Qualified Detection Method, Device and Computer Equipment for LED Coated Backlight Panel

Abstract

The present application relates to a method, device, and computer equipment for qualified detection of an LED film-covered backlight panel. The method includes: obtaining a first pixel value of an LED film-covered backlight panel image, where the LED film-covered backlight panel image is an image obtained by image acquisition of the LED film-covered backlight panel; determining a second pixel value of the LED film-covered backlight panel image after mean filtering; determining the difference between the first pixel value and the second pixel value; taking the pixel points that satisfy a first preset condition in the binarized difference as key pixel points; determining a connected region based on the key pixel points, and counting the number of the key pixel points in the contour of the connected region; when the number is greater than or equal to a preset number, determining that the LED film-covered backlight panel is a non-conforming product; otherwise, determining that the LED film-covered backlight panel is a qualified product. Using this method can improve the detection accuracy and efficiency of the LED film-covered backlight panel.

Description

Technical Field

[0001] The present application relates to the technical field of optical measurement, and particularly to a method, device, and computer device for detecting the qualification of an LED film-coated backlight panel. Background Art

[0002] With the development of optical technology, LED (Light Emitting Diode) technology has emerged. Among them, there are hundreds or thousands of lamp beads on a Mini LED backlight panel, which is very dazzling when directly viewed by the human eye, and at the same time, the light-emitting surface is uneven. In daily applications, it is usually necessary to coat a film on the LED backlight panel to make the light-emitting surface more uniform. At this time, due to problems such as the material of the film and the power supply refresh frequency, stripes may appear on some film-coated backlight panels, that is, the LED film-coated backlight panel is a non-conforming product. During the production process, it is necessary to select such non-conforming products.

[0003] In the traditional method for detecting the qualification of an LED film-coated backlight panel, it mainly uses manual visual inspection to check whether there are stripes on the LED film-coated backlight panel. Inevitably, there are problems of low accuracy and detection efficiency in the detection of the LED film-coated backlight panel. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method, device, and computer device for detecting the qualification of an LED film-coated backlight panel that can improve the detection accuracy and efficiency of the LED film-coated backlight panel.

[0005] In a first aspect, the present application provides a method for detecting the qualification of an LED film-coated backlight panel. The method includes:

[0006] Obtaining a first pixel value of an LED film-coated backlight panel image; the LED film-coated backlight panel image is an image obtained by collecting an image of the LED film-coated backlight panel;

[0007] Determining a second pixel value of the LED film-coated backlight panel image after mean filtering;

[0008] Determining the difference between the first pixel value and the second pixel value;

[0009] Taking the pixel points that meet the first preset condition in the binarized difference as key pixel points;

[0010] Determining a connected region based on the key pixel points, and counting the number of key pixel points in the contour of the connected region;

[0011] When the number is greater than or equal to a preset number, determining that the LED film-coated backlight panel is a non-conforming product; otherwise, determining that the LED film-coated backlight panel is a qualified product.

[0012] In one embodiment, before obtaining the first pixel value of the LED film-covered backlight panel image, the method further includes:

[0013] Obtaining a brightness map of the LED film-covered backlight panel; or

[0014] Obtaining a color map of the LED film-covered backlight panel, performing grayscale processing on the color map of the LED film-covered backlight panel to obtain a grayscale map of the LED film-covered backlight panel;

[0015] Obtaining a Gaussian filter kernel;

[0016] Performing Gaussian filtering on the brightness map of the LED film-covered backlight panel or the grayscale map of the LED film-covered backlight panel through the Gaussian filter kernel to obtain the LED film-covered backlight panel image.

[0017] In one embodiment, before determining the second pixel value of the LED film-covered backlight panel image after mean filtering, the method further includes:

[0018] Obtaining a mean filter kernel;

[0019] Performing mean filtering on the LED film-covered backlight panel image through the mean filter kernel to obtain the LED film-covered backlight panel image after mean filtering.

[0020] In one embodiment, the method further includes:

[0021] Performing image acquisition on the unqualified LED film-covered backlight panel to obtain an unqualified LED film-covered backlight panel image;

[0022] In response to a stripe selection operation, respectively selecting stripes that meet the second preset condition in each of the unqualified LED film-covered backlight panel images, and determining the stripe pixel regions where the stripes are located;

[0023] Determining the number of pixel rows and the number of pixel columns in each of the stripe pixel regions;

[0024] Determining the minimum number of rows among the pixel rows and the minimum number of columns among the pixel columns;

[0025] Determining the mean filter kernel and the preset quantity based on the minimum number of rows and the minimum number of columns; the mean filter kernel is used to perform mean filtering on the LED film-covered backlight panel image.

[0026] In one embodiment, the binarized difference includes a first difference; before using the pixel points in the binarized difference that meet the first preset condition as key pixel points, the method further includes:

[0027] Determining the minimum difference and the maximum difference in the difference;

[0028] Group the differences based on the preset number of groups, the minimum difference, and the maximum difference to obtain difference groups;

[0029] Use the difference group with the largest number of differences as the target group;

[0030] Determine the average value of the differences corresponding to the differences in the target group;

[0031] Determine a threshold based on the average value of the differences;

[0032] Perform binarization processing on the differences based on the threshold to obtain the first differences;

[0033] The first preset condition is that a pixel point corresponds to the first differences; the step of using the pixel points in the binarized differences that meet the first preset condition as key pixel points includes:

[0034] Determine the first differences in the binarized differences;

[0035] Use the pixel points corresponding to the first differences as key pixel points.

