A method, device, system and storage medium for correcting a multi-screen detection platform

Abstract

The present application discloses a method, device, system and storage medium for correcting a multi-screen detection platform, which is used to improve the accuracy of platform correction. The present application includes: placing a screen to be detected on the screen plug-in slot of a loading base plate; fixing the loading base plate on the platform, adjusting the displacement of the platform so that the first screen to be detected on the loading base plate reaches the center position of the field of view of the first detection camera, and recording the current position of the loading platform; performing image acquisition through the first detection camera to generate a first image; performing a correction on the platform once through the positioning mark on the first image; performing image acquisition through the first detection camera to generate a second image; detecting the area of ​​the screen to be detected on the second image, and determining the rectangular frame center coordinate set of each screen to be detected; generating a horizontal correction line based on the rectangular frame center coordinate set; verifying the correction degree of the platform based on the horizontal correction line, and performing a secondary correction if the verification fails.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of screen stage correction, and in particular, to a method, device, system and storage medium for multi-screen detection stage correction. Background Art

[0002] With the rapid development of intelligent manufacturing, the new generation of display technology is also developing rapidly. The application of display technology is very extensive. Commonly used mobile phones, televisions, cars, VR, AR and other products are classic examples of display technology applications. The main material of display technology is the display screen. In the production process of LCD screens, although each link is strictly controlled, it is inevitable that screens with certain defects will be produced.

[0003] In order to provide customers with a good experience, defect detection has become an indispensable part of the LCD screen production process, and defect detection of display screens has always been an important process.

[0004] Before defect detection, it is necessary to place the screen to be detected on the loading base plate, and then fix the loading base plate on the stage, and control the loading base plate to move to the detection area for detection by the stage. Before controlling the loading base plate to move to the detection area by the stage, it is necessary to correct the stage first, the purpose of which is to enable the screen to be detected on the loading base plate to align with the field of view frame of the detection camera and reduce the tilt of the screen to be detected. In the prior art, a plurality of positioning marks are usually set on the loading base plate, and the image is collected by the detection camera, and then the position of the positioning mark in the image is detected. Through the positional relationship between the plurality of positioning marks, it is detected whether the loading base plate is tilted. If there is a tilt, correction processing can be performed through the positional relationship between the plurality of positioning marks.

[0005] However, the above correction method is based on determining the center position of the positioning mark on the image before analyzing the positional relationship. The positioning marks are usually distributed around the loading base plate. After the detection camera captures and generates an image, there may be a problem of blurred positioning mark imaging in the image. When there is a problem of blurred positioning mark imaging, there will be deviations in the subsequent positional relationship analysis between multiple positioning marks, resulting in deviations in tilt detection, which in turn reduces the accuracy of subsequent stage correction. Summary of the invention

[0006] The present application discloses a method, device, system and storage medium for multi-screen detection stage correction, which are used to improve the accuracy of stage correction.

[0007] The first aspect of the present application provides a method for correcting a multi-screen detection stage, comprising:

[0008] The screen to be tested is placed on the screen plug-in slot of the loading base plate, the loading base plate is provided with a positioning mark, and the loading base plate is provided with at least two screen plug-in slots arranged neatly in horizontal direction;

[0009] Fix the loading base plate on the stage, adjust the stage displacement so that the first screen to be inspected on the loading base plate reaches the center of the field of view of the first inspection camera, and record the current position of the unloading stage;

[0010] Capturing an image through a first detection camera to generate a first image;

[0011] Performing a correction on the stage using the positioning mark on the first image;

[0012] Capturing an image through a first detection camera to generate a second image;

[0013] Detecting the area of ​​the screen to be detected on the second image, and determining a set of center coordinates of a rectangular frame of each screen to be detected;

[0014] Generate a horizontal correction line based on the center coordinate set of the rectangular frame;

[0015] The correction degree of the stage is verified according to the horizontal correction line, and a second correction is performed if the verification fails.

[0016] Optionally, the stage is corrected once using the positioning mark on the first image, including:

[0017] Identify the marking area of ​​the positioning mark on the first image by using a template matching algorithm;

[0018] Calculate the initial correction angle based on the marked area;

[0019] Control the motor axis and perform a correction on the stage according to the initial correction angle.

[0020] Optionally, four positioning marks are provided on the loading bottom plate, each positioning mark has a different distance from the center of the field of view of the first detection camera, and there are four rectangular marking areas on the first image;

[0021] Calculate the initial correction angle based on the marked area, including:

[0022] Generate four calibration lines on the first image according to the four rectangular marking areas respectively;

[0023] Generate 4 adjustment angles according to 4 calibration lines;

[0024] Generate 4 calculation weights according to the distance from each positioning mark to the center of the field of view of the first detection camera;

[0025] The initial correction angle is calculated based on the 4 calculation weights and the 4 adjustment angles.

[0026] Optionally, generating a horizontal correction line according to the rectangular frame center coordinate set includes:

[0027] The screen to be tested on the screen plug-in slot is lit up by the same calibration picture. The calibration picture is set with 4 calibration points, and the center of the rectangle formed by the 4 calibration points is the center of the calibration picture;

[0028] Capturing an image through the first detection camera to generate a third image;

[0029] Determine the four calibration points on each screen to be detected, calculate the screen center coordinates for each screen to be detected, and generate a screen center coordinate set;

[0030] Perform straight line fitting on the rectangular frame center coordinate set to generate a first fitting straight line;

[0031] The first fitting straight line is used to filter out the coordinates of the center of the rectangular frame whose deviation is greater than a preset condition;

[0032] Compare the corresponding points of the screen center coordinate set with the screened rectangular frame center coordinate set, and select the target point set that meets both the distance deviation condition and the azimuth deviation condition according to the comparison result;

[0033] Generate a horizontal correction line based on a set of target points.

[0034] Optionally, after verifying the degree of correction of the stage according to the horizontal correction line and performing secondary correction when the verification fails, the method further comprises:

[0035] Move the stage to a position on the inspection area corresponding to the center position of the field of view of the first inspection camera;

[0036] The screen to be inspected on the loading base plate is inspected by a second inspection camera on the inspection area.

