Method, electronic device, and storage medium for detecting an LCD module

Abstract

The present application relates to a method, an electronic device, and a storage medium for detecting an LCD module. The method includes: providing a first light wave and a second light wave, where the first light wave is a light wave emitted by a surface illumination light source, the first light wave is any one of the three primary color lights, the primary color filter is any one of the three primary color filters in the filter device, and the second light wave is emitted by a backlight light source, and the second light wave includes at least one primary color light different from the first light wave; switching the first primary color filter according to the primary color of the first light wave; photographing the LCD module through the first primary color filter by a black-and-white industrial camera to obtain a first LCD module image; switching the second primary color filter according to the primary color of the second light wave; and photographing the LCD module through the second primary color filter by the black-and-white industrial camera to obtain a second LCD module image. The solution provided by the present application can achieve defect detection and differentiation of the LCD module.

Description

[0001] This application claims the priority of a Chinese patent application with the application number 202110496483.9 and the title "Method, Electronic Device and Storage Medium for Detecting LCD Module", which was filed on May 7, 2021. Technical Field

[0002] This application relates to the field of defect detection technology, and particularly to a method, an electronic device and a storage medium for detecting an LCD module. Background Art

[0003] An LCD module is usually a multi-layer structure. During the production and manufacturing process of the LCD module, there are various processes of film sticking and lamination. Inevitably, some foreign matters such as dust and impurities will be introduced during the processing, resulting in defects in the finished product of the LCD module. The traditional solution is to use manual inspection. However, with the rapid development of the machine vision industry, machine vision defect detection has replaced the old manual inspection method in many industries, greatly improving the inspection efficiency. Machine vision defect detection usually uses a high-resolution black-and-white industrial camera to image and detect the LCD module screen, and takes two product images respectively. One is the imaging image of the LCD module when the backlight is lit, and the other is the imaging image of the LCD module with surface lighting. By detecting the algorithm to compare the positions of the bright spots between the two images, foreign matter defects can be distinguished and identified.

[0004] In the prior art, in the patent with the publication number CN110445921A (a method and device for diagnosing backlight foreign matter defects of a mobile phone screen based on machine vision), a foreign matter defect diagnosis method is proposed. A dust side-light device is designed for removing the interference factor of dust, which can exclude the interference of dust on backlight foreign matter defects, and a set of detection algorithms are designed for the detection of the whole backlight foreign matter defects to identify whether there are defects in the mobile phone screen.

[0005] The above prior art has the following disadvantages:

[0006] When the dust side-light device lights up and images the dust, since there is no ideal parallel light, the light used for side-light illumination will penetrate the polarizing film of the mobile phone screen and scatter after irradiating the foreign matter. The scattered light exits from the polarizing film, so that the foreign matter defect is easily imaged, and the defect may be misjudged as surface dust and filtered out, resulting in the problem of missed detection of foreign matter defects. Therefore, it is necessary to develop a method for distinguishing surface dust and foreign matter defects according to the gray value in the image to be measured. Summary of the Invention

[0007] To overcome the problems existing in the related art, the present application provides a method for detecting an LCD module, which can improve the accuracy of detecting foreign object defects in the LCD module and improve the detection efficiency.

[0008] The first aspect of the present application provides a method for detecting an LCD module, including: providing a first light wave and a second light wave, where the first light wave is the light wave emitted by a surface illumination light source, the first light wave is any one of the three primary color lights, the primary color filter is any one of the three primary color filters in the filter device, the second light wave is emitted by a backlight source, and the second light wave includes at least one primary color light different from the first light wave; switching the first primary color filter according to the primary color of the first light wave; photographing the LCD module through the first primary color filter by a black and white industrial camera to obtain a first LCD module image; switching the second primary color filter according to the primary color of the second light wave; photographing the LCD module through the second primary color filter by the black and white industrial camera to obtain a second LCD module image.

[0009] In one embodiment, the method further includes: extracting regions of interest from each LCD module image respectively to obtain corresponding LCD images to be detected, where each LCD image to be detected includes at least one response bright spot; obtaining the bright spot gray values corresponding to at least one response bright spot in the LCD image to be detected respectively; using a gray threshold to perform threshold segmentation on the bright spot gray values corresponding to at least one response bright spot respectively to determine the foreign object types corresponding to at least one response bright spot in each LCD module image, and the foreign object types include dust and foreign object defects.

[0010] In one embodiment, switching the second primary color filter according to the primary color of the second light wave includes: if the second light wave is a light composed of a combination of three primary colors, switching the second primary color filter to a filter with a color different from the primary color of the first light wave among the three primary color filters; if the second light wave is a light composed of any two primary color combinations, switching the second primary color filter to a filter with a color different from the primary color of the first light wave and consistent with any one of the primary colors of the second light wave among the three primary color filters; if the second light wave is a single primary color light, switching the second primary color filter to a filter with a color consistent with the primary color of the second light wave among the three primary color filters.

[0011] In one embodiment, the gray threshold is determined according to the numerical range of the bright spot gray values corresponding to at least one response bright spot in the same LCD image to be detected; using the gray threshold to perform threshold segmentation on the bright spot gray values corresponding to at least one response bright spot respectively includes: comparing each bright spot gray value with the gray threshold respectively.

