A method and system for detecting breakage of an OLED display glass backplane

Abstract

This invention provides a method and system for detecting damage to the glass back panel of an OLED display, relating to the field of defect detection technology. The method includes: performing grayscale conversion and image enhancement processing on the original glass back panel image P0 to obtain an enhanced glass back panel image P1; performing threshold segmentation processing on the enhanced glass back panel image P1 to obtain the contour coordinates of the glass back panel; removing edge protrusion noise from the binarized glass back panel image P2 to obtain a standard glass back panel contour image P3; generating a glass back panel mask image P4 using the contour coordinates of the glass back panel; performing differential processing between the glass back panel mask image P4 and the standard glass back panel contour image P3 to obtain a glass back panel damage detection image P5; and determining whether the glass back panel is damaged based on the glass back panel damage detection image P5. This solves the problem in the prior art of OLED display glass back panel defect detection where the small difference between the defect and the background leads to over-detection or under-detection.

Description

Technical Field

[0001] This invention relates to the field of defect detection technology, and more specifically, to a method and system for detecting damage to the glass back panel of an OLED display screen. Background Technology

[0002] OLED (Organic Light Emitting Diode) devices, also known as organic electroluminescent diode devices, have attracted widespread attention due to their advantages such as self-illumination, rich colors, fast response speed, wide viewing angle, light weight, thinness, low power consumption, and the ability to realize flexible displays. Moreover, OLED displays made using OLED devices are regarded as displays with huge application prospects.

[0003] During the production of OLED displays, industrial cameras are used to capture images, which are then processed and classified using an ADC (Automatic Defect Classification) system. However, due to factors such as process variations, machine differences, and lighting conditions, the defect areas in the captured images may be very similar to the background. This can lead to over-detection or under-detection issues when using deep learning for defect detection. Summary of the Invention

[0004] To address the issue of over-detection or under-detection due to the small difference between defects and the background during OLED display glass back panel defect detection in the prior art, this invention provides a method and system for OLED display glass back panel damage detection.

[0005] In a first aspect, embodiments of the present invention provide a method for detecting damage to the glass back panel of an OLED display, the method comprising the following steps:

[0006] (1) Obtain the original image P0 of the glass back panel of the OLED display, perform grayscale conversion and image enhancement processing on the original image P0 of the glass back panel to obtain the enhanced image P1 of the glass back panel.

[0007] (2) Threshold segmentation is performed on the glass back plate enhancement image P1 to obtain the contour coordinates of the glass back plate;

[0008] (3) Remove the edge protrusion noise of the binarized glass back plate image P2 to obtain the standard outline image P3 of the glass back plate. Use the outline coordinates of the glass back plate to generate a glass back plate mask image P4 with the same size as the original glass back plate image P0. Perform differential processing on the glass back plate mask image P4 and the standard outline image P3 of the glass back plate to obtain the glass back plate damage detection image P5.

[0009] (4) Determine whether the glass back panel is damaged based on the glass back panel damage detection diagram P5.

[0010] In the above embodiments, by adaptive threshold segmentation, the enhanced glass backplane image P1 after image enhancement processing is threshold segmented to accurately find the coordinate frame Box of the glass backplane region of the OLED display; and by differential processing of the coordinate frame Box of the glass backplane region, defects in the edge region of the glass backplane region of the OLED display are accurately found, reducing the over-detection or under-detection problem of the ADC system for defect detection and improving the defect recognition accuracy.

[0011] As one of the optional embodiments of this application, the formula for image enhancement processing of the original glass backplate image P0 after grayscale conversion is as follows:

[0012] dst(I) = src(I) * alpha + beta

[0013] Where src(I) is the pixel value of the original glass backplate image P0 before image enhancement processing, dst(I) is the pixel value of the enhanced glass backplate image P1 after image enhancement processing, and alpha and beta are constants.