[0036] In one embodiment, after determining that when the quantity is greater than or equal to the preset quantity, the LED film-coated backlight panel is determined to be a non-conforming product; conversely, when the LED film-coated backlight panel is determined to be a conforming product, the method further includes:

[0037] Display the determination result on the product determination page; the determination result includes that the LED film-coated backlight panel is a non-conforming product and that the LED film-coated backlight panel is a conforming product;

[0038] Perform a diversion process on the LED film-coated backlight panel products on the production line according to the determination result.

[0039] In a second aspect, the present application further provides a qualified detection device for an LED film-coated backlight panel. The device includes:

[0040] An acquisition module, configured to acquire the first pixel value of an LED film-coated backlight panel image; the LED film-coated backlight panel image is an image obtained by performing image acquisition on the LED film-coated backlight panel;

[0041] A first determination module, configured to determine the second pixel value of the LED film-coated backlight panel image after mean filtering;

[0042] A second determination module, configured to determine the difference between the first pixel value and the second pixel value;

[0043] A first determination module, configured to use the pixel points in the binarized differences that meet the first preset condition as key pixel points;

[0044] A determination and statistics module, configured to determine a connected region based on the key pixel points and count the number of the key pixel points in the contour of the connected region;

[0045] A second determination module, configured to determine that the LED film-coated backlight panel is a non-conforming product when the number is greater than or equal to a preset number; otherwise, determine that the LED film-coated backlight panel is a conforming product.

[0046] In one embodiment, the device further includes:

[0047] A preprocessing module, configured to obtain a brightness image of the LED film-coated backlight panel; or

[0048] Obtain a color image of the LED film-coated backlight panel, perform gray-scale processing on the color image of the LED film-coated backlight panel to obtain a gray-scale image of the LED film-coated backlight panel;

[0049] Obtain a Gaussian filter kernel;

[0050] Perform Gaussian filtering on the brightness image of the LED film-coated backlight panel or the gray-scale image of the LED film-coated backlight panel through the Gaussian filter kernel to obtain the image of the LED film-coated backlight panel.

[0051] In one embodiment, the first determination module is further configured to obtain a mean filter kernel; perform mean filtering on the image of the LED film-coated backlight panel through the mean filter kernel to obtain a mean-filtered image of the LED film-coated backlight panel.

[0052] In one embodiment, the preprocessing module is further configured to perform image acquisition on a non-conforming LED film-coated backlight panel to obtain a non-conforming LED film-coated backlight panel image; in response to a stripe selection operation, respectively select stripes that meet a second preset condition in each of the non-conforming LED film-coated backlight panel images, and determine stripe pixel regions where the stripes are located; determine the number of pixel rows and the number of pixel columns in each of the stripe pixel regions; determine the minimum number of pixel rows and the minimum number of pixel columns in each of the pixel rows; determine a mean filter kernel and the preset number based on the minimum number of pixel rows and the minimum number of pixel columns; the mean filter kernel is used to perform mean filtering on the image of the LED film-coated backlight panel.

[0053] In one embodiment, the second determination module is further configured to determine the minimum difference and the maximum difference among the differences; group the differences based on a preset number of groups, the minimum difference, and the maximum difference to obtain difference groups; take the difference group with the largest number of differences as the target group; determine the average value of the differences corresponding to the target group; determine a threshold based on the average value of the differences; perform binarization processing on the differences based on the threshold to obtain the first difference;

[0054] The first preset condition is that the pixel point corresponds to the first difference; the first determination module is further configured to determine the first difference among the binarized differences; and take the pixel point corresponding to the first difference as the key pixel point.

[0055] In one embodiment, the device further includes:

[0056] A display and shunt module, configured to display a determination result on a product determination page; the determination result includes that the LED film-covered backlight panel is a non-conforming product and that the LED film-covered backlight panel is a conforming product; and perform shunt processing on the LED film-covered backlight panel products on the production line according to the determination result.

[0057] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the steps of the above method are implemented.

[0058] In a fourth aspect, the present application further provides a computer-readable storage medium. On the computer-readable storage medium, a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0059] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0060] The above-mentioned qualified detection method, device and computer equipment for the LED film-coated backlight panel obtain the first pixel value of the LED film-coated backlight panel image; the LED film-coated backlight panel image is an image obtained by image acquisition of the LED film-coated backlight panel; determine the second pixel value of the LED film-coated backlight panel image after mean filtering; determine the difference between the first pixel value and the second pixel value; use the pixel points that meet the first preset condition in the binarized difference as key pixel points; determine the connected regions based on the key pixel points, and count the number of key pixel points in the contours of the connected regions; when the number is greater than or equal to the preset number, determine that the LED film-coated backlight panel is a non-conforming product; otherwise, determine that the LED film-coated backlight panel is a qualified product. This improves the detection accuracy and efficiency of whether the LED film-coated backlight panel is qualified. Description of the Drawings

[0061] Figure 1 It is an application environment diagram of the qualified detection method for the LED film-coated backlight panel in an embodiment;

[0062] Figure 2 It is a flowchart of the qualified detection method for the LED film-coated backlight panel in an embodiment;

[0063] Figure 3 It is a flowchart of the steps for determining the mean filter kernel and the preset number in an embodiment;

[0064] Figure 4 It is a structural block diagram of the qualified detection device for the LED film-coated backlight panel in an embodiment;

[0065] Figure 5 It is a structural block diagram of the qualified detection device for the LED film-coated backlight panel in another embodiment;

[0066] Figure 6 It is an internal structure diagram of a computer device in an embodiment. Detailed Description of the Embodiments

[0067] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] The qualified detection method for the LED film-coated backlight panel provided in the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers.

