Method and device for automatically detecting scratches of liquid crystal display screen

Abstract

The invention discloses an automatic detection method and device for scratches of a liquid crystal display screen. The method comprises the steps that a plurality of annular LED light sources emit annular LED light to the liquid crystal display screen to be detected at different angles in a dark field environment; collecting a first image of the liquid crystal display screen to be detected when each annular LED light irradiates; segmenting scratches from the plurality of second images by adopting a threshold segmentation algorithm to obtain a plurality of third images, and fitting the plurality of third images by utilizing a morphological expansion algorithm to obtain a fourth image of a scratch area; performing preliminary judgment processing on the fifth image by adopting an image processing algorithm to obtain a sixth image of a preliminary defect area; and performing difference set processing on the sixth image and the fourth image to obtain a final scratch area. By implementing the method and the device, the accuracy of scratch judgment is improved, and the problems of low efficiency and low accuracy of an existing liquid crystal display screen scratch detection scheme are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic detection of scratches on a liquid crystal display screen, and in particular to a method and a device for automatic detection of scratches on a liquid crystal display screen. Background Art

[0002] Liquid crystal display is a flat ultra-thin display device, which consists of a certain number of color or black and white pixels, placed in front of a light source or a reflective surface. Liquid crystal displays have very low power consumption, so they are favored by engineers and are suitable for electronic devices that use batteries. The surface of the liquid crystal display is very fragile. In the production process of liquid crystal displays, due to the many and complex process flows, it is easy to cause scratches of varying depths and directions on the protective film on the display polarizer during the handling process. Due to reflections and other reasons, it is difficult for workers to find all the scratches with the naked eye, which is easy to miss, and the efficiency is low, time-consuming and labor-intensive.

[0003] Therefore, it is necessary to detect scratches or marks on the LCD screen to ensure the production quality of LCD products. The existing detection method is generally carried out by combining manual detection with semi-automatic detection instruments. Obviously, the traditional detection method is not efficient, and the semi-automatic detection method is easy to damage or contaminate the LCD screen, thereby affecting the quality of the product and the accuracy of the detection. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a method and device for automatically detecting scratches on a liquid crystal display screen, so as to solve the problems of low efficiency and low accuracy of existing solutions for detecting scratches on a liquid crystal display screen.

[0005] In a first aspect, a method for automatically detecting scratches on a liquid crystal display screen comprises: Acquire an image acquisition module and a plurality of annular LED light sources, wherein the plurality of annular LED light sources emit annular LED light at different angles to a liquid crystal display screen to be tested in a dark field environment; Turning on and off the annular LED light source in sequence, and using the image acquisition module to acquire a first image of the liquid crystal display screen to be tested when each annular LED light is irradiated; Performing enhancement processing on each of the first images to obtain a plurality of second images, using a threshold segmentation algorithm to segment the scratches from the plurality of second images to obtain a plurality of third images, and using a morphological dilation algorithm to fit the plurality of third images to obtain a fourth image of the scratch area; Lighting up the LCD screen to be tested by using the fixture, acquiring a fifth image by using the image acquisition module, and performing preliminary determination processing on the fifth image by using an image processing algorithm to acquire a sixth image of a preliminary defect area; The sixth image is subjected to difference processing with the fourth image to obtain a final scratch area.

[0006] Furthermore, the image acquisition module includes: Fixing the image acquisition module directly above the area of ​​the fixture corresponding to the LCD screen to be tested; The exposure parameters and gain coefficients of the image acquisition module are configured so that the acquired image is not overexposed.

[0007] Further, a plurality of annular LED light sources are obtained, including: A fixing frame is provided in an area between the image acquisition module and an area where the fixture is placed on the LCD screen to be tested; An opening is provided at the center of the fixing frame to facilitate the image acquisition module to acquire images; An arc-shaped circuit board is arranged on the inner side of the fixing frame; A plurality of annular LED light strips are arranged on the inner side of the arc-shaped circuit board, and the annular LED light strips are made to illuminate a specified area of ​​the liquid crystal display screen to be tested at different illumination angles; The brightness of the annular LED light source is configured to enhance the contrast between the scratches on the liquid crystal display screen to be tested and the background, thereby obtaining the plurality of annular LED light sources; Wherein, the irradiation angle is the angle between the LED light and the liquid crystal display screen to be tested.