[0014] As one of the optional embodiments of this application, the process for obtaining the contour coordinates of the glass back plate is as follows:

[0015] (2.1) Each pixel in the enhanced glass backplate image P1 after image enhancement is denoted as V. x,y And for each pixel V x,y Threshold segmentation is performed to obtain the binarized image P2 of the glass backplate;

[0016] (2.2) Denoising and contour extraction are performed on the binarized image P2 of the glass back plate to obtain the set of contour region points Cnts. all ;

[0017] (2.3) Based on the contour region point set Cnts all Calculate the contour area and obtain the set of points Cnt that has the largest contour area. maxArea ;

[0018] (2.4) Based on the contour region point set Cnt maxArea Get the midline x of the contour region c Set the contour region points Cnt maxArea The x-coordinates of all points in the region are defined by the median x-axis. c The left and right regions are divided using a threshold, resulting in x-coordinates x. l x r ;

[0019] (2.5) Based on the contour region point set Cnt maxArea Get the midline y of the contour region c Set the contour region points Cnt maxArea The y-coordinates of all points in the region are defined by the median line y. c The upper and lower regions are divided using a threshold, resulting in their y-coordinates. u y d The coordinates of the upper left corner of the glass back panel outline (x) are obtained. l ,y u ), lower right corner coordinates (x r ,y d ).

[0020] As some alternative embodiments of this application, the method uses morphological opening operations to remove white noise in the binarized image P2 of the glass backplate.

[0021] As some optional implementations of this application, based on the contour region point set Cnts all The formula for calculating the area of ​​the outline is:

[0022]

[0023] Where (x,y) is the set of points Cnts in the contour region. all The coordinates of the point.

[0024] As some optional embodiments of this application, the left and right region coordinates x l x r The acquisition process is as follows:

[0025] (2.41) Extract the set of points Cnt in the contour region maxArea Find the x-coordinate of all points and obtain the minimum x-coordinate. min Maximum value x max ;

[0026] (2.42) Calculate the median x c =(x min +x max ) / 2, and with the middle line x c The set of contour region points Cnt is set to a threshold. maxArea The x-coordinates of all points are divided into two sets P. l P r ;

[0027] (2.43) For binding P l P r Histograms are performed on the y-coordinates of all points, and the x-coordinate corresponding to the maximum value in the histogram is obtained, thus yielding the x-coordinates of the left and right regions. l x r.

[0028] As some optional implementations of this application, the upper and lower region coordinates y u y d The acquisition process is as follows:

[0029] (2.51) Extract the set of points Cnt in the contour region maxArea Find the y-coordinate of all points and obtain the minimum y-coordinate. min Maximum value y max ;

[0030] (2.52) Calculate the median line y c =(y min +y max ) / 2, and with the middle line y c The set of contour region points Cnt is set to a threshold. maxArea The y-coordinates of all points are divided into two sets P. u P d ;

[0031] (2.53) For binding P u P d Histograms are performed on the x-coordinates of all points, and the y-coordinate corresponding to the maximum value in the histogram is obtained, thus yielding the upper and lower region coordinates. u y d .

[0032] As one of the optional implementations of this application, the process for generating a glass backplate mask image P4 with the same dimensions as the original glass backplate image P0 is as follows:

[0033] (3.1) Based on the coordinates of the upper left corner of the glass back panel profile (x... l ,y u ) and the coordinates of the lower right corner (x r ,y d Construct the coordinate frame Box for the glass back panel area;

[0034] (3.2) Construct a white background image m1 with the same size as the original glass back panel image P0. Using the glass back panel area coordinate frame Box as the boundary, set the inside of the glass back panel area coordinate frame Box to white and the outside to black, thus obtaining the glass back panel mask image P4.

[0035] In a second aspect, the present invention provides a system for detecting damage to the glass back panel of an OLED display, the system comprising:

[0036] An image processing unit is used to acquire the original image P0 of the glass back panel of the OLED display, perform grayscale conversion processing and image enhancement processing on the original image P0 of the glass back panel to obtain an enhanced image P1 of the glass back panel.

[0037] A contour extraction unit is used to perform threshold segmentation processing on the glass back plate enhancement image P1 to obtain the contour coordinates of the glass back plate.

[0038] The differential processing unit removes edge protrusion noise from the binarized glass backplate image P2 to obtain a standard outline image P3 of the glass backplate. It then uses the outline coordinates of the glass backplate to generate a glass backplate mask image P4 with the same size as the original glass backplate image P0. Finally, it performs differential processing on the glass backplate mask image P4 and the standard outline image P3 to obtain a glass backplate damage detection image P5.