[0069] The terminal 102 obtains the first pixel value of the LED film-coated backlight panel image; the LED film-coated backlight panel image is an image obtained by image acquisition of the LED film-coated backlight panel; the terminal 102 determines the second pixel value of the LED film-coated backlight panel image after mean filtering; the terminal 102 determines the difference between the first pixel value and the second pixel value; the terminal 102 uses the pixel points that meet the first preset condition in the binarized difference as key pixel points; the terminal 102 determines the connected regions based on the key pixel points and counts the number of key pixel points in the contours of the connected regions; when the number is greater than or equal to the preset number, the terminal 102 determines that the LED film-coated backlight panel is a non-conforming product; otherwise, the terminal 102 determines that the LED film-coated backlight panel is a conforming product.

[0070] Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0071] In one embodiment, as Figure 2 shown, a method for detecting the conformity of an LED film-coated backlight panel is provided. Taking the method applied to the Figure 1 terminal 102 as an example, the method includes the following steps:

[0072] S202, obtaining the first pixel value of the LED film-coated backlight panel image; the LED film-coated backlight panel image is an image obtained by image acquisition of the LED film-coated backlight panel.

[0073] Among them, the LED film-coated backlight panel image can refer to the relevant image of the LED film-coated backlight panel after Gaussian filtering. The LED film-coated backlight panel can refer to the LED backlight panel after film coating. The first pixel value can refer to the pixel value of the pixel points in the LED film-coated backlight panel image, and the first pixel value and the second pixel value are different pixel values.

[0074] Specifically, the terminal can obtain the first pixel value of the LED film-coated backlight panel image stored in the terminal in response to the conformity detection instruction of the LED film-coated backlight panel; the terminal can also obtain the first pixel value of the LED film-coated backlight panel image uploaded by the user in response to the conformity detection instruction of the LED film-coated backlight panel.

[0075] In one embodiment, before S202, obtain the brightness map of the LED laminated backlight panel; or obtain the color map of the LED laminated backlight panel, perform grayscale processing on the color map of the LED laminated backlight panel to obtain the grayscale map of the LED laminated backlight panel; obtain the Gaussian filter kernel; perform Gaussian filtering on the brightness map of the LED laminated backlight panel or the grayscale map of the LED laminated backlight panel through the Gaussian filter kernel to obtain the image of the LED laminated backlight panel.

[0076] Among them, the brightness map of the LED laminated backlight panel may refer to the image of the LED laminated backlight panel collected by a CCD (charge coupled device) surface brightness meter. The color map of the LED laminated backlight panel may refer to the image of the LED laminated backlight panel collected by a CCD color surface camera. The grayscale map of the LED laminated backlight panel may refer to the image obtained after performing grayscale processing on the color map of the LED laminated backlight panel. The Gaussian filter kernel may refer to the filter kernel in Gaussian filtering.

[0077] S204, determine the second pixel value of the LED laminated backlight panel image after mean filtering.

[0078] Among them, the second pixel value may refer to the pixel value of a pixel point in the LED laminated backlight panel image after mean filtering.

[0079] Specifically, the terminal may first obtain the LED laminated backlight panel image after mean filtering, and then sequentially determine the pixel values of each pixel point in the LED laminated backlight panel image after mean filtering until the pixel values of all pixel points are determined.

[0080] In one embodiment, before S204, the terminal obtains the mean filter kernel; performs mean filtering on the LED laminated backlight panel image through the mean filter kernel to obtain the LED laminated backlight panel image after mean filtering.

[0081] Among them, the mean filter kernel may refer to the filter kernel in mean filtering.

[0082] S206, determine the difference between the first pixel value and the second pixel value.

[0083] Among them, the difference may refer to the difference between pixel values.

[0084] Specifically, the terminal may subtract the first pixel value from the second pixel value to obtain the difference between the first pixel value and the second pixel value. The terminal may also call the difference function and substitute the first pixel value and the second pixel value into the difference function to obtain the difference between the first pixel value and the second pixel value. Among them, the difference function may be: second pixel value - first pixel value = difference.

[0085] In one embodiment, after S206, when the difference is less than the first preset value, the difference is assigned the first preset value. Herein, the first preset value may refer to a pre-set value, and the first preset value and the second preset value are different values. The first preset value may be 0.

[0086] S208, use the pixel points in the binarized difference that meet the first preset condition as key pixel points.

[0087] Herein, the binarized difference includes a first difference and a second difference. For example, the first difference may be 1 and the second difference may be 0. The first preset condition may be a condition for screening pixel points. For example, the first preset condition may be that the pixel point corresponds to the first difference, or the first preset condition may be that the pixel point corresponds to the second difference. The key pixel points may refer to the pixel points used to form a connected region. The connected region may refer to the region in the LED film backlight panel image that contains stripes or not.

