CN115937212B - Glass plate crack detection method, device, equipment and medium - Google Patents
Glass plate crack detection method, device, equipment and medium Download PDFInfo
- Publication number
- CN115937212B CN115937212B CN202310079413.2A CN202310079413A CN115937212B CN 115937212 B CN115937212 B CN 115937212B CN 202310079413 A CN202310079413 A CN 202310079413A CN 115937212 B CN115937212 B CN 115937212B
- Authority
- CN
- China
- Prior art keywords
- crack
- target glass
- detection
- region
- glass plate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P40/00—Technologies relating to the processing of minerals
- Y02P40/50—Glass production, e.g. reusing waste heat during processing or shaping
- Y02P40/57—Improving the yield, e-g- reduction of reject rates
Abstract
The application discloses a glass plate crack detection method, device, equipment and medium, relates to the technical field of glass plate detection, and is used for solving the technical problem that the quality of a glass plate is affected by the fact that the crack defect of a broken glass plate cannot be accurately detected in the prior art. The method comprises the steps of firstly obtaining a detection area of a target glass plate based on a segmentation threshold value; the segmentation threshold is obtained from a plurality of historical glass plates; dividing the detection area of the target glass plate based on the gray threshold of the detection area to obtain a preliminary screening crack area of the target glass plate; and then comparing the average gray value of the primary screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet. According to the method, the area containing the broken piece cracks can be gradually reduced, and the broken piece crack defects can be accurately detected in a smaller area.
Description
Technical Field
The application relates to the technical field of glass plate detection, in particular to a glass plate crack detection method, a device, equipment and a medium.
Background
The panel industry is vigorously developed, the market demand is continuously increased, the production efficiency is improved, the productivity is increased, the production cost is reduced, and the product quality is improved. The carrier of the panel is glass, and in a complex process flow, breakage (chipping or cracking) of the glass carrier plate directly causes complete scrapping of the glass, which is the most serious defect. Therefore, it is necessary to detect a crack in the broken glass sheet.
However, the prior art cannot accurately detect the crack defect of the broken glass sheet, thereby affecting the quality of the glass sheet.
Disclosure of Invention
The main aim of the application is to provide a method, a device, equipment and a medium for detecting glass plate cracks, which aim to solve the technical problem that the quality of the glass plate is affected by the fact that the crack defects of broken glass plates cannot be accurately detected in the prior art.
To achieve the above object, a first aspect of the present application provides a glass sheet crack detection method, the method comprising:
based on the segmentation threshold value, obtaining a detection area corresponding to the target glass plate on the target glass carrier plate image; the segmentation threshold is obtained based on pixel statistics of a plurality of glass carrier plate images;
dividing the detection area of the target glass plate based on the gray threshold of the detection area to obtain a preliminary screening crack area of the target glass plate;
comparing the average gray value of the primary screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet; wherein the non-crack region is a region outside of a pre-screened crack region of the target glass sheet; the comparing the average gray value of the pre-screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet comprises:
and filtering a region of which the average gray value of the central region of the primary screening crack region is higher than the preset proportion of the average gray value of the non-crack region so as to obtain a final crack region of the target glass plate.
Optionally, the obtaining, based on the segmentation threshold, a detection area corresponding to the target glass plate on the target glass carrier plate image includes:
based on a segmentation threshold value, obtaining an external rectangular frame of the edge of the target glass plate on the target glass carrier plate image;
and obtaining the detection area based on the circumscribed rectangular frame.
According to the segmentation threshold value, an external rectangular frame on the target glass carrier plate image is obtained, and then the detection area is obtained according to the external rectangular frame, so that the range of the corresponding part on the target glass carrier plate image can be reduced and defined by the external rectangular frame, and the more accurate detection area can be obtained.
Optionally, the obtaining the detection area based on the circumscribed rectangular frame includes:
obtaining a detection edge of the target glass plate based on the circumscribed rectangular frame;
based on the detection edge, a first detection zone of the target glass sheet is obtained.
According to the circumscribed rectangular frame, the detection edge of the target glass plate is obtained first, and then the first detection area is obtained according to the detection edge, so that the crack area of the target glass plate is located in the first detection area because the crack area is located in the detection edge.
Optionally, the obtaining the detection edge of the target glass plate based on the circumscribed rectangular frame includes:
and cutting off four cut corners of the circumscribed rectangular frame of the edge of the target glass plate to obtain the detection edge of the target glass plate.
Because the four corners and the top positions of the glass edge are cut off in actual production, the precise pixel coordinates of the four top positions of the glass edge are required to be extracted, the top corner cutting areas are drawn, and the four corner cutting areas of the edge are cut off in the obtained circumscribed rectangular image, so that the detection edge can be obtained more accurately.
