Screen detection method, device and computer equipment based on visual technology

Abstract

The application relates to a screen detection method and device based on visual technology and a computer device. In one embodiment, a global image of a screen is acquired through a global camera, position information of a defective point is acquired according to the global image, then the camera is moved to a specified position, a plurality of sets of re-judgment photos with different depths are obtained after the focal length of the re-judgment camera lens is adjusted multiple times, the sets of re-judgment photos are analyzed, and the height information of the defective point is compared with the height information of the screen to make a judgment. In this way, multiple re-judgment photos with different depths are obtained through multiple focusing of one re-judgment camera in the scheme, and the height information of the defective point can be directly recognized by using a software algorithm. Whether the detected liquid crystal screen is qualified can be accurately judged according to the height of the defective point and the screen information, and the detection accuracy is improved. In addition, the process can be completely realized through a software algorithm, the manual re-checking process is reduced, the labor cost is saved, the detection efficiency is greatly improved, and the detection time is reduced.

Description

Technical Field

[0001] This disclosure relates to the field of screen detection, and more particularly to a screen detection method, apparatus, and computer device based on vision technology. Background Technology

[0002] With advancements in LCD technology, the cost of LCD panels has continuously decreased, leading to an increasing number of electronic devices adopting LCD screens. Consequently, the increased shipment volume has made the rapid and efficient testing and acceptance of these screens a significant challenge.

[0003] Currently, the mainstream LCD screens are LCD and OLED screens. OLED screens consist of a pixel layer, polarizer, and surface glass, while LCD screens have a backlight and polarizer below the pixel layer. During AOI (automatically optical inspection) of LCD screens, many defects are found. Depending on the manufacturer's definition, these defects are usually smaller than one or more pixels. Traditional LCD screen inspection involves using a 2D area scan camera to photograph the lit screen and analyze the images for potential defects. However, because area scan cameras produce 2D planar images, these defects can only be represented as individual dots. The causes of these defects could be pixel layer defects or dust or foreign matter on the surface glass. Pixel layer defects represent LCD quality issues, while dust or foreign matter on the surface glass can be wiped off without affecting screen quality. Therefore, in traditional inspection processes, screens with defects need to undergo manual review to confirm whether the defects will cause product non-compliance. This makes the inspection process more cumbersome and carries the risk of missed defects.

[0004] Therefore, there is an urgent need for a detection method that can accurately identify the cause of screen defects in one go. Summary of the Invention

[0005] This disclosure provides a screen inspection method, apparatus, and computer device based on vision technology to solve the problem that existing inspection methods are unable to distinguish the causes of screen defects. The technical solution of this disclosure is as follows:

[0006] According to a first aspect of the present disclosure, a screen detection method based on visual technology is provided, comprising:

[0007] Capture a global image of the screen using the global camera;

[0008] The location information of defective points is obtained from the global image;

[0009] Based on the location information, the re-judgment camera is moved to a designated location, and the re-judgment camera uses a liquid lens;

[0010] Adjust the focal length of the liquid lens, and take pictures of the defective points after each focal length adjustment to obtain a set of re-judgment photos;

[0011] The height information of the defective points is obtained from the set of re-evaluated photos;

[0012] Obtain screen height information, and determine whether the screen is qualified based on the screen height information and the height information of the defective points.

[0013] In one embodiment, obtaining the location information of defective points based on the global image includes:

[0014] By performing binarization, the screen display area is set to white, and the area outside the screen display area is set to black. The white area is extracted separately to obtain a magnified image, and the location information of the defective point is obtained based on the magnified image.

[0015] In one embodiment, moving the re-judgment camera to a designated position includes:

[0016] The location information is converted into pixel coordinates using a software algorithm;

[0017] The image coordinates of the global camera and the initial coordinates of the re-judgment camera are calibrated using the nine-point calibration method;

[0018] Obtain the actual coordinates corresponding to the pixel coordinates;

[0019] Move the re-judgment camera to the actual coordinates.