[0039] The defect detection unit determines whether the glass back panel is damaged based on the glass back panel damage detection diagram P5.

[0040] In a third aspect, the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor performing a method for detecting damage to the glass back panel of the OLED display.

[0041] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements a method for detecting damage to the glass back panel of an OLED display.

[0042] The beneficial effects of the present invention are as follows: The present invention performs threshold segmentation on the enhanced glass backplane image P1 after image enhancement processing through adaptive threshold segmentation, accurately finding the coordinate box Box of the glass backplane region of the OLED display; and performs differential processing on the coordinate box Box of the glass backplane region to accurately find defects in the edge region of the glass backplane region of the OLED display, reducing the over-detection or under-detection problem of the ADC system for defect detection and improving the defect identification accuracy. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart of a glass backplate damage detection method according to some embodiments of the present invention.

[0045] Figure 2 This is the original drawing P0 of the glass backplate according to some embodiments of the present invention.

[0046] Figure 3 This is a glass backplate reinforcement diagram P1 according to some embodiments of the present invention.

[0047] Figure 4 P2 is a binarized image of the glass backplate according to some embodiments of the present invention.

[0048] Figure 5 This is a schematic diagram of contour extraction processing according to some embodiments of the present invention.

[0049] Figure 6 This is a standard outline diagram P3 of the glass backplate according to some embodiments of the present invention.

[0050] Figure 7 This is a glass backplate mask diagram P4 according to some embodiments of the present invention.

[0051] Figure 8 Figure P5 shows the glass backplate breakage detection diagram according to some embodiments of the present invention. Detailed Implementation

[0052] To better understand the above technical solutions, the technical solutions of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solutions of the present invention, rather than limitations on the technical solutions of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0053] It should also be understood that, in order to simplify the description of the invention and thus aid in the understanding of at least one embodiment, multiple features may sometimes be grouped into a single embodiment, drawing, or description thereof in the foregoing description of the embodiments of the invention. However, this method of disclosure does not imply that the subject matter of the invention requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of the single embodiment disclosed above.

[0054] Example 1

[0055] This invention provides a method for detecting damage to the glass back panel of an OLED display. Please refer to [link / reference]. Figure 1 The method includes the following steps:

[0056] (1) Obtain the original image P0 of the glass backplate of the OLED display (see [reference]). Figure 2 The original glass backing image P0 was subjected to grayscale conversion and image enhancement processing to obtain the enhanced glass backing image P1 (see [link]). Figure 3 ).

[0057] In this embodiment of the invention, the formula for image enhancement processing of the original glass backplate image P0 after grayscale conversion is as follows:

[0058] dst(I) = src(I) * alpha + beta

[0059] Where src(I) represents the pixel values ​​of the original glass backplane image P0 before image enhancement processing, dst(I) represents the pixel values ​​of the enhanced glass backplane image P1 after image enhancement processing, and alpha and beta are constants that need to be calculated based on the actual average grayscale value Mean of the enhanced glass backplane image P1 after grayscale conversion processing. gray Debugging, Mean gray <=80, beta and alpha are 20 and 3 respectively.

[0060] (2) Threshold segmentation is performed on the glass back plate enhancement image P1 to obtain the contour coordinates of the glass back plate.

[0061] In this embodiment of the invention, the process for obtaining the contour coordinates of the glass back plate is as follows:

[0062] (2.1) Each pixel in the enhanced glass backplate image P1 after image enhancement is denoted as V. x,y And for each pixel V x,y Threshold segmentation is performed to obtain the binarized image P2 of the glass backplate (see [link]). Figure 4 The value is 255 for values ​​between the maximum and minimum values, and 0 for all other values.

[0063]

[0064] Here, thresh is a constant that is set.

[0065] (2.2) Morphological opening operations were used to remove white noise from the binarized glass backplate image P2, and the findContours contour detection method was used to extract the contours from the denoised glass backplate image P2 (see [link to relevant documentation]). Figure 5 Obtain the set of points Cnts in the contour region. all .

[0066] (2.3) Based on the contour region point set Cnts all Calculate the contour area and use Green's formula to obtain the set of points Cnt that maximizes the contour area. maxArea .