[0008] Furthermore, sequentially lighting up and shutting down the annular LED light source, and using the image acquisition module to acquire a first image of the liquid crystal display screen to be tested when each annular LED light is irradiated, comprises: Turn on the annular LED light source at a first irradiation angle, use the image acquisition module to acquire an image of the liquid crystal display screen to be tested, and after the image acquisition is completed, turn off the annular LED light source at the first irradiation angle; Turn on the annular LED light source at the second irradiation angle, use the image acquisition module to acquire the image of the liquid crystal display screen to be tested, and after the image acquisition is completed, turn off the annular LED light source at the second irradiation angle; The above two steps are executed in a loop until the first images of the liquid crystal display screen to be tested at all illumination angles are collected.

[0009] Furthermore, the step of performing enhancement processing on each of the first images to obtain a plurality of second images includes: Performing noise reduction processing on the first image by using mean filtering; The grayscale value of the first image after noise reduction processing is adjusted through linear transformation to enhance the image contrast, thereby obtaining the second image.

[0010] Furthermore, the threshold segmentation algorithm is used to segment the scratches from the plurality of second images to obtain a plurality of third images, including: Determine a segmentation threshold of the second image using an OSTU algorithm; comparing the grayscale value of each pixel in the second image with the segmentation threshold; If it is greater than the segmentation threshold, it is determined to be a scratch pixel; if it is less than the segmentation threshold, it is determined to be a background pixel, and a third image is obtained.

[0011] Furthermore, the step of fitting the plurality of third images using a morphological dilation algorithm to obtain a fourth image of the scratch area includes: Obtaining a structure element and a dilation operator of the fourth image, and moving the structure element pixel by pixel in the fourth image, wherein the dilation operator is a maximum value operator; Selecting the maximum value operator for each pixel position to determine the grayscale value of the target pixel of the disconnected area; The above two steps are executed in a loop until all pixels of the fourth image are traversed; Repeat the previous step and perform multiple expansion operations until all disconnected parts are connected.

[0012] In a second aspect, an automatic detection device for scratches on a liquid crystal display screen adopts the automatic detection method for scratches on a liquid crystal display screen described in the first aspect, comprising: An acquisition module is used to acquire an image acquisition module and a plurality of annular LED light sources, wherein the plurality of annular LED light sources emit annular LED light to a liquid crystal display screen to be tested at different angles in a dark field environment; A first acquisition module, used to sequentially light up and turn off the annular LED light source, and use an image acquisition module to acquire a plurality of first images of the liquid crystal display screen to be tested when each annular LED light is irradiated; a processing module, configured to perform enhancement processing on each of the first images to obtain a plurality of second images, segment the scratches from the plurality of second images using a threshold segmentation algorithm to obtain a plurality of third images, and fit the plurality of third images using a morphological dilation algorithm to obtain a fourth image of the scratch area; A second acquisition module is used to light up the LCD screen to be tested by using a fixture, and use the image acquisition module to obtain a fifth image, and use an image processing algorithm to perform preliminary determination processing on the fifth image to obtain a sixth image of a preliminary defect area; The determination module is used to perform a difference process on the sixth image and the fourth image to obtain a final scratch area.

[0013] Furthermore, the processing module includes: A noise reduction unit, configured to perform noise reduction processing on the first image by using mean filtering; The linear transformation unit is used to adjust the grayscale value of the first image after noise reduction processing through linear transformation to enhance the image contrast and obtain the second image.

[0014] Furthermore, the processing module also includes: A determining unit, configured to determine a segmentation threshold of the third image by using an OSTU algorithm; The comparison and judgment unit is used to compare the grayscale value of each pixel in the third image with the segmentation threshold: if it is greater than the segmentation threshold, it is judged as a scratch pixel; if it is less than the segmentation threshold, it is judged as a background pixel to obtain a third image.

