A display screen detection method and apparatus

Abstract

The application discloses a display screen detection method and device, the method comprises the following steps: firstly, acquiring the image of the detected screen when it is lighted and the image of the qualified screen when it is lighted; then, calculating the first row and column coordinates corresponding to the multiple pixel points of the detected screen and the second row and column coordinates corresponding to the multiple pixel points of the qualified screen from the image of the detected screen and the image of the qualified screen respectively; then, calculating the center coordinates and / or area size of each pixel area according to the first row and column coordinates and the second row and column coordinates, wherein the pixel area is composed of multiple pixel points; finally, establishing the evaluation formula of the detected screen according to the center coordinates and / or area size of the first row and column coordinates and the second row and column coordinates, which is used for evaluating whether the detected screen is qualified. When detecting the to-be-detected screen, the offset degree, screen size, ghosting and distortion of the current to-be-detected screen are evaluated, if the score of any one of them is less than the threshold value, the to-be-detected screen is considered to be unqualified, and the offset degree and the screen size are two indexes that cannot be detected by human eyes, the application can provide accurate information and improve the detection efficiency.

Description

Technical Field

[0001] This invention relates to the field of image detection for smart devices, and in particular to a method and apparatus for detecting display screens. Background Technology

[0002] As people place increasing emphasis on health and exercise assessment, the variety of smart wearable devices capable of detecting human physiological indicators of movement is growing, such as smart bracelets and watches that can detect swimming and running indicators. In recent years, with the development of optical technology and the exploration of digital twins and visualization, the demand for visualized data is becoming increasingly easier to meet. In AR glasses, visually projecting data displayed on an OLED screen using optomechanical devices is gradually becoming a trend. However, this leads to problems. The image projected onto the OLED screen by optomechanical devices may have some display defects, such as: the position of the displayed image changing, causing the image the user needs to see to be off-center from the ideal display position, a deviation known as offset; secondly, the size of the displayed image may change, and ghosting or distortion may occur due to display defects on the OLED screen or problems with the optomechanical device's projection. In the process of detecting display defects in smart wearable devices, it is necessary to calculate four indicators: offset, image size, ghosting, and distortion, and to score these four indicators for different devices to distinguish their quality.

[0003] Traditional display defect detection methods typically involve manual inspection, where inspectors on the production line visually observe each display and subjectively evaluate its quality. This method has several drawbacks. Firstly, offset and image size are often not directly observable by the human eye, making it impossible to determine image size and offset directly. Secondly, manually inspecting a large number of products for offset, image size, ghosting, and distortion is a difficult task. Prolonged inspections lead to salt fatigue, and the inherent uncertainty of subjective judgment results in numerous false positives.

[0004] Existing patents disclose a method for detecting display defects, which includes acquiring each pixel of a sampled image, performing brightness removal processing on each pixel to find the defect location, and replacing the defective pixels with brightness compensation from high to low. The brightness compensation process is relatively complex. In some display screens to be sampled, there are more or less defective products. Eliminating a small number of defective products is relatively more labor-saving and cost-effective.

[0005] Existing patents also disclose a method for detecting a display screen, which includes acquiring a grayscale histogram of an image of the display screen to be tested, calculating the area of ​​the defective region of the display screen to be tested using the Bartlett distance method, detecting missing pixels in different regions, and then accumulating all the missing pixels. If a certain threshold is met, it is judged as a defective product. The detection method is relatively simple, only considering the case where the pixels are not lit, and does not consider the case of screen distortion or ghosting.