[0037] Optionally, after verifying the degree of correction of the stage according to the horizontal correction line and performing secondary correction when the verification fails, before moving the stage to a position on the inspection area corresponding to the center position of the field of view of the first inspection camera, the method further includes:

[0038] Capturing images through a first detection camera;

[0039] The collected image is used to identify the arrangement of the screen to be detected on the loading base plate using a template matching algorithm, and the missing data of the screen to be detected is obtained by identification;

[0040] The screen to be inspected on the loading base plate is inspected by the second inspection camera in the inspection area, including:

[0041] The screen to be inspected on the loading base plate is inspected by a second inspection camera on the inspection area in combination with the missing data.

[0042] The second aspect of the present application provides a device for correcting a multi-screen detection platform, comprising:

[0043] A placement unit is used to place the screen to be tested on the screen plug-in slot of the loading base plate, the loading base plate is provided with a positioning mark, and the loading base plate is provided with at least two horizontally arranged screen plug-in slots;

[0044] An adjustment unit is used to fix the loading base plate on the stage, adjust the displacement of the stage, make the first screen to be detected on the loading base plate reach the center position of the field of view of the first detection camera, and record the current position of the unloading stage;

[0045] A first generating unit, configured to collect images through a first detection camera to generate a first image;

[0046] A first correction unit, used for performing a correction on the stage by using the positioning mark on the first image;

[0047] A second generating unit, configured to collect an image through the first detection camera to generate a second image;

[0048] A determination unit, used to detect the area of ​​the screen to be detected on the second image, and determine a set of center coordinates of a rectangular frame of each screen to be detected;

[0049] A third generating unit, used for generating a horizontal correction line according to a set of center coordinates of the rectangular frame;

[0050] The second correction unit is used to verify the correction degree of the carrier according to the horizontal correction line, and perform secondary correction when the verification fails.

[0051] Optionally, the first correction unit includes:

[0052] An identification module, used to identify a marking area of ​​a positioning mark on the first image by using a template matching algorithm;

[0053] A calculation module, used for calculating an initial correction angle according to the marked area;

[0054] The correction module is used to control the motor axis and perform a correction on the stage according to the initial correction angle.

[0055] Optionally, four positioning marks are provided on the loading bottom plate, each positioning mark has a different distance from the center of the field of view of the first detection camera, and there are four rectangular marking areas on the first image;

[0056] Computing module, including:

[0057] Generate four calibration lines on the first image according to the four rectangular marking areas respectively;

[0058] Generate 4 adjustment angles according to 4 calibration lines;

[0059] Generate 4 calculation weights according to the distance from each positioning mark to the center of the field of view of the first detection camera;

[0060] The initial correction angle is calculated based on the 4 calculation weights and the 4 adjustment angles.

[0061] Optionally, the third generating unit includes:

[0062] The screen to be tested on the screen plug-in slot is lit up by the same calibration picture. The calibration picture is set with 4 calibration points, and the center of the rectangle formed by the 4 calibration points is the center of the calibration picture;

[0063] Capturing an image through the first detection camera to generate a third image;

[0064] Determine the four calibration points on each screen to be detected, calculate the screen center coordinates for each screen to be detected, and generate a screen center coordinate set;

[0065] Perform straight line fitting on the rectangular frame center coordinate set to generate a first fitting straight line;

[0066] The first fitting straight line is used to filter out the coordinates of the center of the rectangular frame whose deviation is greater than a preset condition;

[0067] Compare the corresponding points of the screen center coordinate set with the screened rectangular frame center coordinate set, and select the target point set that meets both the distance deviation condition and the azimuth deviation condition according to the comparison result;

[0068] Generate a horizontal correction line based on a set of target points.

[0069] Optionally, after the second correction unit, the device further comprises:

[0070] A displacement unit, used to move the stage to a position on the detection area corresponding to the center position of the field of view of the first detection camera;

[0071] The detection unit is used to detect the screen to be detected on the loading base plate through a second detection camera on the detection area.

[0072] Optionally, after the second correction unit and before the displacement unit, the device further comprises:

[0073] A collection unit, used for collecting images through a first detection camera;

[0074] The recognition unit is used to use the template matching algorithm to identify the arrangement of the screen to be detected on the loading base plate using the collected image, and identify the missing data of the screen to be detected;

[0075] Detection unit, comprising:

[0076] The screen to be inspected on the loading base plate is inspected by a second inspection camera on the inspection area in combination with the missing data.

[0077] The third aspect of the present application provides a system for multi-screen detection and stage correction, comprising:

[0078] Processor, memory, input-output unit, and bus;

[0079] The processor is connected to the memory, the input and output unit, and the bus;

[0080] The memory stores a program, and the processor calls the program to execute the first aspect and any optional method of the first aspect.

[0081] A fourth aspect of the present application provides a computer-readable storage medium, on which a program is stored. When the program is executed on a computer, the program executes the first aspect and any optional method of the first aspect.

[0082] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0083] In the present application, firstly, a screen to be detected is placed on the screen plug-in slot of a loading base plate, a positioning mark is provided on the loading base plate, and at least two horizontally arranged neat screen plug-in slots are provided on the loading base plate. The loading base plate is fixed on the carrier, and the displacement of the carrier is adjusted so that the first screen to be detected on the loading base plate reaches the center position of the field of view of the first detection camera, and the current position of the loading platform is recorded. The first detection camera is used to acquire an image to generate a first image. The carrier is corrected once by the positioning mark on the first image. The first detection camera is used to acquire an image to generate a second image. The area of ​​the screen to be detected on the second image is detected to determine the set of center coordinates of the rectangular frame of each screen to be detected. A horizontal correction line is generated according to the set of center coordinates of the rectangular frame. The correction degree of the carrier is verified according to the horizontal correction line, and a secondary correction is performed if the verification fails.

