LED backlight panel lamp bead detection method, device and computer equipment

Abstract

The application relates to a lamp bead detection method and device of an LED backlight plate and a computer device. The method comprises the following steps: acquiring a pixel value of an LED lamp bead in the LED backlight plate in an LED backlight plate diagram; searching for a first threshold value and a corresponding first reentrant area and a second threshold value and a corresponding second reentrant area in a lookup table; determining a first average pixel value of the first reentrant area where the LED lamp bead is located and a second average pixel value of the second reentrant area where the LED lamp bead is located; when the pixel value is greater than the first average pixel value, determining a first ratio between the pixel value and the first average pixel value, and when the pixel value is less than the second average pixel value, determining a second ratio between the pixel value and the second average pixel value; when the first ratio is less than the first threshold value or the second ratio is greater than the second threshold value, determining that the LED backlight plate is a qualified product. The method can improve the efficiency of lamp bead detection of the LED backlight plate.

Description

Technical Field

[0001] This application relates to the field of optical measurement technology, and in particular to a method, apparatus and computer equipment for detecting LED beads in an LED backlight panel. Background Technology

[0002] With the development of optics, LED (Light Emitting Diode) technology emerged. MiniLED refers to LED chips with a size on the order of 100μm, and is an upgrade to traditional LCD (Liquid Crystal Display) screens. The LEDs on a Mini LED backlight board are made extremely small, allowing for the integration of more backlight chips on the same screen, thus dividing it into more fine backlight zones. Before leaving the factory, Mini LED backlight boards need to be tested for brightness uniformity, requiring the brightness of each LED chip to be measured to determine whether the LED backlight board is qualified. Traditionally, the qualification test for Mini LED backlight boards mainly relies on manual visual inspection. Since there are tens of thousands of LED chips on a single backlight board, the efficiency of testing the LED chips on the LED backlight board is low. Summary of the Invention

[0003] Therefore, it is necessary to provide an LED backlight chip detection method, apparatus, and computer equipment that can improve the chip detection efficiency of LED backlight boards in response to the above-mentioned technical problems.

[0004] Firstly, this application provides a method for detecting LED beads in an LED backlight panel. The method includes:

[0005] In the LED backlight panel diagram, obtain the pixel values ​​of the LED beads in the LED backlight panel;

[0006] Based on the pixel level of the LED backlight panel, the first threshold and the corresponding first loop area, as well as the second threshold and the corresponding second loop area, are searched in the lookup table.

[0007] In the LED backlight panel diagram, a first average pixel value of the first loop-shaped area where the LED beads are located and a second average pixel value of the second loop-shaped area where the LED beads are located are determined.

[0008] When the pixel value is greater than the first average pixel value, a first ratio between the pixel value and the first average pixel value is determined; and when the pixel value is less than the second average pixel value, a second ratio between the pixel value and the second average pixel value is determined.

[0009] When the first ratio is less than the first threshold, or the second ratio is greater than the second threshold, the LED backlight panel is determined to be a qualified product.

[0010] In one embodiment, before obtaining the pixel values ​​of the LED beads in the LED backlight panel, the method further includes:

[0011] A color image is obtained, and the color image is processed into grayscale to obtain the LED backlight panel image;

[0012] The LED backlight panel image is binarized to obtain a binarized image;

[0013] Based on the binarized image, extract the LED bead outlines from the LED backlight panel image;

[0014] The step of obtaining the pixel values ​​of the LED beads in the LED backlight panel includes:

[0015] Based on the outline of the LED beads, the pixel values ​​of the LED beads in the LED backlight panel are obtained from the LED backlight panel diagram.

[0016] In one embodiment, before obtaining the pixel values ​​of the LED beads in the LED backlight panel, the method further includes:

[0017] Obtain a brightness diagram and use the brightness diagram as the LED backlight panel diagram;

[0018] Extract the LED bead outline from the LED backlight panel image;

[0019] The process of obtaining the pixel values ​​of the LED beads in the LED backlight panel includes:

[0020] Based on the outline of the LED beads, the pixel values ​​of the LED beads in the LED backlight panel are obtained from the LED backlight panel diagram.

[0021] In one embodiment, obtaining the pixel values ​​of the LED beads in the LED backlight panel from the LED backlight panel diagram based on the LED bead outline includes:

[0022] In the LED backlight panel diagram, the value of each pixel located within the outline of the LED bead is determined;

[0023] The values ​​of each pixel within the outline of the LED bead are sorted to obtain a value sequence;

[0024] The difference between each adjacent value in the value sequence is calculated to obtain the difference sequence.

[0025] Based on the extreme points in the difference sequence, determine the maximum value in the value sequence;

[0026] Summing the maximum value and the values ​​in the value sequence preceding the maximum value yields a sum.

[0027] The sum is averaged to obtain the pixel value of the LED bead.

[0028] In one embodiment, before searching for the first threshold and the corresponding first loop region in the lookup table, the method further includes:

[0029] Based on the pixel level, images of the defective LED backlight panels are acquired to obtain an image of the target LED backlight panel;

[0030] Multiple loop-shaped areas are determined with the defective LED beads in the target LED backlight board diagram as the center;

[0031] Determine the average pixel value corresponding to each of the multiple loop-shaped regions to obtain multiple average pixel values;

[0032] When the pixel value of the defective LED bead is greater than at least one of the pixel average values, the defective LED bead is determined to be an overbright bead, and the minimum ratio between the pixel value of the overbright bead and the pixel average value is selected and used as the first threshold.

[0033] The average pixel value corresponding to the minimum ratio is taken as the first target value, and the loop region corresponding to the first target value is taken as the first loop region;

[0034] The first circular region and the corresponding first threshold are stored in the lookup table.

[0035] In one embodiment, the method further includes:

[0036] When the pixel value of the defective LED bead is less than at least one of the pixel average values, the defective LED bead is determined to be an overly dim bead, and the maximum ratio between the pixel value of the overly dim bead and the pixel average value is selected as the second threshold.

