A method and apparatus for defect detection in Mini LED backlight panels

Abstract

This disclosure relates to the fields of intelligent manufacturing and artificial intelligence, and discloses a method and apparatus for defect detection of Mini LED backlight panels. The defect detection method of the Mini LED backlight panel is applied to a computing device and includes: performing a difference operation on an image of the Mini LED backlight panel to be detected and a reference template image to obtain a difference image; for any Mini LED in the difference image, matching its area with the area of ​​the LED corresponding to each defect type; if there is a matching LED area, then taking the defect type corresponding to the matching LED area as the defect type of any Mini LED; and determining the position of any Mini LED in the difference image based on the row spacing and column spacing of the Mini LEDs corresponding to the reference template image, thereby effectively improving the defect detection efficiency and detection accuracy.

Description

Technical Field

[0001] This application relates to intelligent manufacturing and artificial intelligence technologies, and in particular to a method and apparatus for defect detection of Mini LED backlight panels. Background Technology

[0002] Compared to traditional Liquid Crystal Display (LCD) technology, the advancements in image quality from the recently developed Mini LED (Light Emitting Diode) technology are obvious. The higher density of light-emitting devices allows Mini LED panels to achieve a backlighting effect closer to pixelation, resulting in significantly improved brightness and contrast. Compared to Organic Light Emitting Display (OLED), Mini LED offers the advantage of achieving comparable display quality at a lower cost, while also boasting a longer lifespan and lower power consumption. Mini LED backlighting combined with flexible substrates can also achieve curved displays similar to OLED, and it also offers advantages in light source reliability compared to OLED.

[0003] However, during the production of Mini LED backlight panels, defects such as component damage, extrusion, or poor welding processes can lead to various problems, including the inability to light up due to damaged LED chips, severely impacting the panel's performance. Currently, manual inspection is used to address these defects. However, the large volume of backlight panels to be inspected in actual production, coupled with the unpredictable accuracy of manual inspection (leading to missed or over-inspections), and the long inspection cycle, results in low efficiency and accuracy in defect detection. Summary of the Invention

[0004] This disclosure provides a method and apparatus for defect detection of Mini LED backlight panels, which improves the efficiency and accuracy of defect detection in liquid crystal panels.

[0005] The specific technical solution provided in this disclosure is as follows:

[0006] In a first aspect, a defect detection method for a Mini LED backlight panel, applied to a computing device, includes:

[0007] The image of the Mini LED backlight panel to be detected is compared with the reference template image to obtain a difference image. The coordinates of each Mini LED in the image of the Mini LED backlight panel to be detected are the same as the coordinates of the corresponding Mini LED in the reference template image.

[0008] For any Mini LED in the differential image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type. If there is a matching LED area, the defect type corresponding to the matching LED area is taken as the defect type of any Mini LED.

[0009] Based on the row spacing and column spacing of the Mini LEDs corresponding to the reference template image, the position of any Mini LED in the difference image is determined.

[0010] Optionally, the image of the Mini LED backlight panel to be tested is taken when the angle between the Mini LED backlight panel to be tested and the horizontal plane is zero.

[0011] Optionally, the area of ​​the LED corresponding to each defect type can be determined in the following ways:

[0012] Based on the standard LED bead area and the preset explosion defect discrimination ratio, the preset explosion area is determined, and the preset explosion area is used as the LED bead area corresponding to the explosion defect type.

[0013] Based on the standard LED area and the preset lamp-extinguishing defect discrimination ratio, the preset lamp-extinguishing area is determined, and the preset lamp-extinguishing area is used as the LED area corresponding to the lamp-extinguishing defect type.

[0014] Based on the standard LED bead area and the preset weak brightness defect discrimination ratio, the preset weak brightness area is determined, and the preset weak brightness area is used as the LED bead area corresponding to the weak brightness defect type.

[0015] The standard LED area is the luminous area corresponding to any normally emitting Mini LED in the reference template image.