[0084] By setting positioning marks and neatly arranged and evenly spaced screen slots on the loading base plate, a screen to be tested can be placed on each loading base plate. Before testing, firstly, the detection camera is used to collect images, and a correction is performed using the positioning marks on the first image. Then, the detection camera is used to capture a second image to determine the center of the area of ​​the screen to be tested on the second image. Since each screen slot is the same size, the screen slots are arranged horizontally, that is, the line connecting the center points of each screen slot and the horizontal line of the first detection camera should be parallel to or even coincide with each other. The screen to be tested is placed on the screen slot, and the center point of the rectangular box corresponding to the screen to be tested corresponds one-to-one to the center point of the screen slot, so a horizontal correction line can be generated through the set of center coordinates of the rectangular box corresponding to the screen to be tested. The correction degree of the carrier is verified by the horizontal correction line, and a secondary correction is performed if the verification fails. Even if the positioning mark imaging is blurred during a correction process, the correction can be verified to be up to standard through the set of center coordinates of the rectangular frames of multiple screens to be tested. If it fails to meet the standard, a second correction can be performed, which greatly improves the accuracy of the stage correction. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0086] Figure 1 A schematic diagram of an embodiment of a method for correcting a multi-screen detection stage of the present application;

[0087] Figure 2 A schematic diagram of an embodiment of a method for correcting a carrier through positioning marks in the present application;

[0088] Figure 3 A schematic diagram of an embodiment of a method for calculating an initial correction angle of the present application;

[0089] Figure 4 A schematic diagram of an embodiment of a method for generating a horizontal correction line according to a set of center coordinates of a rectangular frame in the present application;

[0090] Figure 5 A schematic diagram of an embodiment of a method for detecting a screen to be detected in the present application;

[0091] Figure 6 A schematic diagram of an embodiment of a device for correcting a multi-screen detection stage of the present application;

[0092] Figure 7 A schematic diagram of an embodiment of a preprocessing system for display screen images of the present application;

[0093] Figure 8 This is a schematic diagram of the hardware architecture of this application;

[0094] Fig. 9 This is a schematic diagram of the carrier structure of this application;

[0095] Fig.10 A schematic diagram of the initial setting of the base plate detection for this application;

[0096] Fig.11 This is a schematic diagram of one-time correction of the carrier and loading base plate of this application;

[0097] Fig.12 A schematic diagram of the verification and correction process for this application;

[0098] Fig.13 This is a schematic diagram of the arrangement and identification of the screens to be detected in this application. DETAILED DESCRIPTION

[0099] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0100] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0101] It should also be understood that the term “and / or” throughout the specification and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0102] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0103] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0104] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0105] In the prior art, before defect detection, it is necessary to first place the screen to be detected on the loading base plate, and then fix the loading base plate on the stage, and control the loading base plate to move to the detection area for detection by the stage. Before the loading base plate is controlled to move to the detection area by the stage, the stage needs to be corrected first, the purpose of which is to enable the screen to be detected on the loading base plate to align with the field of view frame of the detection camera and reduce the tilt of the screen to be detected. In the prior art, a plurality of positioning marks are usually set on the loading base plate, and the image is collected by the detection camera, and then the position of the positioning mark in the image is detected. Through the positional relationship between the plurality of positioning marks, it is detected whether the loading base plate is tilted. If there is a tilt, the positional relationship between the plurality of positioning marks can be used for correction processing. However, the above correction method is based on determining the center position of the positioning mark on the image, and then the positional relationship can be analyzed. The positioning marks are usually distributed around the loading base plate. After the detection camera shoots and generates an image, there may be a problem of blurred imaging of the positioning marks in the image. If the image of the positioning mark is blurred, there will be deviations in the subsequent positional relationship analysis between multiple positioning marks, resulting in deviations in tilt detection, which will in turn reduce the accuracy of subsequent stage correction.

[0106] Based on this, the present application discloses a method, device, system and storage medium for multi-screen detection stage correction, which are used to improve the accuracy of stage correction.

[0107] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0108] The method of the present application can be applied to a server, a device, a terminal or other devices with logic processing capabilities, and the present application does not limit this. For the convenience of description, the following description is made by taking the execution subject as an example of a terminal.

[0109] See also Figure 1 The present application provides an embodiment of a method for correcting a multi-screen detection platform, comprising:

[0110] 101. Place the screen to be tested on the screen plug-in slot of the loading base plate, the loading base plate is provided with a positioning mark, and the loading base plate is provided with at least two screen plug-in slots arranged neatly in horizontal direction;

[0111] In this embodiment, before the test, the terminal's pre-process will plug the Micro LED screen to be tested (screen to be tested) into the screen plug slot of the loading base plate, so as to light up the screen to be tested later and ensure that the position of each Micro LED screen to be tested is arranged in an orderly and accurate manner. Figure 8 , Figure 8 This is the hardware architecture diagram. The hardware system is divided into a loading base plate and a loading platform with a 12M camera and a 65M camera and a screen. It is mainly used for correction at the feeding position, and enters the detection position after correction. Please refer to Fig. 9 , Fig. 9 It is a schematic diagram of the carrier. The loading base plate is fixed on the carrier plate by a limit bayonet. Four positioning marks are provided on the loading base plate. The positioning marks are used to detect whether the loading base plate is flush with the horizontal line of the field of view of the detection camera. In this embodiment, the positioning marks are rectangular and are respectively located in the four corner areas of the loading base plate (rectangular loading base plate). In this embodiment, at least two horizontally arranged screen plug slots are provided on the loading base plate. The purpose is to be able to pass to the center position of the screen to be detected during the subsequent correction process. The purpose of setting screen plug slots that are equally spaced and horizontally arranged is to allow the screen to be detected placed on the screen plug slot to be arranged horizontally at an equal distance like the screen plug slot. Therefore, when designing the loading base plate, it is necessary to design screen plug slots that are strictly horizontally arranged, and one row or multiple rows can be designed. In this embodiment, two rows of screen plug slots are set.

[0112] The above-mentioned reloading base plate is designed with multiple screen plug-in slots. Firstly, in the subsequent testing process, there is no need to frequently replace the loading base plate, and multiple screens to be tested can be tested on one loading base plate. Secondly, the carrier and the loading base plate can be corrected through the horizontally arranged screens to be tested.

[0113] 102. Fix the loading base plate on the stage, adjust the displacement of the stage, so that the first screen to be detected on the loading base plate reaches the center position of the field of view of the first detection camera, and record the current position of the loading platform;

[0114] The terminal fixes the loading base plate on the stage. At this time, the terminal needs to perform initial positioning first. In this embodiment, the loading base plate is displaced by moving the stage, so that a certain screen to be detected on the screen plug slot reaches the center of the first detection camera. In this embodiment, the first screen to be detected in the upper left corner is usually selected and moved to the center of the first detection camera. The current position of the current stage is recorded, and the loading base plate can be corrected and the defects of the screen to be detected can be detected based on the coordinates as the reference point.