[0037] The average pixel value corresponding to the maximum ratio is taken as the second target value, and the loop region corresponding to the second target value is taken as the second loop region;

[0038] The second circular region and the corresponding second threshold are stored in the lookup table.

[0039] In one embodiment, the method further includes:

[0040] When the LED backlight panel is a qualified product, the LED backlight panel will be displayed as a qualified product on the LED bead test page.

[0041] When the LED backlight panel is a defective product, the LED backlight panel will be displayed as a defective product on the LED bead test page, along with the location information of the defective LED beads in the LED backlight panel.

[0042] Secondly, this application also provides a lamp bead detection device for an LED backlight panel. The device includes:

[0043] The acquisition module is used to acquire the pixel values ​​of LED beads in the LED backlight panel from the LED backlight panel image.

[0044] The lookup module is used to look up a first threshold and the corresponding first loop area, and a second threshold and the corresponding second loop area in a lookup table based on the pixel level of the LED backlight panel.

[0045] The first determining module is used to determine, in the LED backlight panel diagram, the first average pixel value of the first loop-shaped area where the LED beads are located, and the second average pixel value of the second loop-shaped area where the LED beads are located.

[0046] The second determining module is configured to determine a first ratio between the pixel value and the first average pixel value when the pixel value is greater than the first average pixel value, and to determine a second ratio between the pixel value and the second average pixel value when the pixel value is less than the second average pixel value.

[0047] The third determining module is used to determine that the LED backlight panel is a qualified product when the first ratio is less than the first threshold or the second ratio is greater than the second threshold.

[0048] In one embodiment, the device further includes,

[0049] The contour extraction module is used to acquire a color image and perform grayscale processing on the color image to obtain the LED backlight panel image; perform binarization processing on the LED backlight panel image to obtain a binarized image; extract the LED bead contours from the LED backlight panel image based on the binarized image; the acquisition module is also used to acquire the pixel values ​​of the LED beads in the LED backlight panel from the LED backlight panel image based on the LED bead contours.

[0050] In one embodiment, the contour extraction module is further configured to acquire a brightness map and use the brightness map as the LED backlight panel image; extract the LED bead contours from the LED backlight panel image; and the acquisition module is further configured to acquire the pixel values ​​of the LED beads in the LED backlight panel from the LED backlight panel image based on the LED bead contours.

[0051] In one embodiment, the acquisition module is further configured to: determine the value of each pixel point located within the outline of the LED bead in the LED backlight panel image; sort the values ​​of each pixel point within the outline of the LED bead to obtain a value sequence; perform subtraction on each adjacent value in the value sequence to obtain a difference sequence; determine the maximum value in the value sequence based on the extreme points in the difference sequence; sum the maximum value and the values ​​in the value sequence before the maximum value to obtain a sum; and perform averaging on the sum to obtain the pixel value of the LED bead.

[0052] In one embodiment, the device further includes

[0053] A lookup table generation module is used to acquire images of unqualified LED backlight panels based on the pixel level to obtain a target LED backlight panel image; determine multiple loop-shaped regions centered on the unqualified LED beads in the target LED backlight panel image; determine the average pixel value corresponding to each of the multiple loop-shaped regions to obtain multiple average pixel values; when the pixel value of the unqualified LED bead is greater than at least one of the average pixel values, the unqualified LED bead is determined to be an overbright bead, and the minimum ratio between the pixel value of the overbright bead and the average pixel value is selected as the first threshold; the average pixel value corresponding to the minimum ratio is taken as the first target value, and the loop-shaped region corresponding to the first target value is taken as the first loop-shaped region; the first loop-shaped region and the corresponding first threshold are stored in the lookup table.

[0054] In one embodiment, the lookup table generation module is further configured to determine that the unqualified LED bead is an overly dim bead when the pixel value of the unqualified LED bead is less than at least one of the pixel average values, and select the maximum ratio among the ratios between the pixel value of the overly dim bead and the pixel average value, and use the maximum ratio as the second threshold; use the pixel average value corresponding to the maximum ratio as the second target value, and use the loop region corresponding to the second target value as the second loop region; and store the second loop region and the corresponding second threshold in the lookup table.

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

[0056] The display module is used to display that the LED backlight panel is a qualified product on the LED bead test page when the LED backlight panel is a qualified product; and to display that the LED backlight panel is a unqualified product on the LED bead test page when the LED backlight panel is an unqualified product, and to display the position information of the unqualified LED beads in the LED backlight panel.

[0057] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described method.

[0058] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0059] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described method.

[0060] The aforementioned LED backlight panel LED bead detection method, apparatus, and computer equipment obtain the pixel values ​​of the LED beads in the LED backlight panel from the LED backlight panel image; based on the pixel level of the LED backlight panel, look up a first threshold and its corresponding first loop region, and a second threshold and its corresponding second loop region in a lookup table; in the LED backlight panel image, determine the first average pixel value of the first loop region where the LED beads are located, and the second average pixel value of the second loop region where the LED beads are located; when the pixel value is greater than the first average pixel value, determine a first ratio between the pixel value and the first average pixel value, and when the pixel value is less than the second average pixel value, determine a second ratio between the pixel value and the second average pixel value; when the first ratio is less than the first threshold, or the second ratio is greater than the second threshold, the LED backlight panel is determined to be a qualified product. This achieves automated qualification detection of the LED beads in the LED backlight panel, greatly improving the efficiency of LED bead detection. Attached Figure Description

[0061] Figure 1 This is an application environment diagram of the LED backlight chip detection method in one embodiment;

[0062] Figure 2 This is a flowchart illustrating a method for detecting LED beads in an LED backlight panel in one embodiment.

[0063] Figure 3 This is a schematic diagram of the LED backlight panel in one embodiment;

[0064] Figure 4This is a flowchart illustrating the LED backlight chip detection method in another embodiment;

[0065] Figure 5 This is a schematic diagram of the loop-shaped area of ​​the LED backlight panel in one embodiment;

[0066] Figure 6 This is a schematic diagram illustrating the steps for obtaining the pixel values ​​of an LED bead in one embodiment;

[0067] Figure 7 This is a schematic diagram of the slope of the difference sequence curve in one embodiment;

[0068] Figure 8 This is a structural block diagram of an LED backlight panel LED bead detection device in one embodiment;

[0069] Figure 9 This is a structural block diagram of the LED backlight panel lamp bead detection device in another embodiment;

[0070] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0071] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0072] The LED backlight chip detection method provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown is illustrated. Terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server. This embodiment uses terminal 102 as an example for explanation.