[0015] Compared with the prior art, the embodiments of the present application mainly have the following technical effects: by setting annular LED light sources at different angles to obtain an image of a liquid crystal display screen to be tested, and by adopting a threshold segmentation algorithm and a morphological dilation algorithm to segment and fit the scratch image, the accuracy of the fitting of the scratch image is improved; by obtaining an image of the display screen to be tested when it is lit and performing image processing, a preliminary defect area is obtained, and the preliminary defect area is compared with the fitted scratch image, thereby further improving the accuracy of scratch judgment, and solving the problems of low efficiency and low accuracy of the existing scratch detection scheme for liquid crystal displays. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 A flow chart of an embodiment of a method for automatically detecting scratches on a liquid crystal display screen according to the present application; Figure 2 yes Figure 1 A flowchart of a specific implementation of S100; Figure 3 yes Figure 2 A flowchart of a specific implementation method after S120; Figure 4 yes Figure 1 A flowchart of a specific implementation of S200; Figure 5 yes Figure 1 A flowchart of a specific implementation of S300; Figure 6 yes Figure 5A flowchart of a specific implementation method after S320; Figure 7 yes Figure 6 A flowchart of a specific implementation method after S350; Figure 8 It is a structural schematic diagram of an embodiment of an automatic detection device for scratches on a liquid crystal display screen according to the present application; Fig. 9 is a structural schematic diagram of an embodiment of the image acquisition system in the present application; Figure 10-12 It is a scratch image at three different illumination angles collected according to an automatic detection method for scratches on a liquid crystal display screen of the present application; Fig.13 It is a scratch image detected by an automatic detection method for scratches on a liquid crystal display screen according to the present application. DETAILED DESCRIPTION

[0018] The following will be combined with the accompanying drawings in the invention to clearly and completely describe the technical solutions in the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0019] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0021] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0022] The purpose of the embodiments of the present application is to provide a method and device for automatically detecting scratches on a liquid crystal display screen, so as to solve the problems of low efficiency and low accuracy of existing solutions for detecting scratches on a liquid crystal display screen.

[0023] In a first aspect, a method for automatically detecting scratches on a liquid crystal display screen is provided. Figure 1 , Figure 1 A flow chart of an embodiment of a method for automatically detecting scratches on a liquid crystal display screen according to the present application; comprising: S100 , acquiring an image acquisition module 101 and a plurality of annular LED light sources 102 , wherein the plurality of annular LED light sources 102 emit annular LED light at different angles to a liquid crystal display screen 106 to be tested in a dark field environment.

[0024] In this embodiment, the image acquisition module 101 may be a camera, and the purpose of using multiple annular light sources is to make most of the scratches appear after being irradiated from multiple angles.

[0025] In a preferred embodiment, Figure 2 , Figure 2 yes Figure 1 A flowchart of a specific implementation of S100; S100 includes: S110, fixing the image acquisition module 101 directly above the area of ​​the fixture 105 corresponding to the LCD screen 106 to be tested; S120, configuring the exposure parameters and gain coefficients of the image acquisition module 101 so that the acquired image is not overexposed.

[0026] like Fig. 9 , Fig. 9 1 is a schematic diagram of the structure of an embodiment of the image acquisition system in the present application; the image acquisition system includes an image acquisition module 101, an annular LED light source 102, a fixing frame 103, an arc-shaped circuit board 104, a fixture 105 and a liquid crystal display screen 106 to be tested. The image acquisition module 101 is directly facing the liquid crystal display screen 106 to be tested on the fixture 105 and is located directly above it to facilitate image acquisition. The purpose of configuring the exposure parameters and the gain coefficient is to avoid overexposure when the first image is acquired under the illumination of the annular LED light source 102.

[0027] In this embodiment, when image acquisition is performed on the liquid crystal display screen 106 to be tested, it is necessary to perform the acquisition in a dark field environment. The liquid crystal display screen LCD is placed on a lighting fixture 105, and there is no need to brighten the display screen. The annular LED light source 102 is set directly above the liquid crystal display screen LCD, and the camera or image acquisition module 101 is mounted directly above the annular LED light source 102. The entire test platform is required to be performed in a dark field environment to prevent external light from affecting the imaging.