[0067] In this embodiment of the invention, based on the contour region point set Cnts all The formula for calculating the area of ​​the outline is:

[0068]

[0069] Where (x,y) is the set of points Cnts in the contour region. all The coordinates of the point.

[0070] (2.4) Based on the contour region point set Cnt maxArea Get the midline x of the contour region c Set the contour region points Cnt maxArea The x-coordinates of all points in the region are defined by the median x-axis. c The left and right region coordinates x are obtained by using the threshold as a dividing line. l x r .

[0071] In this embodiment of the invention, the coordinates x of the left and right regions are... l x r The acquisition process is as follows:

[0072] (2.41) Extract the set of points Cnt in the contour region maxArea Find the x-coordinate of all points and obtain the minimum x-coordinate. min Maximum value x max .

[0073] (2.42) Calculate the median x c =(x min +x max ) / 2, and with the middle line x c The set of contour region points Cnt is set to a threshold. maxArea The x-coordinates of all points are divided into two sets P. l P r .

[0074] (2.43) For binding P l P r Histograms are performed on the y-coordinates of all points, and the x-coordinate corresponding to the maximum value in the histogram is obtained, thus yielding the x-coordinates of the left and right regions. l x r .

[0075] (2.5) Based on the contour region point set Cnt maxArea Get the midline y of the contour region c Set the contour region points Cnt maxArea The y-coordinates of all points in the region are defined by the median line y. c The upper and lower regions are divided using a threshold, resulting in their y-coordinates. u y d Therefore, the coordinates of the upper left corner of the glass back panel profile are (x... l ,y u The coordinates of the lower right corner are (xr ,y d ).

[0076] In this embodiment of the invention, the coordinates y of the upper and lower regions are... u y d The acquisition process is as follows:

[0077] (2.51) Extract the set of points Cnt in the contour region maxArea Find the y-coordinate of all points and obtain the minimum y-coordinate. min Maximum value y max .

[0078] (2.52) Calculate the median line y c =(y min +y max ) / 2, and with the middle line y c The set of contour region points Cnt is set to a threshold. maxArea The y-coordinates of all points are divided into two sets P. u P d .

[0079] (2.53) For binding P u P d Histograms are performed on the x-coordinates of all points, and the y-coordinate corresponding to the maximum value in the histogram is obtained, thus yielding the upper and lower region coordinates. u y d .

[0080] (3) Remove the edge protrusion noise (i.e., outward-facing noise) from the binarized image P2 of the glass backplate to obtain the standard profile image P3 of the glass backplate (see [reference]). Figure 6 (The remaining inward-protruding breakage); Use the contour coordinates of the glass backing to generate a glass backing mask P4 with the same dimensions as the original glass backing image P0 (see [reference]). Figure 7 Furthermore, the glass back panel mask image P4 and the standard outline image P3 of the glass back panel are differentially processed to obtain the glass back panel damage detection image P5 (see [link to relevant documentation]). Figure 8 ).

[0081] In this embodiment of the invention, the process for generating a glass backplate mask image P4 with the same dimensions as the original glass backplate image P0 is as follows:

[0082] (3.1) Based on the coordinates of the upper left corner of the glass back panel profile (x... l ,y u ) and the coordinates of the lower right corner (x r ,y d Construct the coordinate frame Box for the glass back panel area.

[0083] (3.2) Construct a white background image m1 with the same size as the original glass back panel image P0. Using the glass back panel area coordinate frame Box as the boundary, set the inside of the glass back panel area coordinate frame Box to white and the outside to black, thus obtaining the glass back panel mask image P4.

[0084] (4) Determine whether the glass back panel is damaged based on the glass back panel damage detection diagram P5.

[0085] The determination of whether the glass back panel is damaged is based on the ADC system. That is, the glass back panel damage detection image P5 is input into the ADC system to determine whether there is a damage defect.

[0086] In summary, this invention uses adaptive threshold segmentation to perform threshold segmentation on the enhanced glass backplane image P1 after image enhancement processing, accurately identifying the coordinate frame Box of the glass backplane region of the OLED display; and performs differential processing on the coordinate frame Box of the glass backplane region to accurately identify defects in the edge region of the glass backplane region of the OLED display, reducing the over-detection or under-detection problems of the ADC system for defect detection and improving the defect identification accuracy.