Optionally, the obtaining a first detection area of the target glass sheet based on the detection edge includes:
and sequentially expanding the detection edge of the target glass plate inwards by preset pixels to obtain a first detection area of the target glass plate.
According to the practical situation, after the detection edges are sequentially expanded inwards by preset pixels, a first detection area is obtained, and as the range in the detection edges can be reduced after the preset pixels are expanded inwards, the first detection area can be accurately obtained.
Optionally, the sequentially expanding the detection edges of the target glass plate inward by a preset number of pixels to obtain a first detection area of the target glass plate includes:
and sequentially expanding twenty pixels inwards from four sides of the detection edge of the target glass plate to obtain a first detection area of the target glass plate.
"inward expansion" refers to the expansion toward the center of the target glass sheet, and setting a preset number of pixels to twenty pixels can further reduce the area where the crack area is located.
Optionally, after the step of obtaining the first detection area of the target glass sheet based on the detection edge, the method further comprises:
clipping a clamping area of the first detection area of the target glass plate to obtain a second detection area; the area ratio of the glass plate crack in the second detection area is higher than that of the glass plate crack in the first detection area;
dividing the detection area of the target glass plate based on the gray threshold of the detection area to obtain a preliminary screening crack area of the target glass plate, wherein the preliminary screening crack area comprises the following steps:
dividing the second detection region of the target glass plate based on the gray threshold of the second detection region to obtain a preliminary screening crack region of the target glass plate.
In actual production, glass moves through the clamping structure, and each piece of glass has clamping areas with the same size at four sides fixed positions, so that the clamping areas of the first detection areas of the target glass plates need to be cut off, the first detection areas after the clamping areas are cut off are second detection areas, the obtained second detection areas are more simplified than the first detection areas in scope, and the areas where the crack areas are located are further reduced.
Optionally, before the step of dividing the second detection region of the target glass sheet based on the gray threshold of the second detection region to obtain the preliminary screening crack region of the target glass sheet, the method further comprises:
and calculating the average gray value of the second detection area to obtain a gray threshold value of the second detection area.
The average gray value of the second detection area may include information of all gray values of the second detection area, so that the gray threshold value is obtained by the average gray value, and the gray threshold value of the second detection area may be more accurate.
Optionally, the calculating the average gray value of the second detection area to obtain the gray threshold of the second detection area includes:
and calculating the average gray value of the second detection area, and taking one half of the average gray value of the second detection area as a gray threshold value of the second detection area.
A preferred way of obtaining the gray threshold value is given, i.e. half the average gray value of the second detection area is used as the gray threshold value, so that the gray threshold value of the second detection area can be obtained more easily and accurately.
Optionally, the filtering the area of the center area of the primary screening crack area having an average gray value higher than a preset proportion of the average gray value of the non-crack area to obtain a final crack area of the target glass sheet includes:
filtering a region of the primary screening crack region having an average gray value higher than one-half the average gray value of the non-crack region to obtain a final crack region of the target glass sheet.
The method has the advantages that an optimal value of a preset proportion, namely one half of the optimal value is given, the area, with the average gray value of the central area of the primary screening crack area higher than one half of the average gray value of the non-crack area, of the primary screening crack area is filtered, the area where the crack area is located can be further reduced and defined, therefore, a more accurate crack area can be obtained through the final crack area, and the quality of the target glass plate can be greatly improved after the crack area of the target glass plate is processed.
Optionally, before the step of obtaining the detection area corresponding to the target glass plate on the target glass carrier plate image based on the segmentation threshold value, the method further includes:
acquiring a range of first gray values of actual edges of glass plates in a plurality of glass carrier images based on the plurality of glass carrier images, and acquiring a range of second gray values of image black edges of the glass plates in the plurality of glass carrier images;
obtaining a segmentation threshold based on the range of first gray values and the range of second gray values; the segmentation threshold is greater than the second gray level value and less than the first gray level value.
The determination of the distribution of the first gray value of the actual edge of the glass plate and the second gray value range of the image black edge is a statistical process, namely, the gray values of the black edge and the actual glass edge in hundreds of identical production and photographing environments are counted, the second gray value distribution range of the image black edge and the first gray value distribution range of the actual edge can be obtained, the intermediate values of the two gray value ranges (namely, the first gray value range and the second gray value range) are selected as the segmentation threshold, and more accurate segmentation threshold can be obtained due to counting of a large number of glass plates.