[0006] Existing patents also disclose a screen detection method, apparatus, and head-mounted display device, including acquiring an original image of the screen to be detected, removing interference information from the original image to obtain a detection image; extracting edge regions of the detection image based on the screen contour; detecting lines and the position of line center points in the edge regions using a line extraction algorithm, using the screen contour as a boundary line, selecting the region where the line center point is located as a suspected defect region when the position of the line center point is within the screen contour; selecting key pixels in the suspected defect region, binarizing the key pixels based on a binarization threshold, obtaining defect index detection values ​​based on the binarization results of the key pixels; and comparing the defect index detection values ​​with corresponding defect indicators to obtain the detection result. Summary of the Invention

[0007] The purpose of this invention is to provide a display screen testing method and apparatus, which simultaneously scores the offset, screen size, ghosting, and distortion of the test samples, distinguishes the quality of each indicator of different test samples, and eliminates unqualified products among the test samples.

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A method for detecting a display screen, comprising:

[0010] Acquire images of the screen being tested when it is lit and images of the qualified screen when it is lit;

[0011] The first row and column coordinates corresponding to multiple pixels of the screen under test and the second row and column coordinates corresponding to multiple pixels of the screen under test are calculated from the image of the screen under test and the image of the qualified screen, respectively.

[0012] The center coordinates and / or size of each pixel region are calculated based on the first row and column coordinates and the second row and column coordinates, wherein the pixel region is composed of multiple pixels; and

[0013] An evaluation formula for the screen under test is established based on the center coordinates of the first row and column coordinates and the second row and column coordinates and / or the area size, and is used to evaluate whether the screen under test is qualified.

[0014] Optionally, calculating the first row and column coordinates and the second row and column coordinates includes:

[0015] The images of the screen under test and the screen that is tested lit up are respectively subjected to grayscale processing, binarization processing, and noise reduction processing to obtain binarized images;

[0016] Select the pixels with a grayscale value of 255 in the binarized image to obtain the first row and column coordinates and the second row and column coordinates corresponding to multiple pixels.

[0017] Optionally, calculating the center coordinates and / or size of each pixel region based on the first row and column coordinates and the second row and column coordinates includes:

[0018] Based on the first row and column coordinates and the second row and column coordinates, the maximum and minimum values ​​of the row and column coordinates of each pixel region are calculated to determine the region size of each pixel region in the detected screen and the region size of each pixel region in the qualified screen.

[0019] Optionally, the step of establishing an evaluation formula for the screen under test based on the center coordinates of the first row and column coordinates and / or the area size of the second row and column coordinates, used to evaluate whether the screen under test is qualified, includes:

[0020] The evaluation formula for the screen being tested is established as follows:

[0021]

[0022] Where s1 is the matching degree between the detected screen and the qualified screen, n1 is the size of one or more pixel regions in the detected screen, and n is the size of one or more pixel regions in the qualified screen. It is the relative error between the screen being tested and the qualified screen, and β is a set parameter.

[0023] Optionally, the step of establishing an evaluation formula for the screen under test based on the center coordinates of the first row and column coordinates and / or the area size of the second row and column coordinates, used to evaluate whether the screen under test is qualified, includes:

[0024] The evaluation formula for the screen being tested is established as follows:

[0025]

[0026] Where s2 is the ghosting intensity of the screen being tested, p i and q i w represents the length and width of each pixel region in the screen being detected, respectively. i and h i These represent the length and width of each pixel region in a valid screen, respectively, with abs indicating the absolute value. These are the set parameters. The summation is expressed as a summation.

[0027] Optionally, calculating the center coordinates and / or size of each pixel region based on the first row and column coordinates and the second row and column coordinates includes:

[0028] Based on the first row and column coordinates and the second row and column coordinates, the maximum and minimum values ​​of the row and column coordinates of each pixel region are calculated respectively, and the average value of the maximum and minimum values ​​is determined as the center coordinates of each pixel region in the detected screen and the center coordinates of each pixel region in the qualified screen.

[0029] Optionally, the step of establishing an evaluation formula for the screen under test based on the center coordinates of the first row and column coordinates and / or the area size of the second row and column coordinates, used to evaluate whether the screen under test is qualified, includes:

[0030] The evaluation formula for the screen being tested is established as follows:

[0031] in, It is the offset of the center coordinates of one or more pixel regions in the tested screen and the qualified screen. These are the set parameters, where (x1, y1) and (x, y) represent the center coordinates of each pixel region in the qualified screen and the center coordinates of each pixel region in the tested screen, respectively.