[0087] Example 2

[0088] This invention provides a system for detecting damage to the glass back panel of an OLED display screen, the system comprising:

[0089] An image processing unit is used to acquire the original image P0 of the glass back panel of the OLED display, perform grayscale conversion processing and image enhancement processing on the original image P0 of the glass back panel to obtain an enhanced image P1 of the glass back panel.

[0090] ① Contour extraction unit, the contour extraction unit is used to perform threshold segmentation processing on the glass back plate enhancement image P1 to obtain the contour coordinates of the glass back plate;

[0091] In this embodiment of the invention, the formula for image enhancement processing of the original glass backplate image P0 after grayscale conversion is as follows:

[0092] dst(I) = src(I) * alpha + beta

[0093] Where src(I) represents the pixel values ​​of the original glass backplane image P0 before image enhancement processing, dst(I) represents the pixel values ​​of the enhanced glass backplane image P1 after image enhancement processing, and alpha and beta are constants that need to be calculated based on the actual average grayscale value Mean of the enhanced glass backplane image P1 after grayscale conversion processing. gray Debugging, Mean gray <=80, beta and alpha are 20 and 3 respectively.

[0094] ②The process of obtaining the contour coordinates of the glass back plate by the contour extraction unit is as follows:

[0095] (2.1) Each pixel in the enhanced glass backplate image P1 after image enhancement is denoted as V. x,y And for each pixel V x,y Threshold segmentation is performed to obtain the binarized image P2 of the glass backplate;

[0096] (2.2) Denoising and contour extraction are performed on the binarized image P2 of the glass back plate to obtain the set of contour region points Cnts. all ;

[0097] (2.3) Based on the contour region point set Cnts all Calculate the contour area and obtain the set of points Cnt that has the largest contour area. maxArea ;

[0098] In this embodiment of the invention, based on the contour region point set Cnts all The formula for calculating the area of ​​the outline is:

[0099]

[0100] Where (x,y) is the set of points Cnts in the contour region. all The coordinates of the point.

[0101] (2.4) Based on the contour region point set Cnt maxArea Get the midline x of the contour region c Set the contour region points Cnt maxArea The x-coordinates of all points in the region are defined by the median x-axis. c The left and right regions are divided using a threshold, resulting in x-coordinates x. l x r ;

[0102] In this embodiment of the invention, the coordinates x of the left and right regions are... l x r The acquisition process is as follows:

[0103] (2.41) Extract the set of points Cnt in the contour region maxArea Find the x-coordinate of all points and obtain the minimum x-coordinate. min Maximum value x max ;

[0104] (2.42) Calculate the median x c =(x min +x max ) / 2, and with the middle line x c The set of contour region points Cnt is set to a threshold. maxAreaThe x-coordinates of all points are divided into two sets P. l P r ;

[0105] (2.43) For binding P l P r Histograms are performed on the y-coordinates of all points, and the x-coordinate corresponding to the maximum value in the histogram is obtained, thus yielding the x-coordinates of the left and right regions. l x r .

[0106] (2.5) Based on the contour region point set Cnt maxArea Get the midline y of the contour region c Set the contour region points Cnt maxArea The y-coordinates of all points in the region are defined by the median line y. c The upper and lower regions are divided using a threshold, resulting in their y-coordinates. u y d The coordinates of the upper left corner of the glass back panel outline (x) are obtained. l ,y u ), lower right corner coordinates (x r ,y d ).

[0107] In this embodiment of the invention, the coordinates y of the upper and lower regions are... u y d The acquisition process is as follows:

[0108] (2.51) Extract the set of points Cnt in the contour region maxArea Find the y-coordinate of all points and obtain the minimum y-coordinate. min Maximum value y max ;

[0109] (2.52) Calculate the median line y c =(y min +y max ) / 2, and with the middle line y c The set of contour region points Cnt is set to a threshold. maxArea The y-coordinates of all points are divided into two sets P. u P d ;

[0110] (2.53) For binding P u P d Histograms are performed on the x-coordinates of all points, and the y-coordinate corresponding to the maximum value in the histogram is obtained, thus yielding the upper and lower region coordinates. u y d .