[0028] In a preferred embodiment, Figure 3 , Figure 3 yes Figure 2 A flowchart of a specific implementation after S120 in the embodiment; after S120, S100 also includes: S130, setting a fixing frame 103 in the area between the image acquisition module 101 and the area where the fixture 105 places the LCD screen 106 to be tested; S140, setting an opening in the center of the fixing frame 103 to facilitate the image acquisition module 101 to perform image acquisition; S150, setting an arc-shaped circuit board 104 on the inner side of the fixing frame 103; S160, setting a plurality of annular LED light strips on the inner side of the arc-shaped circuit board 104, and making the annular LED light strips illuminate the specified area of ​​the LCD screen 106 to be tested at different illumination angles; S170, configuring the brightness of the annular LED light source 102 to enhance the contrast between the scratches on the LCD screen 106 to be tested and the background, and obtaining a plurality of annular LED light sources 102; wherein the illumination angle is the angle between the LED light and the LCD screen 106 to be tested.

[0029] like Fig. 9 In the specific implementation of this embodiment, three annular LED light sources 102 may be used. The irradiation angles of the light emitted by each annular LED light source 102 are different. From the lowest to the highest, the irradiation angles of each ring of LEDs are 15°, 45°, and 60°, respectively, and the light of each ring is directed to 1 / 3 of the distance from the edge of the display screen. Such angle design and irradiation conditions can make most of the scratches appear as much as possible in the camera image through reflection, such as Figure 10-12 , Figure 10-12 These are scratch images at three different illumination angles collected according to an automatic detection method for scratches on a liquid crystal display screen of the present application.

[0030] A light source controller may be used to control the LED light source, and the light source controller may be configured to adjust the brightness, thereby ensuring that the acquired first image has a high contrast.

[0031] S200, sequentially turn on and off the annular LED light source 102, and use the image acquisition module 101 to acquire a plurality of first images of the LCD display screen 106 to be tested when each annular LED light is irradiated, such as Figure 10-12 .

[0032] In a preferred embodiment, Figure 4 , Figure 4 yes Figure 1A flowchart of a specific implementation of S200; S200 includes: S210, turning on the annular LED light source 102 at a first illumination angle, using the image acquisition module 101 to acquire the image of the liquid crystal display screen 106 to be tested, and after the image acquisition is completed, turning off the annular LED light source 102 at the first illumination angle; S220, turning on the annular LED light source 102 at a second illumination angle, using the image acquisition module 101 to acquire the image of the liquid crystal display screen 106 to be tested, and after the image acquisition is completed, turning off the annular LED light source 102 at the second illumination angle; S230, repeating S210-S220 until the first image of the liquid crystal display screen 106 to be tested at all illumination angles is acquired.

[0033] In the present embodiment, when the image of the liquid crystal display screen 106 to be tested is collected, it is done separately, that is, when the first illumination angle is turned on, the image of the liquid crystal display screen 106 to be tested corresponding to the first illumination angle, that is, the first image, is collected. After the use is completed, the annular light source of the first illumination angle is turned off, and then, the image of the liquid crystal display screen 106 to be tested at the next illumination angle is collected according to this process until the images of the liquid crystal display screen 106 to be tested at all illumination angles are collected. During the collection process, the scratches appear bright in the image, and each first image captures the imaging part of the scratch after reflection under light sources of different angles.

[0034] In this embodiment, the first image is an image of the liquid crystal display screen 106 to be tested at different illumination angles captured by the image capture module 101 or the camera, and therefore there are multiple first images.

[0035] S300, performing enhancement processing on each first image to obtain multiple second images, using a threshold segmentation algorithm to segment scratches from the multiple second images to obtain multiple third images, and using a morphological dilation algorithm to fit the multiple third images to obtain a fourth image of the scratch area.

[0036] In a preferred embodiment, Figure 5 , Figure 5 yes Figure 1 A flowchart of a specific implementation of S300; S300 includes: S310, using mean filtering to reduce noise on the first image; S320, adjusting the grayscale value of the first image after noise reduction through linear transformation to enhance the image contrast and obtain a second image.