[0115] Specifically, set the starting point of the Micro LED screen (screen to be tested) for testing, adjust the lateral movement of the stage, make the first Micro LED screen to be tested (screen to be tested) reach the center of the field of view of the testing camera, and then record the position of the stage. According to the lateral arrangement interval of the Micro LED screen, set the distance x of each lateral movement of the stage. Please refer to Fig.10 , Fig.10 This is a schematic diagram of the initial settings for loading the base plate detection, where y represents the number of screen plug-in slots.

[0116] 103. Capturing an image through a first detection camera to generate a first image;

[0117] In this embodiment, the terminal realizes image acquisition of the loading bottom plate by using a detection camera, and the first image includes all positioning marks.

[0118] 104. Correct the stage once using the positioning mark on the first image;

[0119] In this embodiment, the automatic detection process begins, and when the loading base plate is set to the center of the stage, the first stage correction is performed. Real-time photography is performed through the first detection camera to generate a first image. After the terminal obtains the first image, it can first correct the stage according to the positioning mark on the first image. The correction here can be calculated through the center coordinates of multiple positioning marks, and then the horizontal line of the loading base plate is determined by the center coordinates of multiple positioning marks, and the horizontal line of the loading base plate is compared with the horizontal line of the field of view of the detection camera for correction. In addition to the above method, there are other correction methods, which are not limited here.

[0120] 105. Capture an image through a first detection camera to generate a second image;

[0121] After one correction is completed, the terminal collects images through the first detection camera to generate a second image.

[0122] 106. Detect the area of ​​the screen to be detected on the second image, and determine a set of center coordinates of a rectangular frame of each screen to be detected;

[0123] The terminal performs regional detection on the screen to be detected on a screen plug-in slot on the second image, determines the center coordinates of the rectangular frame of each screen to be detected, and generates a set of center coordinates of the rectangular frame.

[0124] 107. Generate a horizontal correction line according to the center coordinate set of the rectangular frame;

[0125] The terminal generates a horizontal correction line by performing straight line fitting according to the coordinate points in the coordinate set of the center of the rectangular frame. Specifically, the straight line fitting can be performed directly through the coordinate points in the coordinate set of the center of the rectangular frame.

[0126] Specifically, after the initial correction, due to the accuracy of mark recognition and deviations such as jitter during movement, the stage cannot maintain an absolute horizontal position, and the stage needs to be precisely aligned and corrected. Therefore, by identifying the Micro LED screen (screen to be detected) on the loading base plate, extracting the center coordinates of the rectangular frame of the Micro LED screen image, and using the least squares method to perform straight line fitting on a whole row of Micro LED screen center coordinate points, the straight line fitting equation can be simply expressed as the following equation:

[0127]

[0128] Among them: A, B, C are the coefficients of the fitting equation, , are the actual coordinates of the centers of the fitting points.

[0129]

[0130] in: is the center coordinate position of the actual point, The position of the fitted straight line equation is guaranteed to be Reach the minimum.

[0131] The algorithm is used to fit the arrangement angle of the Micro LED screen on the loading base plate to verify the correction level. If the correction deviation requirement is not met, the stage is rotated again for correction to ensure the correction accuracy. Fig.12 , Fig.12 This is a schematic diagram of the fitting verification correction link. The horizontal line is the horizontal line of the detection camera's field of view, the fitting line is the horizontal correction line, and the angle between the two lines is the correction angle.

[0132] 108. Verify the degree of correction of the platform according to the horizontal correction line, and perform secondary correction if the verification fails.

[0133] After the terminal generates the horizontal correction line, it first needs to determine whether the horizontal correction line is parallel to the horizontal line of the detection camera's field of view. If there is an angle, whether the angle is less than the preset threshold. If so, no further correction is required. If not, the stage needs to be corrected again using the horizontal correction line.

[0134] In this embodiment, first, the screen to be detected is placed on the screen plug-in slot of the loading base plate, and a positioning mark is provided on the loading base plate, and at least two horizontally arranged neat screen plug-in slots are provided on the loading base plate. The loading base plate is fixed on the carrier, and the displacement of the carrier is adjusted so that the first screen to be detected on the loading base plate reaches the center position of the field of view of the first detection camera, and the current position of the loading platform is recorded. The first detection camera is used to capture the image and generate a first image. The carrier is corrected once by the positioning mark on the first image. The first detection camera is used to capture the image and generate a second image. The area of ​​the screen to be detected on the second image is detected to determine the set of center coordinates of the rectangular frame of each screen to be detected. A horizontal correction line is generated according to the set of center coordinates of the rectangular frame. The correction degree of the carrier is verified according to the horizontal correction line, and a secondary correction is performed if the verification fails.

[0135] By setting positioning marks and neatly arranged and evenly spaced screen slots on the loading base plate, a screen to be tested can be placed on each loading base plate. Before testing, firstly, the detection camera is used to collect images, and a correction is performed using the positioning marks on the first image. Then, the detection camera is used to capture a second image to determine the center of the area of ​​the screen to be tested on the second image. Since each screen slot is the same size, the screen slots are arranged horizontally, that is, the line connecting the center points of each screen slot and the horizontal line of the first detection camera should be parallel to or even coincide with each other. The screen to be tested is placed on the screen slot, and the center point of the rectangular box corresponding to the screen to be tested corresponds one-to-one to the center point of the screen slot, so a horizontal correction line can be generated through the set of center coordinates of the rectangular box corresponding to the screen to be tested. The correction degree of the carrier is verified by the horizontal correction line, and a secondary correction is performed if the verification fails. Even if the positioning mark imaging is blurred during a correction process, the correction can be verified to be up to standard through the set of center coordinates of the rectangular frames of multiple screens to be tested. If it fails to meet the standard, a second correction can be performed, which greatly improves the accuracy of the stage correction.