[0012] In one embodiment, determining the foreign object type corresponding to at least one response highlight in each LCD module image includes: in the LCD image to be tested corresponding to the second LCD module image, if the current highlight gray value is less than the gray threshold, it is determined that the foreign object type of the response highlight corresponding to the current highlight gray value is dust; if the current highlight gray value is greater than the gray threshold, it is determined that the foreign object type of the response highlight corresponding to the current highlight gray value is a foreign object defect; in the LCD image to be tested corresponding to the first LCD module image, if the current highlight gray value is greater than the gray threshold, it is determined that the foreign object type of the response highlight corresponding to the current highlight gray value is the dust; if the current highlight gray value is less than the gray threshold, it is determined that the foreign object type of the response highlight corresponding to the current highlight gray value is the foreign object defect.

[0013] In one embodiment, after determining the foreign object type corresponding to at least one response highlight in each LCD module image, it includes: filtering out the response highlights determined to be dust in the LCD image to be tested.

[0014] In one embodiment, extracting the region of interest from each LCD module image includes: extracting the region of interest from each LCD module image through a threshold segmentation algorithm.

[0015] In one embodiment, before photographing the LCD module with a black-and-white industrial camera, the method further includes: illuminating the LCD module through a backlight source and a surface illumination source; the surface illumination source illuminates the LCD module at an illumination angle of α, where the illumination angle is the angle formed by the light wave emitted by the surface illumination source and the normal of the horizontal plane, and α is greater than zero.

[0016] In one embodiment, photographing the LCD module through the first primary color filter or the second primary color filter with a black-and-white industrial camera includes: photographing the front view of the screen surface of the LCD module through the first primary color filter or the second primary color filter with a black-and-white industrial camera.

[0017] The second aspect of the present application provides an electronic device, including: a processor; and a memory, on which executable code is stored, and when the executable code is executed by the processor, the processor is caused to execute the method as described above.

[0018] The third aspect of the present application provides a non-transitory machine-readable storage medium, on which executable code is stored, and when the executable code is executed by the processor of an electronic device, the processor is caused to execute the method as described above.

[0019] The technical solution provided by the present application may include the following beneficial effects:

[0020] Switch the first primary color filter according to the primary color of the first light wave, switch the second primary color filter according to the primary color of the second light wave, and use a black-and-white industrial camera to take pictures of the LCD module through the switched primary color filters under a preset light source, so that the surface dust and foreign object defects of the LCD module present different colors, in order to realize the detection and differentiation of dust and foreign object defects. The first light wave is any one of the primary color lights emitted by the surface lighting source, the primary color filter is a filter with one of the primary colors in the three primary color filters in the filtering device, the preset light source includes a backlight source and a surface lighting source, and the second light wave emitted by the backlight source includes at least one primary color light different from the first light wave.

[0021] In some embodiments, by separately extracting the regions of interest from the obtained first LCD module image and the second LCD module image, at least one response bright spot is included in the corresponding LCD image to be tested obtained after extraction. Obtain the gray values of each response bright spot of all response bright spots in the LCD image to be tested, perform a threshold segmentation operation on the gray values of the response bright spots corresponding to all response bright spots in the LCD image to be tested, and obtain the foreign object attribute classification of the response bright spots. Compared with the prior art, in this solution, the LCD module is photographed through the switched primary color filter by a black-and-white industrial camera in a specific environment where the light waves emitted by the background light source and the surface lighting source are significantly different, illuminating the foreign object defects in the LCD module and the surface dust of the LCD module, so that the foreign object defects and dust both appear as response bright spots in the imaged LCD module image. Obtain the gray values of the response bright spots corresponding to each response bright spot respectively, and determine the foreign object type corresponding to the response bright spot by thresholding the gray values of the response bright spots through a gray threshold, so as to achieve the effect of distinguishing surface dust and foreign object defects in the module, improve the detection accuracy, the detection implementation difficulty is low, improve the detection efficiency, reduce the detection cost, and have strong compatibility for foreign object detection.

[0022] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. Brief Description of the Drawings

[0023] By describing the exemplary embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other objects, features and advantages of the present application will become more obvious. Among them, in the exemplary embodiments of the present application, the same reference numerals generally represent the same components.

[0024] Figure 1 is a schematic flowchart of the first embodiment of the method for detecting an LCD module shown in the embodiments of the present application;

[0025] Figure 2 is a schematic flowchart of the second embodiment of the method for detecting an LCD module shown in the embodiments of the present application;

[0026] Figure 3 It is a schematic flowchart of the third method embodiment for detecting an LCD module shown in an embodiment of the present application;

[0027] Figure 4 It is a schematic structural diagram of an electronic device shown in an embodiment of the present application. Detailed implementation manners

[0028] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0029] The terms used in the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0030] It should be understood that although the terms "first", "second", "third", etc. may be used in the present application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, "a plurality" means two or more unless otherwise specifically defined.

