.
According to the method and the system for detecting the cracks on the surface of the ceramic tile, disclosed by the invention, the crack defects of the texture area are subjected to image enhancement and segmentation treatment by adopting an automatic area growing method, so that the cracks of the pattern area can be accurately extracted, the cracks of the texture area are in a gully type, and the cracks are easily subjected to false detection by the texture. The crack characteristics of the texture area in the ceramic tile are darker, the seed point is automatically determined by comparing the central point with the window mean value, the texture interference can be removed, and the accurate extraction of the cracks in the pattern area is facilitated. Compared with the traditional image detection algorithm, the method not only improves the contrast of the image, but also can effectively enhance the edge details of the workpiece defect and well preserve the image characteristics of the crack.
Drawings
Fig. 1 is a schematic diagram of a method for detecting cracks on the surface of a ceramic tile according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other. The present invention will be described in further detail with reference to specific embodiments.
Fig. 1 is a schematic diagram of a method for detecting cracks on the surface of a ceramic tile according to an embodiment of the present invention. As shown in fig. 1, a method for detecting cracks on the surface of a ceramic tile comprises the following steps:
step 1: acquiring a surface image of a ceramic tile to be detected, performing filtering processing on the image to be detected by utilizing rapid self-adaptive median filtering, and dividing the image into a tile head area and a texture area;
the specific process is as follows:
the method comprises the steps of acquiring a ceramic tile surface image by using a strip-shaped LED light source, a high-definition CCD camera and an image acquisition card, and carrying out image denoising by using a self-adaptive median filtering method, wherein,
the self-adaptive median filtering method specifically comprises the following steps:
performing a first filtering processThe value of A1 ═ Zmed-ZminAnd a2 ═ Zmed-Zmax；
If A1>0 and A2<0, then jump to the second filtering process; otherwise, increasing the size of the window;
if the increased size is not greater than SmaxRepeating the first filtering process; otherwise, output Zmed；
The second filtering process is as follows: calculation of B1 ═ Zxy-ZminAnd B2 ═ Zxy-Zmax；
If B1>0, and B2<0, then output Zxy(ii) a Otherwise output Zmed；
Wherein S isxy: the central point of the area is the y-th row and x-th column pixel points in the image;
Zmin：Sxythe smallest gray value;
Zmax：Sxythe medium and maximum gray scale values;
Zmed：Sxythe median of all gray values;
Zxy: expressing the gray value of the pixel point of the ith row and the xth column in the image;
Smax：Sxythe maximum window size allowed.
Thus realizing the self-adaptive median filtering, and then respectively dividing the image into a tile area and a pattern area;
in this embodiment, the image may be processed by an industrial personal computer (intel (r) core (tm) i 7-6700K CPU @4.00GHz, 32GB memory, 64-bit Windows7 operating system), so as to complete the simulation experiment of the detection method of the present invention and the existing detection method. The image noise processed by the denoising method of the detection method is effectively removed, the edge of the processed image is clear, namely, the image detail is effectively protected, and experimental results show that the detection method of the invention has higher filtering speed and can better meet the requirement of on-site real-time property.
As an example, the size of the ceramic tile is fixed, and the tile area is on the left part of the image matrix, the pattern area is on the right part of the image matrix, and the image can be divided into two areas, namely the tile area and the pattern area, by taking the position of 350 pixels from left to right as a dividing position on the left and right parts;
step 2, carrying out image enhancement and segmentation processing on the crack defects of the tile head region by adopting a user-defined sliding filtering method to obtain a binary image of the tile head region; carrying out image enhancement and segmentation processing on the crack defects of the texture region by adopting an automatic region growing method so as to obtain a binary image of the texture region;
as an example, the image enhancement and segmentation processing on the crack defect in the tile head region by using the custom sliding filtering method specifically includes:
the self-defined filter is of a double-window structure, the size of a self-defined filter template is 15 multiplied by 7, and the self-defined filter template specifically comprises the following steps:
h0＝[h1h2h1]T
wherein h is1A first window of custom filter template size 1 x 4; h is2A second window of custom filter template size 1 × 7; h is0A certain column of the filter template is defined by users;
s＝[1 … 1]15
h(m,n)＝h0×s
wherein s is a certain line of the custom filter template, and the size of s is 1 × 15; h (m, n) is the custom filter template. The operation process is as follows:
g(x,y)＝h(m,n)*f(x,y)
f (x, y) is an image after median filtering, and g (x, y) is an image after sliding filtering;
and carrying out global threshold segmentation on the crack area image by using the self-defined filter so as to obtain a binary image of the crack area.