[0032] Optionally, the step of establishing an evaluation formula for the screen under test based on the center coordinates of the first row and column coordinates and / or the area size of the second row and column coordinates, used to evaluate whether the screen under test is qualified, includes:

[0033] The evaluation formula for the screen being tested is established as follows:

[0034]

[0035] in, These are the set parameters, (e) ix e iy (d) ix d iy ( ) represent the center coordinates of each pixel region in the qualified screen and the center coordinates of each pixel region in the tested screen, respectively. This indicates a summation.

[0036] Optionally, the image is one of a center image, a white image, a 9-dot image, and a 35-dot image.

[0037] A display screen detection device, comprising:

[0038] Memory, used to store computer programs;

[0039] A processor is configured to implement the steps of the display screen detection method described above when executing the computer program.

[0040] As can be seen from the above technical solution, the display screen detection method and apparatus provided by the present invention includes: firstly, acquiring an image of the screen to be tested when it is lit up and an image of the qualified screen when it is lit up; then, calculating the first row and column coordinates corresponding to multiple pixels of the screen to be tested and the second row and column coordinates corresponding to multiple pixels of the qualified screen from the image of the screen to be tested and the image of the qualified screen, respectively; then, calculating the center coordinates and / or area size of each pixel area according to the first row and column coordinates and the second row and column coordinates, wherein the pixel area is composed of multiple pixels; finally, establishing an evaluation formula for the screen to be tested according to the center coordinates and / or area size of the first row and column coordinates and the second row and column coordinates, for evaluating whether the screen to be tested is qualified.

[0041] The display screen detection method and apparatus of the present invention calculate the offset between the current screen to be tested and the qualified screen based on the image displayed by the optomechanical system, and score the offset of each screen to be tested to remove unqualified screens; calculate the screen size of the current screen to be tested, score the screen size of each screen to be tested to remove unqualified screens; and score the ghosting and distortion of the display image of the current screen to be tested to remove unqualified products.

[0042] Based on four display images of qualified products deemed to have good display quality, this method calculates prior information for qualified screens and uses this prior information as a reference threshold. When inspecting a screen to be tested, this prior information is used to evaluate the screen's offset, screen size, ghosting, and distortion. If any of these evaluation scores is below the threshold, the screen is considered unqualified and is removed. In the process of inspecting the optomechanical display image effect of smart devices, offset and screen size are two indicators that inspectors cannot detect with the human eye. This method can provide accurate information to distinguish whether these indicators are qualified. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart of a display screen detection method provided in an embodiment of the present invention;

[0045] Figure 2 This is a 9-pixel image provided in an embodiment of the present invention;

[0046] Figure 3 A flowchart of a display screen detection method provided in another embodiment of the present invention.

[0047] Figure 4(a) is an image of the screen being tested before correction in one embodiment of the present invention;

[0048] Figure 4(b) is an image of the screen image under test shown in Figure 4(a) after correction in one embodiment of the present invention;

[0049] Figure 5 This embodiment provides a flowchart of a specific implementation method for a display screen detection method.

[0050] Figure 6 This is a structural diagram of a display screen detection method provided in an embodiment of the present invention. Implementation

[0051] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0052] Please refer to Figure 1 , Figure 1 This is a flowchart of a display screen detection method provided in this embodiment, as follows: Figure 1 As shown, this display screen detection method includes the following steps:

[0053] S11: Acquire the image of the screen being tested when it is lit up and the image of the qualified screen when it is lit up;

[0054] S12: Perform grayscale processing, binarization processing, and noise reduction processing on the image of the detected screen when it is lit and the image of the qualified screen when it is lit to obtain a binarized image;

[0055] S13: Select the pixels with a grayscale value of 255 in the binarized image to obtain the first row and column coordinates corresponding to multiple pixels of the screen being tested and the second row and column coordinates corresponding to multiple pixels of the qualified screen.