[0031] Embodiment 1

[0032] An LCD module is usually a multi-layer structure. During the production and manufacturing process of the LCD module, there are various processes such as film pasting and pressing. Inevitably, some foreign matters such as dust and impurities will be introduced during the processing, resulting in defects in the finished product of the LCD module. The traditional solution is to use manual inspection methods. However, with the rapid development of the machine vision industry, machine vision defect detection has replaced the old manual inspection methods in many industries, greatly improving the inspection efficiency. Machine vision defect detection usually uses a high-resolution black-and-white industrial camera to image and detect the LCD module screen, taking two product images respectively. One is the imaging image of the LCD module when the backlight is lit, and the other is the imaging image of the LCD module with surface lighting. By detecting the algorithm to compare the positions of the bright spots between the two images, foreign matter defects can be distinguished and identified. In the prior art, a foreign matter defect diagnosis method is proposed. A dust side-light device is designed to remove the interference of dust, which can exclude the interference of dust on the backlight foreign matter defects, and a set of detection algorithms is designed for the detection of the entire backlight foreign matter defects to identify whether there are defects in the mobile phone screen. However, the above prior art has disadvantages: when the dust side-light device lights up and images the dust, it is easy to image the foreign matter defects as well. The defects may be misjudged as surface dust and filtered out, resulting in the problem of missed detection of foreign matter defects. Therefore, it is necessary to develop a method for distinguishing surface dust and foreign matter defects according to the gray value in the image to be measured.

[0033] In view of the above problems, an embodiment of the present application provides a method for detecting an LCD module, which can improve the accuracy of foreign matter defect detection of the LCD module and improve the detection efficiency.

[0034] The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0035] Figure 1 It is a schematic flowchart of the first embodiment of the method for detecting an LCD module shown in the embodiment of the present application.

[0036] Please refer to Figure 1 , the first embodiment of the LCD foreign matter defect detection method shown in the embodiment of the present application includes:

[0037] 101. Switch the base color filter according to the base color of the first light wave;

[0038] In the embodiment of the present application, the first light wave is the light wave emitted by the surface lighting source, and the first light wave is any one of the three primary color lights. The three primary colors refer to red, green, and blue. The three primary color lights refer to red light, green light, and blue light. The primary color light refers to any one of red light, green light, and blue light.

[0039] In some embodiments, the filter device includes a first primary color filter, a second primary color filter, and a third primary color filter. The primary color filter refers to any one of the three primary color filters in the filter device. The filter device has the function of converting the three primary color filters. The three primary color filters refer to a red filter, a green filter, and a blue filter. Ideally, any primary color filter can only allow light of the primary color to pass through, for example, a red filter can only allow red light to pass through. In actual situations, the wavelength band of light that can be passed by the primary color filter actually used may overlap with the wavelength of other primary color lights, so that the primary color filter cannot filter out 100% of the light of other primary colors, so weak light of other primary colors may pass through. For example, a red filter may allow weak blue light or green light to pass through.

[0040] Assuming that the first light wave is red light, the first light wave highlights the dust on the surface and then forms an image. The color of the dust can be regarded as the same as the color of the first light wave within a reasonable error range. Therefore, the response bright spot corresponding to the dust will only be more obvious when shooting with a red filter. However, since the second light wave is significantly different from the first light wave, the response bright spot corresponding to the foreign body defect highlighted by the second light wave can also be more obvious when shooting with a green filter or a blue filter, while the response bright spot corresponding to the dust is not obvious or even does not appear. Therefore, in the current situation, a green filter or a blue filter can be selected as the primary color filter for shooting, so that the response bright spot corresponding to the dust and the response bright spot corresponding to the foreign body defect can be clearly distinguished. When a red filter is selected as the primary color filter for shooting, since the response bright spot corresponding to the dust can be more obvious, while the response bright spot corresponding to the foreign body defect highlighted by the second light wave is not obvious or even does not appear, the response bright spot corresponding to the dust can be clearly located.

[0041] It is understandable that the above method for switching the primary color filter is only exemplary and is only for a better understanding of the principle of switching the primary color filter. In actual applications, the first light wave may also be green light or blue light, which is not the only limitation here.

[0042] 102. Use a black and white industrial camera to photograph the LCD module through the first primary color filter and the second primary color filter respectively;

[0043] An industrial camera is a key component in a machine vision system. Its most essential function is to convert optical signals into ordered electrical signals, featuring high image stability, high transmission ability, and high anti-interference ability. Most of its image sensors are based on CCD chips or CMOS chips. The photos taken by a black-and-white industrial camera are black-and-white photos. In the embodiments of this application, the black-and-white industrial camera is used to photograph an LCD module and obtain an LCD module image.

[0044] Taking a photo with a black-and-white industrial camera can be done under a preset light source. The preset light source means that the shooting environment includes a backlight source and a surface lighting source. The backlight source emits a second light wave, and the second light wave contains at least one primary color light different from the first light wave. Exemplarily, assuming the first light wave is red light, then the second light wave contains at least one primary color light different from red light, that is, the second light wave can be blue light, or a composite light of red light and blue light, or white light, but cannot be the same red light as the first light wave, so as to achieve the effect that the light waves emitted by the surface lighting source and the backlight source should have obvious differences.

[0045] An LCD module is usually a multi-layer structure, at least including an upper polarizer layer, a liquid crystal layer, and a lower polarizer layer, where the liquid crystal layer is located between the upper polarizer layer and the lower polarizer layer. Foreign object defects existing in the finished product of the LCD module are between the upper polarizer and the liquid crystal layer and between the lower polarizer and the liquid crystal layer. The characteristic of this kind of foreign object defect is that when the LCD module is illuminated by the backlight source, the foreign object defect exists as a bright spot in the screen, which is determined by the optical principle of the LCD module.