[0037] In this embodiment, the spatial domain method is used for image enhancement, and the image is enhanced by changing the grayscale value, color value and other attributes of the pixel based on the pixel value and its spatial position relationship. For example, the grayscale level of the pixel of the first image can be directly adjusted to improve the contrast and remove noise, making the image easier to observe and analyze.

[0038] Linear transformation can enhance contrast by changing the grayscale value range of pixels, for example, stretching the part of the original image with a narrow grayscale value range to a wider range.

[0039] In this embodiment, a mean filter is used to smooth the image and remove noise.

[0040] In a preferred embodiment, Figure 6 , Figure 6 yes Figure 5 A flowchart of a specific implementation method after S320 in the figure; after S320, S300 includes: S330, using the OSTU algorithm to determine the segmentation threshold of the second image; S340, comparing the grayscale value of each pixel in the second image with the segmentation threshold; S350, if it is greater than the segmentation threshold, it is determined to be a scratch pixel, and if it is less than the segmentation threshold, it is determined to be a background pixel, thereby obtaining a third image.

[0041] In this embodiment, a threshold segmentation method is used to determine target pixels, that is, scratch pixels, and pixels in the image are divided into different categories by setting a threshold.

[0042] In this embodiment, a global threshold method is used for threshold segmentation, that is, a fixed threshold suitable for the entire image is selected. Each pixel in the image is compared with the determined threshold. If the gray value of the pixel is greater than the threshold, it is classified as a target class, that is, a scratch pixel; if the gray value of the pixel is less than the threshold, it is classified as a background class pixel.

[0043] In a preferred embodiment, Figure 7 , Figure 7 yes Figure 6 A flowchart of a specific implementation method after S350 in FIG. 1 ; after S350, S300 further includes: S360, obtain the structural element and dilation operator of the fourth image, move the structural element pixel by pixel in the fourth image, and the dilation operator is the maximum value operator; S370, select the maximum value operator for each pixel position to determine the gray value of the target pixel of the disconnected area; S380, repeat S360-370, until all pixels of the fourth image are traversed; S390, repeat S380, perform multiple dilation operations, until all disconnected parts are connected, such as Fig.13 , Fig.13 It is a scratch image detected by an automatic detection method for scratches on a liquid crystal display screen according to the present application.

[0044] In this embodiment, the structural element is a small image template. In specific implementation, a rectangular structural element is selected.

[0045] In this embodiment, the maximum value operator takes the maximum pixel value in the area covered by the structure element as the grayscale value of the target pixel. The structure element is moved pixel by pixel on the image.

[0046] The expansion operation can be repeated multiple times as needed to further enlarge the target area or connect more disconnected parts.

[0047] S400 , using the fixture 105 to light up the liquid crystal display screen 106 to be tested, and using the image acquisition module 101 to obtain a fifth image, using an image processing algorithm to perform preliminary determination processing on the fifth image, and obtaining a sixth image of a preliminary defect area.

[0048] S500: performing difference processing on the sixth image and the fourth image to obtain a final scratch area.

[0049] Second, as Figure 8 , Figure 8 1 is a schematic diagram of a structure of an embodiment of an automatic detection device for scratches on a liquid crystal display screen according to the present application; an automatic detection device 600 for scratches on a liquid crystal display screen adopts the automatic detection method for scratches on a liquid crystal display screen of the first aspect, comprising: The acquisition module 601 is used to acquire the image acquisition module 101 and the multiple annular LED light sources 102, and the multiple annular LED light sources 102 emit annular LED light to the liquid crystal display screen 106 to be tested at different angles in a dark field environment; The first acquisition module 602 is used to sequentially light up and turn off the annular LED light source 102, and use the image acquisition module 101 to acquire a plurality of first images of the liquid crystal display screen 106 to be tested when each annular LED light is irradiated; The processing module 603 is used to perform enhancement processing on each first image to obtain multiple second images, segment the scratches from the multiple second images using a threshold segmentation algorithm to obtain multiple third images, and fit the multiple third images using a morphological dilation algorithm to obtain a fourth image of the scratch area; The second acquisition module 604 is used to light up the LCD screen 106 to be tested by using the fixture 105, and obtain the fifth image by using the image acquisition module 101, and perform preliminary determination processing on the fifth image by using the image processing algorithm to obtain the sixth image of the preliminary defect area; The determination module 05 is used to perform a difference process on the sixth image and the fourth image to obtain a final scratch area.