[0111] ③ Differential processing unit: The differential processing unit removes edge protrusion noise from the binarized glass back plate image P2 to obtain the standard outline image P3 of the glass back plate. It uses the outline coordinates of the glass back plate to generate a glass back plate mask image P4 with the same size as the original glass back plate image P0. The glass back plate mask image P4 and the standard outline image P3 of the glass back plate are differentially processed to obtain the glass back plate damage detection image P5.

[0112] In this embodiment of the invention, the process by which the differential processing unit generates a glass backplate mask image P4 with the same dimensions as the original glass backplate image P0 is as follows:

[0113] (3.1) Based on the coordinates of the upper left corner of the glass back panel profile (x... l ,y u ) and the coordinates of the lower right corner (x r ,y d Construct the coordinate frame Box for the glass back panel area;

[0114] (3.2) Construct a white background image m1 with the same size as the original glass back panel image P0. Using the glass back panel area coordinate frame Box as the boundary, set the inside of the glass back panel area coordinate frame Box to white and the outside to black, thus obtaining the glass back panel mask image P4.

[0115] ④ Defect detection unit: The defect detection unit determines whether the glass back panel is damaged based on the glass back panel damage detection image P5. The determination of whether the glass back panel is damaged is based on the ADC system. That is, the glass back panel damage detection image P5 is input into the ADC system to determine whether there is a damage defect.

[0116] Example 3

[0117] This invention provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the computer program executes the OLED display glass back panel breakage detection method described in Embodiment 1 when the processor is running.

[0118] The computer device provided in this embodiment can implement the method described in Embodiment 1. To avoid repetition, it will not be described again here.

[0119] Example 4

[0120] This invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the OLED display glass back panel breakage detection method described in Embodiment 1.

[0121] The computer-readable storage medium provided in this embodiment can implement the method described in Embodiment 1. To avoid repetition, it will not be described again here.

[0122] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0123] The memory can be used to store the computer program and / or modules. The processor implements various functions of the printed circuit board defect detection device of the invention by running or executing the data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart memory card, secure digital card, flash memory card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0124] If an OLED display glass backplane breakage detection system is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program that can be stored in a computer-readable storage medium. When executed by a processor, this computer program can implement the steps of the various method embodiments described above. The computer program includes computer program code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory, random access memory, dot carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0125] The basic concepts of this invention have been described. It is obvious to those skilled in the art that the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0126] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0127] Furthermore, those skilled in the art will understand that various aspects of this specification can be described and illustrated in several patentable ways or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, various aspects of this specification can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as a “data block,” “module,” “engine,” “unit,” “component,” or “system.” Furthermore, various aspects of this specification may be represented as a computer product located on one or more computer-readable media, including computer-readable program code.

[0128] Computer storage media may contain a propagated data signal containing computer program code, for example, on baseband or as part of a carrier wave. This propagated signal may take various forms, including electromagnetic, optical, and suitable combinations thereof. Computer storage media can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, apparatus, or device to enable communication, propagation, or transmission of a program for use. The program code located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