In a second aspect, the present application provides a glass sheet crack detection device, the device comprising:
the acquisition module is used for acquiring a detection area corresponding to the target glass plate on the target glass carrier plate image based on the segmentation threshold value; the segmentation threshold is obtained based on pixel statistics of a plurality of glass carrier plate images;
the dividing module is used for dividing the detection area of the target glass plate based on the gray threshold value of the detection area so as to obtain a preliminary screening crack area of the target glass plate;
a comparison module for comparing the average gray value of the primary screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet; wherein the non-crack region is a region outside of a pre-screened crack region of the target glass sheet; the comparing the average gray value of the pre-screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet comprises:
and filtering a region of which the average gray value of the central region of the primary screening crack region is higher than the preset proportion of the average gray value of the non-crack region so as to obtain a final crack region of the target glass plate.
In a third aspect, the present application provides a computer device comprising a memory, in which a computer program is stored, and a processor executing the computer program to implement the method described in the embodiments.
In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the method described in the embodiments.
Through above-mentioned technical scheme, this application has following beneficial effect at least:
the method, the device, the equipment and the medium for detecting the glass plate crack comprise the steps of obtaining a detection area corresponding to a target glass plate on a target glass carrier plate image based on a segmentation threshold value; the segmentation threshold is obtained based on pixel statistics of a plurality of glass carrier plate images; dividing the detection area of the target glass plate based on the gray threshold of the detection area to obtain a preliminary screening crack area of the target glass plate; comparing the average gray value of the primary screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet; wherein the non-crack region is a region outside of the pre-screened crack region of the target glass sheet.
When the crack region of the target glass plate needs to be detected, the detection region of the target glass plate is obtained according to the segmentation threshold value obtained in advance, the detection region is segmented according to the gray level threshold value of the detection region so as to obtain a preliminary screening crack region of the target glass plate, and finally the average gray level values of the preliminary screening crack region and the non-crack region are compared so as to obtain a final crack region of the target glass plate.
The method comprises the steps of finding a detection area of a target glass plate containing a broken piece crack through a segmentation threshold value obtained in advance, finding a preliminary screening crack area containing the broken piece crack in the detection area, and finally finding a final crack area in the preliminary screening crack area according to average threshold value comparison. Therefore, the area containing the broken piece crack can be gradually reduced, and the broken piece crack defect of the target glass plate can be accurately detected in a smaller area, so that the quality of the target glass plate can be improved.
Drawings
FIG. 1 is a schematic diagram of a computer device in a hardware operating environment according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for crack detection of a glass sheet according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an obtained detection area according to an embodiment of the present application;
fig. 4 is a flowchart of a specific implementation method of step S10 provided in this embodiment;
FIG. 5 is a schematic view of a first corner cut of a cut-out circumscribed rectangular image according to an embodiment of the present application;
FIG. 6 is a schematic diagram of a second corner cut for cutting off a circumscribed rectangular image according to an embodiment of the present application;
FIG. 7 is a schematic view of a third corner cut for cutting off a circumscribed rectangular image according to an embodiment of the present application;
FIG. 8 is a schematic view of a fourth corner cut of a cut-out circumscribed rectangular image according to an embodiment of the present application;
FIG. 9 is a schematic diagram of providing a second detection region according to an embodiment of the present application;
FIG. 10 is a schematic diagram of a center region and an edge non-fragmented region of a fragment provided in an embodiment of the present application;
FIG. 11 is a schematic illustration of a final crack region provided in an embodiment of the present application;
fig. 12 is a schematic diagram of a glass plate crack detection device according to an embodiment of the present application.
The realization, functional characteristics and advantages of the present application will be further described with reference to the embodiments, referring to the attached drawings.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The panel industry is vigorously developed, the market demand is continuously increased, the production efficiency is improved, the productivity is increased, the production cost is reduced, and the product quality is improved. With the wide application of artificial intelligence in industrial defect detection, an image processing-based defect automatic detection classification system (ADC) can replace the original artificial visual sampling inspection mode, so that the comprehensive and efficient detection of the product quality is realized. The carrier of the panel is glass, and in a complex process production flow, the breakage (fragments or cracks) of the glass carrier plate can directly cause the glass carrier plate to be completely scrapped, so that the carrier plate is the most serious defect, and the ADC system is required to be capable of detecting 100% of the fragments and cracks, and the omission factor is 0%. However, the crack defect of the glass plate cannot be accurately detected at present, so that the quality of the glass plate is affected.
In order to solve the technical problems, the application provides a method, a device, equipment and a medium for detecting glass plate cracks, and before introducing the specific technical scheme of the application, the hardware operation environment related to the scheme of the embodiment of the application is introduced.
Referring to fig. 1, fig. 1 is a schematic diagram of a computer device structure of a hardware running environment according to an embodiment of the present application.
As shown in fig. 1, the computer device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the architecture shown in fig. 1 is not limiting of a computer device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a data storage module, a network communication module, a user interface module, and an electronic program may be included in the memory 1005 as one type of storage medium.