[0046] Specifically, a polarizer has the characteristic of only allowing light with a specific polarization direction to pass through. When light penetrates a layer of polarizer (such as the lower polarizer layer), the light will be attenuated by nearly 50% to become polarized light, and when the polarized light penetrates another polarizer orthogonal to the previous layer of polarizer (such as the upper polarizer layer), almost all of the light is attenuated. For the dust on the LCD surface, the second light wave emitted by the backlight source needs to penetrate two layers of orthogonal polarizer layers to reach the LCD surface. At this time, almost all of the second light wave is attenuated, so there is no or only a weak second light wave (about 3%) that can illuminate the dust. Therefore, when taking a photo with a second primary color filter, the dust does not appear or is darker. For the foreign objects inside the LCD, after the second light wave penetrates the lower polarizer layer and shines on the foreign objects, scattering occurs, causing the polarization state of the second light wave to disappear (i.e., non-polarized light). Therefore, only about 50% of the brightness of the non-polarized second light wave is attenuated after it exits from the upper polarizer layer. It can be seen that compared with the surface dust, the foreign objects in the LCD module are more easily illuminated by the second light wave, while the dust will be very dark or even not appear.

[0047] Therefore, in the embodiments of the present application, the preset light source will include a backlight source. In order to distinguish the dust and foreign object defects on the surface of the LCD module, the preset light source will also include a surface lighting source that is significantly different from the backlight source to illuminate the dust on the surface of the LCD module.

[0048] 103. Extract the region of interest from each LCD module image to obtain the corresponding LCD image to be tested.

[0049] Perform image processing on each of the captured LCD module images (i.e., the first LCD module image and the second LCD module image). In each LCD module image, since the backlight source can only penetrate the position where the foreign object defect is located and cannot penetrate the normal part of the screen (based on the above optical principle of the LCD module), and since the main function of the surface lighting source is to illuminate the surface dust, each of the obtained LCD module images presents an image mostly in dark tones, with sporadic response highlights in the image, that is, including at least one response highlight. Taking the second LCD module image as an example, in some embodiments, among several response highlights, there are mainly foreign object defect highlights illuminated by the backlight source, and some weak response highlights may be dust highlights illuminated by stray light in the shooting environment. These response highlights are all extracted through image processing technology to form the LCD image to be tested. Similarly, extract the region of interest from the first LCD module image. Among the several response highlights it includes, there are mainly dust highlights illuminated by the surface lighting source, and some weak response highlights may be foreign object defect highlights generated by some weak second light waves passing through the first color filter in the actual situation.

[0050] 104. Obtain the highlight gray values corresponding to at least one response highlight in the LCD image to be tested.

[0051] The highlight gray value refers to the gray value of the response highlight. After passing through the color filter, the highlight gray value of the response highlight reflects the brightness of the primary color light passing through the color filter in the response highlight. If the highlight gray value is low, it means that the response highlight is darker; if the highlight gray value is high, it means that the response highlight is brighter.

[0052] Regarding the method of obtaining the highlight gray value, in the embodiments of the present application, it is obtained through an image color picker software. It can be understood that in practical applications, the methods of obtaining the highlight gray value are diverse. The above method of obtaining through software is only exemplary, and other suitable algorithms or software can be selected according to the actual application situation. Here, the method of obtaining the highlight gray value is not uniquely limited.

[0053] 105. Use a grayscale threshold to perform threshold segmentation on the highlight grayscale values corresponding to at least one response highlight respectively, and determine the foreign object types corresponding to at least one response highlight in each LCD module image.

[0054] In some embodiments, for the LCD image to be measured corresponding to each LCD module image, use a grayscale threshold to separate the highlight grayscale values corresponding to all response highlights into two sets. The foreign object type corresponding to the response highlights with the highlight grayscale values in one set is dust, and the foreign object type corresponding to the response highlights with the highlight grayscale values in the other set is a foreign object defect in the LCD module.

[0055] The following beneficial effects can be seen from the above Embodiment 1:

[0056] By switching the first primary color filter according to the primary color of the first light wave for shooting, and switching the second primary color filter according to the primary color of the second light wave for shooting. The first light wave is any one of the three primary color lights emitted by the surface lighting source, and the primary color filter is a filter with a color of one of the three primary color filters in the filter device. Shoot the LCD module through the switched primary color filter by a black and white industrial camera under a preset light source. The preset light source includes a backlight source and a surface lighting source. The second light wave emitted by the backlight source includes at least one primary color light different from the first light wave. Extract the region of interest from each LCD module image obtained by shooting. The corresponding LCD image to be measured obtained after extraction includes at least one response highlight. Obtain the respective highlight grayscale values of all response highlights in each LCD image to be measured. Perform a threshold segmentation operation on the highlight grayscale values corresponding to all response highlights in each LCD image to be measured, and obtain the foreign object attribute classification of the response highlights.

[0057] Compared with the prior art, in this solution, a black and white industrial camera shoots the LCD module through the switched primary color filter in a specific environment where the light waves emitted by the background light source and the surface lighting source are significantly different. The foreign object defects in the LCD module and the dust on the surface of the LCD module are illuminated, so that the foreign object defects and the dust appear as response highlights in the imaged LCD module image. Obtain the highlight grayscale values corresponding to each response highlight respectively. After performing threshold segmentation on the highlight grayscale values of the response highlights through the grayscale threshold, determine the foreign object types corresponding to the response highlights, so as to achieve the effect of distinguishing surface dust and foreign object defects in the module, improve the detection accuracy, the detection implementation difficulty is low, improve the detection efficiency, reduce the detection cost, and have strong compatibility for foreign object detection.