[0016] Optionally, the image of the Mini LED backlight panel to be detected is compared with the reference template image to obtain a difference image, including:

[0017] For any defect type, the Mini LED backlight panel image to be inspected is binarized according to the grayscale threshold corresponding to the defect type to obtain the binary image to be inspected.

[0018] By performing a difference operation between the binary image to be inspected and the reference template image, a difference image corresponding to any defect type can be obtained.

[0019] Optionally, for any Mini LED in the differential image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type, including:

[0020] For any Mini LED in any differential image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type.

[0021] Optionally, a difference operation is performed based on the binary image to be inspected and the reference template image to obtain a difference image corresponding to any defect type, including:

[0022] If the grayscale threshold is the same as the grayscale threshold for a burst lamp, then the binary image to be inspected and the reference template image are subjected to forward difference operation to obtain the difference image corresponding to the burst lamp defect type.

[0023] If the grayscale threshold is the same as the grayscale threshold for lamp extinguishing, then the binary image to be inspected and the reference template image are subjected to inverse difference operation to obtain the difference image corresponding to the lamp extinguishing defect type.

[0024] If the grayscale threshold is the weak brightness grayscale threshold, then the binary image to be inspected and the difference image corresponding to the lamp-off defect type are subjected to forward difference operation to obtain the difference image corresponding to the weak brightness defect type.

[0025] Optionally, based on the row and column spacing of the Mini LEDs corresponding to the reference template image, the position of any Mini LED in the difference image is determined, including:

[0026] Based on row spacing, vertical distance, and reference ordinate, determine the row value of any Mini LED identified as defective in the differential image; and

[0027] Based on column spacing, lateral distance, and reference abscissa, determine the column value of any Mini LED identified as a defect in the differential image;

[0028] Wherein, row spacing is the vertical distance between two adjacent Mini LEDs in the reference template image, column spacing is the horizontal distance between two adjacent Mini LEDs in the reference template image, vertical distance is the vertical distance of any Mini LED determined to be defective relative to the reference origin in the differential image, horizontal distance is the horizontal distance of any Mini LED determined to be defective relative to the reference origin in the differential image, reference ordinate is the ordinate of the reference origin in the differential image, and reference abscissa is the abscissa of the reference origin in the differential image.

[0029] Optionally, after determining the position of any Mini LED in the difference image based on the row spacing and column spacing of the Mini LEDs corresponding to the reference template image, the method further includes:

[0030] Obtain the total number of rows and columns of LED switches, wherein each LED switch controls the on / off state of at least one Mini LED, and the LED switches are uniformly arranged in the rectangle formed by at least one LED connected to the LED switch on both the reference template image and the Mini LED backlight panel to be detected.

[0031] The switch row value of any Mini LED that is determined to be defective is determined based on the total number of rows of LED beads, the row value of any Mini LED that is determined to be defective, and the total number of switch rows.

[0032] The switch column value of any Mini LED that is determined to be defective is determined based on the total number of LED columns, the column value of any Mini LED that is determined to be defective, and the total number of switch columns.

[0033] The total number of rows of LED beads is the sum of the number of rows of each Mini LED distributed in the reference template image, and the total number of columns of LED beads is the sum of the number of columns of each Mini LED distributed in the reference template image.

[0034] Secondly, a defect detection device for a Mini LED backlight panel includes:

[0035] The differential unit is used to perform a differential operation on the image of the Mini LED backlight panel to be detected and the reference template image to obtain a differential image, wherein the coordinates of each Mini LED in the image of the Mini LED backlight panel to be detected are the same as the coordinates of the corresponding Mini LED in the reference template image.

[0036] The matching unit is used to match the area of ​​any Mini LED in the differential image with the area of ​​the LED corresponding to each defect type. If there is a matching LED area, the defect type corresponding to the matching LED area is taken as the defect type of any Mini LED.

[0037] The determining unit is used to determine the position of any Mini LED in the differential image based on the row spacing and column spacing of the Mini LEDs corresponding to the reference template image.