[0136] See also Figure 2 The present application provides an embodiment of a method for correcting a stage by using a positioning mark, comprising:

[0137] 201. Identify a marking area of ​​a positioning mark on a first image by using a template matching algorithm;

[0138] In this embodiment, the automatic detection process starts, and when the loading base plate is set to the center of the stage, the first stage correction is performed. The first detection camera takes real-time photos to generate a first image, and the positioning mark on the loading base plate is identified by the template matching algorithm to generate a mark area. The initial correction angle of the positioning mark is calculated by the mark area, and the stage is corrected once by controlling the motor shaft to eliminate the deflection angle of the mark in the image, so that the Micro LED screen on the loading base plate is basically arranged horizontally in the image. Please check Fig.11 , Fig.11 Schematic diagram of one-time correction of the stage and loading base.

[0139] In this embodiment, the terminal identifies the positioning mark on the first image through a template matching algorithm. Specifically, the template matching algorithm uses square difference matching, and the calculation formula of square difference matching is as follows:

[0140]

[0141] Among them, R(x,y) is the area after square difference matching, T is the template image, I is the matching image, and the recognition area is framed at (x, y) of the matching image I, x' to the right, and y' to the bottom. Matching is performed by calculating the square difference between the template and the image area. The best matching value is 0. The worse the match, the greater the matching value. This formula is a commonly used one in the template matching algorithm. The template matching algorithm can be used to identify the positioning mark, and locate the area of ​​the positioning mark, specifically locating a rectangular frame area. The advantage of applying this positioning algorithm to the recognition of the positioning mark is that even if the positioning mark is blurred in the first image, it will not affect the recognition. The bottom edge of the rectangular frame area formed can characterize the tilt of the positioning mark. There is no need to use multiple positioning markers to locate the center coordinates. At least one positioning marker is needed. The inclination of the positioning marker on the loading base plate can be determined through the template matching algorithm. Since the positioning marker and the loading base plate are both rectangular, in the process of setting the positioning marker, the four sides of the positioning marker need to be parallel to the four sides of the loading base plate, so that the four sides of the rectangular recognition area formed after the template matching algorithm can correspond to the four sides of the positioning marker and the four sides of the loading base plate, so that the bottom edge of the rectangular recognition area can represent the current inclination of the loading base plate.

[0142] 202. Calculate an initial correction angle according to the marked area;

[0143] After the terminal identifies the identification area of ​​the positioning marker on the first image through the template matching algorithm, the initial correction angle can be calculated based on the identification area. The initial correction angle can be calculated using the identification area of ​​one positioning marker, or the initial correction angle can be calculated separately using the identification areas of multiple positioning markers. There is no limitation here.

[0144] 203. Control the motor shaft and perform a correction on the stage according to the initial correction angle.

[0145] In this embodiment, after calculating the initial correction angle, the terminal can control the motor shaft and perform a correction on the carrier according to the initial correction angle.

[0146] In this embodiment, the rectangular positioning mark is identified by a template matching algorithm to obtain a rectangular identification area corresponding to the positioning mark, and the bottom edge of the rectangular identification area can characterize the inclination of the positioning mark. The principle is that the positioning mark and the loading base plate are both rectangular. In the process of setting the positioning mark, the four sides of the positioning mark need to be parallel to the four sides of the loading base plate, so that the four sides of the rectangular identification area formed after the template matching algorithm can correspond to the four sides of the positioning mark and the four sides of the loading base plate, so that the bottom edge of the rectangular identification area can characterize the current inclination of the loading base plate. This method can reduce the recognition accuracy requirements for the positioning mark, and even if the imaging is slightly blurred, it will not affect the calculation of the initial correction angle too much.

[0147] See also Figure 3 The present application provides another embodiment of a method for calculating an initial correction angle, comprising:

[0148] 301. Generate four calibration lines on the first image according to the four rectangular identification areas respectively;

[0149] There may be problems with using a single positioning mark. If the positioning mark itself deviates from the loading base plate, the correction will be inaccurate. In this embodiment, four positioning marks are set on the loading base plate. After being identified by the template matching algorithm, four rectangular marking areas can be obtained, and then four calibration lines are generated on the first image through the bottom edges of the four rectangular marking areas.

[0150] 302. Generate four adjustment angles respectively according to the four calibration lines;

[0151] After the terminal generates four calibration lines respectively on the first image through the bottom edges of the four rectangular marking areas, the terminal can generate four adjustment angles respectively according to the four calibration lines.

[0152] 303. Generate four calculation weights according to the distance from each positioning marker to the center of the field of view of the first detection camera;

[0153] In a general solution, the final adjustment angle can be obtained by simply adding and averaging the four adjustment angles. However, the center of the field of view of the detection camera in this embodiment is shifted to a screen to be detected. This screen to be detected is usually not the center of the loading base plate. The center of the loading base plate is usually the limit stop. If the conventional average angle calculation method is used, the accuracy will be reduced.

[0154] In this embodiment, the terminal generates four calculation weights according to the distance from each positioning marker to the center of the field of view of the first detection camera. The distance is a straight-line distance. Before correction, the parameters of the loading base plate can be obtained, such as: the size data of the loading base plate, the position coordinates of the four positioning markers on the loading base plate, and the center coordinates of the first screen socket in the upper left corner (the center of the field of view of the first detection camera is also set here). The distance (the distance from each positioning marker to the center of the field of view of the first detection camera) is calculated using the above parameters.

[0155] In this embodiment, the terminal generates four calculation weights according to the distance from each positioning mark to the center of the field of view of the first detection camera. The purpose is that although the template recognition algorithm can well identify the positioning mark and the imaging blur is less affected, it still exists. The closer to the center of the field of view, the better the imaging clarity, and vice versa. At this time, the angle accuracy generated by the identification area of ​​the positioning mark that is relatively far away will be slightly lower. At this time, it is only necessary to generate an adjustment angle according to the identification area of ​​each positioning mark, and then generate four calculation weights based on the distance from each positioning mark to the center of the field of view of the first detection camera. In this embodiment, the terminal generates four calculation weights in proportion to the distance from each positioning mark to the center of the field of view of the first detection camera, and scales the four calculation weights in proportion so that the four calculation weights add up to 1, and the four calculation weights can be obtained.

[0156] 304. Calculate an initial correction angle according to the four calculation weights and the four adjustment angles.