In the computer device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the computer device may be provided in the computer device, where the computer device invokes the glass plate crack detection device stored in the memory 1005 through the processor 1001, and executes the glass plate crack detection method provided in the embodiment of the application.
Referring to fig. 2, based on the hardware environment of the foregoing embodiment, an embodiment of the present application provides a glass sheet crack detection method, which includes:
s10: based on the segmentation threshold value, obtaining a detection area corresponding to the target glass plate on the target glass carrier plate image; the segmentation threshold is obtained based on pixel statistics of a plurality of glass carrier plate images.
In a specific implementation process, the target glass plate refers to a glass plate needing crack detection, the segmentation threshold is obtained by counting pixels of a plurality of glass carrier images, for example, counting pixel ranges of a plurality of glass carrier images, and then selecting a dividing line of the pixel ranges according to actual conditions, wherein the dividing line is used as the segmentation threshold. Thus, a more accurate segmentation threshold value can be obtained, and finally a more accurate detection area of the target glass plate is obtained; as shown in fig. 3, fig. 3 is a schematic diagram of an obtained detection area according to an embodiment of the present application.
S11: dividing the detection area of the target glass plate based on the gray threshold of the detection area to obtain a preliminary screening crack area of the target glass plate.
In the implementation process, the gray threshold of the detection area can be set according to actual requirements, and the detection threshold is segmented according to the gray threshold of the detection area so as to obtain a preliminary screening crack area of the target glass plate, wherein the preliminary screening crack area can be regarded as a suspected broken piece crack area of the target glass plate. After the primary screening crack region is obtained, the region range of the crack of the target glass plate can be further reduced, so that the final crack region can be further and more conveniently found.
S12: comparing the average gray value of the primary screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet; wherein the non-crack region is a region outside of the pre-screened crack region of the target glass sheet.
In the specific implementation process, after the primary screening crack region is obtained, the final crack region of the target glass plate is obtained by comparing the average gray value of the primary screening crack region with the average gray value of the region except the primary screening crack, namely the non-crack region, and the final crack region is smaller than the range of the primary screening crack region, so that the region range of the crack of the target glass plate can be further reduced, and the crack of the target glass plate can be more accurately detected.
In this embodiment, when a crack region of a target glass plate needs to be detected, a detection region of the target glass plate is obtained according to a segmentation threshold value obtained in advance, then the detection region is segmented according to a gray threshold value of the detection region, so as to obtain a preliminary screening crack region of the target glass plate, and finally average gray values of the preliminary screening crack region and a non-crack region are compared, so as to obtain a final crack region of the target glass plate. The method comprises the steps of finding a detection area of a target glass plate containing a broken piece crack through a segmentation threshold value obtained in advance, finding a preliminary screening crack area containing the broken piece crack in the detection area, and finally finding a final crack area in the preliminary screening crack area according to average threshold value comparison. Therefore, the area containing the broken piece crack can be gradually reduced, and the broken piece crack defect of the target glass plate can be accurately detected in a smaller area, so that the quality of the target glass plate can be improved.
In some embodiments, a preferred method of how to obtain the segmentation threshold is provided, that is, before the step of obtaining the detection region corresponding to the target glass plate on the target glass carrier plate image based on the segmentation threshold, the method further includes:
acquiring a range of first gray values of actual edges of glass plates in a plurality of glass carrier images based on the plurality of glass carrier images, and acquiring a range of second gray values of image black edges of the glass plates in the plurality of glass carrier images; obtaining a segmentation threshold based on the range of first gray values and the range of second gray values; the segmentation threshold is greater than the second gray level value and less than the first gray level value.
In this embodiment, the glass plate of this embodiment refers to a history glass plate, which refers to a glass plate preceding the target glass plate. The determination of the distribution of the first gray value of the actual edge of the historical glass plate and the second gray value range of the black edge of the image is a statistical process, namely, counting hundreds of gray values of the black edge and the actual glass edge in the same production and photographing environment, so that the second gray value distribution range of the black edge of the image and the first gray value distribution range of the actual edge can be obtained, and the intermediate values of the two gray value ranges (namely, the range of the first gray value and the range of the second gray value) are selected as the segmentation threshold; wherein "intermediate value" may be understood as letting all black pixel gray values (second gray values) be below this intermediate value, i.e. all second gray values are smaller than the segmentation threshold; all the pixel gray values (first gray values) of the actual edges of the glass are above the segmentation threshold, i.e. all the first gray values are greater than the segmentation threshold; since a large number of history glass plates are counted, the segmentation threshold can be obtained more accurately through the mode.
In some embodiments, as shown in fig. 4, a preferred method for obtaining the detection area is provided, that is, based on the segmentation threshold, to obtain the detection area corresponding to the target glass plate on the image of the target glass carrier plate, including:
s101: and obtaining an circumscribed rectangular frame of the edge of the target glass plate on the target glass carrier plate image based on the segmentation threshold value.