[0020] In one embodiment, adjusting the focal length of the liquid lens includes:

[0021] Adjust the input voltage of the liquid lens to change the internal curvature of the liquid lens so that the focus height difference is a fixed value each time. After each adjustment, take a picture of the defective point to obtain a set of re-judgment pictures.

[0022] In one embodiment, obtaining the height information of the defective points based on the set of re-evaluated photos includes:

[0023] Based on the clarity and grayscale of the defective points, the photo with the clearest focus at the pixel layer in the set of re-examined photos is selected as the pixel layer photo;

[0024] The pixel layer photo is taken as a photo with the focus at 0 micrometers on the pixel reference plane. The next re-evaluated photo is a photo taken at height X, and so on; where X is the focus height difference.

[0025] Compare all the photos in the re-evaluation photo set, and select the photo with the clearest defect as the defect photo;

[0026] The height difference between the defective image and the pixel layer image is calculated based on the quantitative relationship between the intervals between the defective image and the pixel layer image, and the height information of the defective point is determined.

[0027] In one embodiment, determining whether the screen is qualified includes:

[0028] By comparing the height information of the defective point with the screen height information, if the defective point is located above the screen, it is determined to be surface dust and the screen is qualified; if the defective point is located below the screen, it is determined to be an internal foreign object and the screen is unqualified.

[0029] In one embodiment, the screen includes a mobile phone screen, a tablet screen, a television screen, and a computer screen.

[0030] According to a second aspect of the present disclosure, a screen detection device based on vision technology is also provided, comprising:

[0031] The image acquisition module includes a first image acquisition unit and a second image acquisition unit.

[0032] The first image acquisition unit is used to acquire a global image of the screen; the second image acquisition unit is used to acquire a re-evaluation photo of defective points on the screen;

[0033] The control module is used to control the movement of the fixture equipped with the screen, and also to control the movement of the first image acquisition unit and the second image acquisition unit;

[0034] The image processing module is used to process the global image information and calculate the position coordinates of the defective points, and is also used to perform algorithmic recognition on the clarity of the re-judged photo;

[0035] The display module is used to display the information output by the image processing module.

[0036] According to a third aspect of the present disclosure, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0037] According to a fourth aspect of the present disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the steps of the method described above.

[0038] In the technical solution provided in this disclosure, a re-examination camera repeatedly photographs the defective point at different focal lengths to obtain images of the defective point at different depths. Based on the sharpness relationship between the defective point and the pixel layer, the height information of the defective point is calculated using the focus height difference, thereby quickly and effectively determining the cause of the defect. In this way, it can be determined whether the defect will cause product non-conformity during the first inspection of the LCD screen, simplifying the inspection process and saving inspection time and the cost of manual inspection.

[0039] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0040] Figure 1 This is an application environment diagram of a screen detection method based on vision technology in one embodiment;

[0041] Figure 2 This is a flowchart illustrating a screen detection method based on vision technology in one embodiment;

[0042] Figure 3 This is a schematic diagram of the process for preparing to capture an image before obtaining a global image of the screen in one embodiment;

[0043] Figure 4 This is an image obtained by binarizing a global image in one embodiment;

[0044] Figure 5 This is an example of an image where the white area in a binarized image is magnified;

[0045] Figure 6 This is a flowchart illustrating the process of moving the re-judgment camera to a designated position in one embodiment;

[0046] Figure 7 This is a schematic diagram of a process for obtaining the height information of the defective points based on the set of re-judged photos in one embodiment;

[0047] Figure 8 This is the first re-examination photograph taken in one embodiment;

[0048] Figure 9 This is a second re-examination photograph taken in one embodiment;

[0049] Figure 10 This is the third re-examination photograph taken in one embodiment;

[0050] Figure 11 This is a schematic diagram of the structure of a screen to be tested in one embodiment;

[0051] Figure 12This is a structural block diagram of a screen detection device based on vision technology in one embodiment;

[0052] Figure 13 This is an internal structural diagram of a computer device in one embodiment.