The method for automatically growing the pattern area image comprises the following steps: scanning the texture area by adopting a 21 x 21 window, and if the pixel value of the central point is smaller than a preset multiple of the window mean value, such as k times, taking the central point as a seed point;
calculating an absolute value E of a difference between the seed point and the eight-neighborhood pixel value, wherein the pixel coordinate of E smaller than a preset threshold value T can be marked as the seed point, otherwise, the pixel coordinate can not be marked as the seed point; repeating the marked new seed points in sequence; when no new mark point appears, repeating the operation on the next seed point until the seed points all finish growing;
extracting all the mark points, namely finishing automatic region growth, and obtaining an effect graph of ceramic tile crack region enhancement and a divided binary graph;
in order to more intuitively show the good effect of the method, the method and the maximum entropy method, sobel algorithm and discrete wavelet transform algorithm are utilized to act on the same ceramic tile surface image, and the contrast of the image is improved after the enhancement and segmentation algorithm provided by the invention is adopted for processing, the edge details of the image are completely stored, and the processing effect is greatly optimized compared with other algorithms.
And 3, performing morphological operation on the binary images of the tile head area and the texture area to remove stray interference points, extracting characteristic parameters of the crack, and judging the crack defect according to the extracted characteristic parameters of the crack.
Performing morphological operations on the binary image obtained in the step S2, wherein the morphological operations include a first erosion operation and a second erosion operation, namely, labeling the binary image obtained in the step 2 as f (x, y), performing morphological operations on f (x, y):
when the origin of the structural element S is moved to the position of a point (X, y), if S is contained in X, the point on the corroded image is 1, otherwise, the point is 0; Θ represents a first corrosion operation;
when the original point of the structural element S is moved to the position of a point (x, y), if S comprises at least one point with the pixel value of 1, the point on the expanded image is 1, and if not, the point is 0;
representing a second erosion operation;
extracting characteristic parameters of the image T (x, y) obtained after the morphological operation, and calculating the area A of a communication region of the upper singular point 1 in the image T (x, y)sAspect ratio BaNamely:
wherein T (x, y) is a cracked pixel point, I is a crack area, and AsIs the total area of the cracks, NxThe longest length of the crack, NyMaximum width of crack region, BsIs the aspect ratio; when A issArea greater than detection accuracy, and BsIf the length-width ratio is larger than the detection precision, representing that a certain defect exists on the detected image, and classifying the crack grade according to the calculated characteristic parameters; otherwise, it represents no defect on the detected image.
After the defects are subjected to region marking and connectivity analysis, extracting characteristic parameters of the cracks, classifying the defects, and displaying the characteristic parameters and types of the cracks; wherein the parameters are defined as follows: when A issGreater than 50 pixels or BsIf the value is more than 5, the defect is judged to be a crack defect.
A ceramic tile surface crack detection system comprising at least one processing unit and at least one memory unit, wherein the memory unit stores a computer program which, when executed by the processing unit, causes the processing unit to perform the steps of the above method.