In the specific implementation process, the target glass plate is subjected to binary segmentation based on the segmentation threshold value, the edge of the target glass plate can be obtained, and then the four edges of the target glass plate can be extracted to form an external rectangular image.
S102: and obtaining the detection area based on the circumscribed rectangular frame.
In the specific implementation process, based on the circumscribed rectangular frame, obtaining a detection edge of the target glass plate; based on the detection edge, a first detection zone of the target glass sheet is obtained.
The method for obtaining the detection edge of the target glass plate based on the circumscribed rectangular frame comprises the following steps: and cutting off four cut corners of the circumscribed rectangular image of the edge of the target glass plate to obtain the detection edge of the target glass plate. 5-8, FIG. 5 is a schematic diagram illustrating cutting off a first corner cut of a circumscribed rectangular image according to an embodiment of the present application; FIG. 6 is a schematic diagram of a second corner cut for cutting off a circumscribed rectangular image according to an embodiment of the present application; FIG. 7 is a schematic view of a third corner cut for cutting off a circumscribed rectangular image according to an embodiment of the present application; FIG. 8 is a schematic view of a fourth corner cut of a cut-out circumscribed rectangular image according to an embodiment of the present application; because the four corners and the top positions of the glass edge are cut off in actual production, the accurate pixel coordinates of the four top points of the glass edge are required to be extracted, the corner cutting areas of the top points are drawn, and the four corner cutting areas of the edge are cut off in the obtained circumscribed rectangular image, so that the detection edge of the target glass plate can be obtained.
The obtaining a first detection area of the target glass sheet based on the detection edge includes: and sequentially expanding the detection edge of the target glass plate inwards by preset pixels to obtain a first detection area of the target glass plate. The preset pixels may be set according to actual needs, for example, the preset pixels may be twenty pixels, that is, four sides of the detection edge of the target glass plate are sequentially expanded inwards by twenty pixels, so as to obtain a first detection area of the target glass plate, where "inward expansion" refers to expansion toward the center of the target glass plate. In conclusion, the circumscribed rectangular frame can narrow and clear the range of the corresponding part on the target glass carrier plate image, so that a more accurate detection area can be obtained; since the crack region of the target glass sheet is located within the detection edge, it can be more ensured that the crack region is located within the first detection region.
In some embodiments, after the step of obtaining the first detection region of the target glass sheet based on the detection edge of the target glass sheet, further comprising: clipping a clamping area of the first detection area of the target glass plate to obtain a second detection area; the area ratio of the glass plate crack in the second detection area is higher than that of the glass plate crack in the first detection area;
dividing the detection area of the target glass plate based on the gray threshold of the detection area to obtain a preliminary screening crack area of the target glass plate, wherein the preliminary screening crack area comprises the following steps: dividing the second detection region of the target glass plate based on the gray threshold of the second detection region to obtain a preliminary screening crack region of the target glass plate.
In this embodiment, in actual production, glass moves through the clamping structure, and each glass has clamping areas with the same size at four sides of the clamping structure, so that the clamping area of the first detection area of the target glass plate needs to be cut out, the first detection area after the clamping area is cut out is the second detection area, the obtained second detection area is more simplified than the first detection area in scope, and therefore the area where the crack area is located is further reduced, as shown in fig. 9, and fig. 9 is a schematic diagram of the second detection area provided in this embodiment of the application. And then calculating the average gray value of the second detection area to obtain the gray threshold value of the second detection area. The gray threshold may be set according to actual situations, for example, a half of an average gray value of the second detection area is used as the gray threshold of the second detection area, and then the second detection area of the target glass plate is divided based on the gray threshold of the second detection area, so as to obtain the preliminary screening crack area of the target glass plate. Since the average gray value of the second detection region may include information of all gray values of the second detection region, the gray threshold value is obtained by averaging the gray values, so that the gray threshold value of the second detection region may be more accurate.
In some embodiments, a preferred method of obtaining a final crack region is provided, namely said comparing an average gray value of a pre-screened crack region of said target glass sheet with an average gray value of a non-cracked region of said target glass sheet to obtain a final crack region of said target glass sheet, comprising: and filtering a region of which the average gray value of the central region of the primary screening crack region is higher than the preset proportion of the average gray value of the non-crack region so as to obtain a final crack region of the target glass plate.