Claims

1. A method for detecting breakage of a glass backplane of an OLED display screen, characterized in that, The method includes the following steps: (1) Obtain the original image P0 of the glass back panel of the OLED display, perform grayscale conversion and image enhancement processing on the original image P0 of the glass back panel to obtain the enhanced image P1 of the glass back panel; (2) Threshold segmentation is performed on the glass back plate enhancement image P1 to obtain the contour coordinates of the glass back plate; The process for obtaining the contour coordinates of the glass back panel is as follows: (2.1) Each pixel in the enhanced glass backplate image P1 after image enhancement is denoted as V. x,y And for each pixel V x,y Threshold segmentation is performed to obtain the binarized image P2 of the glass backplate; (2.2) Denoising and contour extraction are performed on the binarized image P2 of the glass back plate to obtain the set of contour region points Cnts. all ; (2.3) Based on the contour region point set Cnts all Calculate the contour area and obtain the set of points Cnt that has the largest contour area. maxArea ; (2.4) Based on the contour region point set Cnt maxArea Get the midline x of the contour region c Set the contour region points Cnt maxArea The x-coordinates of all points in the region are defined by the median x-axis. c The left and right regions are divided using the threshold as a reference, resulting in x-coordinates x1 and x2. r ; Wherein, the left and right region coordinates x1, x r The acquisition process is as follows: (2.41) Extracting the contour region point set Cnt maxArea the x coordinate of all points in the contour region, and obtaining the minimum value x min of the x coordinate max ; (2.42) Calculate the median x c =(x min +x max ) / 2, and with the middle line x c The set of contour region points Cnt is set as a threshold. maxArea The x-coordinates of all points are divided into two sets P1 and P2. r ; (2.43) Regarding the combination of P1 and P r Histograms are performed on the y-coordinates of all points, and the x-coordinate corresponding to the maximum value in the histogram is obtained, thus yielding the x-coordinates x1 and x2 of the left and right regions. r ; (2.5) Based on the set of points in the contour region Cnt maxArea Get the midline y of the contour region c Set the contour region points Cnt maxArea The y-coordinates of all points in the region are defined by the median line y. c The upper and lower regions are divided using a threshold, resulting in their y-coordinates. u y d The coordinates of the upper left corner of the glass back panel (x1, y1) are obtained. u ), lower right corner coordinates (x r ,y d ); wherein the upper and lower region coordinates y u , y d are obtained as follows: (2.51) Extract the contour region point set Cnt maxArea The y coordinate of all points in the set Cnt, and obtain the minimum value y min The maximum value y max ; (2.52) Calculate the median line y c =(y min +y max ) / 2, and with the middle line y c The set of contour region points Cnt is set to a threshold. maxArea The y-coordinates of all points are divided into two sets P. u P d ; (2.53) To combine P u , P d , the x coordinates of all points are histogrammed and the y coordinate corresponding to the maximum of the histogram is taken, resulting in upper and lower region coordinates y u , y d ; (3) Remove the edge protrusion noise of the binarized glass back plate image P2 to obtain the standard outline image P3 of the glass back plate. Use the outline coordinates of the glass back plate to generate a glass back plate mask image P4 with the same size as the original glass back plate image P0. Perform differential processing on the glass back plate mask image P4 and the standard outline image P3 of the glass back plate to obtain the glass back plate damage detection image P5. The process for generating a glass backplate mask image P4 with the same dimensions as the original glass backplate image P0 is as follows: (3.1) Based on the coordinates of the upper left corner of the glass back panel profile (x1, y1) u ) and the coordinates of the lower right corner (x r ,y d Construct the coordinate frame Box for the glass back panel area; (3.2) Construct a white background image m1 with the same size as the original glass back panel image P0. Using the glass back panel area coordinate frame Box as the boundary, set the inside of the glass back panel area coordinate frame Box to white and the outside to black, thus obtaining the glass back panel mask image P4. (4) Determine whether the glass back panel is damaged based on the glass back panel damage detection diagram P5. 2.The method of claim 1, wherein: The formula for image enhancement processing of the original glass backplate image P0 after grayscale conversion is: ； Wherein, src(I) is the pixel value of the original image P0 of the glass backboard before image enhancement processing, dst(I) is the pixel value of the enhanced image P1 of the glass backboard after image enhancement processing, and are constants. 3.The method of claim 1, wherein Cnts all The formula for calculating the contour area is: ； where (x, y) is the point coordinate of the contour region point set Cnts all of the point coordinate.

4. A system for implementing the method of claim 1 for OLED display glass backplane breakage detection, characterized by, The system includes: An image processing unit is used to acquire the original image P0 of the glass back panel of the OLED display, perform grayscale conversion processing and image enhancement processing on the original image P0 of the glass back panel to obtain an enhanced image P1 of the glass back panel. A contour extraction unit is used to perform threshold segmentation processing on the glass back plate enhancement image P1 to obtain the contour coordinates of the glass back plate. The differential processing unit removes edge protrusion noise from the binarized glass backplate image P2 to obtain a standard outline image P3 of the glass backplate. It then uses the outline coordinates of the glass backplate to generate a glass backplate mask image P4 with the same size as the original glass backplate image P0. Finally, it performs differential processing on the glass backplate mask image P4 and the standard outline image P3 to obtain a glass backplate damage detection image P5. The defect detection unit determines whether the glass back panel is damaged based on the glass back panel damage detection diagram P5.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the method for detecting damage to the glass back panel of an OLED display as described in any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method for detecting damage to the glass back panel of an OLED display screen according to any one of claims 1-3.

Images