Table 1 is a schematic diagram comparing the accuracy of the detection method of the embodiment of the present invention with that of the existing method. The existing maximum entropy method adopts gray level transformation and median filtering, then uses the maximum entropy method to segment the image, and finally extracts defects through morphology. The existing sobel algorithm is to filter and preprocess the red channel and the median of the original image and then process the image by using the edge detection sobel. The existing discrete wavelet transform adopts a red channel of an original image and combines a morphological filtering method and a discrete wavelet transform method to process the image. The discrete wavelet transform carries out two-layer wavelet decomposition on a preprocessed image, extracts a low-frequency image of the wavelet transform, processes the low-frequency image by using morphology, then extracts a target by a difference image method, then carries out filtering on other component images of the wavelet transform, and finally extracts defects by wavelet reconstruction. According to the experimental effect, the detection method can well extract the cracks from the complex background, and has high relative accuracy.
TABLE 1 comparison of the accuracy of the detection method of the present invention embodiment with that of the prior art
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (7)
1. A method for detecting cracks on the surface of a ceramic tile is characterized by comprising the following steps:
s1, acquiring a surface image of a ceramic tile to be detected, filtering the image to be detected by using a rapid self-adaptive median filtering method, and dividing the filtered image into a tile head area and a texture area;
s2, carrying out image enhancement and segmentation processing on the crack defects of the tile head area by adopting a user-defined sliding filtering method to obtain a binary image of the tile head area; carrying out image enhancement and segmentation processing on the crack defects of the texture region by adopting an automatic region growing method so as to obtain a binary image of the texture region;
and S3, performing morphological operation on the binary images of the tile head area and the texture area to remove stray interference points, extracting characteristic parameters of the cracks, and judging the defects of the cracks according to the extracted characteristic parameters of the cracks.
2. The method for detecting the surface cracks of the ceramic tiles according to claim 1, wherein the step of acquiring the surface images of the ceramic tiles to be detected specifically comprises the following steps: and acquiring the image of the surface of the ceramic tile by using a strip-shaped LED light source, a high-definition CCD camera and an image acquisition card.
3. The method for detecting the surface cracks of the ceramic tiles according to claim 1 or 2, wherein the fast adaptive median filtering method specifically comprises the following steps:
performing a first filtering process, i.e. calculating a1 ═ Zmed-ZminAnd a2 ═ Zmed-Zmax；
If A1>0 and A2<0, then jump to the second filtering process; otherwise, increasing the size of the window;
if the increased size is not greater than SmaxRepeating the first filtering process; otherwise, output Zmed；
The second filtering process is as follows: calculation of B1 ═ Zxy-ZminAnd B2 ═ Zxy-Zmax；
If B1>0, and B2<0, then output Zxy(ii) a Otherwise output Zmed；
Wherein S isxy: the central point of the area is the y-th row and x-th column pixel points in the image; zmin：SxyThe smallest gray value; zmax：SxyThe medium and maximum gray scale values; zmed：SxyThe median of all gray values; zxy: expressing the gray value of the pixel point of the ith row and the xth column in the image; smax：SxyThe maximum window size allowed.
4. The method for detecting the ceramic tile surface cracks according to claim 1 or 2, wherein the image enhancement and segmentation processing of the crack defects in the tile head region by adopting the custom sliding filtering method specifically comprises the following steps:
the self-defined filter is of a double-window structure, the size of a self-defined filter template is 15 multiplied by 7, and the self-defined filter template specifically comprises the following steps:
h0＝[h1h2h1]T
wherein h is1A first window of custom filter template size 1 x 4; h is2A second window of custom filter template size 1 × 7; h is0A certain column of the filter template is defined by users;
s＝[1 … 1]15
h(m,n)＝h0×s
wherein s is a certain line of the custom filter template, and the size of s is 1 × 15; h (m, n) is the custom filter template.