[0038] Optionally, the image of the Mini LED backlight panel to be tested is taken when the angle between the Mini LED backlight panel to be tested and the horizontal plane is zero.

[0039] Optionally, the area of ​​the LED corresponding to each defect type can be determined in the following ways:

[0040] Based on the standard LED bead area and the preset explosion defect discrimination ratio, the preset explosion area is determined, and the preset explosion area is used as the LED bead area corresponding to the explosion defect type.

[0041] Based on the standard LED area and the preset lamp-extinguishing defect discrimination ratio, the preset lamp-extinguishing area is determined, and the preset lamp-extinguishing area is used as the LED area corresponding to the lamp-extinguishing defect type.

[0042] Based on the standard LED bead area and the preset weak brightness defect discrimination ratio, the preset weak brightness area is determined, and the preset weak brightness area is used as the LED bead area corresponding to the weak brightness defect type.

[0043] The standard LED area is the luminous area corresponding to any normally emitting Mini LED in the reference template image.

[0044] Optionally, the image of the Mini LED backlight panel to be detected is compared with the reference template image to obtain a difference image, including:

[0045] For any defect type, the Mini LED backlight panel image to be inspected is binarized according to the grayscale threshold corresponding to the defect type to obtain the binary image to be inspected.

[0046] By performing a difference operation between the binary image to be inspected and the reference template image, a difference image corresponding to any defect type can be obtained.

[0047] Optionally, for any Mini LED in the differential image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type, including:

[0048] For any Mini LED in any differential image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type.

[0049] Optionally, a difference operation is performed based on the binary image to be inspected and the reference template image to obtain a difference image corresponding to any defect type, including:

[0050] If the grayscale threshold is the same as the grayscale threshold for a burst lamp, then the binary image to be inspected and the reference template image are subjected to forward difference operation to obtain the difference image corresponding to the burst lamp defect type.

[0051] If the grayscale threshold is the same as the grayscale threshold for lamp extinguishing, then the binary image to be inspected and the reference template image are subjected to inverse difference operation to obtain the difference image corresponding to the lamp extinguishing defect type.

[0052] If the grayscale threshold is the weak brightness grayscale threshold, then the binary image to be inspected and the difference image corresponding to the lamp-off defect type are subjected to forward difference operation to obtain the difference image corresponding to the weak brightness defect type.

[0053] Optionally, based on the row and column spacing of the Mini LEDs corresponding to the reference template image, the position of any Mini LED in the difference image is determined, including:

[0054] Based on row spacing, vertical distance, and reference ordinate, determine the row value of any Mini LED identified as defective in the differential image; and

[0055] Based on column spacing, lateral distance, and reference abscissa, determine the column value of any Mini LED identified as a defect in the differential image;

[0056] Wherein, row spacing is the vertical distance between two adjacent Mini LEDs in the reference template image, column spacing is the horizontal distance between two adjacent Mini LEDs in the reference template image, vertical distance is the vertical distance of any Mini LED determined to be defective relative to the reference origin in the differential image, horizontal distance is the horizontal distance of any Mini LED determined to be defective relative to the reference origin in the differential image, reference ordinate is the ordinate of the reference origin in the differential image, and reference abscissa is the abscissa of the reference origin in the differential image.

[0057] Optionally, after determining the position of any Mini LED in the difference image based on the row spacing and column spacing of the Mini LEDs corresponding to the reference template image, the method further includes:

[0058] Obtain the total number of rows and columns of LED switches, wherein each LED switch controls the on / off state of at least one Mini LED, and the LED switches are uniformly arranged in the rectangle formed by at least one LED connected to the LED switch on both the reference template image and the Mini LED backlight panel to be detected.

[0059] The switch row value to which any Mini LED identified as defective belongs is determined based on the total number of rows of LED beads, the row value of any Mini LED identified as defective, and the total number of rows of switches.

[0060] The switch column value of any Mini LED deemed defective is determined based on the total number of LED columns, the column value of any Mini LED deemed defective, and the total number of switch columns; the switch row value is determined based on the switch row spacing and the total number of switch rows; and the switch column value is determined based on the switch column spacing and the total number of switch columns.