[0157] After the terminal calculates the four calculation weights, it can multiply the calculation weights by the adjustment angles respectively, and then add them up to obtain the initial correction angle.

[0158] The calculation method in this embodiment can reduce the problem of inclination between the positioning mark and the loading base plate during the production process of the loading base plate, and can further eliminate the influence of blurred imaging of the positioning mark, thereby improving the accuracy of correction.

[0159] See also Figure 4 The present application provides another embodiment of a method for generating a horizontal correction line according to a set of center coordinates of a rectangular frame, comprising:

[0160] 401. Light up the screen to be detected on the screen plug-in slot through the same calibration picture, the calibration picture is provided with 4 calibration points, and the center of the rectangle formed by the 4 calibration points is the center of the calibration picture;

[0161] In the above-mentioned embodiment, there is no need to light up the screen to be detected. It is only necessary to identify the screen to be detected through the template matching algorithm, and determine the center coordinates of the rectangular frame of each screen to be detected according to the identified rectangular area to generate a set of center coordinates of the rectangular frame, and directly perform straight line fitting through the coordinate points in the set of center coordinates of the rectangular frame. This method has certain problems, which are similar to the positioning mark. Since the template matching algorithm is used, the area of ​​the screen to be detected can be accurately located. However, for determining the center coordinates of the screen to be detected, when the imaging is blurred, the position of the rectangular frame may deviate, so that the accuracy of the center point coordinates may be insufficient, so it is necessary to detect the accuracy of the center coordinates.

[0162] 402. Capture an image through the first detection camera to generate a third image;

[0163] The terminal lights up the screen to be detected on the screen socket through the same calibration picture, collects images through the first detection camera, and generates a third image. The calibration picture is provided with 4 calibration points. The center of the rectangle formed by the 4 calibration points is the center of the calibration picture, which is similar to the positions of the 4 positioning marks set on the loading base plate.

[0164] 403. Determine four calibration points on each screen to be detected, and calculate the screen center coordinates for each screen to be detected to generate a screen center coordinate set;

[0165] At this time, the terminal determines 4 calibration points on each screen to be detected on the third image, and calculates the screen center coordinates for each screen to be detected to generate a screen center coordinate set. In this embodiment, it is necessary to compare the screen center coordinate set and the rectangular frame center coordinate set, and select the coordinate points according to the comparison result.

[0166] 404. Perform straight line fitting on the rectangular frame center coordinate set to generate a first fitting straight line;

[0167] 405. Using the first fitting straight line, filter out the coordinates of the center of the rectangular frame whose deviation is greater than a preset condition;

[0168] It should be noted that, since there may be mura defects on the screen to be detected, there are cases where the calibration points of some screens to be detected are misplaced. In order to solve this problem, in this embodiment, four calibration points are set in the calibration screen, and the center of the rectangle formed by the four calibration points is the center of the calibration screen. Since the defects are usually located in a partial area of ​​the screen to be detected, this embodiment does not choose to set only one central calibration point, but evenly sets four calibration points in four areas close to the corners of a screen to be detected. Even if there is a defective area, the impact on the calibration point detection can be reduced, and the deviation is minimized when calculating the center coordinates of the screen. Unless there are multiple defective areas, there will be deviations in the positions of multiple calibration points, which will affect the position of the center coordinates of the screen. In this embodiment, in order to reduce the impact of imaging blur, the terminal performs a straight line fitting on the set of center coordinates of the rectangular frame to generate a first fitting straight line. The first fitting straight line is used to screen out the points in the set of center coordinates of the rectangular frame whose deviations are greater than the preset conditions, that is, to screen out some points that are obviously affected by imaging blur.

[0169] 406. Compare the corresponding points of the screen center coordinate set and the filtered rectangular frame center coordinate set, and select the target point set that meets both the distance deviation condition and the azimuth deviation condition according to the comparison result;

[0170] Next, the remaining points in the filtered rectangular frame center coordinate set and the corresponding points in the screen center coordinate set are compared and analyzed.

[0171] For example, the rectangular frame center coordinate set originally has 10 rectangular frame center coordinates, and the screen body center coordinate set also has 10 screen body center coordinates, among which the second rectangular frame center coordinate is screened out, then the remaining 9 rectangular frame center coordinates and the corresponding 9 points in the screen body center coordinate set are compared and analyzed respectively.

[0172] Specifically, it is necessary to compare the deviation and distance of the center coordinates of the rectangular frame relative to the center coordinates of the screen. Based on the above case: the center coordinates of the first rectangular frame are 1mm above the center coordinates of the first screen, the center coordinates of the third rectangular frame are 1mm above the center coordinates of the third screen... The center coordinates of the 9th rectangular frame are 1mm below the center coordinates of the 9th screen, and the center coordinates of the 10th rectangular frame are 3mm above the center coordinates of the 10th screen.

[0173] According to the analysis, the deviation direction of the center coordinates of most rectangular boxes is directly upward, but the deviation of the center coordinates of the 9th rectangular box is directly downward, so the center coordinates of the rectangular box are screened out. Although the deviation direction of the center coordinates of the 10th rectangular box is accurate, the deviation distance is too large, so it is screened out.

[0174] 407. Generate a horizontal correction line according to the target point set.

[0175] After the screening is completed, the terminal generates a horizontal correction line based on the target point set, which greatly reduces the impact of imaging blur.

[0176] See also Figure 5 The present application provides another embodiment of a method for detecting a screen to be detected, comprising:

[0177] 501. Capturing an image through a first detection camera;

[0178] Before the detection, the display screen on the loading base plate needs to be detected, and firstly, an image is collected by a first detection camera.

[0179] 502. Using the template matching algorithm to identify the arrangement of the screen to be detected on the loading base plate using the collected image, and identifying the missing data of the screen to be detected;

[0180] After the first detection camera completes the acquisition, the screen to be detected is identified through the template matching algorithm to determine the number and position of the identification frame of the screen to be detected, so as to determine the missing data of the screen to be detected, that is, whether the screen to be detected is placed on the screen socket is determined based on the presence or absence of the identification frame. If there is an identification frame on a certain screen socket, it means that there is a screen to be detected on the current screen socket, otherwise there is no screen to be detected.