5. The method for detecting the cracks on the surface of the ceramic tile according to the claim 1 or 2, wherein the image enhancement and segmentation processing of the crack defects in the texture area by adopting the automatic area growing method is specifically as follows:
scanning the texture area by adopting a 21 x 21 window, and if the pixel value of the central point is smaller than a preset multiple of the window mean value, taking the central point as a seed point;
calculating an absolute value E of a difference between the seed point and the eight-neighborhood pixel value, wherein the pixel coordinate of E smaller than a preset threshold value T can be marked as the seed point, otherwise, the pixel coordinate can not be marked as the seed point; repeating the marked new seed points in sequence; when no new mark point appears, repeating the operation on the next seed point until the seed points all finish growing;
and extracting all the mark points, finishing automatic region growth, and obtaining an enhanced effect image of the texture region and a divided binary image.
6. The method for detecting cracks on the surface of a ceramic tile according to any one of claims 1 to 5, wherein the step S3 is specifically as follows: performing morphological operation on the binary image obtained in the step S2, wherein the morphological operation comprises a first corrosion operation and a second corrosion operation, performing characteristic parameter extraction on the image T (x, y) obtained after the morphological operation, and calculating the area A of a connected region of an upper singular point in the image T (x, y)sAspect ratio BaNamely:
wherein T (x, y) is a cracked pixel point, I is a crack area, and AsIs the total area of the cracks, NxThe longest length of the crack, NyMaximum width of crack region, BsIs the aspect ratio;
when A issArea greater than detection accuracy, and BsIf the length-width ratio is larger than the detection precision, representing that a certain defect exists on the detected image, and classifying the crack grade according to the calculated characteristic parameters; otherwise, it represents no defect on the detected image.
7. A ceramic tile surface crack detection system, characterized in that it comprises at least one processing unit and at least one memory unit, wherein the memory unit stores a computer program which, when executed by the processing unit, causes the processing unit to carry out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910889381.6A CN110687122A (en) | 2019-09-19 | 2019-09-19 | Method and system for detecting surface cracks of ceramic tile |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910889381.6A CN110687122A (en) | 2019-09-19 | 2019-09-19 | Method and system for detecting surface cracks of ceramic tile |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110687122A true CN110687122A (en) | 2020-01-14 |
Family
ID=69109571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910889381.6A Pending CN110687122A (en) | 2019-09-19 | 2019-09-19 | Method and system for detecting surface cracks of ceramic tile |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110687122A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814550A (en) * | 2020-06-05 | 2020-10-23 | 陕西科技大学 | Ceramic texture extraction method based on convolutional neural network and image processing |
| CN112016555A (en) * | 2020-08-20 | 2020-12-01 | 中国民航大学 | Machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloy |
| CN113689404A (en) * | 2021-08-24 | 2021-11-23 | 湖北三江航天红林探控有限公司 | Part counting system and method based on image processing |
| CN114719749A (en) * | 2022-04-06 | 2022-07-08 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
| CN114937006A (en) * | 2022-04-29 | 2022-08-23 | 南通同欧智能装备科技有限公司 | Hammerhead refinement defect detection method based on image enhancement |
| CN116958171A (en) * | 2023-07-31 | 2023-10-27 | 重庆交通大学 | Aggregate image crack segmentation method, apparatus, storage medium and program product |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727244A (en) * | 2019-01-18 | 2019-05-07 | 深圳至汉装备科技有限公司 | A kind of magnetic shoe surface crack testing method |
-
2019
- 2019-09-19 CN CN201910889381.6A patent/CN110687122A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109727244A (en) * | 2019-01-18 | 2019-05-07 | 深圳至汉装备科技有限公司 | A kind of magnetic shoe surface crack testing method |