[0061] The total number of rows of LED beads is the sum of the number of rows of each Mini LED distributed in the reference template image, and the total number of columns of LED beads is the sum of the number of columns of each Mini LED distributed in the reference template image.

[0062] Thirdly, a terminal includes:

[0063] Memory, used to store executable instructions;

[0064] A processor for reading and executing executable instructions stored in memory to implement the method as described in any of the first aspects.

[0065] Fourthly, a computer-readable storage medium, when instructions in the storage medium are executed by a processor, enables the processor to perform the method described in any of the first aspects above.

[0066] In summary, this disclosure presents a defect detection method for a Mini LED backlight panel, applied to a computing device. The method includes: performing a difference operation between an image of the Mini LED backlight panel to be detected and a reference template image to obtain a difference image. It should be noted that the coordinates of each Mini LED in the image of the Mini LED backlight panel to be detected are the same as the corresponding Mini LED in the reference template image. Thus, for any Mini LED in the difference image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type. If a matching LED area exists, the defect type corresponding to the matching LED area is taken as the defect type of any Mini LED. Furthermore, based on the row and column spacing of the Mini LEDs corresponding to the Mini LEDs in the reference template image, the position of any Mini LED in the difference image is determined. This allows for the rapid and accurate acquisition of the defect type and position of the defective Mini LED in the image of the Mini LED backlight panel to be detected, thereby improving the defect detection efficiency and accuracy. Attached Figure Description

[0067] Figure 1 This is a schematic diagram of the system architecture for detecting defects in a Mini LED backlight panel in an embodiment of this application;

[0068] Figure 2 This is a schematic diagram of the process for detecting defects in a Mini LED backlight panel in an embodiment of this application;

[0069] Figure 3 This is a schematic diagram of a normally emitting backlight panel in an embodiment of this application;

[0070] Figure 4 This is a schematic diagram of the process for obtaining differential images in an embodiment of this application;

[0071] Figure 5 This is a flowchart illustrating the process of obtaining differential images corresponding to various defect types in an embodiment of this application.

[0072] Figure 6 This is a flowchart illustrating the process of determining the row and column values ​​of a Mini LED in a differential image, as described in this application embodiment.

[0073] Figure 7 This is a flowchart illustrating the process of determining the location of the LED switch in an embodiment of this application.

[0074] Figure 8 This is a schematic diagram showing the uniform arrangement of the LED switch and Mini LEDs in an embodiment of this application;

[0075] Figure 9 This is a schematic diagram of the logical architecture of a device according to an embodiment of the present disclosure;

[0076] Figure 10 This is a schematic diagram of the physical architecture of the terminal in an embodiment of this disclosure. Detailed Implementation

[0077] The preferred embodiments of this application will now be described in detail with reference to the accompanying drawings. Firstly, in the embodiments of this disclosure, the system includes at least one computing device. (See attached drawings.) Figure 1 As shown, the image of the Mini LED backlight panel to be inspected is input into a computing device for defect detection, that is, the defect type and location of any Mini LED in the image of the Mini LED backlight panel to be inspected are determined.

[0078] The following describes a method for defect detection of Mini LED backlight panels performed by a computing device. (See attached document.) Figure 2 As shown in this embodiment, the specific process of the computing device performing defect detection of the Mini LED backlight panel is as follows:

[0079] Step 201: Perform a difference operation on the Mini LED backlight panel image to be detected and the reference template image to obtain a difference image, wherein the coordinates of each Mini LED in the Mini LED backlight panel image to be detected and the corresponding Mini LED in the reference template image are the same.

[0080] Typically, a Mini LED backlight panel includes multiple Mini LEDs, sometimes even tens of thousands. These Mini LEDs are evenly arranged in the backlight panel and emit light when powered on. However, if a Mini LED is defective, it may not emit light, emit too much light, or emit too little light after power is applied. Clearly, such defective Mini LEDs will affect the display effect of the backlight panel. To make defect detection more accurate, in this embodiment, after acquiring the image of the Mini LED backlight panel to be detected, a difference operation is performed between this image and a reference template image (i.e., the image corresponding to a normally emitting Mini LED backlight panel) to obtain a difference image.