[0073] Terminal 102 obtains the pixel values ​​of LED beads in the LED backlight panel from the LED backlight panel diagram; based on the pixel level of the LED backlight panel, terminal 102 searches for a first threshold and the corresponding first loop area, and a second threshold and the corresponding second loop area in a lookup table; terminal 102 determines the first average pixel value of the first loop area where the LED beads are located, and the second average pixel value of the second loop area where the LED beads are located, in the LED backlight panel diagram; when the pixel value is greater than the first average pixel value, terminal 102 determines a first ratio between the pixel value and the first average pixel value, and when the pixel value is less than the second average pixel value, terminal 102 determines a second ratio between the pixel value and the second average pixel value; when the first ratio is less than the first threshold, or the second ratio is greater than the second threshold, terminal 102 determines that the LED backlight panel is a qualified product.

[0074] The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0075] In one embodiment, such as Figure 2 As shown, a method for detecting LED beads in an LED backlight panel is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps:

[0076] S202, in the LED backlight panel diagram, obtain the pixel values ​​of the LED beads in the LED backlight panel.

[0077] Here, "LED backlight panel image" can refer to images related to LED backlight panels, which can be grayscale or brightness images. A grayscale image is obtained by processing a color image into grayscale. "LED backlight panel" can also refer to a backlight panel for Mini LEDs, where Mini LEDs are LED chips with a size on the order of 100μm. "LED beads" can refer to the LED beads on the LED backlight panel. Figure 3 This is a schematic diagram of the LED backlight chips in one embodiment; as shown. Figure 3 As shown, an LED backlight panel can have multiple LED beads. Pixel values ​​can be grayscale values ​​or brightness values. It should be noted that... Figure 4 This is a flowchart illustrating the LED backlight chip detection method in another embodiment; as shown. Figure 4As shown, the LED backlight chip testing process can be mainly divided into four parts: data acquisition, data extraction, data analysis, and result output. Data acquisition refers to the process of acquiring the color image or brightness image of the LED backlight. The data acquisition device can be a CCD (Charge Coupled Device) surface measurement instrument, which has the advantage of fast data acquisition speed. The CCD surface measurement instrument can be a CCD camera or a CCD luminance / color meter. A CCD camera can be used to acquire the color image, and a CCD luminance / color meter can be used to acquire the brightness image. Data extraction refers to the process of extracting the grayscale values ​​of the LED chips from the color image of the LED backlight after grayscale processing, or extracting the brightness values ​​of the LED chips from the brightness image of the LED backlight. Data analysis refers to the process of analyzing the extracted grayscale or brightness values ​​of the LED chips to determine whether the LED backlight is qualified. Result output refers to the process of outputting the result indicating whether the LED backlight is a qualified product.

[0078] Specifically, when the LED backlight panel image is a grayscale image, the terminal obtains the grayscale value of the LED beads in the grayscale image; when the LED backlight panel image is a brightness image, the terminal obtains the brightness value of the LED beads in the brightness image.

[0079] In one embodiment, when the LED backlight panel image is a grayscale image, the terminal sequentially obtains the grayscale value of each LED in the grayscale image; when the LED backlight panel image is a brightness image, the terminal sequentially obtains the brightness value of each LED in the brightness image.

[0080] In one embodiment, before S202, the terminal acquires a color image and performs grayscale processing on the color image to obtain an LED backlight panel image; the LED backlight panel image is binarized to obtain a binarized image; and the LED bead outline is extracted from the LED backlight panel image based on the binarized image.

[0081] Here, "color image" refers to an image captured by a CCD camera. "Binarized image" refers to a grayscale image containing two grayscale values. "LED bead outline" refers to the edge outline of an LED bead. Grayscale processing can be performed using grayscale image operators in image processing software such as OpenCV and Halcon, or by using the formula Gray = R * 0.299 + G * 0.587 + B * 0.114.

[0082] In one embodiment, binarizing the LED backlight panel image includes setting grayscale points in the LED backlight panel image with grayscale values ​​greater than or equal to a preset grayscale threshold as first grayscale values, and setting grayscale points with grayscale values ​​less than the preset grayscale threshold as second grayscale values.

[0083] The preset grayscale threshold refers to a pre-set grayscale threshold used to filter pixels in the LED backlight panel image. The first grayscale value refers to one of the corresponding grayscale values ​​during the binarization process of the LED backlight panel image. The second grayscale value refers to another corresponding grayscale value during the binarization process of the LED backlight panel image. For example, the first grayscale value can be 1, and the second grayscale value can be 0.

[0084] In one embodiment, extracting the lamp bead outline from the LED backlight panel image based on the binarized image includes the terminal determining the boundary line between the first gray value and the second gray value in the binarized image, and using the boundary line as the lamp bead outline in the LED backlight panel image.

[0085] In one embodiment, prior to S202, the terminal acquires a brightness map and uses the brightness map as an LED backlight panel image; the LED bead outline is extracted from the LED backlight panel image.

[0086] The luminance map can refer to an image acquired by a CCD luminance and colorimeter. Extracting the LED bead contours from the LED backlight panel image can be done using contour detection functions provided in the OpenCV software library, such as `boundingRect`, `minEnclosingCircle`, and `minAreaRect`.

[0087] S204, based on the pixel level of the LED backlight panel, look up the first threshold and the corresponding first loop area, as well as the second threshold and the corresponding second loop area in the lookup table.

[0088] Pixel level refers to the level of grayscale or brightness. A pixel level can be either a grayscale level or a brightness level, with a grayscale level ranging from 0 to 255. A brightness level refers to different brightness levels, such as 8000 lx or 10000 lx. Typically, the LEDs on an LED backlight board are of the same type, meaning their pixel levels are consistent. A lookup table can refer to a table containing a first threshold and its corresponding first loop region, a second threshold and its corresponding second loop region for different pixel levels.