[0088] Specifically, the terminal may first obtain the first preset condition, and then screen the binarized difference through the first preset condition, and use the pixel points corresponding to the first difference or the second difference selected as the key pixel points.

[0089] In one embodiment, screening the binarized difference through the first preset condition and using the pixel points corresponding to the first difference or the second difference selected as the key pixel points includes: when the first preset condition is that the pixel point corresponds to the first difference, screening out the first difference in the binarized difference, and determining the pixel points corresponding to the first difference, and using the pixel points corresponding to the first difference as the key pixel points; when the first preset condition is that the pixel point corresponds to the second difference, screening out the second difference in the binarized difference, and determining the pixel points corresponding to the second difference, and using the pixel points corresponding to the second difference as the key pixel points.

[0090] In one embodiment, before S208, the terminal may determine the minimum difference and the maximum difference in the difference; group the difference based on the preset number of groups, the minimum difference and the maximum difference to obtain a difference grouping; use the difference grouping with the largest number of differences as the target grouping; determine the difference average value corresponding to the differences in the target grouping; determine a threshold based on the difference average value; perform binarization processing on the difference based on the threshold to obtain the first difference.

[0091] Among them, the minimum difference can refer to the minimum value among the differences. The maximum difference can refer to the maximum value among the differences. The preset number of groups can refer to the pre-set number of groups. For example, the preset number of groups can be 10. The difference grouping can refer to the grouping of differences. For example, the difference grouping can be Group 1, Group 2, … Group n. The target grouping can refer to the grouping used to determine the threshold. The difference average value can refer to the average value of the sum of all differences in the difference grouping. The threshold can be used to binarize the differences. For example, the threshold can be a% of the difference average value corresponding to the target grouping, and a can be 60, 70, 80, etc.

[0092] In one embodiment, the first preset condition is that the pixel point corresponds to the first difference, and the terminal determines the first difference among the binarized differences; and takes the pixel point corresponding to the first difference as the key pixel point.

[0093] In one embodiment, the differences are grouped based on the preset number of groups, the minimum difference, and the maximum difference to obtain the difference grouping, including determining the group interval based on the preset number of groups, the minimum difference, and the maximum difference, and grouping the differences based on the group interval to obtain the difference grouping.

[0094] Among them, the group interval can refer to the interval between adjacent difference groupings, and the calculation formula of the group interval can be:

[0095]

[0096] For example, the differences are 1, 3, 5, 6, and 7, and the preset number of groups is 3. It can be observed that the minimum difference among the differences is 1, and the maximum difference is 7. Substituting into the group interval formula, then 1 and 3 falling into the interval [1, 3.3) can be used as the first group, 5 falling into the interval [3.3, 5.6) can be used as the second group, and 6 and 7 falling into the interval [5.6, 7.9) can be used as the third group, where “[” is a closed interval and “)” is an open interval.

[0097] In one embodiment, the differences are binarized based on the threshold to obtain the first difference, including binarizing the differences greater than the threshold among the differences to obtain the first difference; and binarizing the differences other than the differences greater than the threshold to obtain the second difference.

[0098] In one embodiment, binarizing the differences other than the differences greater than the threshold to obtain the second difference includes binarizing the differences less than or equal to the threshold among the differences to obtain the second difference.

[0099] S210, determine the connected region based on the key pixel points, and count the number of key pixel points in the contour of the connected region.

[0100] Specifically, the terminal can determine the pixel positions of each key pixel point in the LED film-coated backlight panel image, determine the contours of each connected region formed by all the pixel positions in the LED film-coated backlight panel image, and then sequentially count the number of key pixel points contained within the contours of each connected region. It should be noted that the key pixel points can form 1 to multiple connected regions in the LED film-coated backlight panel image. When there is 1 connected region, the number of key pixel points in the contour of the connected region is the number of key pixel points.

[0101] Among them, the pixel position can refer to the position of the pixel point in the corresponding image.

[0102] S212. When the quantity is greater than or equal to the preset quantity, it is determined that the LED film-coated backlight panel is a non-conforming product; otherwise, it is determined that the LED film-coated backlight panel is a conforming product.

[0103] Among them, the preset quantity can refer to the quantity set in advance.

[0104] Specifically, the terminal can first obtain the preset quantity, and judge the magnitude relationship between the number of key pixel points in the contour of the connected region and the preset quantity. When the number of key pixel points in the contour of the connected region is greater than the preset quantity, then this connected region contains stripes, and thus it is determined that the LED film-coated backlight panel is a non-conforming product; when the number of key pixel points in the contour of the connected region is less than or equal to the preset quantity, then this connected region does not contain stripes, and thus it is determined that the LED film-coated backlight panel is a conforming product.

[0105] In one embodiment, when there is 1 connected region in the LED film-coated backlight panel image, when the number of key pixel points in the contour of the connected region is greater than the preset quantity, then this connected region contains stripes, and thus it is determined that the LED film-coated backlight panel is a non-conforming product; when the number of key pixel points in the contour of the connected region is less than or equal to the preset quantity, then this connected region does not contain stripes, and thus it is determined that the LED film-coated backlight panel is a conforming product.