[0081] Furthermore, considering that Mini LED backlight panels of different specifications have different sizes, the number of Mini LEDs they contain also varies, and the arrangement, row spacing, and column spacing of each Mini LED in the backlight panel also differ. To make the above differential calculation meaningful, in this embodiment, the coordinates of each Mini LED in the Mini LED backlight panel image to be detected are the same as the coordinates of the corresponding Mini LED in the reference template image, that is, the specifications of the Mini LED backlight panel to be detected and the backlight panel corresponding to the reference template image are consistent.

[0082] The following describes the process of obtaining the reference template image:

[0083] The first step is to create a reference template image based on a normally emitting backlight panel.

[0084] It should be noted here that, see Figure 3 As shown, the luminous brightness and luminous area of ​​the multiple MiniLEDs included in the backlight panel that are emitting light normally are all the same, that is, the multiple MiniLEDs included in the backlight panel that are emitting light normally have all achieved the ideal luminous brightness.

[0085] In addition, since the placement angle of the backlight panel affects the row and column spacing in the corresponding image, the placement angle of the backlight panel can be detected and corrected using detection equipment before creating the reference template image.

[0086] Specifically, first obtain the angle between the normally emitting backlight panel and the horizontal plane. If the angle is not zero, rotate the backlight panel until the angle is zero. The rotation angle value is determined based on the coordinates of at least two Mini LEDs in the backlight panel, and the at least two Mini LEDs are located in different columns. That is, the angle value is determined based on the coordinates of Mini LEDs in different columns of the backlight panel. For example, this angle value can be obtained by formula (1).

[0087]

[0088] In formula (1), α is the angle value mentioned above, and x 1,N y 1,N It is the coordinate of the Mini LED located in the first row and Nth column, x 1,1 y 1,1 These are the coordinates of the Mini LED located in the first row and first column. After determining the above angle values, rotate the backlight panel in the opposite direction by an angle α.

[0089] Next, the image containing the rotated backlight panel is converted to grayscale to obtain a reference template image. That is, the pixel values ​​in the above reference template image are between 0 and 255, but only the brightness of the image needs to be considered.

[0090] Additionally, it should be noted that, for the same reason, the placement angle of the Mini LED backlight panel to be tested also affects the spacing between rows and columns in the corresponding image. During the testing process, the Mini LED backlight panel to be tested can be rotated in the same way to obtain an image of the Mini LED backlight panel to be tested with zero angle to the horizontal plane. That is, the image of the Mini LED backlight panel to be tested is taken when the angle between the Mini LED backlight panel to be tested and the horizontal plane is zero.

[0091] The second step is to determine the row spacing and column spacing between every two Mini LEDs in the reference template image, as well as the standard LED bead area for each Mini LED.

[0092] During implementation, after creating the reference template image, it is necessary to further calculate the row spacing and column spacing between every two MiniLEDs, as well as the standard lamp bead area of ​​each MiniLED.

[0093] Since the coordinates of each Mini LED in the Mini LED backlight panel image to be tested are the same as those of the corresponding Mini LED in the reference template image, once the row spacing and column spacing in the reference template image are determined, the position of any Mini LED in the Mini LED backlight panel image to be tested can be calculated based on these row spacing and column spacing. Similarly, once the standard lamp bead area of ​​each Mini LED in the reference template image is determined, the Mini LED in the Mini LED backlight panel image to be tested can be judged based on the standard lamp bead area to determine whether the Mini LED emits light normally, i.e., whether it is a defective Mini LED.