[0089] The first threshold can refer to the minimum ratio between the pixel value of a defective LED bead and the first average pixel value of the corresponding first loop area at a certain pixel level. The first threshold can be used to screen qualified LED beads, that is, the ratio between the pixel value of a qualified LED bead and the first average pixel value of the corresponding first loop area is less than the first threshold. The first loop area can refer to the loop area corresponding to the first threshold in the lookup table, and the first loop area is in the LED backlight panel image. Figure 5 This is a schematic diagram of the loop-shaped area of ​​the LED backlight panel in one embodiment; as shown. Figure 5 As shown, the loop-shaped region can refer to the area surrounding the LED bead in layers. The layer closest to the LED bead can be the first loop-shaped region, followed by the second loop-shaped region, which contains the first loop-shaped region, and so on, until the i-th loop-shaped region, i = {1, 2, 3…N}. The first loop-shaped region can be the i-th loop-shaped region, i = {1, 2, 3…N}. For example, when the first threshold in the lookup table corresponds to the first loop-shaped region, the first loop-shaped region is the first loop-shaped region of the LED bead in the LED backlight panel diagram.

[0090] The second threshold can refer to the maximum ratio between the pixel value of a defective LED and the second average pixel value of the corresponding second loop area at a certain pixel level. The second threshold can be used to filter qualified LEDs; that is, the ratio between the pixel value of a qualified LED and the second average pixel value of the corresponding second loop area is greater than the second threshold. The second loop area can refer to the loop area corresponding to the second threshold in the lookup table, and this second loop area is in the LED backlight panel diagram. The second loop area can be the i-th layer loop area, i = {1, 2, 3…N}. For example, when the second threshold corresponds to the second layer loop area in the lookup table, the second loop area is the second layer loop area of ​​the LED in the LED backlight panel diagram.

[0091] In one embodiment, prior to S204, the terminal acquires an image of the defective LED backlight panel based on pixel level to obtain a target LED backlight panel image; multiple loop-shaped regions are determined centered on the defective LED beads in the target LED backlight panel image; the average pixel value corresponding to each of the multiple loop-shaped regions is determined to obtain multiple average pixel values; when the pixel value of the defective LED bead is greater than at least one average pixel value, the defective LED bead is determined to be an overbright bead, and the minimum ratio between the pixel value of the overbright bead and the average pixel value is selected as the minimum ratio as a first threshold; the average pixel value corresponding to the minimum ratio is taken as a first target value, and the loop-shaped region corresponding to the first target value is taken as a first loop-shaped region; the first loop-shaped region and the corresponding first threshold are stored in a lookup table.

[0092] In this context, a "substandard LED backlight board" refers to an LED backlight board containing at least one substandard LED chip, thus constituting a substandard product. The "target LED backlight board image" can refer to a grayscale or brightness image of the substandard LED backlight board. "Substandard LED chips" can refer to LED chips that are excessively bright or dim, as defined by the user based on actual needs. The "average pixel value" can refer to the average of the pixel values ​​of all LED chips within the loop area. An "overly bright chip" is defined as a substandard LED chip whose pixel value exceeds at least one pixel average value. The "first target value" can refer to the minimum ratio between the pixel value of an overly bright chip and the average pixel value that corresponds to the average pixel value.

[0093] In one embodiment, before S204, when the pixel value of a defective LED bead is less than at least one pixel average value, the terminal determines that the defective LED bead is an overly dark bead, and selects the maximum ratio among the ratios between the pixel value and the pixel average value of the overly dark bead, and uses the maximum ratio as a second threshold; uses the pixel average value corresponding to the maximum ratio as a second target value, and uses the loop-shaped area corresponding to the second target value as a second loop-shaped area; and stores the second loop-shaped area and the corresponding second threshold value in a lookup table.

[0094] In this context, an "overly dim LED" refers to an LED whose pixel value is less than at least one pixel average value. The second target value can refer to the pixel average value corresponding to the smallest ratio between the pixel value and the pixel average value of the overly dim LED.

[0095] For example, before testing the LED beads in an LED backlight panel, it is necessary to prepare 50 defective products of different brightness levels for each brightness level.

[0096] For defective products, the locations of excessively dim or bright LEDs are manually marked. A backlight panel LED acquisition device collects brightness data from defective products, and a backlight panel LED extraction device extracts the brightness data of each individual LED. The data is then diffused in a spiral pattern centered on the defective LED, and the average brightness of all LEDs within each spiral area is calculated. Let the brightness of the defective LEDs on the LED backlight panel be L. NGJ The average brightness of the LEDs in the first layer of the loop area is L. PJ1 The average brightness of the LEDs in the second-layer loop area is L. PJ2 The average brightness of the LEDs in the i-th layer of the loop region is L. PJi Step 1: Select a brightness level and calculate the threshold K = L NGJ / L PJiJ = {1, 2, 3…N}, i = {1, 2, 3}; J = the number of defective LED beads on the backlight panel. The J value will be different for each backlight panel. i represents the layer number where the loop area is located. The maximum value of i is 3.

[0097] Step 2: Divide K into two groups, one group greater than 1 and the other group less than 1;

[0098] Step 3: When K > 1, take the minimum value of K as the first threshold and its corresponding loop region layer; when K < 1, take the maximum value of K as the second threshold and its corresponding loop region layer.

[0099] Step 4: Record the brightness level, the first threshold and its corresponding herringbone area layer, the second threshold and its corresponding herringbone area layer into the lookup table; process other brightness levels in the same way.

[0100] Specifically, the terminal determines the pixel level of the LED beads in the LED backlight panel. When the pixel level is grayscale, it obtains the lookup table corresponding to the grayscale level and determines the first threshold and the corresponding first loop region, as well as the second threshold and the corresponding second loop region, within the lookup table. When the pixel level is brightness level, it obtains the lookup table corresponding to the brightness level and determines the first threshold and the corresponding first loop region, as well as the second threshold and the corresponding second loop region, within the lookup table.