[0050] Furthermore, the processing module includes: A noise reduction unit, configured to perform noise reduction processing on the first image by using mean filtering; The linear transformation unit is used to adjust the grayscale value of the first image after the noise reduction process through linear transformation to enhance the image contrast and obtain the second image.

[0051] Furthermore, the processing module also includes: A determination unit, configured to determine a segmentation threshold of the third image by using an OSTU algorithm; The comparison and judgment unit is used to compare the grayscale value of each pixel in the third image with the segmentation threshold: if it is greater than the segmentation threshold, it is judged as a scratch pixel; if it is less than the segmentation threshold, it is judged as a background pixel to obtain the third image.

[0052] Compared with the prior art, the embodiments of the present application mainly have the following technical effects: by setting annular LED light sources at different angles to obtain an image of a liquid crystal display screen to be tested, and by adopting a threshold segmentation algorithm and a morphological dilation algorithm to segment and fit the scratch image, the accuracy of the fitting of the scratch image is improved; by obtaining an image of the display screen to be tested when it is lit and performing image processing, a preliminary defect area is obtained, and the preliminary defect area is compared with the fitted scratch image, thereby further improving the accuracy of scratch judgment, and solving the problems of low efficiency and low accuracy of the existing scratch detection scheme for liquid crystal displays.

[0053] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for automatically detecting scratches on a liquid crystal display screen, comprising: Acquire an image acquisition module and a plurality of annular LED light sources, wherein the plurality of annular LED light sources emit annular LED light at different angles to a liquid crystal display screen to be tested in a dark field environment; Turning on and off the annular LED light source in sequence, and using the image acquisition module to acquire a first image of the liquid crystal display screen to be tested when each annular LED light is irradiated; Performing enhancement processing on each of the first images to obtain a plurality of second images, using a threshold segmentation algorithm to segment the scratches from the plurality of second images to obtain a plurality of third images, and using a morphological dilation algorithm to fit the plurality of third images to obtain a fourth image of the scratch area; Lighting up the LCD screen to be tested by using the fixture, acquiring a fifth image by using the image acquisition module, and performing preliminary determination processing on the fifth image by using an image processing algorithm to acquire a sixth image of a preliminary defect area; The sixth image is subjected to difference processing with the fourth image to obtain a final scratch area.

2. The automatic detection method for scratches on a liquid crystal display screen according to claim 1, characterized in that: The image acquisition module comprises: Fixing the image acquisition module directly above the area of ​​the fixture corresponding to the LCD screen to be tested; The exposure parameters and gain coefficients of the image acquisition module are configured so that the acquired image is not overexposed.

3. The automatic detection method for scratches on a liquid crystal display screen according to claim 1, characterized in that: Get multiple ring LED light sources, including: A fixing frame is provided in an area between the image acquisition module and an area where the fixture is placed on the LCD screen to be tested; An opening is provided at the center of the fixing frame to facilitate the image acquisition module to acquire images; An arc-shaped circuit board is arranged on the inner side of the fixing frame; A plurality of annular LED light strips are arranged on the inner side of the arc-shaped circuit board, and the annular LED light strips are made to illuminate a specified area of ​​the liquid crystal display screen to be tested at different illumination angles; The brightness of the annular LED light source is configured to enhance the contrast between the scratches on the liquid crystal display screen to be tested and the background, thereby obtaining the plurality of annular LED light sources; Wherein, the irradiation angle is the angle between the LED light and the liquid crystal display screen to be tested.