[0094] The following sections will explain the process of obtaining row spacing, column spacing, and the area of ​​a standard LED bead, in different scenarios:

[0095] Case 1: Determine the row spacing and column spacing between every two Mini LEDs in the reference template image, including:

[0096] (1) Obtain multiple center coordinates of multiple Mini LEDs contained in at least two rows or at least two columns in the reference template image, wherein each center coordinate includes a center horizontal coordinate and a center vertical coordinate.

[0097] (2) Calculate the row spacing value between the center ordinates of any two adjacent Mini LEDs, weight the obtained row spacing values, and calculate the row spacing based on the weighted sum of row spacing and the number of Mini LEDs.

[0098] (3) Calculate the column spacing value between the center horizontal coordinates of any two adjacent Mini LEDs respectively, perform weighted processing on the obtained column spacing values, and calculate the column spacing based on the weighted sum of column spacing and the number of Mini LEDs.

[0099] The row spacing and column spacing mentioned above can be obtained using formula (2).

[0100]

[0101] In formula (2), MeanH is the row spacing, MeanW is the column spacing, and x 2,j It is the x-coordinate of the center of the MiniLED located in the second row and j-th column, x 1,j It is the y-coordinate of the center of the Mini LED located in the first row and j-th column. i,2 The y-coordinate is the center coordinate of the Mini LED located in the i-th row and 2nd column. i,2 x is the ordinate of the center of the Mini LED located in the i-th row and first column. 2,j -x 1,jFor the column spacing value mentioned above, y i,2 -y i,1 The above row spacing value is N, which is half the number of Mini LEDs used in the column spacing calculation, and M is half the number of Mini LEDs used in the row spacing calculation.

[0102] Case 2: Determine the standard LED bead area for each Mini LED in the reference template image, including:

[0103] 1) Obtain the area of ​​each Mini LED in the reference template image.

[0104] 2) Sum the areas of each LED bead. Based on the total area of ​​the LED beads obtained after summation and the total number of MiniLEDs, calculate the standard LED bead area.

[0105] The row spacing and column spacing mentioned above can be obtained using formula (3).

[0106]

[0107] Where MeanS is the standard LED area, S i,j Let M be the area of ​​the Mini LED in the i-th row and j-th column, and M and N be the number of rows and columns of the Mini LED, respectively.

[0108] It should be noted that the reference template image can be acquired by the computing device, or it can be acquired by other devices and then sent to the computing device. After acquiring the reference template image and the image of the Mini LED backlight panel to be inspected, the subsequent inspection process can be performed. Specifically, the image of the Mini LED backlight panel to be inspected and the reference template image are subjected to a difference operation to obtain a difference image. See [link to relevant documentation]. Figure 4 As shown, it includes:

[0109] Step 2011: For any defect type, the Mini LED backlight panel image to be inspected is binarized according to the grayscale threshold corresponding to the defect type to obtain the binary image to be inspected.

[0110] During implementation, for any defect type, the Mini LED backlight panel image to be inspected is binarized according to the grayscale threshold corresponding to the defect type to obtain the binary image to be inspected. That is, the above-mentioned binary image to be inspected is a black and white image with pixel values ​​including only 0 or 255.

[0111] Specifically, for the "exploded" defect type, the Mini LED backlight panel image to be inspected is binarized according to the grayscale threshold corresponding to the "exploded" defect type to obtain the "exploded" binary image to be inspected; for the "extinguished" defect type, the Mini LED backlight panel image to be inspected is binarized according to the grayscale threshold corresponding to the "extinguished" defect type to obtain the "extinguished" binary image to be inspected; for the "weak brightness" defect type, the Mini LED backlight panel image to be inspected is binarized according to the grayscale threshold corresponding to the "weak brightness" defect type to obtain the "weak brightness" binary image to be inspected.

[0112] The grayscale thresholds here are mainly divided into: saturated grayscale threshold, off-light grayscale threshold, and low-light grayscale threshold. Typically, the saturated grayscale threshold ranges from 100 to 150 pixels, the off-light grayscale threshold ranges from 200 to 230 pixels, and the low-light grayscale threshold ranges from 50 to 70 pixels.