In this embodiment, as shown in fig. 10, fig. 10 is a schematic diagram of a broken central area and an edge non-broken area provided in the embodiment of the present application. The preset proportion may be set according to actual needs, for example, the preset proportion is set to be one half, that is, an area with an average gray value of a central area (a broken central area) of the initial screen crack area being higher than that of the non-crack area (an edge non-broken area) is filtered, so as to obtain a final crack area of the target glass plate, so that an area where the crack area is located can be further reduced and clarified, a more accurate crack area can be obtained through the final crack area, and after the crack area of the target glass plate is processed, the quality of the target glass plate can be greatly improved, as shown in fig. 11, and fig. 11 is a schematic diagram of the final crack area provided in the embodiment of the application.
In summary, the real incidence of broken piece cracks is extremely low, sample collection is difficult, and if a deep learning scheme is used for detecting the defects, a large number of training samples are needed, so that the method is not feasible in reality. According to the method, the characteristic of image edge gray value distribution is utilized, and the area range where the crack defects are located is greatly reduced by combining a computer vision processing method, so that the detection and positioning functions of the crack defects of the carrier plate fragments are realized, and the crack defects of the target glass plate fragments in panel production can be detected more accurately.
In another embodiment, as shown in fig. 12, based on the same inventive concept as the previous embodiment, an embodiment of the present application further provides a glass sheet crack detection device, including:
the acquisition module is used for acquiring a detection area corresponding to the target glass plate on the target glass carrier plate image based on the segmentation threshold value; the segmentation threshold is obtained based on pixel statistics of a plurality of glass carrier plate images;
the dividing module is used for dividing the detection area of the target glass plate based on the gray threshold value of the detection area so as to obtain a preliminary screening crack area of the target glass plate;
a comparison module for comparing the average gray value of the primary screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet; wherein the non-crack region is a region outside of the pre-screened crack region of the target glass sheet.
It should be noted that, each module in the glass plate crack detection device in this embodiment corresponds to each step in the glass plate crack detection method in the foregoing embodiment one by one, so the specific implementation manner and the achieved technical effect of this embodiment may refer to the implementation manner of the foregoing glass plate crack detection method, and will not be described herein again.
Furthermore, in an embodiment, the present application also provides a computer device, which includes a processor, a memory, and a computer program stored in the memory, which when executed by the processor, implements the method in the foregoing embodiment.
Furthermore, in an embodiment, the present application also provides a computer storage medium, on which a computer program is stored, which when being executed by a processor, implements the method in the foregoing embodiment.
In some embodiments, the computer readable storage medium may be FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; but may be a variety of devices including one or any combination of the above memories. The computer may be a variety of computing devices including smart terminals and servers.
In some embodiments, the executable instructions may be in the form of programs, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and they may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.
As an example, the executable instructions may, but need not, correspond to files in a file system, may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a hypertext markup language (HTML, hyper Text Markup Language) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
As an example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices located at one site or, alternatively, distributed across multiple sites and interconnected by a communication network.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
From the above description of embodiments, it will be clear to a person skilled in the art that the above embodiment method may be implemented by means of software plus a necessary general hardware platform, but may of course also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. read-only memory/random-access memory, magnetic disk, optical disk), comprising several instructions for causing a multimedia terminal device (which may be a mobile phone, a computer, a television receiver, or a network device, etc.) to perform the method described in the embodiments of the present application.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the claims, and all equivalent structures or equivalent processes using the descriptions and drawings of the present application, or direct or indirect application in other related technical fields are included in the scope of the claims of the present application.
Claims (14)
1. A method of glass sheet crack detection, the method comprising:
based on the segmentation threshold value, obtaining a detection area corresponding to the target glass plate on the target glass carrier plate image; the segmentation threshold is obtained based on pixel statistics of a plurality of glass carrier plate images;
dividing the detection area of the target glass plate based on the gray threshold of the detection area to obtain a preliminary screening crack area of the target glass plate;
comparing the average gray value of the primary screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet; wherein the non-crack region is a region outside of a pre-screened crack region of the target glass sheet; the comparing the average gray value of the pre-screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet comprises:
and filtering a region of which the average gray value of the central region of the primary screening crack region is higher than the preset proportion of the average gray value of the non-crack region so as to obtain a final crack region of the target glass plate.
2. The method for detecting glass plate cracks according to claim 1, wherein the obtaining a detection area corresponding to the target glass plate on the target glass carrier plate image based on the segmentation threshold value comprises:
based on a segmentation threshold value, obtaining an external rectangular frame of the edge of the target glass plate on the target glass carrier plate image;
and obtaining the detection area based on the circumscribed rectangular frame.
3. The glass sheet crack detection method according to claim 2, wherein the obtaining the detection area based on the circumscribed rectangular frame includes:
obtaining a detection edge of the target glass plate based on the circumscribed rectangular frame;
based on the detection edge, a first detection zone of the target glass sheet is obtained.