[0056] S14: Based on the first row and column coordinates and the second row and column coordinates, calculate the maximum and minimum values ​​of the row and column coordinates of each pixel region to determine the region size of each pixel region in the detected screen and the region size of each pixel region in the qualified screen, wherein each pixel region is composed of multiple pixels; and

[0057] S15: Establish an evaluation formula for the screen under test based on the area size of the first row and column coordinates and the second row and column coordinates, which is used to evaluate whether the screen under test is qualified.

[0058] This embodiment's method is used to calculate the matching degree of screen size between the screen to be tested and the qualified screen. Based on a full-white image of the qualified screen, the full-white image needs to illuminate all pixel areas of both the screen to be tested and the qualified screen. First, the full-white image of the qualified screen is converted into a grayscale image. Grayscale processing means representing the brightness of each pixel in the image numerically, ranging from 0 to 255, with 255 being the brightest and 0 being the darkest. Second, the grayscale image is binarized to obtain a binarized image. Binarization processing means binarizing all grayscale images, leaving only pixels with a grayscale value of 0 or 255. Then, a dilation and erosion operation is performed on the binarized image to remove noise from the pixels; brightness shaving serves the same function.

[0059] Each pixel region contains multiple pixels, each with corresponding row and column coordinates. The maximum and minimum values ​​of the row and column coordinates for each pixel region are calculated. Subtracting the minimum from the maximum gives the size of each pixel region. The number of pixels with a grayscale value of 255 in each pixel region is then counted. The sum of these counts across all pixel regions is used as the screen size *n* of a qualified screen. The size *n1* of the all-white image in the currently inspected screen is calculated using the same method. The evaluation formula for the inspected screen is established as follows:

[0060]

[0061] Where s1 is the matching degree between the detected screen and the qualified screen, n1 is the size of one or more pixel regions in the detected screen, and n is the size of one or more pixel regions in the qualified screen. This represents the relative error between the tested screen and the qualified screen, where β is a set parameter. It indicates that when the relative error is β, the screen size score is 60, meaning it's just a qualified product. The smaller the difference in screen size between the tested screen and the qualified screen's all-white image, the higher the score.

[0062] The ghosting of the screen being tested is calculated using the method described in the above embodiments, such as... Figure 2 As shown, Figure 2The 9-dot pixel map provided in this embodiment is used to evaluate screen ghosting based on a qualified screen, where each dot represents a pixel region. However, this is not limited to 9 pixel regions; in fact, 12 regions are also acceptable. Each pixel region consists of multiple pixels, and the size M of each region can be determined by the maximum and minimum values ​​of its row and column coordinates. i = (w i h i Similarly, the size N of each region in the 9-dot map of the screen being detected is obtained. i =(p i q i The evaluation formula for the screen being tested is established as follows:

[0063]

[0064] Where s2 is the ghosting intensity of the screen being tested, p i and q i w represents the length and width of each pixel region in the screen being detected, respectively. i and h i These represent the length and width of each pixel region in a valid screen, respectively, with abs indicating the absolute value. These are the set parameters. This indicates summation. If the s2 evaluation score is greater than the threshold, such as 60, then the ghosting of the screen under test is considered acceptable.

[0065] In another embodiment of this application, a flowchart of a display screen detection method is provided, which can be specifically referred to. Figure 3 This display screen detection method includes the following steps:

[0066] S21: Acquire the image of the screen being tested when it is lit up and the image of the qualified screen when it is lit up;

[0067] S22: Perform grayscale processing, binarization processing, and noise reduction processing on the image of the screen being tested when it is lit and the image of the qualified screen when it is lit, respectively, to obtain a binarized image;

[0068] S23: Select the pixels with a grayscale value of 255 in the binarized image to obtain the first row and column coordinates corresponding to multiple pixels of the screen being tested and the second row and column coordinates corresponding to multiple pixels of the qualified screen.