[0101] For example, if the gray level is 128 or the brightness level is 8000 lx, the first threshold in the lookup table corresponding to the gray level 128 or brightness level 8000 lx is 1.2, the first loop area is the second loop area, the second threshold is 0.8, and the second loop area is the third loop area.

[0102] S206, in the LED backlight panel diagram, determine the first average pixel value of the first loop area where the LED beads are located, and the second average pixel value of the second loop area where the LED beads are located.

[0103] The first average pixel value can refer to the average of the sum of pixel values ​​of all LEDs within the first loop area of ​​the LED backlight panel image. The second average pixel value can refer to the average of the sum of pixel values ​​of all LEDs within the second loop area of ​​the LED backlight panel image.

[0104] Specifically, in the LED backlight panel diagram, after the terminal determines the first loop-shaped area and the second loop-shaped area where the LED beads are located, it obtains the pixel values ​​of all LED beads in the first loop-shaped area and averages the sum of the pixel values ​​of all LED beads in the first loop-shaped area to obtain the first average pixel value; it then obtains the pixel values ​​of all LED beads in the second loop-shaped area and averages the sum of the pixel values ​​of all LED beads in the second loop-shaped area to obtain the second average pixel value.

[0105] S208, when the pixel value is greater than the first average pixel value, a first ratio between the pixel value and the first average pixel value is determined, and when the pixel value is less than the second average pixel value, a second ratio between the pixel value and the second average pixel value is determined.

[0106] The first ratio can be the ratio between the pixel value of the LED bead and the first average pixel value when the pixel value is greater than the first average pixel value. The second ratio can be the ratio between the pixel value of the LED bead and the second average pixel value when the pixel value is less than the second average pixel value.

[0107] Specifically, in the LED backlight panel diagram, the terminal can sequentially compare the pixel value of the LED with the first average pixel value and the second average pixel value. When the pixel value is greater than the first average pixel value, the LED may be a defective LED, i.e., an overly bright LED. Therefore, a first ratio between the pixel value of the LED and the first average pixel value is determined. When the pixel value is less than the second average pixel value, the LED may be a defective LED, i.e., an overly dim LED. Therefore, a second ratio between the pixel value of the LED and the second average pixel value is determined.

[0108] S210, when the first ratio is less than the first threshold or the second ratio is greater than the second threshold, the LED backlight panel is determined to be a qualified product.

[0109] Among them, qualified products can refer to LED backlight panels that do not contain unqualified LED beads.

[0110] Specifically, the terminal can sequentially compare the first ratio of each LED bead with the first threshold or the second ratio with the second threshold. When the first ratio of all LED beads in the LED backlight is less than the first threshold or the second ratio is greater than the second threshold, the LED backlight is determined to be a qualified product.

[0111] In one embodiment, when the first ratio of LED beads in the LED backlight panel is greater than or equal to a first threshold, or the second ratio is less than or equal to a second threshold, the terminal determines that the LED backlight panel is a defective product.

[0112] In one embodiment, when the LED backlight panel is a qualified product, the terminal displays "LED backlight panel is qualified product" on the LED bead test page; when the LED backlight panel is a defective product, the terminal displays "LED backlight panel is defective product" on the LED bead test page, and displays the location information of the defective LED beads in the LED backlight panel.

[0113] The LED bead test page can refer to the page used to display test results. Location information can refer to the position of the defective LED bead on the LED backlight board diagram; for example, the location information can be the coordinates of the defective LED bead.

[0114] In the aforementioned LED backlight chip detection method, the pixel values ​​of the LED chips in the LED backlight are obtained from the LED backlight image. Based on the pixel level of the LED backlight, a first threshold and its corresponding first loop region, and a second threshold and its corresponding second loop region are looked up in a lookup table. In the LED backlight image, a first average pixel value for the first loop region where the LED chips are located, and a second average pixel value for the second loop region where the LED chips are located are determined. When the pixel value is greater than the first average pixel value, a first ratio between the pixel value and the first average pixel value is determined; when the pixel value is less than the second average pixel value, a second ratio between the pixel value and the second average pixel value is determined. When the first ratio is less than the first threshold, or the second ratio is greater than the second threshold, the LED backlight is determined to be a qualified product. This method automates the qualification detection of the LED chips in the LED backlight, greatly improving the efficiency of LED chip detection.

[0115] In one embodiment, such as Figure 6 As shown, the steps to obtain the pixel values ​​of LED beads include:

[0116] S602, in the LED backlight panel diagram, determine the value of each pixel point located within the outline of the LED bead.

[0117] The value of a pixel can refer to the grayscale value or brightness value of a pixel in the LED backlight panel image.

[0118] Specifically, in the LED backlight panel diagram, the terminal determines the grayscale value or brightness value of each pixel within the outline of the LED lamp bead.

[0119] S604: Sort the values ​​of each pixel within the LED bead outline to obtain a value sequence.

[0120] Here, "value" can refer to grayscale value or brightness value. A value sequence can refer to a sequence composed of the grayscale or brightness values ​​of each pixel within the LED bead's outline.

[0121] Specifically, the terminal can sort the pixels within the LED bead outline according to their grayscale or brightness values ​​to obtain a sequence of grayscale or brightness values ​​arranged from largest to smallest.

[0122] S606, perform subtraction on adjacent values ​​in the value sequence to obtain the difference sequence.

[0123] Among them, the difference sequence can refer to the sequence obtained by subtracting each adjacent gray value or brightness value in the value sequence.

[0124] Specifically, the terminal can subtract the next gray value or brightness value from the previous gray value or brightness value in the value sequence in turn to obtain the difference values, and combine the difference values ​​into a difference value sequence.

[0125] S608, determine the maximum value in the value sequence based on the extreme points in the difference sequence.

[0126] An extreme point can be defined as the first extreme point on the curve formed by the differences, with the horizontal axis representing the sequence number of each difference in the difference sequence and the vertical axis representing the curve formed by the differences. A maximum value can be defined as the larger of two adjacent values ​​corresponding to an extreme point in the value sequence. Figure 7 This is a schematic diagram of the slope of the difference sequence curve in one embodiment; such as Figure 7 As shown, point A is an extreme point. For example, the extreme point A is the difference between the adjacent gray values ​​100 and 90 in the value sequence. Since 100 is greater than 90, the maximum value is 100.