[0058] Embodiment 2

[0059] For ease of understanding, an embodiment of the LCD foreign object defect detection method is provided below for illustration. In practical applications, in addition to considering the primary color of the first light wave, the number of primary colors included in the second light wave is also considered to accurately determine the second primary color filter. After switching the second primary color filter, a black-and-white industrial camera can also take pictures through the second primary color filter under a preset light source to improve the detection efficiency and avoid taking pictures with the same detection effect repeatedly.

[0060] Figure 2 It is a schematic flowchart of Embodiment 2 of the LCD foreign object defect detection method shown in the embodiments of the present application.

[0061] Please refer to Figure 2 , Embodiment 2 of the method for detecting an LCD module shown in the embodiments of the present application includes:

[0062] 201. Determine a primary color filter according to the colors of the first light wave and the second light wave;

[0063] Switch the first primary color filter according to the primary color of the first light wave. The first primary color filter can be a filter with the same primary color as the first light wave. Assume that the first light wave is red, and the first primary color filter can be a red filter. Switch the second primary color filter according to the primary color of the second light wave. The primary color of the second primary color filter can be determined according to the primary colors of the first light wave and the second light wave, which will be described in detail below.

[0064] If the second light wave is a combination of three primary colors, switch the second primary color filter to a filter with a color different from the primary color of the first light wave among the three primary color filters. Assume that the first light wave is red light, and the second light wave is a composite light in which all three primary colors are involved in the combination. It can be determined that in the image of the second LCD module formed after filtering with a green filter or a blue filter, since the first light wave cannot be imaged through the green filter or the blue filter, the response highlights corresponding to the dust illuminated by the first light wave are displayed darker, while the green light and blue light in the second light wave can both pass through the green filter and the blue filter, and the response highlights corresponding to the foreign object defects illuminated by the second light wave are displayed brighter. The difference in brightness between the response highlights corresponding to the dust and the response highlights corresponding to the foreign object defects is relatively large. Thus, in this case, a green filter or a blue filter can be selected as the second primary color filter.

[0065] If the second light wave is a combination of any two primary colors, switch the second primary color filter to the filter in the three primary color filters whose color is different from the primary color of the first light wave and is consistent with any one of the primary colors of the second light wave. Assume that the first light wave is red light, then the second light wave may be a combination of red light and blue light or green light, or a combination of blue light and green light. In the case of the combination of red light and blue light, both the first light wave and the second light wave can pass through the red filter, and the blue light part of the second light wave can pass through the blue filter. It shows that it can be determined that in the image of the second LCD module formed after filtering with the blue filter in this case, the response highlights corresponding to the foreign object defects illuminated by the second light wave are displayed brighter, and the response highlights corresponding to the dust illuminated by the first light wave are displayed darker. The difference in brightness between the response highlights corresponding to the dust and the response highlights corresponding to the foreign object defects is relatively large. From this, it can be obtained that the blue filter can be selected as the second primary color filter in the current case.

[0066] If the second light wave is a single primary color light, switch the second primary color filter to the filter in the three primary color filters whose color is consistent with the primary color of the second light wave. Assume that the first light wave is red light and the second light wave is green light different from the first light wave. It can be determined that in the image of the second LCD module formed after filtering with the green filter, since the first light wave cannot be imaged through the green filter, the response highlights corresponding to the dust illuminated by the first light wave are displayed darker, while the green light in the second light wave can pass through the green filter, and the response highlights corresponding to the foreign object defects illuminated by the second light wave are displayed brighter. The difference in brightness between the response highlights corresponding to the dust and the response highlights corresponding to the foreign object defects is relatively large. From this, it can be obtained that the green filter can be selected as the second primary color filter in the current case.

[0067] It can be understood that the above hypothetical descriptions are only for better understanding the solution. For the first light wave and the second light wave, different settings can be made according to the actual application situation in actual applications, and there is no unique limitation here.

[0068] It can be understood that by using the lighting method of two different color light sources (i.e., the first light wave and the second light wave) in the embodiments of the present invention, the dust on the surface of the LCD module can present one color, while the foreign object defects inside the LCD module present another color. Thus, different images of the LCD module can be obtained by switching the primary color filter to achieve the distinction between dust and foreign object defects. Although a color industrial camera can achieve the purpose of distinguishing dust and foreign objects by directly distinguishing RGB imaging, the imaging accuracy of the color industrial camera is lower than that of a black-and-white industrial camera. To more intuitively understand the advantages of this embodiment, the following is described in conjunction with Table 1. In the prior art, considering the accuracy problem, a black-and-white industrial camera is generally used to detect foreign object defects on the LCD screen.

[0069] Table 1:

[0070] Whether dust and foreign objects can be distinguished Imaging accuracy Existing technology (i.e., using a black-and-white industrial camera alone) No Higher Color industrial camera solution Yes Lower Black-and-white industrial camera + external filter Yes Higher

[0071] From the comparison results in Table 1, it can be seen that by combining the black-and-white industrial camera of the embodiment of the present invention with the primary color filter, not only can the purpose of distinguishing dust and foreign object defects be achieved, but also the imaging accuracy can be effectively improved, which is beneficial to further improving the accuracy of defect detection.