[0106] In one embodiment, when there are multiple connected regions in the LED film-coated backlight panel image, when the number of key pixel points in the contour of at least 1 connected region is greater than the preset quantity, then this connected region contains stripes, and thus it is determined that the LED film-coated backlight panel is a non-conforming product; when the number of key pixel points in the contours of each connected region is less than or equal to the preset quantity, then each connected region does not contain stripes, and thus it is determined that the LED film-coated backlight panel is a conforming product.

[0107] In one embodiment, after S212, the terminal displays the determination result on the product determination page; the determination result includes that the LED film-coated backlight panel is a non-conforming product and the LED film-coated backlight panel is a conforming product; and the LED film-coated backlight panel products on the production line are sorted according to the determination result.

[0108] Among them, the determination result can refer to the determination result of whether the LED film-covered backlight panel is a qualified product. The production line can refer to the production line of products related to the LED film-covered backlight panel. The LED film-covered backlight panel product can refer to the products related to the LED film-covered backlight panel.

[0109] In the above LED film-covered backlight panel method, the first pixel value of the LED film-covered backlight panel image is obtained; the LED film-covered backlight panel image is an image obtained by image acquisition of the LED film-covered backlight panel; the second pixel value of the LED film-covered backlight panel image after mean filtering is determined; the difference between the first pixel value and the second pixel value is determined; the pixel points satisfying the first preset condition in the binarized difference are used as key pixel points; the connected regions are determined based on the key pixel points, and the number of key pixel points in the contours of the connected regions is counted; when the number is greater than or equal to the preset number, it is determined that the LED film-covered backlight panel is an unqualified product; otherwise, it is determined that the LED film-covered backlight panel is a qualified product. The detection accuracy and detection efficiency of whether the LED film-covered backlight panel is qualified are improved.

[0110] In one embodiment, as Figure 3 shown, the steps of determining the mean filtering kernel and the preset number include:

[0111] S302, image acquisition is performed on the unqualified LED film-covered backlight panel to obtain an unqualified LED film-covered backlight panel image.

[0112] Among them, the unqualified LED film-covered backlight panel image can refer to the image of the LED film-covered backlight panel being an unqualified product.

[0113] Specifically, brightness image acquisition or color image acquisition is performed on the unqualified LED film-covered backlight panel to obtain an unqualified LED film-covered backlight panel image. Among them, brightness image acquisition can refer to acquisition through a brightness map acquisition device, and the brightness map acquisition device can be a CCD surface brightness meter. Color image acquisition can refer to acquisition through a color map acquisition device, and the color map acquisition device can be a CCD color surface camera.

[0114] S304, in response to the stripe selection operation, stripes satisfying the second preset condition are respectively selected in each unqualified LED film-covered backlight panel image, and the stripe pixel regions where the stripes are located are determined.

[0115] Among them, the stripe can refer to the stripe generated after laminating the LED backlight panel. The second preset condition can refer to the condition for screening the stripe. For example, the second preset condition can refer to the smallest stripe that can be detected by the normal human eye. The stripe pixel region can refer to the region formed by the stripe in the unqualified LED film-covered backlight panel image.

[0116] Specifically, in response to the stripe selection operation, the minimum stripe in each unqualified LED film-covered backlight panel image is sequentially selected according to the second preset condition. After the minimum stripe in each unqualified LED film-covered backlight panel image is selected, the stripe pixel region where each minimum stripe is located in each unqualified LED film-covered backlight panel image is sequentially determined.

[0117] S306. Determine the number of pixel rows and the number of pixel columns in each stripe pixel region.

[0118] Among them, the number of pixel rows may refer to the number of rows of pixel points. The number of pixel columns may refer to the number of columns of pixel points.

[0119] Specifically, the terminal sequentially determines the pixel points in each stripe pixel region, and then statistically determines the number of pixel rows and the number of pixel columns corresponding to each stripe pixel region based on the pixel points in each stripe pixel region.

[0120] S308. Determine the minimum number of pixel rows among all the pixel rows and the minimum number of pixel columns among all the pixel columns.

[0121] Among them, the minimum number of pixel rows may refer to the minimum value among the pixel rows. The minimum number of pixel columns may refer to the minimum value among the pixel columns.

[0122] Specifically, the terminal can sequentially judge the magnitudes of each pixel row, and thus select the minimum number of pixel rows among all the pixel rows; sequentially judge the magnitudes of each pixel column, and thus select the minimum number of pixel columns among all the pixel columns.

[0123] S310. Determine the mean filter kernel and the preset quantity based on the minimum number of pixel rows and the minimum number of pixel columns; the mean filter kernel is used to perform mean filtering processing on the LED film-covered backlight panel image.

[0124] Specifically, the terminal can determine the mean filter kernel and the preset quantity based on the minimum number of pixel rows, the minimum number of pixel columns, and the second preset value. Among them, the mean filter kernel can be (the minimum number of pixel rows + the second preset value, the minimum number of pixel columns + the second preset value), and the preset quantity can be: (the minimum number of pixel rows + the second preset value) * (the minimum number of pixel columns + the second preset value). Among them, the second preset value may refer to a value preset according to actual requirements.

[0125] In this embodiment, by performing image acquisition on the unqualified LED film-covered backlight panel, an unqualified LED film-covered backlight panel image is obtained; in response to the stripe selection operation, stripes that meet the second preset condition are respectively selected in each unqualified LED film-covered backlight panel image, and the stripe pixel region where each stripe is located is determined; the number of pixel rows and the number of pixel columns in each stripe pixel region are determined; the minimum number of pixel rows among all the pixel rows and the minimum number of pixel columns among all the pixel columns are determined; the mean filter kernel and the preset quantity are determined based on the minimum number of pixel rows and the minimum number of pixel columns; the mean filter kernel is used to perform mean filtering processing on the LED film-covered backlight panel image. It is possible to accurately determine the mean filter kernel and the preset quantity.