Non-Patent Citations (6)
| Title |
|---|
| 刘国华等: "《HALCON数字图像处理》", 31 May 2018, 西安：西安电子科技大学出版社 * |
| 刘鹏宇等: "改进的自适应中值滤波算法及其应用", 《北京工业大学学报》 * |
| 帅慕容等: "一种改进均值的自适应中值滤波算法", 《测绘通报》 * |
| 张绍伟等: "基于机器视觉的陶瓷瓦表面鼓包缺陷检测算法研究", 《南阳理工学院学报》 * |
| 李丹等: "基于 FCM 和分水岭算法的无人机影像中林分因子提取", 《林业科学》 * |
| 李小磊等: "基于滑动滤波和自动区域生长的陶瓷瓦表面裂纹检测", 《激光与光电子学进展》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814550A (en) * | 2020-06-05 | 2020-10-23 | 陕西科技大学 | Ceramic texture extraction method based on convolutional neural network and image processing |
| CN111814550B (en) * | 2020-06-05 | 2023-11-21 | 陕西科技大学 | Ceramic texture extraction method based on convolutional neural network and image processing |
| CN112016555A (en) * | 2020-08-20 | 2020-12-01 | 中国民航大学 | Machine learning-based image recognition algorithm for surface cracking of aviation aluminum alloy |
| CN113689404A (en) * | 2021-08-24 | 2021-11-23 | 湖北三江航天红林探控有限公司 | Part counting system and method based on image processing |
| CN114719749A (en) * | 2022-04-06 | 2022-07-08 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
| CN114719749B (en) * | 2022-04-06 | 2023-07-14 | 重庆大学 | Metal surface crack detection and real size measurement method and system based on machine vision |
| CN114937006A (en) * | 2022-04-29 | 2022-08-23 | 南通同欧智能装备科技有限公司 | Hammerhead refinement defect detection method based on image enhancement |
| CN116958171A (en) * | 2023-07-31 | 2023-10-27 | 重庆交通大学 | Aggregate image crack segmentation method, apparatus, storage medium and program product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110687122A (en) | Method and system for detecting surface cracks of ceramic tile | |
| CN114937055B (en) | Image self-adaptive segmentation method and system based on artificial intelligence | |
| CN115082419B (en) | Blow-molded luggage production defect detection method | |
| CN110163219B (en) | Target detection method based on image edge recognition | |
| CN108171688B (en) | Wafer surface defect detection method based on Gabor characteristics and random dimensionality reduction | |
| CN112837290B (en) | Crack image automatic identification method based on seed filling algorithm | |
| CN112614062B (en) | Colony counting method, colony counting device and computer storage medium | |
| CN110309806B (en) | Gesture recognition system and method based on video image processing | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN103175844A (en) | Detection method for scratches and defects on surfaces of metal components | |
| CN109540925B (en) | Complex ceramic tile surface defect detection method based on difference method and local variance measurement operator | |
| CN102324099A (en) | Step edge detection method oriented to humanoid robot | |
| CN110687121B (en) | Intelligent online detection and automatic grading method and system for ceramic tiles | |
| CN105447489B (en) | A kind of character of picture OCR identifying system and background adhesion noise cancellation method | |
| CN108921813A (en) | Unmanned aerial vehicle detection bridge structure crack identification method based on machine vision | |
| CN112861654B (en) | Machine vision-based famous tea picking point position information acquisition method | |
| CN109781737A (en) | A kind of detection method and its detection system of hose surface defect | |
| CN110807763A (en) | Method and system for detecting ceramic tile surface bulge | |
| CN109543686B (en) | Character recognition preprocessing binarization method based on self-adaptive multi-threshold | |
| CN103177244B (en) | Method for quickly detecting target organisms in underwater microscopic images | |
| CN105373798B (en) | One kind scratching figure and the morphologic writing brush word extracting method of mathematics based on k nearest neighbor | |
| Valliammal et al. | A hybrid method for enhancement of plant leaf recognition | |
| CN107239761B (en) | Fruit tree branch pulling effect evaluation method based on skeleton angular point detection | |
| CN116703921B (en) | Method for detecting quality of surface coating of flexible circuit board | |
| CN104102911A (en) | Image processing for AOI (automated optical inspection)-based bullet appearance defect detection system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200114 |
|
| RJ01 | Rejection of invention patent application after publication |