[0127] Specifically, the terminal uses the horizontal axis as the sequence number of each difference in the difference sequence and the vertical axis as the curve formed by the differences. It determines the first extreme point that appears on the curve, identifies the two adjacent values ​​corresponding to the extreme point in the value sequence, compares the two adjacent values, determines the larger of the two adjacent values, and takes the larger value as the maximum value in the value sequence.

[0128] S610 sums the values ​​before the maximum in the sequence of maximum and sum values ​​to obtain the sum value.

[0129] The sum can refer to the result of summing the maximum value with the values ​​in the value sequence that precede the maximum value.

[0130] Specifically, the sum of the values ​​preceding the maximum value in the sequence of maximum and sum values ​​is obtained.

[0131] S612, average the sum to obtain the pixel value of the LED bead.

[0132] Specifically, the terminal determines the number of values ​​in the value sequence that contain a maximum value and the number of values ​​preceding the maximum value. Based on this number of values, the sum of the values ​​is averaged to obtain the pixel value of the LED bead. The formula for calculating the pixel value of the LED bead can be:

[0133]

[0134] For example, if the values ​​of each pixel within the LED bead's outline are 21, 18, 20, 12, 13, and 15, sorting these values ​​yields a value sequence of {21, 20, 18, 15, 13, 12}. Subtracting adjacent values ​​from this sequence yields a difference sequence of {1, 2, 3, 2, 1}. Graphing this sequence reveals that the extreme value is 3. The two adjacent values ​​corresponding to 3 are 18 and 15. Since 18 is greater than 15, the maximum value is 18. Summing the maximum value and the values ​​preceding it in the sequence yields a sum of {21, 20, 18}, resulting in a sum of 59. With 3 values, the pixel value of the LED bead is 59 / 3 = 19.67.

[0135] In this embodiment, by determining the value of each pixel within the LED bead outline in the LED backlight panel diagram, sorting the values ​​of each pixel within the LED bead outline to obtain a value sequence, subtracting adjacent values ​​in the value sequence to obtain a difference sequence, determining the maximum value in the value sequence based on the extreme points in the difference sequence, summing the maximum value and the values ​​in the value sequence before the maximum value to obtain a sum, and averaging the sum to obtain the pixel value of the LED bead, thus achieving accurate acquisition of the pixel value of the LED bead.

[0136] As an example, this embodiment is as follows:

[0137] A schematic diagram of the Mini LED backlight LED beads is shown below. Figure 3 As shown, the actual LED arrangement will be even denser. The backlight panel LED acquisition device includes: Mini LED backlight panel, Mini LED backlight panel lighting device, CCD acquisition instrument, data receiving device, and data transmission line.

[0138] The working steps of the backlight LED chip acquisition device are as follows:

[0139] Step 1: The Mini LED backlight panel lighting device illuminates the Mini LED backlight panel;

[0140] Step 2: The CCD acquisition instrument acquires Mini LED data;

[0141] Step 3: The CCD acquisition instrument transmits the acquired data to the data receiving device via a data transmission line.

[0142] The CCD acquisition instrument includes, but is not limited to, a CCD surface luminance meter, and the data receiving device includes, but is not limited to, a computer. The backlight LED chip extraction device is mainly responsible for extracting the luminance / grayscale value of each Mini LED chip from the data information acquired by the backlight LED chip acquisition device. The extraction of luminance / grayscale values ​​can be divided into two steps.

[0143] Step 1: When the brightness value of the LED beads is collected using a CCD luminance and colorimeter, the outline of the LED beads can be extracted using common contour extraction algorithms, and the coordinates of the positions of all the points enclosing the outline of the beads can be returned.

[0144] When using a CCD camera to acquire data, a color image is captured. Before using the contour extraction algorithm, the backlight LED chip acquisition device needs to process the color image into grayscale, and then perform binarization to obtain a binary image. The grayscale to binary conversion requires a threshold, which can be set according to the actual product requirements. Furthermore, all brightness values ​​mentioned below will be represented by grayscale values. After obtaining the contours of each LED chip in the Mini LED backlight panel and the points contained within those contours in step one, the chip contour data can be processed. Some excessively dark points need to be removed to obtain the corresponding brightness value for each LED chip. The removal method is as follows:

[0145] 1. Sort the brightness values ​​inside the outline of each LED bead in descending order;

[0146] 2. Plot a curve representing the difference between the previous brightness value and the next brightness value. The horizontal axis represents the sequence number of the differences, and the vertical axis represents the difference value.

[0147] 3. When the slope of the curve changes on both sides, that point is an inflection point;

[0148] 4. The point corresponding to the inflection point is the difference between two brightness values. The relatively larger value and the value before it are taken as the corresponding area of ​​the Mini LED bead.

[0149] 5. Take the average value of the brightness values ​​in this area as the brightness value of the LED bead.

[0150] In this way, we obtain the brightness value of each LED in the Mini LED backlight panel.

[0151] Step 2: Read the brightness value of each LED on the Mini LED backlight panel.

[0152] During the actual testing process, the backlight panel LED bead brightness acquisition device first acquires the brightness of the LED backlight panel, and the backlight panel LED bead extraction device then extracts the brightness value of each LED bead. The backlight panel LED bead brightness / grayscale analysis and processing device queries a lookup table based on the brightness / grayscale level of the LED backlight panel to find suitable parameters, and finally judges whether the product is qualified. If the product is qualified, the LED bead test page outputs "This product is qualified"; otherwise, if the product is unqualified, the LED bead test page outputs "This product is unqualified", and provides the location information of the unqualified LED beads.

[0153] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed 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 performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0154] Based on the same inventive concept, this application also provides an LED backlight chip detection device for implementing the LED backlight chip detection method described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more LED backlight chip detection device embodiments provided below can be found in the limitations of the LED backlight chip detection method described above, and will not be repeated here.