[0053] Figure label:

[0054] 11-Host computer; 12-Control computer; 13-Mechanical device; 14-Jig; 15-Global camera; 16-Reassessment camera; 21-Surface glass; 22-Polarizer; 23-Pixel layer. Detailed Implementation

[0055] To enable those skilled in the art to better understand the technical solutions of this disclosure, the technical solutions in the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0056] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitation, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. For example, the use of terms such as "first," "second," etc., is to denote names and does not indicate any specific order.

[0057] In this disclosure, when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is considered to be "connected to" another element or an element "connected" to another element, it can be directly connected to the other element or there may be an intervening element, and should be interpreted broadly; for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0058] The terms “vertical,” “horizontal,” “left,” “right,” “up,” “down,” “front,” “back,” “circumferential,” “direction of travel,” and similar expressions used herein are based on the orientation or positional relationship shown in the accompanying drawings and are used only for the convenience of describing the invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention.

[0059] Unless otherwise defined, the technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the specification of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The terms “and / or,” “and / or,” and “at least one of” as used herein include any and all combinations of one or more of the associated listed items. It should be noted that the connections, links, etc., described in this disclosure can be direct connections via interfaces or pins between devices, or connections via leads.

[0060] The screen detection method based on vision technology disclosed herein can be applied to, for example... Figure 1 The application environment is shown. The host computer 11 is connected to the control computer 12, and can send commands to and receive signals from the control computer 12. The host computer 11 is also connected to the global camera 15 and the re-judgment camera 16, and can send commands to and receive images captured by the global camera 15 and the re-judgment camera 16, and perform image processing on the received images. The control computer 12 is connected to the mechanical device 13, and can control the movement of the movable axis on the mechanical device 13. The mechanical device 13 has a movable fixture 14, which is used to mount the LCD screen to be tested. The mechanical device 13 also has the global camera 15 and the re-judgment camera 16, which are used to take pictures of the LCD screen to be tested. It should be noted that the re-judgment camera 16 is specifically mounted on one movable axis of the mechanical device 13. In some embodiments, the global camera 15 may also be mounted on one movable axis. In some application scenarios, the host computer 11 can be a computer system with processing and computing functions, such as an industrial computer or a personal computer, and the control computer 12 can be a device unit with instruction receiving and control functions, such as a PLC (Programmable Logic Controller).

[0061] In one embodiment, such as Figure 2 As shown, a screen detection method based on vision technology is provided, which can be applied to... Figure 1 Taking the application environment in [the document] as an example, the following steps are included:

[0062] Step S202: Obtain a global image of the screen using the global camera 15.

[0063] The global camera 15 is the camera that takes the first picture of all the screens to be inspected during the inspection process; the global image is the picture obtained from the first picture. The screen is the liquid crystal screen to be inspected, mounted on a movable fixture 14. In some embodiments, the global camera 15 can be a 2D area scan camera.

[0064] Step S204: Obtain the location information of the defective points based on the global image.

[0065] Among them, defective points are foreign objects that may appear in the global image.

[0066] Specifically, after receiving the first global image captured by the global camera 15, the host computer 11 identifies the global image and records the location information of the defective points after identifying them.

[0067] Step S206: Based on the location information of the defective points, move the re-judgment camera 16 to the designated position. The re-judgment camera 16 uses a liquid lens.

[0068] The re-judgment camera 16 is located on a moving axis of the mechanical device 13. After receiving commands from the controller 12, it can move on the same plane. The designated position can be a location convenient for photographing defective points. Generally, the closer the re-judgment camera is to the defective point after movement, the clearer the photographic result and the more accurate the identification effect. The re-judgment camera 16 is also connected to the host computer 11, and can receive instructions from the host computer 11 and output the photographic results to the host computer 11. Furthermore, the imaging lens inside the re-judgment camera 16 uses a liquid lens. A liquid lens is a new type of camera lens composed of water droplets. By pressurizing and adjusting the DC voltage at both ends of a tube using a spring device, a crescent-shaped curved surface equivalent to a glass lens is formed at one end of the tube. The curvature of the curved surface is the focal length of the liquid lens. The focal length is changed by adjusting the voltage, and image software can automatically capture images within the focal length range.