[0069] S24: Based on the first row and column coordinates and the second row and column coordinates, calculate the maximum and minimum values ​​of the row and column coordinates of each pixel region, and calculate the average of the maximum and minimum values ​​to determine the center coordinates of each pixel region in the detected screen and the center coordinates of each pixel region in the qualified screen, wherein each pixel region is composed of multiple pixels; and

[0070] S25: Establish an evaluation formula for the screen under test based on the area size of the first row and column coordinates and the second row and column coordinates, which is used to evaluate whether the screen under test is qualified.

[0071] This embodiment is based on the center image of a qualified screen that has been illuminated. First, the center image of the qualified screen is converted into a grayscale image. Grayscale processing means representing the brightness of each pixel in the image with a numerical value, ranging from 0 to 255, with 255 being the brightest and 0 being the darkest. Second, the grayscale image is binarized to obtain a binarized image. Binarization means binarizing all grayscale images, leaving only pixels with a grayscale value of 0 or 255. Then, a dilation and erosion operation is performed on the binarized image to remove noise from the pixels. Brightness noise reduction processing here serves the same function.

[0072] Each pixel region contains multiple pixels, each with corresponding row and column coordinates. The maximum and minimum values ​​of the row and column coordinates for each pixel region are calculated. The average of the maximum row and column coordinates is used as the row and column coordinates of the center point of the center image. The center coordinates of the center point of the qualified screen's center image are thus obtained as c = (x, y). Using the same method, the center coordinates of the center point of the screen being inspected are obtained as c1 = (x1, y1). An evaluation formula for the inspected screen is established based on the offset between the inspected screen and the qualified screen.

[0073]

[0074] in, It is the offset of the center coordinates of one or more pixel regions in the tested screen and the qualified screen. These are the set parameters, where (x1, y1) and (x, y) represent the center coordinates of each pixel region in the qualified screen and the center coordinates of each pixel region in the screen being tested, respectively. If the S3 evaluation score is greater than the threshold, such as 60, then the offset of the screen to be tested is considered qualified.

[0075] Optionally, if the center coordinates of the screen being tested and the qualified screen are the same, but the center image is offset, the following method should be used for correction, including the following steps:

[0076] The center map contour of the screen being tested is detected in the image captured by the screen being tested. The four corners of the contour are divided into ABCO, as shown in Figure 4(a) with the tilted center map 101 corresponding to the screen being tested 100.

[0077] According to the preset standard frame, rotate or translate the image of the screen to be detected so that the image of the screen to be detected matches the standard frame. The corrected image is used as the image of the screen to be detected, as shown in the corrected center figure 101 in Figure 4(b), where the four corners ABCO of the outline are the corrected coordinate points.

[0078] The image of the screen being detected is rotated or translated. The image of the screen being detected refers to the image corresponding to the screen being detected in the captured image. According to the preset standard frame, the image of the screen being detected is made to match the standard frame so that the image of the screen being detected remains horizontal and without tilt.

[0079] Optionally, if the image captured of the screen to be detected is a color image, it can be converted to grayscale first, and the detection can be performed on the grayscale image. Optionally, threshold binarization can also be performed on the grayscale image to more accurately detect the screen image to be detected from the image.

[0080] Optionally, a CCD camera can be used to capture images of the display screen. Before capturing the image, the relative positions of the CCD camera and the display screen should be fixed. If a slight change in the relative positions of the CCD camera and the display screen occurs during the capturing process, causing the display screen to not remain horizontal in the captured image, this can be corrected using the method described above.

[0081] In another embodiment, a 35-dot map of the qualified screen is used, where each dot represents a region. The 35-dot map represents 35 pixel regions that illuminate the qualified screen, but this is not limited to 35. Image distortion has two causes: one is the influence of the lens's shape on light propagation, and the other is that the lens and the imaging plane are not perfectly parallel, such as color cast, blurring, geometric distortion, geometric tilt, etc., all of which can cause distortion. The distortion of the screen being tested is calculated using the method described in the above embodiment. The evaluation formula for the screen being tested is established as follows:

[0082]

[0083] in, These are the set parameters, (e) ix e iy (d) ix d iy ( ) represent the center coordinates of each pixel region in the qualified screen and the center coordinates of each pixel region in the tested screen, respectively. This indicates a summation. If the S4 evaluation score is greater than the threshold, such as 60, then the distortion of the screen being tested is considered acceptable.