[0155] In one embodiment, such as Figure 8 As shown, an LED backlight chip detection device is provided, comprising: an acquisition module 802, a search module 804, a first determination module 806, a second determination module 808, and a third determination module 810, wherein:

[0156] The acquisition module 802 is used to acquire the pixel values ​​of LED beads in the LED backlight panel from the LED backlight panel image.

[0157] The lookup module 804 is used to look up a first threshold and the corresponding first loop area, and a second threshold and the corresponding second loop area in a lookup table based on the pixel level of the LED backlight panel.

[0158] The first determining module 806 is used to determine, in the LED backlight panel diagram, the first average pixel value of the first loop area where the LED beads are located, and the second average pixel value of the second loop area where the LED beads are located.

[0159] The second determining module 808 is used to determine a first ratio between the pixel value and the first average pixel value when the pixel value is greater than the first average pixel value, and to determine a second ratio between the pixel value and the second average pixel value when the pixel value is less than the second average pixel value.

[0160] The third determining module 810 is used to determine that the LED backlight panel is a qualified product when the first ratio is less than the first threshold or the second ratio is greater than the second threshold.

[0161] In one embodiment, the acquisition module 802 is further configured to: determine the value of each pixel point located within the outline of the LED backlight panel in the LED backlight panel image; sort the values ​​of each pixel point within the outline of the LED to obtain a value sequence; perform subtraction on each adjacent value in the value sequence to obtain a difference sequence; determine the maximum value in the value sequence based on the extreme points in the difference sequence; sum the maximum value and the values ​​in the value sequence before the maximum value to obtain a sum; and perform average processing on the sum to obtain the pixel value of the LED.

[0162] In one embodiment, such as Figure 9 As shown, the LED backlight panel's lamp bead detection device further includes: a contour extraction module 812, a lookup table generation module 814, and a display module 816, wherein:

[0163] The contour extraction module 812 is used to acquire a color image and perform grayscale processing on the color image to obtain an LED backlight panel image; perform binarization processing on the LED backlight panel image to obtain a binarized image; extract the LED bead contours from the LED backlight panel image based on the binarized image; the acquisition module is also used to obtain the pixel values ​​of the LED beads in the LED backlight panel from the LED backlight panel image based on the LED bead contours.

[0164] The lookup table generation module 814 is used to acquire images of unqualified LED backlight panels based on pixel levels to obtain a target LED backlight panel image; to determine multiple loop-shaped regions centered on the unqualified LED beads in the target LED backlight panel image; to determine the average pixel value corresponding to each of the multiple loop-shaped regions, thus obtaining multiple average pixel values; when the pixel value of an unqualified LED bead is greater than at least one average pixel value, the unqualified LED bead is determined to be an overbright bead, and the minimum ratio between the pixel value of the overbright bead and the average pixel value is selected as the minimum ratio, which is used as the first threshold; the average pixel value corresponding to the minimum ratio is used as the first target value, and the loop-shaped region corresponding to the first target value is used as the first loop-shaped region; the first loop-shaped region and the corresponding first threshold are stored in the lookup table.

[0165] Display module 816 is used to display "LED backlight board is a qualified product" on the LED bead test page when the LED backlight board is a qualified product; and to display "LED backlight board is a unqualified product" on the LED bead test page when the LED backlight board is a unqualified product, and to display the position information of the unqualified LED beads in the LED backlight board. In the embodiments, in addition to the embodiments of the device alone, embodiments of the device items corresponding to all method claims must also be written.

[0166] In one embodiment, the contour extraction module 812 is further configured to obtain a brightness map and use the brightness map as an LED backlight panel image; extract the LED bead contours from the LED backlight panel image; and the acquisition module is further configured to obtain the pixel values ​​of the LED beads in the LED backlight panel from the LED backlight panel image based on the LED bead contours.

[0167] In one embodiment, the lookup table generation module 814 is further configured to: determine that the unqualified LED bead is an overly dark bead when the pixel value of the unqualified LED bead is less than at least one pixel average value; select the maximum ratio among the ratios between the pixel value and the pixel average value of the overly dark bead; use the maximum ratio as a second threshold; use the pixel average value corresponding to the maximum ratio as a second target value; use the loop-shaped area corresponding to the second target value as a second loop-shaped area; and store the second loop-shaped area and the corresponding second threshold value in the lookup table.

[0168] The above embodiment obtains the pixel values ​​of LED beads in the LED backlight panel from the LED backlight panel image; based on the pixel level of the LED backlight panel, it searches a lookup table for a first threshold and the corresponding first loop region, and a second threshold and the corresponding second loop region; in the LED backlight panel image, it determines the first average pixel value of the first loop region where the LED beads are located, and the second average pixel value of the second loop region where the LED beads are located; when the pixel value is greater than the first average pixel value, it determines a first ratio between the pixel value and the first average pixel value, and when the pixel value is less than the second average pixel value, it determines a second ratio between the pixel value and the second average pixel value; when the first ratio is less than the first threshold, or the second ratio is greater than the second threshold, the LED backlight panel is determined to be a qualified product. This achieves automated qualification testing of the LED beads in the LED backlight panel, greatly improving the efficiency of LED bead testing in the LED backlight panel.

[0169] Each module in the aforementioned LED backlight chip detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0170] In one embodiment, a computer device is provided, which may be a terminal or a server. Taking the computer device as a terminal as an example, its internal structure diagram can be as follows. Figure 10 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for detecting LED beads in an LED backlight panel. The display unit of the computer device is used to form a visually visible image. It can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0171] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0172] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the embodiments described above.

[0173] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the embodiments described above.

[0174] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the embodiments described above.

[0175] 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 used for analysis, data stored, data displayed, 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 the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0176] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. 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), magnetic 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 take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0177] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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, they should be considered to be within the scope of this specification.