[0072] 202. Illuminate the LCD module through the backlight source and the surface lighting source;

[0073] The LCD module is located between the backlight source and the surface lighting source. The brightness of the backlight source and the surface lighting source should satisfy that the gray value of the response highlights corresponding to the dust and foreign object defects in the image of the LCD module after imaging reaches x or more on any one channel. x can take the value of 150. It can be understood that in actual applications, the value of x needs to be set according to the actual application situation and is not uniquely limited.

[0074] The surface lighting source irradiates the LCD module at an irradiation angle of α. The irradiation angle is the angle formed by the light wave emitted by the surface lighting source and the normal line of the horizontal plane. α is greater than zero. In the embodiment of the present application, the normal line of the horizontal plane can be the normal line of the plane where the surface of the LCD module is located. The range of α can be any angle between 30 - 60 degrees. It can be understood that in actual applications, the range of α needs to be set according to the actual application situation and is not uniquely limited.

[0075] 203. Use the black-and-white industrial camera to take pictures of the LCD module through the corresponding primary color filter;

[0076] The filter device where the primary color filter is located is installed directly in front of the lens group of the black-and-white industrial camera. After the light passes through the filter device and enters the lens group, it is then imaged through the photosensitive chip of the black-and-white industrial camera. In some embodiments, the LCD module is photographed through different primary color filters by the black-and-white industrial camera to respectively obtain a first LCD module image containing dust highlights and a second LCD module image containing foreign object defect highlights for the same LCD module, which is beneficial to more accurately distinguish dust and foreign object defects.

[0077] By using the black-and-white industrial camera to take a front view of the screen surface of the LCD module through the first primary color filter or the second primary color filter, the black-and-white industrial camera can be set directly above the LCD module for shooting.

[0078] The following beneficial effects can be seen from the above Embodiment 2:

[0079] By determining the color filter based on the colors of the first light wave and the second light wave, after determining the color filter, a black-and-white industrial camera is used to photograph the LCD module through the corresponding color filter under a preset light source. When photographing, the backlight source and the surface lighting source are used to illuminate the LCD module with a certain brightness and angle, and a front view of the LCD module is photographed to obtain an LCD module image. Compared with the prior art, the technical solution of this application uses photographing through the color filter to achieve the effect of clearly distinguishing the response highlights corresponding to dust from the response highlights corresponding to foreign object defects. It fully considers various combinations of the colors of the first light wave and the second light wave without the need to use all three color filters for photographing, avoiding taking photos with the same detection effect repeatedly, avoiding repeated detection and ineffective detection, improving the detection efficiency, reducing the detection cost, having strong compatibility for the detection method, ensuring the quality of the obtained LCD module image under the preset light source, and improving the detection accuracy.

[0080] Embodiment III

[0081] For ease of understanding, an embodiment of the LCD foreign object defect detection method is provided below for illustration. In actual applications, after distinguishing the types of foreign objects corresponding to the response highlights, the response highlights corresponding to dust are filtered out, and the positions of foreign object defects are detected.

[0082] Figure 3 It is a schematic flowchart of Embodiment III of the method for detecting an LCD module shown in the embodiments of this application.

[0083] Please refer to Figure 3 , the method Embodiment III shown in the embodiments of this application includes:

[0084] 301. Extract the region of interest from each LCD module image to obtain the corresponding LCD image to be measured;

[0085] The region of interest is extracted from each LCD module image through a threshold segmentation algorithm, and other non-target detection objects outside each LCD module are filtered out to obtain the LCD image to be measured corresponding to each LCD module image, that is, each LCD module image corresponds to an LCD image to be measured.

[0086] The threshold segmentation algorithm is a region-based image segmentation technology. The principle is to divide the image pixel points into several categories, which is a necessary image processing process before image analysis, feature extraction, and pattern recognition.

[0087] 302. Obtain the highlight gray values corresponding to at least one response highlight in the LCD image to be measured;

[0088] In the embodiment of the present application, the specific content of step 302 is similar to that of step 104 in the first embodiment above, and will not be elaborated here.

[0089] 303. Use a grayscale threshold to perform threshold segmentation on the highlight grayscale values corresponding to at least one response highlight, and determine the foreign object types corresponding to at least one response highlight in each LCD module image;

[0090] The grayscale threshold is determined according to the numerical range of the highlight grayscale values corresponding to at least one response highlight in the same LCD image to be measured. The average value of the highlight grayscale values corresponding to all response highlights in the same LCD image to be measured can be selected as the grayscale threshold. It can be understood that in actual applications, a suitable grayscale threshold needs to be set according to the actual application situation. The above method for setting the grayscale threshold is only exemplary and is not the only limitation of the setting method. The grayscale thresholds determined for different LCD images to be measured can be different.