[0069] Specifically, the host computer 11 sends the movement command and the calculated actual coordinates of the defective point to the controller 12. The controller 12 controls the movement axis to move the re-judgment camera 16 to a designated position that facilitates the imaging of the defective point. In some other embodiments, the re-judgment camera can be moved directly above the actual coordinates of the defective point.

[0070] S208, adjust the focal length of the liquid lens, and take pictures of the defective points after each focal length adjustment to obtain a set of re-judgment photos.

[0071] Specifically, the host computer 11 sends multiple commands to the re-judgment camera 16 to adjust the focus and take pictures. The re-judgment camera 16 adjusts the focus of the liquid lens according to the received commands, takes pictures of the defective points after each focus adjustment, and outputs the pictures to the host computer 11, thereby obtaining a set of re-judgment pictures containing multiple re-judgment pictures.

[0072] S210, based on the set of re-judged photos, obtain the height information of the defective points.

[0073] The height information of the defective point refers to the relative relationship between the height of the defective point and the height of the screen pixel layer. Specifically, since the set of re-evaluated photos consists of multiple photos with different depths taken by the liquid lens at different focal lengths, the focusing method of the liquid lens can be set according to a predetermined calculation relationship in some implementations. The host computer 11 can obtain the height information of the defective point by the difference in sharpness of the re-evaluated photos and the predetermined calculation relationship.

[0074] Step S212: Obtain screen height information, and determine whether the screen is qualified based on the screen height information and the height information of the defective points.

[0075] The screen height information refers to the relative height of the LCD screen surface from the bottom of the pixel layer. Each LCD screen has a fixed product thickness depending on its model. This product thickness includes the sum of the thicknesses of all constituent layers of the LCD screen, such as the pixel layer thickness, polarizer thickness, and surface glass thickness, which is also the total height of the LCD screen. Therefore, the relative height information can be obtained by adding the thicknesses of each constituent layer between the pixel layer and the surface glass.

[0076] Specifically, the screen height information is compared with the defective point height information. The screen height information refers to the height of the screen surface from the bottom of the pixel layer, and the defective point height information refers to the relative height of the defective point to the pixel layer. This is used to determine whether the defective point can cause the product to be unqualified.

[0077] In the technical solution provided in this disclosure, a re-examination camera repeatedly photographs the defective point at different focal lengths to obtain images of the defective point at different depths. Based on the sharpness relationship between the defective point and the pixel layer, the height information of the defective point is calculated using the focus height difference, thereby quickly and effectively determining the cause of the defect. In this way, it can be determined whether the defect will cause product non-conformity during the first inspection of the LCD screen, simplifying the inspection process and saving inspection time and the cost of manual inspection.

[0078] In one embodiment, such as Figure 3 As shown, before acquiring a global image of the screen through the global camera 15, the screen detection method further includes:

[0079] In step S102, the controller 12 controls the fixture 14 equipped with the screen to move to the position where the global camera 15 takes a picture;

[0080] In step S104, the controller 12 sends an arrival signal to the host computer 11;

[0081] In step S106, the host computer 11 sends a shooting command to the global camera 15 via software.

[0082] In one embodiment, obtaining the location information of defective points based on the global image specifically includes:

[0083] like Figure 4 As shown, through binarization, the screen display area is set to white, and the area outside the screen display area is set to black. The white area is then extracted to obtain a magnified image (e.g., ...). Figure 5 As shown in the enlarged image, the location information of the defective point is obtained.

[0084] When the global camera 15 takes its first shot, the captured image includes areas outside the screen display area, while the detection only targets the screen display area. Therefore, through the above processing method, the host computer 11 only needs to identify and analyze the magnified image of the display area to obtain the location of the defective point in the magnified image of the display area, which greatly reduces the processing difficulty and allows for more accurate analysis of the defective point.