[0181] After the stage is calibrated, the entire loading base is imaged again, and the template matching algorithm is used to identify the arrangement of the Micro LED screen (screen to be tested) on the loading base, identify the total number of Micro LED screen points, and determine whether the screen is missing at the point. If there is a missing point, it will be calculated and recorded, and the point will be automatically skipped during the test. Fig.13 What I see, Fig.13 This is a schematic diagram of the arrangement and identification of the screen to be tested. The number y of screen plug-in slots is 9, and there are gaps on the 4th and 7th screen plug-in slots.

[0182] Point moving distance calculation formula:

[0183] in To detect the screen number. This is the horizontal arrangement spacing of the Micro LED screen recorded in step 1. is the missing coefficient, if missing =1, if not missing =0. for The distance that the detection point needs to move relative to the initial detection origin, and x is the distance between two adjacent screen sockets.

[0184] 503. Move the stage to a position on the detection area corresponding to the center position of the field of view of the first detection camera;

[0185] 504 . Inspect the screen to be inspected on the loading base plate by using a second inspection camera on the inspection area in combination with the missing data.

[0186] The terminal moves the stage into the detection position, that is, moves the stage to the detection area and moves to the preset initial detection point of the Micro LED screen (i.e., the center of the field of view of the first detection camera in Example 1, and the second detection camera is located at the same position as the first detection camera). According to the lateral spacing of each Micro LED screen (screen to be detected) recorded in Example 1 (i.e., the distance between two adjacent screen plug-in slots, which data can be collected in advance) and the identified and recorded screen arrangement (missing data of the screen to be detected), the screen to be detected is calculated one by one according to the formula and the stage is moved to detect the screen to be detected. When all the Micro LED screens to be tested on a loading base plate have been tested, the unloaded materials are reloaded to perform the above correction steps and tests.

[0187] See also Figure 6 The present application provides an embodiment of a device for correcting a multi-screen detection platform, comprising:

[0188] The placement unit 601 is used to place the screen to be tested on the screen plug-in slot of the loading base plate, the loading base plate is provided with a positioning mark, and the loading base plate is provided with at least two screen plug-in slots arranged neatly in horizontal direction;

[0189] The adjustment unit 602 is used to fix the loading base plate on the stage, adjust the displacement of the stage, so that the first screen to be detected on the loading base plate reaches the center position of the field of view of the first detection camera, and record the current position of the unloading stage;

[0190] A first generating unit 603 is used to collect images through a first detection camera to generate a first image;

[0191] A first correction unit 604, used to perform a correction on the stage using the positioning mark on the first image;

[0192] Optionally, the first correction unit 604 includes:

[0193] The identification module 6041 is used to identify the identification area of ​​the positioning mark on the first image through a template matching algorithm;

[0194] A calculation module 6042, used for calculating an initial correction angle according to the marked area;

[0195] Optionally, four positioning marks are provided on the loading bottom plate, each positioning mark has a different distance from the center of the field of view of the first detection camera, and there are four rectangular marking areas on the first image;

[0196] The computing module 6042 includes:

[0197] Generate four calibration lines on the first image according to the four rectangular marking areas respectively;

[0198] Generate 4 adjustment angles according to 4 calibration lines;

[0199] Generate 4 calculation weights according to the distance from each positioning mark to the center of the field of view of the first detection camera;

[0200] The initial correction angle is calculated based on the 4 calculation weights and the 4 adjustment angles.

[0201] The correction module 6043 is used to control the motor shaft and perform a correction on the carrier according to the initial correction angle.

[0202] The second generating unit 605 is used to collect images through the first detection camera to generate a second image;

[0203] A determination unit 606 is used to detect the area of ​​the screen to be detected on the second image, and determine a set of center coordinates of a rectangular frame of each screen to be detected;

[0204] The third generating unit 607 is used to generate a horizontal correction line according to the rectangular frame center coordinate set;

[0205] Optionally, the third generating unit 607 includes:

[0206] The screen to be tested on the screen plug-in slot is lit up by the same calibration picture. The calibration picture is set with 4 calibration points, and the center of the rectangle formed by the 4 calibration points is the center of the calibration picture;

[0207] Capturing an image through the first detection camera to generate a third image;

[0208] Determine the four calibration points on each screen to be detected, calculate the screen center coordinates for each screen to be detected, and generate a screen center coordinate set;

[0209] Perform straight line fitting on the rectangular frame center coordinate set to generate a first fitting straight line;

[0210] The first fitting straight line is used to filter out the coordinates of the center of the rectangular frame whose deviation is greater than a preset condition;

[0211] Compare the corresponding points of the screen center coordinate set with the screened rectangular frame center coordinate set, and select the target point set that meets both the distance deviation condition and the azimuth deviation condition according to the comparison result;

[0212] Generate a horizontal correction line based on a set of target points.

[0213] The second correction unit 608 is used to verify the correction degree of the stage according to the horizontal correction line, and perform secondary correction if the verification fails;

[0214] A collection unit 609, configured to collect images through a first detection camera;

[0215] The recognition unit 610 is used to use the template matching algorithm to identify the arrangement of the screen to be detected on the loading base plate using the collected image, and identify the missing data of the screen to be detected;

[0216] A displacement unit 611 is used to move the stage to a position on the detection area corresponding to the center position of the field of view of the first detection camera;

[0217] The detection unit 612 is used to detect the screen to be detected on the loading base plate through a second detection camera on the detection area.

[0218] The detection unit 612 includes:

[0219] The screen to be inspected on the loading base plate is inspected by a second inspection camera on the inspection area in combination with the missing data.

[0220] See also Figure 7 , the present application provides a display screen image preprocessing system, comprising:

[0221] Processor 701 , memory 702 , input / output unit 703 , and bus 704 .

[0222] The processor 701 is connected to the memory 702 , the input and output unit 703 , and the bus 704 .

[0223] The memory 702 stores a program, and the processor 701 calls the program to execute the following steps: Figure 1 , Figure 2 , Figure 3 Figure 4 and Figure 5 The method in .

[0224] The present application provides a computer-readable storage medium, on which a program is stored, and when the program is executed on a computer, the program performs the following steps: Figure 1 , Figure 2 , Figure 3 Figure 4 and Figure 5The method in .