4. The glass sheet crack detection method according to claim 3, wherein the obtaining the detection edge of the target glass sheet based on the circumscribed rectangular frame comprises:
and cutting off four cut corners of the circumscribed rectangular frame of the edge of the target glass plate to obtain the detection edge of the target glass plate.
5. The glass sheet crack detection method according to claim 3, wherein the obtaining a first detection area of the target glass sheet based on the detection edge comprises:
and sequentially expanding the detection edge of the target glass plate inwards by preset pixels to obtain a first detection area of the target glass plate.
6. The glass sheet crack detection method according to claim 5, wherein sequentially expanding the detection edge of the target glass sheet inward by a preset number of pixels to obtain a first detection area of the target glass sheet comprises:
and sequentially expanding twenty pixels inwards from four sides of the detection edge of the target glass plate to obtain a first detection area of the target glass plate.
7. The glass sheet crack detection method according to claim 3, further comprising, after the step of obtaining the first detection area of the target glass sheet based on the detection edge:
clipping a clamping area of the first detection area of the target glass plate to obtain a second detection area; the area ratio of the glass plate crack in the second detection area is higher than that of the glass plate crack in the first detection area;
dividing the detection area of the target glass plate based on the gray threshold of the detection area to obtain a preliminary screening crack area of the target glass plate, wherein the preliminary screening crack area comprises the following steps:
dividing the second detection region of the target glass plate based on the gray threshold of the second detection region to obtain a preliminary screening crack region of the target glass plate.
8. The glass sheet crack detection method according to claim 7, further comprising, prior to the step of dividing the second detection region of the target glass sheet based on the gray level threshold of the second detection region to obtain a preliminary screening crack region of the target glass sheet:
and calculating the average gray value of the second detection area to obtain a gray threshold value of the second detection area.
9. The glass sheet crack detection method according to claim 8, wherein the calculating the average gray value of the second detection region to obtain the gray threshold value of the second detection region includes:
and calculating the average gray value of the second detection area, and taking one half of the average gray value of the second detection area as a gray threshold value of the second detection area.
10. The glass sheet crack detection method according to claim 1, wherein the filtering the area of the center area of the preliminary screening crack area having an average gray value higher than a preset proportion of the average gray value of the non-crack area to obtain a final crack area of the target glass sheet comprises:
filtering a region of the primary screening crack region having an average gray value higher than one-half the average gray value of the non-crack region to obtain a final crack region of the target glass sheet.
11. The glass sheet crack detection method according to any one of claims 1 to 10, further comprising, prior to the step of obtaining a detection region corresponding to the target glass sheet on the target glass carrier image based on the segmentation threshold value:
acquiring a range of first gray values of actual edges of glass plates in a plurality of glass carrier images based on the plurality of glass carrier images, and acquiring a range of second gray values of image black edges of the glass plates in the plurality of glass carrier images;
obtaining a segmentation threshold based on the range of first gray values and the range of second gray values; the segmentation threshold is greater than the second gray level value and less than the first gray level value.
12. A glass sheet crack detection device, the device comprising:
the acquisition module is used for acquiring a detection area corresponding to the target glass plate on the target glass carrier plate image based on the segmentation threshold value; the segmentation threshold is obtained based on pixel statistics of a plurality of glass carrier plate images;
the dividing module is used for dividing the detection area of the target glass plate based on the gray threshold value of the detection area so as to obtain a preliminary screening crack area of the target glass plate;
a comparison module for comparing the average gray value of the primary screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet; wherein the non-crack region is a region outside of a pre-screened crack region of the target glass sheet; the comparing the average gray value of the pre-screened crack region of the target glass sheet with the average gray value of the non-crack region of the target glass sheet to obtain a final crack region of the target glass sheet comprises:
and filtering a region of which the average gray value of the central region of the primary screening crack region is higher than the preset proportion of the average gray value of the non-crack region so as to obtain a final crack region of the target glass plate.
13. A computer device, characterized in that it comprises a memory in which a computer program is stored and a processor which executes the computer program, implementing the method according to any of claims 1-11.