[0126] As an example, this embodiment is as follows:

[0127] The qualified detection algorithm of the LED film-coated backlight board of this application includes: an image data acquisition module, an image data preprocessing module, an image data analysis module, and an image data result feedback module.

[0128] I. Image data acquisition module

[0129] The image data acquisition module uses a CCD surface testing instrument to collect the image data of the film-coated backlight board. The CCD surface testing instrument includes but is not limited to a CCD surface luminance meter and a CCD surface camera (color / black and white). The acquisition module is responsible for transmitting the collected product information to the data processing module through an image acquisition card.

[0130] The working steps of the image data acquisition module are as follows:

[0131] Step 1: The Mini LED backlight board lighting device lights the film-coated Mini LED backlight board;

[0132] Step 2: The CCD acquisition instrument collects the film-coated Mini LED data;

[0133] Step 3: The CCD acquisition instrument transmits the collected data information to the data processing module through a data acquisition card.

[0134] Among them, the data receiving device includes but is not limited to an electronic computer.

[0135] II. Image data processing module

[0136] The image processing module receives the image information collected by the image acquisition module and needs to process the image information. The data collected by the image data acquisition module contains noise and also contains non-product areas. We need to perform noise reduction processing on the image and at the same time extract the product area, which can improve the detection accuracy and speed. The image information collected by the CCD surface luminance meter and the CCD black and white surface camera is all in one channel and can be directly filtered. The image information collected by the CCD color surface camera is in three channels, so the three-channel color information needs to be converted into one-channel grayscale information first. The conversion of a color image to a grayscale image can call the grayscale image operator in image processing software such as OpenCV and Halcon, or use the formula Gray = R * 0.299 + G * 0.587 + B * 0.114 for conversion, and then perform filtering processing after conversion.

[0137] The image processing module first uses Gaussian filtering to remove noise, and then performs mean filtering on the image after Gaussian filtering. There are written operators for Gaussian filtering and mean filtering, which can be directly called in OpenCV and Halcon. Both Gaussian filtering and mean filtering require setting the filter kernel size. Different settings of the filter kernel size may result in different calculation results. We can set the size of the Gaussian filter kernel to 9 according to the empirical value to obtain the picture Pg. The size of the mean filter kernel needs to be analyzed and determined according to the characteristics of the product;

[0138] The specific method is as follows:

[0139] Find 50 NG products. These NG products should meet the condition that the stripes on the products can just be detected by the human eye. Note: The severity of the striped products will be graded on the production line. Here, it just corresponds to the slightly graded striped products that can be detected. After the CCD is fixed at a certain height, take pictures of the 50 NG products, and use the manual selection software to select the smallest stripe marked on the production line for each NG (No Good, unqualified) product. The manual selection software can identify the position of the mouse, and calculate the number of pixel rows and columns of the selected area according to the change of the mouse position. Count the number of pixel rows N and columns M of the selected stripes, and then separately select the minimum value N of the number of rows min and the minimum value M of the number of columns min . Then set (N min + 5, M min + 5) as the filter kernel of the mean filter, where the value 5 can be adjusted according to the actual situation. Finally, use this filter kernel to perform mean filtering on the picture that has been subjected to Gaussian filtering to obtain the picture Pgm.

[0140] III. Image data analysis module

[0141] The image data analysis module analyzes the data in the image data processing module and sends the processing results to the image data result feedback module.

[0142] The first step: Subtract the pixel values of the corresponding pixel points of the picture Pgm that has been subjected to Gaussian filtering and then mean filtering and the picture Pg that has only been subjected to Gaussian filtering; Since the stripes are dark stripes, after subtraction, the pixel values (differences) corresponding to the stripes are greater than the pixel values of the surrounding areas without stripes. At the same time, if there are numbers less than 0 in the differences, set the pixel value at this point to 0.

[0143] Step 2: After subtracting the pixels corresponding to the first-step images, the pixel values in the area without stripes are close to 0, while in the area with stripes, there are corresponding pixel values according to the brightness and darkness of the stripes. At this time, perform a histogram statistics on the pixel values of the image after subtraction. Method: Find the maximum and minimum pixel values, divide them into 10 groups, with the group interval being (maximum pixel value - minimum pixel value + 1) / 10. Find the group with the largest number of data, calculate the average of this group of data, and obtain the average value K M , and set 80% of this average value K M as the threshold. Binarize the image after subtraction according to this threshold. Points greater than the threshold are set to 255, and points less than the threshold are set to 0.

[0144] Step 3: Find the contour of the connected area where the pixel value is 255, and output the number of pixels with the value 255 contained inside the contour. There are corresponding operators in Halcon, OpenCV, etc. that can be directly called.

[0145] Let the product of (N min + 5) * (M min + 5) be the threshold for the number of pixels contained in the contour, that is, if the number of pixels with the value 255 contained in the connected area is greater than or equal to (N min + 5) * (M min + 5), it is judged as a stripe, and the product is NG; otherwise, the product is OK.