[0084] This embodiment provides a specific implementation method for a display screen detection method, including:

[0085] By illuminating different positions and numbers of pixels on the OLED, the OLED displays different images. Therefore, the optical engine also displays different images, and a CCD captures the image displayed when the OLED is off. The OLED pixels are illuminated at various levels: all pixels are lit, only the center pixel is lit, 9 pixels are lit, and 35 pixels are lit. The CCD then sequentially captures a full white image, a center image, a 9-pixel image, and a 35-pixel image. Based on the center image, full white image, 9-pixel image, and 35-pixel image displayed by the optical engine, the center image, full white image, 9-pixel image, and 35-pixel image of a qualified product are manually selected. The positions of the center image, full white image, 9-pixel image, and 35-pixel image of the qualified product are calculated as reference thresholds. When testing a product to be inspected, the positions of its center image, full white image, 9-pixel image, and 35-pixel image are calculated sequentially. The deviation between the center image positions of the qualified product and the product to be inspected is calculated; this deviation is the offset of the center point. Based on the position information of the full white images of the qualified product and the product to be inspected, the display screen size of both products can be determined. Based on the positional information of the 9-dot images of qualified and untested products, the ghosting of the untested product image is calculated. Based on the positional information of the 35-dot images of qualified and untested products, the distortion of the untested product image is calculated. According to the image displayed by the optomechanical system, the offset between the current untested product and qualified products is calculated, and the offset of each untested product is scored, eliminating unqualified products; the screen size of the current untested product is calculated, and the screen size of each untested product is scored, eliminating unqualified products; the ghosting and distortion of the displayed image of the current untested product are scored, and unqualified products are eliminated.

[0086] Based on four display images of qualified products selected by human screening for good display quality, this embodiment calculates the prior information of the corresponding qualified products and uses this prior information as a reference threshold. When inspecting the product to be inspected, this prior information is used to evaluate the offset, screen size, ghosting, and distortion of the current product, and unqualified products are eliminated. In the process of inspecting the optical-mechanical display image effect of smart devices, offset and screen size are two indicators that inspectors cannot detect with the human eye. This embodiment can provide accurate information to distinguish whether these two indicators are qualified. For the ghosting and distortion indicators, this embodiment scores these two indicators. If the score is less than the threshold, these two indicators are considered unqualified, and the product is considered qualified.

[0087] like Figure 5 As shown, this embodiment provides a specific implementation method for a display screen detection method, including:

[0088] By illuminating different positions and numbers of pixels on the OLED, the OLED displays different images. Consequently, the optical engine module also displays different images, and a CCD captures the image displayed when the OLED is off. The CCD sequentially captures images of a full white image, a center image, a 9-pixel image, and a 35-pixel image by illuminating all OLED pixels, only the center pixel, 9 pixels, and 35 pixels.

[0089] Based on the center image, full white image, 9-dot image, and 35-dot image displayed by the optomechanical system, the center image, full white image, 9-dot image, and 35-dot image of the qualified product are selected, and their positions are calculated as reference thresholds. When testing the product to be inspected, its center image position, full white image position, 9-dot image position, and 35-dot image position are calculated sequentially. The deviation between the center image position of the qualified product and the center image position of the product to be inspected is calculated; this deviation is the offset of the center point. Based on the position information of the full white images of the qualified product and the product to be inspected, the display screen size of the qualified product and the product to be inspected can be obtained. Based on the position information of the 9-dot image of the qualified product and the product to be inspected, the ghosting of the product image to be inspected is calculated. Based on the position information of the 35-dot image of the qualified product and the product to be inspected, the distortion of the product image to be inspected is calculated according to the evaluation formula. Based on the image displayed by the optical engine, the offset between the current test item and the qualified item is calculated according to the evaluation formula, and the offset of each test item is scored, eliminating unqualified items; the screen size of the current test item is calculated, and the screen size of each test item is scored, eliminating unqualified items; the ghosting and distortion of the displayed image of the current test item are scored, and unqualified items are eliminated. Only when the evaluation of each indicator of the test item—offset, ghosting, screen size, and distortion—is greater than the threshold, is the test item considered qualified.

[0090] Figure 6 A structural diagram of a display screen detection device provided in this embodiment includes:

[0091] Memory 60 is used to store computer programs;

[0092] The processor 61 is used to execute computer programs to implement the steps of the display screen detection method mentioned in the above embodiments.

[0093] The display screen detection device provided in this embodiment may include, but is not limited to, smartphones, tablets, laptops, or desktop computers.

[0094] The processor 61 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 61 may be implemented using at least one hardware form selected from Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 61 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 61 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 61 may also include an Artificial Intelligence (AI) processor, which handles computational operations related to machine learning.

[0095] The memory 60 may include one or more computer-readable storage media, which may be non-transitory. The memory 60 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 60 is used to store at least the following computer program, which, after being loaded and executed by the processor 61, is capable of implementing the relevant steps of the display screen detection method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 60 may also include an operating system and data, and the storage method may be temporary or permanent. The operating system may include Windows, Unix, Linux, etc. The data may include, but is not limited to, the display screen detection method.

[0096] In some embodiments, the display screen testing device may further include a display screen, an input / output interface, a communication interface, a power supply, and a communication bus.

[0097] Those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the display screen detection device and may include more or fewer components than shown.

[0098] The display screen detection device provided in this application includes a memory 60 and a processor 61. When the processor 61 executes the program stored in the memory 50, it can implement the display screen detection method.

[0099] Finally, this application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps described in the above method embodiments.

[0100] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] The display screen testing device of the above embodiment, in a manually selected set of 325 qualified products, the test results of this display screen testing device are shown in the table below, where the pass rate for the two indicators of screen size and distortion is 99%. In fact, for the detection of offset, screen size, distortion and ghosting, each embodiment can be used alone or in combination, and no specific limitation is made here.

[0102] Compared with the prior art, this embodiment has the following advantages, as shown in Table 1:

[0103] Table 1

[0104] index offset Screen size distortion Double image pass rate % 93 99 99 88

[0105] Compared to manual inspection, this embodiment can calculate the offset and screen size; and score the offset and screen size, thereby improving inspection efficiency and saving labor costs.

[0106] Compared to existing technologies, which typically only detect whether pixels are missing before performing brightness compensation, this approach is relatively simplistic and prone to false positives. This embodiment provides multiple detection methods, including offset, screen size, distortion, and ghosting, allowing for different processing of display screens with different problems.

[0107] This application is based on image detection formed by the display screen through a lens, and does not simply detect whether the display screen is qualified. Therefore, it involves multiple detections, such as offset, screen size, distortion, and ghosting, especially distortion detection. It is not simply a matter of detecting the brightness of pixels to determine whether the display screen is qualified.

[0108] The present invention has provided a detailed description of a display screen detection method and apparatus. Specific examples have been used to illustrate the principles and specific implementation methods of the invention. The descriptions of these embodiments are merely illustrative of the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to the invention without departing from its principles, and these improvements and modifications also fall within the scope of protection of the claims.