[0085] In one embodiment, such as Figure 6 As shown, moving the re-judgment camera 16 to the designated position specifically includes:

[0086] Step S302: The location information is converted into pixel coordinates using a software algorithm.

[0087] Since the photos taken by the camera are composed of individual pixels, the host computer 11 obtains a pixel coordinate D(X,Y) by the position of the defective point in the magnified image of the display area.

[0088] Step S304: The image coordinates of the global camera 15 and the initial coordinates of the re-judgment camera 16 are calibrated according to the nine-point calibration method.

[0089] The nine-point calibration method is a method that uses an algorithm to obtain the actual coordinate relationship between points with known coordinates on the calibration object and points in its image.

[0090] In one specific implementation, a calibration plate with multiple points can be placed at the same height on the screen to be tested. A global camera is used to capture and identify nine points, and the image coordinate information of the nine points is output. Then, the re-judgment camera is controlled to move the nine points to the center point of the re-judgment camera's field of view, thereby obtaining the actual positions of the nine re-judgment cameras. The nine points in the image and the actual nine points are then calibrated.

[0091] Step S306: Obtain the actual coordinates corresponding to the pixel coordinates.

[0092] Specifically, the host computer 11 converts the pixel coordinates D(X,Y) of the defective point into the actual coordinates F(X1,Y1) according to the conversion relationship of the nine-point calibration method. The host computer 11 sends the actual coordinates F(X1,Y1) of the defective point to the controller 12 and sends a movement command to the controller 12.

[0093] Step S308: Move the re-judgment camera 16 to the actual coordinates.

[0094] Specifically, the controller 12 controls the moving axis to move the re-judgment camera 16 to coordinate F(X1,Y1).

[0095] The moving axis of the re-judgment camera 16 does not move up or down. After the re-judgment camera 16 moves to coordinate F, it is directly above the defective point.

[0096] In the technical solution provided in this embodiment, using a computer to perform the nine-point calibration method is more efficient and convenient. After obtaining the pixel coordinates of the defective point, the actual coordinates can be calculated more quickly. In addition, since the re-judgment camera does not need to move along the Z-axis after moving, compared to conventional lenses that require multiple Z-axis movements and shooting when moving above the defective point, which require time for movement and stabilization, the use of a liquid lens greatly reduces this time. Therefore, the efficiency is greatly improved, and the detection efficiency is higher.

[0097] In one embodiment, adjusting the focal length of the liquid lens includes:

[0098] By adjusting the input voltage of the liquid lens, the internal curvature of the liquid lens is changed so that the focus height difference is a fixed value each time. After each adjustment, a photo is taken to obtain the set of re-judged photos.

[0099] Specifically, the host computer 11 sets the focusing height difference of the liquid lens via software. This focusing height difference is a fixed value each time. The input voltage is adjusted according to the characteristics of the liquid lens to change the focal length. After focusing, the software controls the liquid lens to take pictures of any defects. After taking the picture, the system refocuses and repeats the process.

[0100] In the above embodiments, by adjusting the input voltage of the liquid lens to change the focal length, a faster and more efficient focusing and shooting process is achieved during the re-judgment process. At the same time, a set of multiple re-judgment photos with different depths from low to high can be obtained, reducing the shooting time of the re-judgment process and improving the re-judgment efficiency.

[0101] In one embodiment, such as Figure 7 As shown, the height information of the defective points obtained from the set of re-evaluated photos includes:

[0102] Step S402: Based on the clarity and grayscale of the defective points, determine the photo with the clearest pixel layer focus in the set of re-examined photos as the pixel layer photo.

[0103] Specifically, the host computer 11 uses an algorithm to analyze and identify all the photos in the set of photos to be reviewed, and selects the photo with the clearest focus at the pixel layer as the pixel layer photo.