[0091] Performing threshold segmentation on the highlight grayscale values means comparing each highlight grayscale value with the grayscale threshold. In the corresponding LCD image to be measured of the second LCD module image, if the current highlight grayscale value is less than the grayscale threshold, it indicates that the main light source of the current response highlight is the first light wave or ambient stray light, and it is determined that the foreign object type of the response highlight corresponding to the current highlight grayscale value is dust; if the current highlight grayscale value is greater than the grayscale threshold, it indicates that the main light source of the current response highlight is the second light wave, and it is determined that the foreign object type of the response highlight corresponding to the current highlight grayscale value is a foreign object defect. Similarly, in the corresponding LCD image to be measured of the first LCD module image, if the current highlight grayscale value is greater than the grayscale threshold, it indicates that the main light source of the current response highlight is the first light wave, and it is determined that the foreign object type of the response highlight corresponding to the current highlight grayscale value is dust; if the current highlight grayscale value is less than the grayscale threshold, it indicates that the main light source of the current response highlight is the second light wave, and it is determined that the foreign object type of the response highlight corresponding to the current highlight grayscale value is a foreign object defect.

[0092] For the response highlights at the same position, if its grayscale value in the corresponding LCD image to be measured of the first LCD module image is greater than the corresponding grayscale threshold, and its grayscale value in the corresponding LCD image to be measured of the second LCD module image is less than the corresponding grayscale threshold, it indicates that the main light source of the current response highlight is the first light wave, and it is determined that the foreign object type of the current response highlight is dust. For the response highlights at the same position, if its grayscale value in the corresponding LCD image to be measured of the first LCD module image is less than the corresponding grayscale threshold, and its grayscale value in the corresponding LCD image to be measured of the second LCD module image is greater than the corresponding grayscale threshold, it indicates that the main light source of the current response highlight is the second light wave, and it is determined that the foreign object type of the current response highlight is a foreign object defect.

[0093] 304. Detect the position of foreign object defects in the LCD.

[0094] In each LCD image to be tested, filter out the response highlights determined to be dust. Then, the remaining response highlights in each LCD image to be tested are the response highlights of foreign object defects. Thus, it can be determined that the position of the foreign object defect is the position of the remaining response highlights.

[0095] The following beneficial effects can be seen from the above Embodiment 3:

[0096] By using the threshold segmentation algorithm to extract the region of interest from the LCD module image, filter out other non-target detection objects outside the LCD module, and obtain the LCD image to be tested. In the LCD image to be tested, compare the gray value of the highlights with the gray threshold to distinguish the response highlights corresponding to dust and the response highlights corresponding to foreign object defects, filter out the response highlights corresponding to dust, and detect the position of the response highlights corresponding to foreign object defects. Compared with the prior art, this solution filters out other non-target detection objects other than the response highlights, reduces interference with the detection, distinguishes the response highlights in the LCD image to be tested through the gray threshold, accurately determines the position of the foreign object defect after removing the response highlights corresponding to the distinguished dust, improves the detection accuracy, has a low implementation difficulty of detection, and a high detection efficiency.

[0097] By performing threshold segmentation on the corresponding LCD image to be tested for each LCD module image, the position of dust can be accurately determined from the first LCD module image, and the position of foreign object defects can be accurately determined from the second LCD module image. Thus, accurate distinction between dust and foreign object defects can be achieved by using them alone or in combination. By accurately determining the position of dust from the first LCD module image, in addition to being able to be used in combination with the second LCD module image to accurately determine the position of foreign object defects in the second LCD module image, it can also be used to exclude the influence of dust in subsequent other detections.

[0098] Embodiment 4

[0099] Corresponding to the foregoing method embodiments for implementing application functions, the present application also provides an electronic device for executing the LCD foreign object defect detection method and corresponding embodiments.

[0100] Figure 4 It is a schematic structural diagram of the electronic device shown in the embodiments of the present application.

[0101] See Figure 4 , the electronic device 1000 includes a memory 1010 and a processor 1020.

[0102] The processor 1020 can be a Central Processing Unit (CPU), or it can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0103] The memory 1010 can include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, the ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device can be a read-write storage device. The permanent storage device can be a non-volatile storage device that does not lose the stored instructions and data even when the computer is powered off. In some embodiments, the permanent storage device uses a mass storage device (such as a magnetic or optical disk, flash memory) as the permanent storage device. In some other embodiments, the permanent storage device can be a removable storage device (such as a floppy disk, optical drive). The system memory can be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. The system memory can store some or all of the instructions and data required by the processor during operation. In addition, the memory 1010 can include any combination of computer-readable storage media, including various types of semiconductor storage chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and magnetic disks and / or optical disks can also be used. In some embodiments, the memory 1010 can include a removable storage device that can be read and / or written, such as a compact disc (CD), read-only digital versatile disc (such as DVD-ROM, dual-layer DVD-ROM), read-only Blu-ray disc, super density disc, flash memory card (such as SD card, min SD card, Micro-SD card, etc.), magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and instantaneous electronic signals transmitted wirelessly or wired.

[0104] An executable code is stored on the memory 1010. When the executable code is processed by the processor 1020, it can cause the processor 1020 to execute some or all of the methods described above.

[0105] The solution of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. Those skilled in the art should also be aware that the actions and modules involved in the specification are not necessarily essential to the present application. In addition, it can be understood that the steps in the method embodiments of the present application can be adjusted, combined, and deleted according to actual needs, and the modules in the device embodiments of the present application can be combined, divided, and deleted according to actual needs.

[0106] In addition, the method according to the present application can also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0107] Alternatively, the present application can also be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium), on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or an electronic device, a server, etc.), the processor is caused to execute some or all of the steps of the above method according to the present application.