[0225] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0226] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0227] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0228] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0229] If the integrated unit is implemented in the form of a software functional unit and sold or passed as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims

1. A method for correcting a multi-screen detection stage, characterized in that: include: Placing a screen to be tested on a screen plugging slot of a loading base plate, wherein a positioning mark is provided on the loading base plate, and at least two screen plugging slots arranged along a first direction are provided on the loading base plate; Fixing the loading base plate on the stage, adjusting the displacement of the stage so that the first screen to be inspected on the loading base plate reaches the center position of the field of view of the first inspection camera, and recording the current position of the stage; Capturing an image of the loading base plate by using the first detection camera to generate a first image; Performing a first correction on the stage according to the positioning mark on the first image; After the correction is completed, the first detection camera is used to collect an image of the loading base plate to generate a second image; Detecting the area of ​​the screen to be detected on the second image, and determining a set of center coordinates of a rectangular frame of each screen to be detected; Generate a horizontal correction line according to the rectangular frame center coordinate set; Generate a horizontal correction line according to the rectangular frame center coordinate set, including: light up the screen to be detected on the screen plug-in slot through the same calibration picture, the calibration picture is provided with 4 calibration points, and the center of the rectangle formed by the 4 calibration points is the center of the calibration picture; perform image acquisition through the first detection camera to generate a third image; determine the 4 calibration points on each screen to be detected, and calculate the screen center coordinates for each screen to be detected to generate a screen center coordinate set; perform straight line fitting on the rectangular frame center coordinate set to generate a first fitting straight line; filter out the rectangular frame center coordinate set with deviations greater than a preset condition through the first fitting straight line; compare the corresponding points of the screen center coordinate set with the screen center coordinate set after filtering, and filter out a target point set that meets both the distance deviation condition and the azimuth deviation condition according to the comparison result; generate a horizontal correction line according to the target point set; The correction degree of the carrier is verified according to the horizontal correction line, and a secondary correction is performed if the verification fails.

2. The method according to claim 1, characterized in that Correcting the stage once using the positioning mark on the first image includes: Identify the identification area of ​​the positioning mark on the first image by a template matching algorithm; Calculating an initial correction angle according to the marked area; The motor shaft is controlled and the stage is corrected once according to the initial correction angle.

3. The method according to claim 2, characterized in that Four positioning marks are arranged on the loading bottom plate, each of the positioning marks has a different distance from the center of the field of view of the first detection camera, and there are four rectangular marking areas on the first image; Calculating an initial correction angle according to the marked area includes: Generate four calibration lines respectively on the first image according to the four rectangular marking areas; Generate four adjustment angles respectively according to the four calibration lines; Generate four calculation weights respectively according to the distance from each of the positioning markers to the center of the field of view of the first detection camera; An initial correction angle is calculated according to the four calculation weights and the four adjustment angles.

4. The method according to any one of claims 1 to 3, characterized in that After verifying the degree of correction of the stage according to the horizontal correction line and performing secondary correction when the verification fails, the method further includes: Moving the stage to a position on the detection area corresponding to the center position of the field of view of the first detection camera; The screen to be inspected on the loading bottom plate is inspected by the second inspection camera on the inspection area.

5. The method according to claim 4, characterized in that After verifying the degree of correction of the stage according to the horizontal correction line and performing secondary correction when the verification fails, before moving the stage to a position on the detection area corresponding to the center position of the field of view of the first detection camera, the method further includes: Capturing images through the first detection camera; Using the template matching algorithm to identify the arrangement of the screen to be detected on the loading base plate, the collected image is used to identify the missing data of the screen to be detected; The detecting the screen to be detected on the loading bottom plate by the second detection camera on the detection area includes: The screen to be inspected on the loading base plate is inspected by using a second inspection camera on the inspection area in combination with the missing data.

6. A device for correcting a multi-screen detection stage, characterized in that: include: A placement unit, used for placing the screen to be tested on the screen plug-in slot of the loading base plate, the loading base plate is provided with a positioning mark, and the loading base plate is provided with at least two screen plug-in slots arranged neatly in horizontal direction; An adjusting unit, used for fixing the loading base plate on the stage, adjusting the displacement of the stage so that the first screen to be detected on the loading base plate reaches the center position of the field of view of the first detection camera, and recording the current position of the stage; A first generating unit, configured to collect images through the first detection camera to generate a first image; A first correction unit, used for performing a correction on the stage by using the positioning mark on the first image; A second generating unit, configured to collect an image through the first detection camera to generate a second image; A determination unit, configured to detect the area of ​​the screen to be detected on the second image, and determine a set of center coordinates of a rectangular frame of each screen to be detected; A third generating unit, configured to generate a horizontal correction line according to the rectangular frame center coordinate set; The third generation unit includes: The screen to be detected on the screen plug-in slot is lit up by the same calibration picture, and the calibration picture is provided with 4 calibration points, and the center of the rectangle formed by the 4 calibration points is the center of the calibration picture; the image is collected by the first detection camera to generate a third image; the 4 calibration points on each screen to be detected are determined, and the screen center coordinates for each screen to be detected are calculated to generate a screen center coordinate set; a straight line is fitted to the rectangular frame center coordinate set to generate a first fitting straight line; the rectangular frame center coordinate set with a deviation greater than a preset condition is screened out by the first fitting straight line; the corresponding points of the screen center coordinate set are compared with the screen center coordinate set after screening, and a target point set that meets both the distance deviation condition and the azimuth deviation condition is screened out according to the comparison result; a horizontal correction line is generated according to the target point set; The second correction unit is used to verify the correction degree of the carrier according to the horizontal correction line, and perform secondary correction when the verification fails.

7. The device according to claim 6, characterized in that The first correction unit comprises: An identification module, used for identifying a marking area of ​​the positioning mark on the first image by using a template matching algorithm; A calculation module, used for calculating an initial correction angle according to the marked area; The correction module is used to control the motor shaft and perform a correction on the carrier according to the initial correction angle.

8. A system for multi-screen detection and stage correction, characterized in that: Includes processor, memory, input and output unit and bus; The processor is connected to the memory, the input and output unit, and the bus; The memory stores a program, and the processor calls the program to execute the method according to any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, and when the program is executed on a computer, the method according to any one of claims 1 to 5 is performed.

Images