4. The automatic detection method for scratches on a liquid crystal display screen according to claim 1, characterized in that: The step of sequentially lighting up and shutting down the annular LED light source and using the image acquisition module to acquire a first image of the liquid crystal display screen to be tested when each annular LED light is irradiated comprises: Turn on the annular LED light source at a first irradiation angle, use the image acquisition module to acquire an image of the liquid crystal display screen to be tested, and after the image acquisition is completed, turn off the annular LED light source at the first irradiation angle; Turn on the annular LED light source at the second irradiation angle, use the image acquisition module to acquire the image of the liquid crystal display screen to be tested, and after the image acquisition is completed, turn off the annular LED light source at the second irradiation angle; The above two steps are executed in a loop until the first images of the liquid crystal display screen to be tested at all illumination angles are collected.

5. The automatic detection method for scratches on a liquid crystal display screen according to claim 1, characterized in that: The step of performing enhancement processing on each of the first images to obtain a plurality of second images comprises: Performing noise reduction processing on the first image by using mean filtering; The grayscale value of the first image after noise reduction processing is adjusted through linear transformation to enhance the image contrast, thereby obtaining the second image.

6. The automatic detection method for scratches on a liquid crystal display screen according to claim 1, characterized in that: The method of using a threshold segmentation algorithm to segment the scratches from the plurality of second images to obtain a plurality of third images includes: Determine a segmentation threshold of the second image using an OSTU algorithm; comparing the grayscale value of each pixel in the second image with the segmentation threshold; If it is greater than the segmentation threshold, it is determined to be a scratch pixel; if it is less than the segmentation threshold, it is determined to be a background pixel, and a third image is obtained.

7. The automatic detection method for scratches on a liquid crystal display screen according to claim 1, characterized in that: The step of fitting the plurality of third images using a morphological dilation algorithm to obtain a fourth image of the scratch area includes: Obtaining a structure element and a dilation operator of the fourth image, and moving the structure element pixel by pixel in the fourth image, wherein the dilation operator is a maximum value operator; Selecting the maximum value operator for each pixel position to determine the grayscale value of the target pixel of the disconnected area; The above two steps are executed in a loop until all pixels of the fourth image are traversed; Repeat the previous step and perform multiple expansion operations until all disconnected parts are connected.

8. An automatic detection device for scratches on a liquid crystal display screen, using the automatic detection method for scratches on a liquid crystal display screen according to any one of claims 1 to 7, characterized in that: include: An acquisition module is used to acquire an image acquisition module and a plurality of annular LED light sources, wherein the plurality of annular LED light sources emit annular LED light to a liquid crystal display screen to be tested at different angles in a dark field environment; A first acquisition module, used to sequentially light up and turn off the annular LED light source, and use an image acquisition module to acquire a plurality of first images of the liquid crystal display screen to be tested when each annular LED light is irradiated; a processing module, configured to perform enhancement processing on each of the first images to obtain a plurality of second images, segment the scratches from the plurality of second images using a threshold segmentation algorithm to obtain a plurality of third images, and fit the plurality of third images using a morphological dilation algorithm to obtain a fourth image of the scratch area; A second acquisition module is used to light up the LCD screen to be tested by using a fixture, and use the image acquisition module to obtain a fifth image, and use an image processing algorithm to perform preliminary determination processing on the fifth image to obtain a sixth image of a preliminary defect area; The determination module is used to perform a difference process on the sixth image and the fourth image to obtain a final scratch area.

9. The automatic detection device for scratches on a liquid crystal display screen according to claim 8, characterized in that: The processing module comprises: A noise reduction unit, configured to perform noise reduction processing on the first image by using mean filtering; The linear transformation unit is used to adjust the grayscale value of the first image after noise reduction processing through linear transformation to enhance the image contrast and obtain the second image.

10. The automatic detection device for scratches on a liquid crystal display screen according to claim 8, characterized in that: The processing module also includes: A determining unit, configured to determine a segmentation threshold of the third image by using an OSTU algorithm; The comparison and judgment unit is used to compare the grayscale value of each pixel in the third image with the segmentation threshold: if it is greater than the segmentation threshold, it is judged as a scratch pixel; if it is less than the segmentation threshold, it is judged as a background pixel to obtain a third image.

Images