[0104] Step S404: The pixel layer photo is taken as a photo with the focal point at 0 micrometers on the pixel reference plane, and the next re-evaluated photo is taken as a photo taken at the X height, and so on.

[0105] Here, the pixel reference plane can be considered as the bottom surface of the pixel layer, and X is the difference in focus height for each focus.

[0106] Specifically, the pixel layer photo is the photo with the clearest pixel layer among all the re-judgment photos. By comparing all the photos in the re-judgment photo set, the photo with the clearest pixel layer is found and regarded as a photo taken with the focus at 0 micrometers below the pixel layer. Since the focus height difference is X for each shot, according to the shooting order of the re-judgment photos, the next re-judgment photo can be regarded as a photo taken with the focus at a height X above the bottom of the pixel layer, and the next re-judgment photo is a photo taken with the focus at a height 2X above the bottom of the pixel layer.

[0107] Step S406: Compare all photos in the re-evaluation photo set and select the photo with the clearest defect as the defect photo.

[0108] The comparison process can be implemented by the host computer 11 using an algorithm.

[0109] Step S408: Calculate the height difference between the defective point photo and the pixel layer photo based on the quantitative relationship between the intervals between the defective point photo and the pixel layer photo, thereby obtaining the height information of the defective point.

[0110] Specifically, in one application scenario, the first re-judgment photo is determined to be a pixel layer photo, and the fourth re-judgment photo is a defective point photo. Since the focus height difference for each shot is X, the focus height difference between the defective point photo and the pixel layer photo can be calculated to be 3X. Therefore, the height of the defective point is 3X heights from the bottom of the pixel layer.

[0111] In one embodiment, determining whether the screen is qualified includes:

[0112] By comparing the height information of the defective point with the screen height information, if the defective point is located above the screen, it is determined to be surface dust or foreign matter, and the screen is qualified; if the defective point is located below the screen, it is determined to be internal foreign matter, and the screen is unqualified.

[0113] To further illustrate the technical solutions and beneficial effects provided in this disclosure, a specific embodiment is provided in conjunction with a specific application scenario:

[0114] During the detection process of a screen to be tested, the following steps are performed: Figure 2 The steps shown;

[0115] After completing step S206, adjust the focus of the liquid lens to make the image clear and take the first re-examination photo. The result is as follows. Figure 8 As shown.

[0116] Continue adjusting the focal length of the liquid lens to achieve a focus height difference of 20µm compared to the first shot, and take a second re-evaluation image. The result is as follows. Figure 9 As shown.

[0117] The focal length of the liquid lens was readjusted to achieve a focus height difference of 20µm compared to the second shot. A third re-evaluation image was then taken, and the result is as follows. Figure 10 As shown in the figure, Width is the horizontal coordinate of the defective point, and Height is the vertical coordinate of the defective point.

[0118] Repeat the above steps until the shooting is complete, resulting in a set of ten re-evaluation photos (only the first three are shown in the attached image).

[0119] In some implementations, software can be used to perform algorithmic identification on all re-evaluation photos to identify the pixel layer with the clearest image in the second re-evaluation photo and the defective point with the clearest image in the third re-evaluation photo.

[0120] Therefore, by using the second re-evaluation photo as the pixel layer photo, the pixel layer photo can be regarded as a photo taken when the focus is on the reference plane at 0 micrometers at the bottom of the pixel layer.

[0121] Using the third re-evaluation photo as the defect photo, the defect photo can be regarded as a photo taken when the focus point is 20um away from the bottom reference plane of the pixel layer.

[0122] Figure 11 This is a schematic diagram of the structure of the screen to be tested, which includes a surface glass 21, a polarizer 22, and a pixel layer 23. The height information of the screen to be tested is obtained, and the total height is 220µm. The thickness of the surface glass 21 plus the polarizer 22 is 180µm. Since the surface glass 21 is at the top of the screen, the polarizer 22 is below it, and the pixel layer 23 is below the polarizer 22, the distance between the polarizer 22 and the bottom surface of the pixel layer 23 is 40µm. According to the calculation process of the re-evaluation photo, the defective point is 20µm above the bottom reference surface of the pixel layer 23. Since the height of the screen to be tested is 220µm, the defective point is located below the screen, indicating that it is caused by an internal foreign object, and the screen to be tested is unqualified.