14. A computer readable storage medium, having stored thereon a computer program, the computer program being executable by a processor to implement the method of any of claims 1-11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310079413.2A CN115937212B (en) | 2023-02-08 | 2023-02-08 | Glass plate crack detection method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310079413.2A CN115937212B (en) | 2023-02-08 | 2023-02-08 | Glass plate crack detection method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115937212A CN115937212A (en) | 2023-04-07 |
| CN115937212B true CN115937212B (en) | 2023-05-09 |
Family
ID=85823706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310079413.2A Active CN115937212B (en) | 2023-02-08 | 2023-02-08 | Glass plate crack detection method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115937212B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116485350B (en) * | 2023-06-20 | 2023-09-01 | 山东鲁玻玻璃科技有限公司 | Intelligent production system of medium borosilicate glass based on image recognition |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179243A (en) * | 2019-12-25 | 2020-05-19 | 武汉昕竺科技服务有限公司 | Small-size chip crack detection method and system based on computer vision |
| CN113822890A (en) * | 2021-11-24 | 2021-12-21 | 中科慧远视觉技术(北京)有限公司 | Microcrack detection method, device and system and storage medium |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104240252A (en) * | 2014-09-22 | 2014-12-24 | 电子科技大学 | Detecting Algorithm for cracks of surface of high-temperature billet of machine vision bar |
| CN108364280B (en) * | 2018-01-03 | 2022-04-15 | 东南大学 | Method and equipment for automatically describing structural crack and accurately measuring width |
| JP7225810B2 (en) * | 2019-01-11 | 2023-02-21 | 富士通株式会社 | Crack line extraction device, crack line extraction method, and crack line extraction program |
| CN109886921A (en) * | 2019-01-16 | 2019-06-14 | 新而锐电子科技(上海)有限公司 | Crack size measure, device and electronic equipment based on digital picture |
| CN111986174A (en) * | 2020-08-17 | 2020-11-24 | 深圳市商汤科技有限公司 | Defect detection method, defect detection device, electronic equipment and computer storage medium |
| CN113109368B (en) * | 2021-03-12 | 2023-09-01 | 浙江华睿科技股份有限公司 | Glass crack detection method, device, equipment and medium |
| CN113240667A (en) * | 2021-06-08 | 2021-08-10 | 长春汽车工业高等专科学校 | Automobile mold plane crack detection method based on image processing |
| CN113379737A (en) * | 2021-07-14 | 2021-09-10 | 西南石油大学 | Intelligent pipeline defect detection method based on image processing and deep learning and application |
| CN115187602A (en) * | 2022-09-13 | 2022-10-14 | 江苏骏利精密制造科技有限公司 | Injection molding part defect detection method and system based on image processing |
| CN115311290A (en) * | 2022-10-12 | 2022-11-08 | 南通市通州区精华电器有限公司 | Method for detecting defects of metal parts of precision instrument |
| CN115631198B (en) * | 2022-12-21 | 2023-08-08 | 深圳新视智科技术有限公司 | Crack detection method and device for glass display screen and computer equipment |
-
2023
- 2023-02-08 CN CN202310079413.2A patent/CN115937212B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179243A (en) * | 2019-12-25 | 2020-05-19 | 武汉昕竺科技服务有限公司 | Small-size chip crack detection method and system based on computer vision |
| CN113822890A (en) * | 2021-11-24 | 2021-12-21 | 中科慧远视觉技术(北京)有限公司 | Microcrack detection method, device and system and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115937212A (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111507958B (en) | Target detection method, training method of detection model and electronic equipment | |
| CN114266773B (en) | Display panel defect positioning method, device, equipment and storage medium | |
| CN115937212B (en) | Glass plate crack detection method, device, equipment and medium | |
| CN106202086B (en) | Picture processing and obtaining method, device and system | |
| CN116542975B (en) | Defect classification method, device, equipment and medium for glass panel | |
| CN115578377B (en) | Panel defect detection method, training method, device, equipment and medium | |
| CN106910195B (en) | Webpage layout monitoring method and device | |
| CN113538603B (en) | Optical detection method and system based on array product and readable storage medium | |
| CN110837809A (en) | Blood automatic analysis method, blood automatic analysis system, blood cell analyzer, and storage medium | |
| CN115545058A (en) | Water meter data analysis method and system and readable storage medium | |
| CN115861327A (en) | PCB color change defect detection method, device, equipment and medium | |
| CN111597845A (en) | Two-dimensional code detection method, device and equipment and readable storage medium | |
| CN110264489B (en) | Image boundary detection method and device and terminal | |
| CN116091503B (en) | Method, device, equipment and medium for discriminating panel foreign matter defects | |
| CN115797314A (en) | Part surface defect detection method, system, equipment and storage medium | |
| CN114241356A (en) | Wood board color identification method and device, electronic equipment and storage medium | |
| CN114511862A (en) | Form identification method and device and electronic equipment | |
| CN114740284A (en) | Method and device for detecting touch screen panel | |
| CN101819632A (en) | Be used for content aware system and method | |
| CN114463242A (en) | Image detection method, device, storage medium and device | |
| CN114677319A (en) | Stem cell distribution determination method and device, electronic equipment and storage medium | |
| CN112163581B (en) | License plate letter recognition method, system, device and storage medium | |
| CN113706556B (en) | Rapid detection and replacement method for image slice edge fragments | |
| CN117495842A (en) | Panel color leakage process defect detection method, system, equipment and medium | |
| CN106934814B (en) | Background information identification method and device based on image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |