Screen display status detection method, device, system and readable storage medium

Abstract

The present invention discloses a method, device, system, and readable storage medium for detecting screen display status. The method comprises: obtaining a display image of a screen to be tested, captured by a camera, in a test scenario; obtaining a matching template corresponding to the display image, and determining a difference image between the display image and the matching template; and determining whether the display status of the screen to be tested is abnormal based on the difference image. The present invention aims to improve the accuracy of detecting screen display status.

Description

Technical Field

[0001] The present invention relates to the field of screen detection, and in particular to a method, device, system and readable storage medium for detecting screen display status. Background Art

[0002] As LCD display technology matures, LCD screens are increasingly used in a variety of devices. In actual use, the screen inevitably undergoes a power-on and screen lighting process. When the screen is disturbed or there are errors in the screen software driver, a distorted screen may appear.

[0003] In the prior art, the detection method for screen distortion relies on manual observation of the screen during power-up or lighting to check for abnormalities. Because abnormal images only appear briefly and rarely, long periods of continuous observation and high concentration are usually required during testing. Therefore, manual detection has a high probability of false detection and is costly, resulting in low accuracy in detecting screen display status.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not constitute an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a screen display status detection method, device, system and readable storage medium, aiming to achieve the effect of improving the detection accuracy of the screen display status.

[0006] To achieve the above object, the present invention provides a method for detecting a screen display state, the method comprising:

[0007] Obtain the display image of the screen to be inspected captured by the camera under the test scenario;

[0008] Obtaining a matching template corresponding to the displayed image, and determining a difference image between the displayed image and the matching template;

[0009] It is determined whether there is an abnormality in the display state of the screen to be inspected according to the difference image.

[0010] Optionally, the step of obtaining a matching template corresponding to the displayed image and determining a difference image between the displayed image and the matching template includes:

[0011] Determining a first brightness value for each pixel on the displayed image, and determining a second brightness value for each pixel on the matching template;

[0012] performing a difference operation on the first brightness value and the second brightness value;

[0013] The difference image is generated according to the result of the difference operation.

[0014] Optionally, after the step of obtaining a camera to capture a display image of the screen to be inspected in a test mode, the method further includes:

[0015] determining the type of the test scene according to the displayed image;

[0016] When the test scene is a screen-off scene, performing the steps of obtaining a matching template corresponding to the displayed image and determining a difference image between the displayed image and the matching template;

[0017] When the type of the test scenario is a restart scenario, dividing the display image into a plurality of sub-areas;

[0018] It is determined whether the display state of the screen to be inspected is abnormal according to the comparison result between the brightness values ​​of the plurality of sub-areas.

[0019] Optionally, the step of determining whether there is an abnormality in the display state of the screen to be inspected based on the comparison result between the brightness values ​​of the plurality of sub-areas includes:

[0020] Determining a main image area and a background area of ​​the displayed image;

[0021] Dividing the main image area into a plurality of first sub-areas;

[0022] Determine a comparison result between the brightness values ​​of the plurality of first sub-regions:

[0023] When the comparison result is not within a preset range, determining that the display state of the screen to be inspected is abnormal;

[0024] When the comparison result is within a preset range, dividing the background area into a plurality of second sub-areas;

[0025] Determine whether the brightness values ​​of the plurality of second sub-areas are greater than a preset brightness:

[0026] When the brightness value is greater than the preset brightness, it is determined that the display state of the screen to be inspected is abnormal;

[0027] When the brightness value is less than or equal to the preset brightness, it is determined that there is no abnormality in the display state of the screen to be inspected.

[0028] Optionally, the step of determining the type of the test scene according to the displayed image includes:

[0029] determining brightness and characteristics of the displayed image;

[0030] comparing the brightness and the features with the brightness and features of the matching template;

[0031] When the comparison result is within a preset range, the test scenario is determined to be a screen-off scenario:

[0032] When the comparison result is not within a preset range, it is determined that the type of the test scenario is a restart scenario.

[0033] Optionally, the step of obtaining a display image of the screen to be inspected in a test scenario captured by a camera includes:

[0034] Controlling the screen to be inspected to turn off the screen when displaying the matching template, and controlling the camera to capture the screen-off process to obtain a first video; or

[0035] Controlling the screen to be inspected to restart when displaying an image, and controlling the camera to capture the restart process to obtain a second video: or

[0036] Controlling the screen to be inspected to restart when displaying a matching template, and controlling the camera to capture the restart process to obtain a third video;

[0037] The display image is determined based on image frames of the first video, the second video, and the third video.

[0038] Optionally, before the step of obtaining a display image of the screen to be inspected in a test scenario captured by a camera, the method further includes:

[0039] Determining a second frequency of the camera according to the first frequency of the screen to be inspected;

[0040] controlling the camera based on the second frequency to photograph the screen to be inspected to obtain a template image when the screen to be inspected displays a matching template;

[0041] Adjust the shooting parameters of the camera according to the brightness value of the template image.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also provides a screen display status detection device, which includes a memory, a processor, and a screen display status detection program stored in the memory and capable of running on the processor. When the screen display status detection program is executed by the processor, the steps of the screen display status detection method described above are implemented.

[0043] In addition, to achieve the above-mentioned purpose, the present invention further provides a screen display status detection system, the screen display status detection system comprising:

[0044] Camera, used to shoot the screen to be tested;

[0045] Screen to be tested;

[0046] A screen display state detection device, wherein the screen display state detection device is the screen display state detection device described above.

[0047] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium, on which a screen display status detection program is stored. When the screen display status detection program is executed by a processor, the steps of the screen display status detection method described above are implemented.

[0048] The embodiments of the present invention propose a method, device, system, and readable storage medium for detecting the display state of a screen. The method first obtains a display image of a screen to be tested captured by a camera in a test scenario; obtains a matching template corresponding to the display image, and determines a difference image between the display image and the matching template; and determines whether the display state of the screen to be tested is abnormal based on the difference image. In this way, the display image of the screen to be tested in the test scenario is captured by a camera, and then matched with the matching template to generate a difference image. The display image is obtained by displaying the matching template on the screen to be tested in the test scenario and then photographing it with a camera. Therefore, based on the difference image, it is possible to determine whether the display state of the screen is abnormal, thereby improving the accuracy of detecting the screen display state. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment of the present invention;

[0050] Figure 2 A schematic flow chart of an embodiment of a method for detecting screen display status according to the present invention;

[0051] Figure 3 Schematic diagram of the flow of another embodiment of the screen display status detection method of the present invention;

[0052] Figure 4 A schematic diagram of an image display of a restart scenario according to an embodiment of the present invention;

[0053] Figure 5 A schematic diagram of a camera gain adjustment process according to an embodiment of the present invention;

[0054] Figure 6 This is a schematic diagram of the difference images of the screen-off scene involved in the embodiment of the present invention.

[0055] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] In the prior art, detection of screen distortion primarily relies on manual observation of the screen during power-up or lighting to check for any anomalies. Because abnormal screens only appear briefly and rarely, they typically require extended continuous observation and intense concentration. Consequently, manual testing carries a high probability of false positives and is expensive, resulting in low accuracy in detecting screen display status.

[0058] In order to improve the accuracy of detecting the screen display status, embodiments of the present invention provide a method, device, system, and readable storage medium for detecting the screen display status. The main steps of the method include:

[0059] Obtain the display image of the screen to be inspected captured by the camera under the test scenario;

[0060] Obtaining a matching template corresponding to the displayed image, and determining a difference image between the displayed image and the matching template;

[0061] It is determined whether there is an abnormality in the display state of the screen to be inspected according to the difference image.

[0062] In this way, the display image of the screen to be tested in the test scene is captured by the camera, and then matched with the matching template corresponding to the display image to generate a difference image. Based on the difference image, it can be determined whether there is any abnormality in the display status of the screen, which can improve the detection accuracy of the screen display status.

[0063] The content to be protected by the claims of the present invention will be described in detail below with reference to the accompanying drawings.

[0064] like Figure 1 As shown, Figure 1 It is a schematic diagram of the terminal structure of the hardware operating environment involved in the embodiment of the present invention.

[0065] The terminal in the embodiment of the present invention may be a screen display status detection device.

[0066] like Figure 1 As shown, the terminal may include: a processor 1001, such as a CPU, a memory 1003, and a communication bus 1002. Communication bus 1002 is used to enable communication between these components. Memory 1003 may be a high-speed RAM memory or a non-volatile memory, such as a disk drive. Memory 1003 may also optionally be a storage device independent of processor 1001.

[0067] Those skilled in the art will understand that Figure 1 The terminal structure shown in the figure does not constitute a limitation to the terminal, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0068] like Figure 1 As shown, the memory 1003 as a computer storage medium may include an operating system and a screen display status detection program.

[0069] exist Figure 1 In the terminal shown, the processor 1001 can be used to call the screen display status detection program stored in the memory 1003 and perform the following operations:

[0070] Obtain the display image of the screen to be inspected captured by the camera under the test scenario;

[0071] Obtaining a matching template corresponding to the displayed image, and determining a difference image between the displayed image and the matching template;

[0072] It is determined whether there is an abnormality in the display state of the screen to be inspected according to the difference image.

[0073] Furthermore, the processor 1001 may call the screen display status detection program stored in the memory 1003 and perform the following operations:

[0074] Determining a first brightness value for each pixel on the displayed image, and determining a second brightness value for each pixel on the matching template;

[0075] performing a difference operation on the first brightness value and the second brightness value;

[0076] The difference image is generated according to the result of the difference operation.

[0077] Furthermore, the processor 1001 may call the screen display status detection program stored in the memory 1003 and perform the following operations:

[0078] determining the type of the test scene according to the displayed image;

[0079] When the test scene is a screen-off scene, performing the steps of obtaining a matching template corresponding to the displayed image and determining a difference image between the displayed image and the matching template;

[0080] When the type of the test scenario is a restart scenario, dividing the display image into a plurality of sub-areas;

[0081] It is determined whether the display state of the screen to be inspected is abnormal according to the comparison result between the brightness values ​​of the plurality of sub-areas.

[0082] Furthermore, the processor 1001 may call the screen display status detection program stored in the memory 1003 and perform the following operations:

[0083] Determining a main image area and a background area of ​​the displayed image;

[0084] Dividing the main image area into a plurality of first sub-areas;

[0085] Determine a comparison result between the brightness values ​​of the plurality of first sub-regions:

[0086] When the comparison result is not within a preset range, determining that the display state of the screen to be inspected is abnormal;

[0087] When the comparison result is within a preset range, dividing the background area into a plurality of second sub-areas;

[0088] Determine whether the brightness values ​​of the plurality of second sub-areas are greater than a preset brightness:

[0089] When the brightness value is greater than the preset brightness, it is determined that the display state of the screen to be inspected is abnormal;

[0090] When the brightness value is less than or equal to the preset brightness, it is determined that there is no abnormality in the display state of the screen to be inspected.

[0091] Furthermore, the processor 1001 may call the screen display status detection program stored in the memory 1003 and perform the following operations:

[0092] determining brightness and characteristics of the displayed image;

[0093] comparing the brightness and the features with the brightness and features of the matching template;

[0094] When the comparison result is within a preset range, the test scenario is determined to be a screen-off scenario:

[0095] When the comparison result is not within a preset range, it is determined that the type of the test scenario is a restart scenario.

[0096] Furthermore, the processor 1001 may call the screen display status detection program stored in the memory 1003 and perform the following operations:

[0097] Controlling the screen to be inspected to turn off the screen when displaying the matching template, and controlling the camera to capture the screen-off process to obtain a first video; or

[0098] Controlling the screen to be inspected to restart when displaying an image, and controlling the camera to capture the restart process to obtain a second video: or

[0099] Controlling the screen to be inspected to restart when displaying a matching template, and controlling the camera to capture the restart process to obtain a third video;

[0100] The display image is determined based on image frames of the first video, the second video, and the third video.

[0101] Furthermore, the processor 1001 may call the screen display status detection program stored in the memory 1003 and perform the following operations:

[0102] Determining a second frequency of the camera according to the first frequency of the screen to be inspected;

[0103] controlling the camera based on the second frequency to photograph the screen to be inspected to obtain a template image when the screen to be inspected displays a matching template;

[0104] Adjust the shooting parameters of the camera according to the brightness value of the template image.

[0105] As LCD display technology matures, LCD screens are increasingly used in a variety of devices. In actual use, the screen inevitably undergoes a power-on and screen lighting process. When the screen is disturbed or there are errors in the screen software driver, a distorted screen may appear.

[0106] In the prior art, the detection method for screen distortion relies on manual observation of the screen during power-up or lighting to check for any anomalies. Because abnormal screens only appear briefly and rarely, they typically require long periods of continuous observation and intense concentration. Consequently, manual testing carries a high probability of false positives, is costly, and time-consuming, resulting in low accuracy in detecting the screen's display status.

[0107] The following is an explanation of the content claimed in the claims of the present invention through specific exemplary schemes, so that those skilled in the art can better understand the scope of protection of the claims of the present invention. It should be understood that the following exemplary schemes do not limit the scope of protection of the present invention, but are only used to explain the present invention.

[0108] For example, referring to Figure 2 In one embodiment of the screen display status detection method of the present invention, the screen display status detection method includes the following steps:

[0109] Step S10: obtaining a display image of the screen to be inspected in a test scenario captured by a camera;

[0110] In this embodiment, the camera can be a high-speed industrial camera that can capture display images that change at high speed. The screen to be inspected can be an LCD screen, which is commonly used in VR screens, such as VR glasses. This type of screen fits the eyes and is often divided into two screens, left and right, so the left and right screens can be inspected at the same time. It is often powered by batteries, so power consumption is strictly controlled. During actual operation, the left and right screen backlights are switched on and off at high speed to control power consumption. The human eye cannot feel the screen status at this time, but when shooting with a high-speed camera, a display that alternates between bright and dark on the left and right can be obtained. In order to detect the display status of the screen to be inspected under different test scenarios, the camera captures an image of the screen to be inspected displaying a matching template under the test scenario, and the image is the display image.

[0111] Optionally, the screen to be inspected is controlled to turn off when displaying the matching template, and the camera is controlled to shoot the screen-off process to obtain a first video; or the screen to be inspected is controlled to restart when displaying the image, and the camera is controlled to shoot the restart process to obtain a second video; or the screen to be inspected is controlled to restart when displaying the matching template, and the camera is controlled to shoot the restart process to obtain a third video; the displayed image is determined based on the image frames of the first video, the second video and the third video.

[0112] The screen to be inspected can be tested in two test scenarios. These two test scenarios can be tested separately or at the same time. The first test scenario is the screen-off scenario, that is, the screen to be inspected is controlled to be off when the matching template is displayed, and the screen to be inspected is turned off when the matching template is displayed. The screen to be inspected is filmed by the camera during the screen-off process and a first video is obtained. The second test scenario is the restart scenario, that is, the screen to be inspected is controlled to restart when displaying an image. The displayed image is arbitrary, but when restarting, the screen to be inspected will display the boot image, such as Figure 4 , there is a large area of ​​completely black image in the boot image, and it is difficult to generate a differential image corresponding to the matching template corresponding to the boot image. Therefore, other methods for confirming the screen display status are required in the restart scenario. The restart scenario and the screen-off scenario can be performed in the same stage. The screen-off scenario is the process of the screen going from bright to dark, while the restart scenario is the process of the screen going from bright to dark and then back to bright. It can include the process of the screen-off scenario going from bright to dark, and then back to bright. It restarts when the screen to be inspected displays the matching template, and obtains a third video of the process through the camera. In order to capture screen abnormalities as much as possible, the screen-off or restart process can be repeated when the matching template is displayed, and the video is obtained. Each frame of the first video, the second video, or the third video can be used as a display image. It is understandable that the camera shooting speed needs to be an integer multiple of the screen refresh speed.

[0113] The camera and the screen to be tested can be set up in a test fixture. The test fixture mainly consists of a high-speed industrial camera, a high-precision adjustable fixed platform, and supporting components such as a darkroom and an illuminometer. Before testing, it is necessary to adjust the darkroom illumination to less than 1 lux by adjusting the illuminometer and measuring with the illuminator. The camera exposure time and gain value are adjusted. The exposure time and gain value are adjusted at different display frame rates to obtain a correlation between the refresh rate of the screen to be tested, the camera exposure time, and the camera gain value. Before testing, the camera shooting parameters, including exposure time and gain value, can be set according to this correlation. The brightness of the captured display image is set to a preset brightness, such as 53. The display image is captured in the test scene using the set shooting parameters.

[0114] Optionally, the second frequency of the camera is determined according to the first frequency of the screen to be inspected; based on the second frequency, the camera is controlled to photograph the screen to be inspected to obtain a template image when the screen to be inspected displays a matching template; and the shooting parameters of the camera are adjusted according to the brightness value of the template image.

[0115] Camera shooting parameters that require adjustment may include the Gain value. Since each screen's brightness varies slightly, and this embodiment provides screen display status detection that is affected by brightness, the higher the screen refresh rate, the shorter the corresponding camera exposure time. Reducing the exposure time will reduce the brightness of the displayed image. Therefore, before testing, the camera Gain value corresponding to each refresh rate of the screen to be tested must be calibrated to ensure that the captured brightness matches the actual screen. The calibrated Gain value will be used in subsequent actual testing.

[0116] For the convenience of testing, before conducting the test, the correlation combination between the refresh rate of the screen to be tested and the gain value of the camera can be obtained according to the above calibration steps. Subsequent tests can directly determine the gain value of the camera shooting parameters based on the correlation combination and the refresh rate.

[0117] Specifically, determine the shooting parameters corresponding to the screen to be inspected at multiple refresh rates. For example, 72Hz, 80Hz, 90Hz, 120Hz, take 72Hz as an example, refer to Figure 5, set the refresh rate of the screen to be inspected to 72Hz; set the camera to an exposure value of 1 / 3 the refresh rate (24Hz) and capture an image to obtain a standard brightness template T; calculate the brightness value TB1 of the standard brightness template T (its value is 53); set the camera to 72Hz and capture an image, calculating the brightness of the captured image 72B; if 72B is greater than TB1, subtract 1 from the camera Gain value; if 72B is less than TB1, add 1 to the camera Gain value; repeat 4 to 5 times until the difference between 72B and TB1 is minimized, and record the Gain value at this time. Then, set the screen to be inspected to 80Hz, 90Hz, or 120Hz, set the camera to the corresponding refresh rate, and repeat 4-6 times to obtain the corresponding Gain values. The Gain value and refresh rate are associated and saved as an associated combination.

[0118] Step S20: obtaining a matching template corresponding to the displayed image, and determining a difference image between the displayed image and the matching template;

[0119] In this embodiment, the matching template corresponding to the displayed image is the image displayed on the screen to be inspected. A camera captures the screen to be inspected while the matching template is displayed, generating a display image that includes an image similar to the matching template. However, since differences between the displayed template and the matching template may persist after the screen to be inspected has been displayed, the displayed image is aligned with the matching module, and a difference image is generated based on the difference between the displayed image and the matching template.

[0120] Optionally, a positioning template is created based on the matching template and used for image alignment to prevent image offset during detection. Before generating the difference image, the displayed image is positioned based on the positioning template so that the displayed image can be aligned with the matching template.

[0121] Optionally, a first brightness value of each pixel on the displayed image is determined, and a second brightness value of each pixel on the matching template is determined; a difference operation is performed on the first brightness value and the second brightness value; and the difference image is generated based on the result of the difference operation.

[0122] The image contents of the matching template and the displayed image correspond to each other. In order to detect whether the screen to be tested has a screen distortion phenomenon, it is necessary to compare the brightness difference between the displayed image and the matching image, determine the brightness value of each pixel on the displayed image as the first brightness value, and determine the brightness value of each point on the matching template as the second brightness value. According to the alignment result of the displayed image and the matching template, determine the correspondence between each pixel on the displayed image and each pixel on the displayed image. According to the correspondence, compare the first brightness value and the second brightness value one by one to obtain the brightness difference value between the first brightness value and the second brightness value. Generate a difference image according to each brightness difference value, and refer to Figure 6 ,like Figure 6 If there are different-colored areas or lines on the screen, it means that the screen to be inspected has a screen distortion phenomenon.

[0123] Step S30: Determine whether there is any abnormality in the display state of the screen to be inspected according to the difference image.

[0124] In this embodiment, the difference between the matching template and the displayed image is due to the screen to be tested. Each point or area on the screen to be tested should be the same as other points and areas, and its influence on each pixel on the matching template is the same, that is, the difference between the matching template and the displayed image is the same. If there are pixels on the displayed image that are different from other pixels, it can be considered that the display state of the screen to be tested in the test scene is abnormal, there is a flowery screen phenomenon, and it is a defective screen. Specifically, the difference image can be subjected to patch analysis to obtain the number and area of ​​the difference areas. Based on the number and area of ​​the difference areas, it is determined whether the display state of the screen to be tested is qualified. If the number and / or area is less than or equal to the preset threshold, it is determined that the display state is qualified. When the display state is qualified, it is determined that there is no abnormality in the display state of the screen to be tested; if the number and / or area is greater than the preset threshold, it is determined that the display state is unqualified, and it is determined that there is an abnormality in the display state of the screen to be tested.

[0125] For a better understanding, this embodiment provides a specific application scenario:

[0126] To test the display status of the VR screen in the off-screen scenario, you can specifically include the following steps:

[0127] (1) Preparation of matching templates: Select an image that is considered normal, divide it into left and right screens, prepare matching templates T_L and T_R respectively, grayscale the templates, and select the ROI area.

[0128] (2) Display image positioning: Based on the matching templates T_L and T_R, positioning templates are prepared for the left and right screens respectively, which are used for image alignment operations to prevent image offset during screen status detection.

[0129] (3) Display image analysis: First, the image used needs to meet the brightness requirements during camera parameter calibration. Then the image is grayscaled and calibrated according to this positioning template.

[0130] (4) Perform a difference calculation between the calibrated image and the matching template. If the two images are completely consistent, a difference image with a brightness of 0 will be obtained. If there is a certain difference between the two images, it will be reflected in the difference image, and the abnormal area will be marked with a rectangular box.

[0131] The screen to be tested is a VR screen. The display image of the VR screen needs to be divided into two areas, left and right. Based on this, in the black screen state, there are eight test results:

[0132] (1) Normal image: The images displayed on the left and right sides of the VR screen have no difference compared with the corresponding matching templates. This situation is considered normal.

[0133] (2) Normal image but the overall image is relatively dark: When the VR screen changes from off to on, there is a process of image brightness change. The camera happened to capture the image before the VR screen is fully lit, resulting in this situation. This situation is considered normal. The specific detection scheme is: the brightness can be used to determine that the image is not in a black screen state, but the overall brightness is much lower than the brightness of the normal template. Therefore, the flower screen detection algorithm can identify the matching image, but there will be a large abnormal area of ​​the difference image. This situation is considered normal.

[0134] (3) One side is normal and the other side is black: This phenomenon occurs when the order of images played on both sides of the VR screen is not completely synchronized. Therefore, when recording with an industrial camera, a normal VR screen will appear on one side while the other side will appear completely black. The specific detection plan is as follows: This phenomenon is currently considered normal and does not affect the performance of the VR screen itself. The screen brightness is tested to determine whether the image is normal. If the image displayed on the left side of the screen is normal, the left side of the displayed image is judged to be the abnormal side.

[0135] (4) Image artifacts: This phenomenon occurs when abnormal points or areas appear in local locations during VR screen display. This phenomenon is considered abnormal. The specific detection scheme is as follows: After the difference operation, a relatively obvious abnormal area can be found on the difference image. The coordinates of the area are returned based on the difference image. Based on the returned result, the abnormal area is marked in the displayed image.

[0136] (5) One side of the screen is completely distorted, and one side is darker: This phenomenon occurs when one side of the VR screen is abnormal and the other side is relatively dark. The specific detection scheme is: first determine whether the displayed image is all black by brightness. If it is all black, it means that the screen on this side is in a black screen state. If the image brightness reaches a certain threshold, it means that the displayed image is not in a completely black state. Normally perform screen status detection on the displayed image on this side. If it can be considered that the displayed image is a normal image, the two sides of the screen to be tested are judged separately to obtain the corresponding matching results.

[0137] (6) One side is completely distorted and the other side is black: During the screen-off process, the display status of the two screens is not completely synchronized. One side is completely black and the other side is abnormally distorted. This situation is identified as a distorted screen. The specific detection scheme is: by judging the brightness of both sides of the displayed image, determine whether the screen is completely black. If the brightness is lower than the specified threshold, it means that the current displayed image is completely black and no screen status detection is required; if the brightness reaches the specified brightness threshold, it means that the image is not completely black and screen status detection is performed; if the difference image is normal, it means that the current image is a normal screen image and no abnormalities such as distorted screens occur. If the difference image is abnormal, it means that there is a large difference between the displayed image and the matching template, and it is determined to be an abnormal situation.

[0138] (7) Both sides of the screen are distorted: When distorted screens appear on both sides of the image, this display condition is considered a distorted screen. Specific detection plan: If the brightness of both sides of the displayed image is not completely black, a screen status test is required. If the difference images on both sides are abnormal, this condition is considered a distorted screen.

[0139] In the technical solution disclosed in this embodiment, the display image of the screen to be tested taken by a camera in a test scene is first obtained; the matching template corresponding to the display image is obtained, and the difference image between the display image and the matching template is determined; and based on the difference image, it is determined whether there is any abnormality in the display state of the screen to be tested. In this way, the display image of the screen to be tested in the test scene is photographed by a camera, and then matched with the matching template to generate a difference image. The display image is obtained by displaying the matching template on the screen to be tested in the test scene and photographed by the shooting device. Therefore, based on the difference image, it can be determined whether there is any abnormality in the display state of the screen. Compared with the method of manual naked eye detection, the screen display state detection provided by this embodiment can also improve accuracy and efficiency, and is more suitable for detecting screen flower screen phenomena.

[0140] Optionally, refer to Figure 3 Based on any of the above embodiments, in another embodiment of the screen display status detection method of the present invention, the screen display status detection method further includes:

[0141] Step S40: determining the type of the test scene according to the displayed image;

[0142] In this embodiment, there are two test scenarios for the screen to be tested, one is the screen-off scenario and the other is the restart scenario. The screen display status detection algorithms for the display images corresponding to the screen-off scenario and the restart scenario are different, so the test scenarios of the display images should be distinguished. Specifically, the objects that need to be detected in the screen-off scenario and the restart scenario, that is, the display images, are different. In the screen-off scenario, the display image to be detected is the display image corresponding to the matching template, while in the restart scenario, the display image to be detected is the display image corresponding to the boot image at restart. By identifying the display image, the type of display scenario corresponding to the display image can be determined.

[0143] In an alternative implementation scheme, the operating parameters of the screen to be tested may be obtained, and the test scenario may be determined based on the operating parameters to determine whether the screen is turned off or restarted, thereby determining the type of the test scenario.

[0144] Optionally, determine the brightness and characteristics of the displayed image; compare the brightness and the characteristics with the brightness and characteristics of the matching template; when the comparison result is within a preset range, determine that the type of the test scene is a screen-off scene; when the comparison result is not within a preset range, determine that the type of the test scene is a restart scene.

[0145] In this embodiment, the brightness of the displayed image is pre-judged, and feature points are identified to determine the brightness and features of the displayed image. The brightness and features are compared with the brightness and features of the matching template to determine the type of test scene corresponding to the displayed image. If the matching template is similar to the displayed image, the comparison result will be within the preset range, and the type of test scene is determined to be a screen-off scene. If the matching template is not similar to the displayed image, the comparison result will not be within the preset range, and the type of test scene is determined to be a restart scene.

[0146] Step S50: When the test scene is a screen-off scene, obtaining a matching template corresponding to the displayed image and determining a difference image between the displayed image and the matching template.

[0147] Optionally, if the test scene is a screen-off scene, the display state is processed using a screen display state detection algorithm corresponding to the screen-off scene. Therefore, when it is determined that the test scene is a screen-off scene, the steps of obtaining a matching template corresponding to the display image and determining a difference image between the display image and the matching template are performed.

[0148] Step S60: When the type of the test scene is a restart scene, dividing the display image into a plurality of sub-areas;

[0149] In this embodiment, if the test scenario is a reboot scenario, the displayed image corresponds to the boot image. The boot image is actually a template, and the operation in step S20 can be performed. However, the boot image contains a large black background area, which is difficult to distinguish from the boot image after the camera captures it. To improve the accuracy of the detection, a different test algorithm is required for the reboot scenario display image. Calculations are performed based on the displayed image itself, dividing the displayed image into multiple sub-areas, and comparing the multiple sub-areas.

[0150] Step S70: Determine whether there is any abnormality in the display state of the screen to be inspected based on the comparison result between the brightness values ​​of the plurality of sub-areas.

[0151] The display image is divided into multiple sub-areas. The brightness values ​​of the sub-areas should be similar, and the difference between the maximum and minimum brightness values ​​should be within a preset range. If the comparison result is not within the preset range, the display status of the screen to be tested is determined to be abnormal. If the comparison result is within the preset range, the display status of the screen to be tested is determined to be normal.

[0152] Optionally, the main image area is divided into multiple first sub-areas; the comparison result between the brightness values ​​of the multiple first sub-areas is determined: when the comparison result is not within a preset range, it is determined that there is an abnormality in the display state of the screen to be inspected; when the comparison result is within the preset range, the background area is divided into multiple second sub-areas; it is determined whether the brightness values ​​of the multiple second sub-areas are greater than a preset brightness: when the brightness value is greater than the preset brightness, it is determined that there is an abnormality in the display state of the screen to be inspected; when the brightness value is less than or equal to the preset brightness, it is determined that there is no abnormality in the display state of the screen to be inspected.

[0153] like Figure 4 The figure shows an example of the display image of the VR screen to be tested in the restart scenario. The figure has a main image area (elliptical area) and a background area (other areas except the elliptical area). The brightness values ​​of the main image area and the background area are quite different. The main image area and the background area sub-areas should be compared separately. Compare the main image area first, then compare the background area. The image of the main image area is more obvious than the image of the background area. If the brightness value comparison range of the sub-area of ​​the main image area is not within the preset range, it can be directly determined that the display state of the screen to be tested is abnormal, which can save calculations. If the brightness value comparison range of the sub-area of ​​the main image area is not within the preset range, the brightness value of the sub-area of ​​the background area is further determined. The background area is black, and the brightness value is 0 or low. If the brightness value of the background area is greater than the preset brightness, it can be determined that the display state of the screen to be tested is abnormal. If the brightness value of the sub-area of ​​the background area is less than or equal to the preset brightness, it can be determined that the display state of the screen to be tested is normal.

[0154] For a better understanding, this embodiment provides a specific application scenario:

[0155] To test the display status of the VR screen in a restart scenario, you can specifically include the following steps:

[0156] (1) First, obtain a matching template of the boot image, then match the display image with the template and calculate the feature points in the template, such as Figure 4 The elliptical area in the image is displayed.

[0157] (2) The elliptical area that is successfully matched in (1) is processed separately as the main image area. The processing process is as follows: the main image area is divided into four parts, and the brightness of each part is calculated. The difference between the maximum and minimum brightness values ​​is calculated. If the difference is greater than the specified threshold, it means that there is an abnormality in the area. Otherwise, it is considered to be normal.

[0158] (3) After shielding the main image area that has been successfully matched in (1) from the displayed image, the remaining background area is divided into 32×32 sub-areas by gridding the image, and then the brightness of each sub-area is determined. If there is a sub-area whose brightness value is greater than the specified threshold, it means that the sub-area is an abnormal area and the area is marked with a rectangular frame.

[0159] (4) The results of steps (2) and (3) are comprehensively judged to determine whether the displayed image is in an abnormal display state.

[0160] In the technical solution disclosed in this embodiment, the type of test scene is determined by displaying an image. When the test scene type is a screen-off scene, step S20 is executed. When the test scene is a restart scene, the display state of the screen to be tested is determined by comparison based on the brightness values ​​obtained from each sub-area of ​​the display image. In this way, based on the differences in the displayed images under different test scenarios, different algorithms are used to process the displayed images in a targeted manner, and the display state of the screen to be tested in different states is detected to determine whether there is a screen distortion phenomenon, thereby improving the accuracy of detecting the screen state.

[0161] In addition, an embodiment of the present invention also proposes a screen display status detection device, which includes a memory, a processor, and a screen display status detection program stored in the memory and runnable on the processor. When the screen display status detection program is executed by the processor, the steps of the screen display status detection method described in the above embodiments are implemented.

[0162] In addition, an embodiment of the present invention further provides a screen display status detection system, the screen display status detection system comprising:

[0163] Camera, used to shoot the screen to be tested;

[0164] Screen to be tested;

[0165] A screen display state detection device, wherein the screen display state detection device is the screen display state detection device described above.

[0166] In addition, an embodiment of the present invention further provides a computer-readable storage medium storing a screen display status detection program. When the screen display status detection program is executed by a processor, the steps of the screen display status detection method described in the above embodiments are implemented.

[0167] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0168] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0169] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for causing the screen display status detection device to execute the method described in each embodiment of the present invention.

[0170] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for detecting screen display status, characterized in that: The method comprises: Obtain the display image of the screen to be inspected captured by the camera under the test scenario; determining the type of the test scene according to the displayed image; When the type of the test scenario is a restart scenario, dividing the display image into a plurality of sub-areas; Determine a main image area and a background area of ​​the displayed image; divide the main image area into a plurality of first sub-areas; and determine a comparison result between brightness values ​​of the plurality of first sub-areas, wherein the comparison result is a difference between a maximum brightness value and a minimum brightness value in the plurality of first sub-areas: When the comparison result is not within a preset range, determining that the display state of the screen to be inspected is abnormal; When the comparison result is within a preset range, dividing the background area into a plurality of second sub-areas; When the brightness value of the second sub-area is greater than the preset brightness, it is determined that the display state of the screen to be inspected is abnormal; otherwise, it is determined that the display state of the screen to be inspected is not abnormal; When the type of the test scene is a screen-off scene, obtaining a matching template corresponding to the displayed image, and determining a difference image between the displayed image and the matching template; It is determined whether the display state of the screen to be inspected is abnormal according to the difference image.

2. The screen display status detection method according to claim 1, wherein: The step of obtaining a matching template corresponding to the displayed image and determining a difference image between the displayed image and the matching template includes: Determining a first brightness value for each pixel on the displayed image, and determining a second brightness value for each pixel on the matching template; performing a difference operation on the first brightness value and the second brightness value; The difference image is generated according to the result of the difference operation.

3. The screen display status detection method according to claim 1, wherein: The step of determining the type of the test scene according to the displayed image comprises: determining brightness and characteristics of the displayed image; comparing the brightness and the features with the brightness and features of the matching template; When the comparison result is within a preset range, the test scenario is determined to be a screen-off scenario: When the comparison result is not within a preset range, it is determined that the type of the test scenario is a restart scenario.

4. The screen display status detection method according to claim 1, wherein: The step of obtaining a display image of the screen to be inspected captured by a camera in a test scenario includes: Controlling the screen to be inspected to turn off the screen when displaying the matching template, and controlling the camera to capture the screen-off process to obtain a first video; or Controlling the screen to be inspected to restart when displaying an image, and controlling the camera to capture the restart process to obtain a second video: or Controlling the screen to be inspected to restart when displaying a matching template, and controlling the camera to capture the restart process to obtain a third video; The display image is determined based on image frames of the first video, the second video, and the third video.

5. The screen display status detection method according to claim 1, wherein: Before the step of obtaining the display image of the screen to be inspected captured by the camera in the test scenario, the method further includes: Determining a second frequency of the camera according to the first frequency of the screen to be inspected; controlling the camera based on the second frequency to photograph the screen to be inspected to obtain a template image when the screen to be inspected displays a matching template; Adjust the shooting parameters of the camera according to the brightness value of the template image.

6. A screen display status detection device, characterized in that: The screen display status detection device includes: a memory, a processor, and a screen display status detection program stored in the memory and executable on the processor. When the screen display status detection program is executed by the processor, the steps of the screen display status detection method according to any one of claims 1 to 5 are implemented.

7. A screen display status detection system, characterized in that: The screen display status detection system includes: Camera, used to shoot the screen to be tested; Screen to be tested; A screen display state detection device, wherein the screen display state detection device is the screen display state detection device according to claim 6.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a screen display status detection program, which, when executed by a processor, implements the steps of the screen display status detection method according to any one of claims 1 to 5.

Images