[0146] Since N min and M min are the minimum length and minimum width among the 50 stripes that can be recognized by the human eye, and their combination may not necessarily be recognizable by the human eye. Therefore, we need to verify the 50 NG products that can just be detected by the human eye. If the false positive rate is greater than 15% and the missed detection rate is greater than 1% (the false positive rate and missed detection rate need to be adjusted according to the production specifications of the manufacturer), then it is necessary to adjust the filter kernel of the threshold mean filter and the corresponding percentage of the threshold K M corresponding percentage.

[0147] IV. Image Data Result Feedback Module

[0148] After the image data analysis module finishes the analysis, it will feedback the result to the image data result feedback template. The image data feedback module will display the product status OK (qualified) or NG on the client software, and communicate with the sorting station on the production line to separate the OK products and NG products.

[0149] It should be understood that although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0150] Based on the same inventive concept, an embodiment of the present application also provides a qualified detection device for an LED film-coated backlight panel for implementing the qualified detection method of the LED film-coated backlight panel involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the qualified detection device for the LED film-coated backlight panel provided below can refer to the limitations on the qualified detection method of the LED film-coated backlight panel in the above text, and will not be repeated here.

[0151] In one embodiment, as Figure 4 shown, a qualified detection device for an LED film-coated backlight panel is provided, including: an acquisition module 402, a first determination module 404, a second determination module 406, a first determination module 408, a determination and statistics module 410, and a second determination module 412, where:

[0152] The acquisition module 402 is used to acquire the first pixel value of the LED film-coated backlight panel image; the LED film-coated backlight panel image is an image obtained by image acquisition of the LED film-coated backlight panel;

[0153] The first determination module 404 is used to determine the second pixel value of the LED film-coated backlight panel image after mean filtering;

[0154] The second determination module 406 is used to determine the difference between the first pixel value and the second pixel value;

[0155] The first determination module 408 is used to use the pixel points that meet the first preset condition in the binarized difference as key pixel points;

[0156] The determination and statistics module 410 is used to determine the connected region based on the key pixel points and count the number of key pixel points in the contour of the connected region;

[0157] The second determination module 412 is configured to determine that the LED film-coated backlight panel is a non-conforming product when the quantity is greater than or equal to a preset quantity; otherwise, determine that the LED film-coated backlight panel is a conforming product.

[0158] In one embodiment, the first determination module 404 is further configured to obtain a mean filter kernel; perform mean filtering on the LED film-coated backlight panel image through the mean filter kernel to obtain a mean-filtered LED film-coated backlight panel image.

[0159] In one embodiment, the second determination module 406 is further configured to determine the minimum difference and the maximum difference among the differences; group the differences based on a preset number of groups, the minimum difference, and the maximum difference to obtain difference groups; take the difference group with the largest number of differences as the target group; determine the difference average value corresponding to the differences in the target group; determine a threshold based on the difference average value; perform binarization processing on the differences based on the threshold to obtain first differences; the first preset condition is that a pixel point corresponds to a first difference; the first determination module 408 is further configured to determine the first differences among the binarized differences; and take the pixel points corresponding to the first differences as key pixel points.

[0160] In one embodiment, as Figure 5 shown, the qualified detection device for the LED film-coated backlight panel includes: a preprocessing module 414 and a display and shunting module 416, where:

[0161] In one embodiment, the device further includes:

[0162] The preprocessing module 414 is configured to obtain the brightness map of the LED film-coated backlight panel; or obtain the color map of the LED film-coated backlight panel, perform grayscale processing on the color map of the LED film-coated backlight panel to obtain the grayscale map of the LED film-coated backlight panel; obtain a Gaussian filter kernel; perform Gaussian filtering on the brightness map of the LED film-coated backlight panel or the grayscale map of the LED film-coated backlight panel through the Gaussian filter kernel to obtain the LED film-coated backlight panel image.

[0163] The display and shunting module 416 is configured to display the determination result on a product determination page; the determination result includes that the LED film-coated backlight panel is a non-conforming product and that the LED film-coated backlight panel is a conforming product; and perform shunting processing on the LED film-coated backlight panel products on the production line according to the determination result.

[0164] In one embodiment, the preprocessing module 414 is further configured to perform image acquisition on the unqualified LED laminated backlight panel to obtain an image of the unqualified LED laminated backlight panel; in response to a stripe selection operation, select stripes that meet the second preset condition from each image of the unqualified LED laminated backlight panel, and determine the stripe pixel regions where the stripes are located; determine the number of pixel rows and the number of pixel columns in each stripe pixel region; determine the minimum number of pixel rows and the minimum number of pixel columns among the pixel rows; determine a mean filter kernel and a preset number based on the minimum number of pixel rows and the minimum number of pixel columns; the mean filter kernel is used to perform mean filtering on the LED laminated backlight panel image.

[0165] In the above embodiment, by obtaining the first pixel value of the LED laminated backlight panel image; the LED laminated backlight panel image is an image obtained by performing image acquisition on the LED laminated backlight panel; determining the second pixel value of the LED laminated backlight panel image after mean filtering; determining the difference between the first pixel value and the second pixel value; taking the pixel points that meet the first preset condition in the binarized difference as key pixel points; determining a connected region based on the key pixel points, and counting the number of key pixel points in the contour of the connected region; when the number is greater than or equal to the preset number, determining that the LED laminated backlight panel is a non-conforming product; otherwise, determining that the LED laminated backlight panel is a conforming product. The detection accuracy and detection efficiency of whether the LED laminated backlight panel is qualified are improved.