[0178] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for detecting LED beads in an LED backlight panel, characterized in that, The method includes: In the LED backlight panel diagram, the pixel values ​​of the LED beads in the LED backlight panel are obtained; the pixel values ​​are grayscale values ​​or brightness values. Based on the pixel level of the LED backlight panel, a first threshold and its corresponding first loop region, as well as a second threshold and its corresponding second loop region, are searched in a lookup table. The first threshold refers to the minimum ratio between the pixel value of an overly bright LED bead in the target LED backlight panel image and the average pixel value of multiple loop regions centered on the overly bright LED bead. The first loop region refers to the loop region corresponding to the minimum ratio. The second threshold refers to the maximum ratio between the pixel value of an underly dark LED bead in the target LED backlight panel image and the average pixel value of multiple loop regions centered on the underly dark LED bead. The second loop region refers to the loop region corresponding to the maximum ratio. The target LED backlight panel image refers to the image obtained by image acquisition of unqualified LED backlight panels based on the pixel level. In the LED backlight panel diagram, a first average pixel value of the first loop-shaped area where the LED beads are located and a second average pixel value of the second loop-shaped area where the LED beads are located are determined. When the pixel value is greater than the first average pixel value, a first ratio between the pixel value and the first average pixel value is determined; and when the pixel value is less than the second average pixel value, a second ratio between the pixel value and the second average pixel value is determined. When the first ratio is less than the first threshold, or the second ratio is greater than the second threshold, the LED backlight panel is determined to be a qualified product.

2. The method according to claim 1, characterized in that, Before obtaining the pixel values ​​of the LED beads in the LED backlight panel, the method further includes: A color image is obtained, and the color image is processed into grayscale to obtain the LED backlight panel image; The LED backlight panel image is binarized to obtain a binarized image; Based on the binarized image, extract the LED bead outlines from the LED backlight panel image; The step of obtaining the pixel values ​​of the LED beads in the LED backlight panel includes: Based on the outline of the LED beads, the pixel values ​​of the LED beads in the LED backlight panel are obtained from the LED backlight panel diagram.

3. The method according to claim 1, characterized in that, Before obtaining the pixel values ​​of the LED beads in the LED backlight panel, the method further includes: Obtain a brightness diagram and use the brightness diagram as the LED backlight panel diagram; Extract the LED bead outline from the LED backlight panel image; The process of obtaining the pixel values ​​of the LED beads in the LED backlight panel includes: Based on the outline of the LED beads, the pixel values ​​of the LED beads in the LED backlight panel are obtained from the LED backlight panel diagram.

4. The method according to claim 2 or 3, characterized in that, The step of obtaining the pixel values ​​of the LED beads in the LED backlight panel from the LED backlight panel diagram based on the outline of the LED beads includes: In the LED backlight panel diagram, the value of each pixel located within the outline of the LED bead is determined; The values ​​of each pixel within the outline of the LED bead are sorted to obtain a value sequence; The difference between each adjacent value in the value sequence is calculated to obtain the difference sequence. Based on the extreme points in the difference sequence, determine the maximum value in the value sequence; Summing the maximum value and the values ​​in the value sequence preceding the maximum value yields a sum. The sum is averaged to obtain the pixel value of the LED bead.

5. The method according to claim 1, characterized in that, Before searching for the first threshold and the corresponding first loop region in the lookup table, the method further includes: Based on the pixel level, images of the defective LED backlight panels are acquired to obtain an image of the target LED backlight panel; Multiple loop-shaped areas are determined with the defective LED beads in the target LED backlight board diagram as the center; Determine the average pixel value corresponding to each of the multiple loop-shaped regions to obtain multiple average pixel values; When the pixel value of the defective LED bead is greater than at least one of the pixel average values, the defective LED bead is determined to be an overbright bead, and the minimum ratio between the pixel value of the overbright bead and the pixel average value is selected and used as the first threshold. The average pixel value corresponding to the minimum ratio is taken as the first target value, and the loop region corresponding to the first target value is taken as the first loop region; The first circular region and the corresponding first threshold are stored in the lookup table.

6. The method according to claim 5, characterized in that, The method further includes: When the pixel value of the defective LED bead is less than at least one of the pixel average values, the defective LED bead is determined to be an overly dim bead, and the maximum ratio between the pixel value of the overly dim bead and the pixel average value is selected as the second threshold. The average pixel value corresponding to the maximum ratio is taken as the second target value, and the loop region corresponding to the second target value is taken as the second loop region; The second circular region and the corresponding second threshold are stored in the lookup table.

7. The method according to claim 1, characterized in that, The method further includes: When the LED backlight panel is a qualified product, the LED backlight panel will be displayed as a qualified product on the LED bead test page. When the LED backlight panel is a defective product, the LED backlight panel will be displayed as a defective product on the LED bead test page, along with the location information of the defective LED beads in the LED backlight panel.

8. A device for detecting LED beads in an LED backlight panel, characterized in that, The device includes: The acquisition module is used to acquire the pixel values ​​of LED beads in the LED backlight panel from the LED backlight panel image; the pixel values ​​are grayscale values ​​or brightness values. The lookup module is used to search a lookup table for a first threshold and a corresponding first loop region, and a second threshold and a corresponding second loop region, based on the pixel level of the LED backlight panel. The first threshold is the minimum ratio between the pixel value of an overly bright LED bead in the target LED backlight panel image and the average pixel value of multiple loop regions centered on the overly bright LED bead. The first loop region is the loop region corresponding to the minimum ratio. The second threshold is the maximum ratio between the pixel value of an underly dark LED bead in the target LED backlight panel image and the average pixel value of multiple loop regions centered on the underly dark LED bead. The second loop region is the loop region corresponding to the maximum ratio. The target LED backlight panel image is an image obtained by image acquisition of unqualified LED backlight panels based on the pixel level. The first determining module is used to determine, in the LED backlight panel diagram, the first average pixel value of the first loop-shaped area where the LED beads are located, and the second average pixel value of the second loop-shaped area where the LED beads are located. The second determining module is configured to determine a first ratio between the pixel value and the first average pixel value when the pixel value is greater than the first average pixel value, and to determine a second ratio between the pixel value and the second average pixel value when the pixel value is less than the second average pixel value. The third determining module is used to determine that the LED backlight panel is a qualified product when the first ratio is less than the first threshold or the second ratio is greater than the second threshold.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

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

Images