[0108] It should be noted that, compared with color industrial cameras, black-and-white industrial cameras have better imaging quality, which will be illustrated below. For example, for a color industrial camera and a black-and-white industrial camera using the same type of sensor, the essential difference is that: a Bayer ("bayer") filter (R and G and B filters) is added in front of the sensor of the color industrial camera, and three pixels are used to receive the R and G and B component information of the same point, and then the RGB information of this point is obtained through internal algorithms of the camera; while there is no filter in front of the sensor of the black-and-white industrial camera, and a single pixel senses the information of a single point. This difference makes the black-and-white industrial camera not retain the color information of the image and can more truly restore the gray scale of each pixel in the image. Therefore, the imaging accuracy of the black-and-white industrial camera is higher.

[0109] Those skilled in the art will also understand that the various exemplary logical blocks, modules, circuits, and algorithm steps described in connection with the application herein can be implemented as electronic hardware, computer software, or a combination of both.

[0110] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or by a combination of dedicated hardware and computer instructions.

[0111] The embodiments of the present application have been described above. The above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art in the technical field without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or the improvement of the technology in the market, or to enable other ordinary skill in the technical field to understand the embodiments disclosed herein.

Claims

1. A method for detecting an LCD module, characterized in that, Including: Providing a first light wave and a second light wave, where the first light wave is the light wave emitted by a surface lighting source, the first light wave is any one of the primary color lights in the three primary color lights, the primary color filter is any one of the three primary color filters in the filter device, the second light wave is emitted by a backlight source, and the second light wave includes at least one primary color light different from the first light wave; Switching the first primary color filter according to the primary color of the first light wave; Taking a picture of the LCD module through the first primary color filter by a black-and-white industrial camera to obtain a first LCD module image; Switching the second primary color filter according to the primary color of the second light wave; Taking a picture of the LCD module through the second primary color filter by the black-and-white industrial camera to obtain a second LCD module image; Extracting regions of interest from each LCD module image respectively to obtain corresponding LCD images to be measured, where the LCD images to be measured include at least one response bright spot; Obtaining the bright spot gray values corresponding to at least one response bright spot in the LCD images to be measured; Using a gray threshold to perform threshold segmentation on the bright spot gray values corresponding to at least one response bright spot respectively to determine the foreign object types corresponding to at least one response bright spot in each LCD module image, where the foreign object types include dust on the surface of the LCD module and foreign object defects inside the LCD module; where, Switching the second primary color filter according to the primary color of the second light wave includes: If the second light wave is a light composed of three primary color combinations, switching the second primary color filter to a filter with a color different from the primary color of the first light wave among the three primary color filters; If the second light wave is a light composed of any two primary color combinations, switching the second primary color filter to a filter with a color different from the primary color of the first light wave and consistent with any one of the primary colors of the second light wave among the three primary color filters; If the second light wave is a light of one primary color, switching the second primary color filter to a filter with a color consistent with the primary color of the second light wave among the three primary color filters; Determining the foreign object types corresponding to at least one response bright spot in each LCD module image includes: In the LCD image to be measured corresponding to the second LCD module image, if the current bright spot gray value is less than the gray threshold, determining that the foreign object type of the response bright spot corresponding to the current bright spot gray value is the dust on the surface of the LCD module; If the current bright spot gray value is greater than the gray threshold, determining that the foreign object type of the response bright spot corresponding to the current bright spot gray value is the foreign object defect inside the LCD module; In the LCD image to be measured corresponding to the first LCD module image, if the current bright spot gray value is greater than the gray threshold, determining that the foreign object type of the response bright spot corresponding to the current bright spot gray value is the dust on the surface of the LCD module; If the current bright spot gray value is less than the gray threshold, determining that the foreign object type of the response bright spot corresponding to the current bright spot gray value is the foreign object defect inside the LCD module.

2. The method according to claim 1, wherein The gray threshold is determined according to the numerical range of the bright spot gray values corresponding to at least one response bright spot in the same LCD image to be measured; Performing threshold segmentation on the highlight gray values corresponding to at least one response highlight using a gray threshold includes: Comparing each highlight gray value with the gray threshold respectively.

3. The method according to claim 1, wherein: After determining the foreign object type corresponding to at least one response highlight in each LCD module image, it includes: Filtering out the response highlights determined to be dust on the surface of the LCD module in the LCD image to be measured.

4. The method according to claim 1, wherein: Before photographing the LCD module with a black and white industrial camera, the method further includes: Illuminating the LCD module with the backlight source and the surface lighting source; The surface lighting source irradiates the LCD module at an irradiation angle of α, where the irradiation angle is the angle formed by the light wave emitted by the surface lighting source and the normal of the horizontal plane, and α is greater than zero.

5. The method according to claim 1, wherein: Photographing the LCD module through the first primary color filter or the second primary color filter with the black and white industrial camera includes: Photographing a front view of the screen surface of the LCD module through the first primary color filter or the second primary color filter with the black and white industrial camera.

6. An electronic device, characterized in that, It includes: A processor; And A memory storing executable code thereon, which when executed by the processor, causes the processor to execute the method according to any one of claims 1-5.

7. A non-transitory machine-readable storage medium storing executable code thereon, which when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1-5.

Images