[0166] Each module in the above-mentioned qualified detection device for the LED laminated backlight panel can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor in the computer device in hardware form or be independent of the processor, or can be stored in the memory in the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0167] In one embodiment, a computer device is provided. The computer device can be a terminal or a server. Taking the computer device as a terminal as an example for illustration, its internal structure diagram can be as Figure 6As shown in the figure. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for detecting the qualification of an LED film backlight panel. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0168] Those skilled in the art can understand that Figure 6 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0169] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the above-mentioned embodiments are implemented.

[0170] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned embodiments are implemented.

[0171] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned embodiments are implemented.

[0172] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions.

[0173] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0174] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0175] The above embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A qualified detection method for an LED film-coated backlight panel, characterized in that, The method includes: Obtaining a first pixel value of an LED film-coated backlight panel image; the LED film-coated backlight panel image is an image obtained by image acquisition of an LED film-coated backlight panel; Determining a second pixel value of the LED film-coated backlight panel image after mean filtering; Determining the difference between the first pixel value and the second pixel value; Regarding the pixel points in the binarized difference that meet a first preset condition as key pixel points; Determining a connected region based on the key pixel points, and counting the number of key pixel points in the contour of the connected region; When the number is greater than or equal to a preset number, determining that the LED film-coated backlight panel is a non-conforming product; otherwise, determining that the LED film-coated backlight panel is a conforming product.

2. The method according to claim 1, characterized in that, Before obtaining the first pixel value of the LED film-coated backlight panel image, the method further includes: Obtaining an LED film-coated backlight panel brightness map; or Obtaining an LED film-coated backlight panel color map, performing grayscale processing on the LED film-coated backlight panel color map to obtain an LED film-coated backlight panel grayscale map; Obtaining a Gaussian filter kernel; Performing Gaussian filtering on the LED film-coated backlight panel brightness map or the LED film-coated backlight panel grayscale map through the Gaussian filter kernel to obtain the LED film-coated backlight panel image.

3. The method according to claim 1, wherein Before determining the second pixel value of the LED film-coated backlight panel image after mean filtering, the method further includes: Obtaining a mean filter kernel; Performing mean filtering on the LED film-coated backlight panel image through the mean filter kernel to obtain the LED film-coated backlight panel image after mean filtering.

4. The method according to claim 1, wherein The method further includes: Performing image acquisition on a non-conforming LED film-coated backlight panel to obtain a non-conforming LED film-coated backlight panel image; In response to a stripe selection operation, respectively selecting stripes that meet a second preset condition in each of the non-conforming LED film-coated backlight panel images, and determining the stripe pixel regions where the stripes are located; Determining the number of pixel rows and the number of pixel columns in each of the stripe pixel regions; Determining the minimum number of pixel rows among the pixel rows and the minimum number of pixel columns among the pixel columns; Determining a mean filter kernel and the preset number based on the minimum number of pixel rows and the minimum number of pixel columns; the mean filter kernel is used for performing mean filtering on the LED film-coated backlight panel image.

5. The method according to claim 1, wherein The binarized difference includes a first difference; before regarding the pixel points in the binarized difference that meet a first preset condition as key pixel points, the method further includes: Determining the minimum difference and the maximum difference in the difference; Grouping the difference based on a preset number of groups, the minimum difference, and the maximum difference to obtain a difference grouping; Regarding the difference grouping with the largest number of differences as the target grouping; Determining the difference average value corresponding to the differences in the target grouping; Determining a threshold based on the difference average value; Performing binarization processing on the difference based on the threshold to obtain the first difference; The first preset condition is that the pixel point corresponds to the first difference; regarding the pixel points in the binarized difference that meet the first preset condition as key pixel points includes: Determining the first difference in the binarized difference; Use the pixel points corresponding to the first difference as key pixel points.

6. The method according to claim 1, wherein When the quantity is greater than or equal to a preset quantity, determine that the LED film-coated backlight panel is a non-conforming product; On the contrary, after determining that the LED film-coated backlight panel is a qualified product, the method further includes: Display the determination result on the product determination page; the determination result includes that the LED film-coated backlight panel is a non-conforming product and that the LED film-coated backlight panel is a qualified product; Perform a diversion process on the LED film-coated backlight panel products on the production line according to the determination result.

7. A qualified detection device for an LED film-coated backlight panel, characterized in that, The device includes: An acquisition module, configured to acquire the first pixel value of the LED film-coated backlight panel image; the LED film-coated backlight panel image is an image obtained by performing image acquisition on the LED film-coated backlight panel; A first determination module, configured to determine the second pixel value of the LED film-coated backlight panel image after mean filtering; A second determination module, configured to determine the difference between the first pixel value and the second pixel value; A first determination module, configured to use the pixel points in the binarized difference that meet the first preset condition as key pixel points; A determination and statistics module, configured to determine a connected region based on the key pixel points and count the number of key pixel points in the contour of the connected region; A second determination module, configured to determine that the LED film-coated backlight panel is a non-conforming product when the quantity is greater than or equal to a preset quantity; on the contrary, determine that the LED film-coated backlight panel is a qualified product.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images