Claims

1. A display screen detection method characterized by, The method comprises the following steps: acquiring an image of a detected screen when the screen is lighted and an image of a qualified screen when the screen is lighted; calculating first row and column coordinates corresponding to a plurality of pixel points of the detected screen and second row and column coordinates corresponding to a plurality of pixel points of the qualified screen respectively from the image of the detected screen and the image of the qualified screen; calculating center coordinates and / or area sizes of each pixel area according to the first row and column coordinates and the second row and column coordinates, wherein the pixel area is composed of a plurality of pixel points; and establishing an evaluation formula of the detected screen according to the center coordinates and / or area sizes of the first row and column coordinates and the second row and column coordinates, so as to evaluate whether the detected screen is qualified; the calculation of the first row and column coordinates and the second row and column coordinates comprises: performing gray processing, binary processing and noise removal processing on the image of the detected screen when the screen is lighted and the image of the qualified screen when the screen is lighted respectively to obtain binary images; selecting pixel points with a gray value of 255 in the binary images to obtain the first row and column coordinates and the second row and column coordinates corresponding to a plurality of the pixel points; the calculation of the center coordinates and / or area sizes of each pixel area according to the first row and column coordinates and the second row and column coordinates comprises: according to the first row and column coordinates and the second row and column coordinates, counting maximum and minimum values of the row and column coordinates of each pixel area to determine the area sizes of each pixel area in the detected screen and the area sizes of each pixel area in the qualified screen; the establishment of the evaluation formula of the detected screen according to the center coordinates and / or area sizes of the first row and column coordinates and the second row and column coordinates for evaluating whether the detected screen is qualified comprises: Wherein, s1 is the matching degree of the detected screen and the qualified screen, n1 is the area size of one or more pixel regions in the detected screen, n is the area size of one or more pixel regions in the qualified screen, is the relative error of the detected screen and the qualified screen, and β is a set parameter.

2. The display screen detection method of claim 1, wherein, the establishment of the evaluation formula of the detected screen according to the center coordinates and / or area sizes of the first row and column coordinates and the second row and column coordinates for evaluating whether the detected screen is qualified comprises: the calculation of the center coordinates and / or area sizes of each pixel area according to the first row and column coordinates and the second row and column coordinates comprises: where s2 is the ghosting degree of the detected screen, p i and q i represent the length and width of each pixel region in the detected screen, respectively, w i and h i represent the length and width of each pixel region in the qualified screen, respectively, abs represents taking an absolute value, and δ is a set parameter. ∑ is represented as a summation.

3. The display screen detection method of claim 1, wherein, according to the first row and column coordinates and the second row and column coordinates, counting maximum and minimum values of the row and column coordinates of each pixel area respectively to calculate average values of the maximum and minimum values as the center coordinates of each pixel area in the detected screen and the center coordinates of each pixel area in the qualified screen. the establishment of the evaluation formula of the detected screen according to the center coordinates and / or area sizes of the first row and column coordinates and the second row and column coordinates for evaluating whether the detected screen is qualified comprises:

4. The display screen detection method of claim 3, wherein, the establishment of the evaluation formula of the detected screen according to the center coordinates and / or area sizes of the first row and column coordinates and the second row and column coordinates for evaluating whether the detected screen is qualified comprises: the establishment of the evaluation formula of the detected screen according to the center coordinates and / or area sizes of the first row and column coordinates and the second row and column coordinates for evaluating whether the detected screen is qualified comprises: wherein, is an offset size of the center coordinates of one or more pixel regions in the detected screen and the qualified screen, a is a set parameter, (x1, y1) and (x, y) represent the center coordinates of each of the pixel regions in the qualified screen and the center coordinates of each of the pixel regions in the detected screen, respectively.

5. The display screen detection method of claim 3, wherein, the image is one of a center image, a full-white image, a 9-point image and a 35-point image. The method comprises the following steps: Where μ is a set parameter, (e ix e iy )(d ix d iy ) represent the center coordinates of each pixel region in the qualified screen and the center coordinates of each pixel region in the detected screen, respectively, and ∑ represents the summation.

6. The display screen detection method of claim 1, wherein, a memory for storing a computer program; 7. A display screen detection apparatus characterized by comprising: ​ ​ a processor for executing the computer program to implement the steps of the display screen detection method according to any one of claims 1 to 6.

Images