[0123] In the above embodiments, considering the thickness information of the screen under test, a suitable fixed value is determined for the focus height difference of the liquid lens focal length each time. After multiple focus shots, a set of multiple re-judgment photos is obtained. After identifying the pixel layer photo and the defect photo, the height relationship between the defect and the pixel layer can be obtained. Based on the known screen information, the height position of the defect in the screen is confirmed, which solves the problem that traditional detection methods cannot know the cause of defect formation. Moreover, using a liquid lens for re-judgment shooting can achieve millisecond-level zoom without movement, which greatly reduces the re-judgment shooting time and improves detection efficiency.

[0124] According to a second aspect of the embodiments of this disclosure, such as Figure 12 As shown, a screen detection device based on vision technology is also provided, comprising:

[0125] The image acquisition module 610 includes a first image acquisition unit 612 and a second image acquisition unit 614. The first image acquisition unit 612 is used to acquire a global image of the screen; the second image acquisition unit 614 is used to acquire re-judgment photos of defects on the screen.

[0126] The control module 620 is used to control the movement of the fixture 14 equipped with the screen, and also to control the movement of the first image acquisition unit 612 and the second image acquisition unit 614.

[0127] The central processing module 630 includes an image processing unit 632, a central processing unit 634, and a display unit 636. The image processing unit 632 is connected to the image acquisition module 610 and is used to process the global image information and calculate the position coordinates of the defective points, as well as to perform algorithmic identification of the sharpness of the re-evaluated photograph. The central processing unit 634 is connected to the control module 620 and is used to send data and instructions to the control module. The display unit 636 is connected to the image processing unit 632 and is used to display the output image information and results.

[0128] In one embodiment, the image processing unit is further configured to: perform binarization processing on the global image, set the screen display area to white and the area outside the screen display area to black, extract the white area separately to obtain a magnified image, and obtain the location information of the defective point based on the magnified image.

[0129] In one embodiment, the central processing unit is further configured to: convert the position information of the enlarged image of the defective point screen display area into pixel coordinates using a software algorithm; calibrate the image coordinates of the first image acquisition unit and the initial coordinates of the second image acquisition unit according to the nine-point calibration method; obtain the actual coordinates corresponding to the pixel coordinates; and send the actual coordinates and movement instructions to the control module.

[0130] In one embodiment, the central processing unit is further configured to: adjust the focal length of the second image acquisition unit so that the focus height difference is a fixed value each time, and send a shooting command to the second image acquisition unit after each adjustment to obtain a set of re-judged photos.

[0131] In one embodiment, the central processing unit is further configured to: determine, based on the clarity and grayscale of the defective point, identify the photo with the clearest focus at the pixel layer in the set of re-judgment photos as the pixel layer photo; take the photo taken at a pixel reference plane of 0 micrometers, and the next re-judgment photo is taken at a height of X, and so on; where X is the focus height difference; compare all re-judgment photos, and select the photo with the clearest focus on the defective point as the defective point photo; calculate the height difference between the defective point photo and the pixel layer photo based on the quantitative relationship between the intervals between the defective point photo and the pixel layer photo, thereby obtaining the height information of the defective point.

[0132] Specific limitations regarding the screen detection device based on vision technology can be found in the limitations of the screen detection method based on vision technology described above, and will not be repeated here. Each module in the aforementioned screen detection device based on vision technology can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0133] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 13 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a screen detection method based on vision technology. The computer device can be connected to a controller for controlling mechanical equipment and can also be connected to imaging devices such as cameras. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0134] Those skilled in the art will understand that Figure 13 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0135] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0136] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0137] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0138] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0139] The embodiments described above are merely illustrative of several implementations of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art, upon considering the specification and practicing the invention disclosed herein, will readily conceive of other embodiments of this disclosure. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0140] It should be understood that this disclosure is not limited to the precise structures already described and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A screen detection method based on vision technology, characterized in that, include: Capture a global image of the screen using the global camera; The location information of defective points is obtained from the global image; Based on the location information, the re-judgment camera is moved to a designated location, and the re-judgment camera uses a liquid lens; Adjust the focal length of the liquid lens, and take pictures of the defective points after each focal length adjustment to obtain a set of re-judgment photos; Based on the clarity and grayscale of the defective points in the re-judged photo set, the photo with the clearest pixel layer focus in the re-judged photo set is determined as the pixel layer photo, and the photo with the clearest defective point is determined as the defective point photo. Based on the interval relationship between the defective point photo and the pixel layer photo in the re-judged photo set, and the preset focus height difference, the height information of the defective point is calculated. Obtain screen height information, and determine whether the screen is qualified based on the screen height information and the height information of the defective points.

2. The screen detection method according to claim 1, characterized in that, The step of obtaining the location information of defective points based on the global image includes: By performing binarization, the screen display area is set to white, and the area outside the screen display area is set to black. The white area is extracted separately to obtain a magnified image, and the location information of the defective point is obtained based on the magnified image.

3. The screen detection method according to claim 1, characterized in that, Moving the re-judgment camera to the designated position includes: The location information is converted into pixel coordinates using a software algorithm; The image coordinates of the global camera and the initial coordinates of the re-judgment camera are calibrated according to the nine-point calibration method; The actual coordinates corresponding to the pixel coordinates are obtained; Move the re-judgment camera to the actual coordinates.

4. The screen detection method according to claim 1, characterized in that, Adjusting the focal length of the liquid lens includes: Adjust the input voltage of the liquid lens to change the internal curvature of the liquid lens so that the focus height difference is a fixed value each time. After each adjustment, take a picture of the defective point to obtain the set of re-judgment pictures.

5. The screen detection method according to claim 4, characterized in that, The step of calculating the height information of the defective point relative to the screen pixel layer based on the interval relationship between the defective point photo and the pixel layer photo in the set of re-evaluated photos, and the preset focus height difference, includes: The pixel layer photo is taken as a photo with the focus at 0 micrometers on the pixel reference plane. The next photo is taken at height X, and so on. X is the focus height difference. The height difference between the defective image and the pixel layer image is calculated based on the quantitative relationship between the intervals between the defective image and the pixel layer image, and the height information of the defective point is determined.

6. The screen detection method according to claim 1, characterized in that, The determination of whether the screen is qualified includes: Compare the height information of the defective point with the screen height information; If the defective point is located on the top of the screen, it is determined to be surface dust, and the screen is qualified; if the defective point is located on the bottom of the screen, it is determined to be an internal foreign object, and the screen is unqualified.

7. The screen detection method according to claim 1, characterized in that, The screens include mobile phone screens, tablet screens, television screens, and computer screens.

8. A screen detection device based on vision technology, characterized in that, include: An image acquisition module, comprising a first image acquisition unit and a second image acquisition unit; The first image acquisition unit is used to acquire a global image of the screen; the second image acquisition unit is used to acquire a re-evaluation photo of defective points on the screen; The control module is used to control the movement of the fixture with the screen, and also to control the movement of the first image acquisition unit and the second image acquisition unit; The image processing module is used to process the global image information and calculate the position coordinates of the defective points. It is also used to perform algorithmic recognition on the sharpness of the re-judged photos. Specifically, based on the sharpness and grayscale of the defective points in the re-judged photo set, the photo with the clearest pixel layer focus in the re-judged photo set is determined as the pixel layer photo, and the photo with the clearest defective point is determined as the defective point photo. Based on the interval relationship between the defective point photo and the pixel layer photo in the re-judged photo set, and a preset focus height difference, the height information of the defective point is calculated. The display module is used to display the information output by the image processing module.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images