[0113] Step 2012: Perform a difference operation based on the binary image to be inspected and the reference template image to obtain the difference image corresponding to any defect type.

[0114] After obtaining the binary image to be inspected, a difference operation is performed between it and the reference template image. In this way, the normally emitting Mini LEDs in the Mini LED backlight panel image to be inspected can be ignored, thereby reducing the amount of computation in the inspection process.

[0115] For the process of obtaining the difference image corresponding to any defect type as described above, please refer to [link / reference]. Figure 5 As shown, it includes:

[0116] Step 20121: If the grayscale threshold is the same as the explosion lamp grayscale threshold, then perform a forward difference operation between the binary image to be inspected and the reference template image to obtain the difference image corresponding to the explosion lamp defect type.

[0117] During implementation, if the grayscale threshold is the same as the burst lamp grayscale threshold, that is, the grayscale threshold falls within the range of 100-150 pixel values, the binary image to be inspected and the reference template image are subjected to forward difference operation, that is, the binary image to be inspected and the reference template image are subjected to forward difference operation to obtain the difference image corresponding to the burst lamp defect type.

[0118] Step 20122: If the grayscale threshold is the same as the lamp-off grayscale threshold, then perform an inverse difference operation between the binary image to be inspected and the reference template image to obtain the difference image corresponding to the lamp-off defect type.

[0119] During implementation, if the grayscale threshold is the same as the light-off grayscale threshold, that is, the grayscale threshold falls within the range of 200-230 pixel values, the binary image to be inspected and the reference template image are subjected to inverse difference operation, that is, the reference template image and the light-off binary image to be inspected are subjected to forward difference operation to obtain the difference image corresponding to the light-off defect type.

[0120] Step 20123: If the grayscale threshold is the weak brightness grayscale threshold, then perform a forward difference operation on the binary image to be inspected and the difference image corresponding to the light-off defect type to obtain the difference image corresponding to the weak brightness defect type.

[0121] During implementation, if the grayscale threshold is a weak brightness grayscale threshold, i.e., the grayscale threshold falls within the range of 50-70 pixel values, a forward difference operation is performed between the binary image to be inspected and the difference image corresponding to the lamp-out defect type. This involves performing a forward difference operation between the lamp-out binary image to be inspected and the reference template image to obtain the result image, and then performing a forward difference operation between the binary image to be inspected and the result image to obtain the difference image corresponding to the weak brightness defect type. The purpose of using two difference operations in obtaining the difference image corresponding to the weak brightness defect type is to eliminate the influence of the lamp-out defect on the weak brightness defect.

[0122] Step 202: For any Mini LED in the differential image, match the area of ​​any Mini LED with the area of ​​the LED corresponding to each defect type. If there is a matching LED area, then take the defect type corresponding to the matching LED area as the defect type of any Mini LED.

[0123] During implementation, the method for determining whether any Mini LED in the differential image is a defective Mini LED is to match its light-emitting area with the area of ​​the LED corresponding to each defect type.

[0124] First, let's introduce how to obtain the LED chip area corresponding to each of the above defect types. Specifically, the LED chip area corresponding to each defect type is determined using the following methods:

[0125] Method 1: Based on the standard LED bead area and the preset explosion defect discrimination ratio, determine the preset explosion area and use the preset explosion area as the LED bead area corresponding to the explosion defect type.

[0126] It should be noted that the preset burst lamp defect discrimination ratio is between 0.2 and 0.5. When the light-emitting area of ​​the Mini LED in the Mini LED backlight panel image to be tested is greater than the product of the standard lamp bead area and the preset burst lamp defect discrimination ratio, the defect type of the Mini LED is determined to be burst lamp, and the preset burst lamp area is taken as the lamp bead area corresponding to the burst lamp defect type.

[0127] Method 2: Based on the standard LED area and the preset lamp-extinguishing defect discrimination ratio, determine the preset lamp-extinguishing area, and use the preset lamp-extinguishing area as the LED area corresponding to the lamp-extinguishing defect type.

[0128] It should be noted that the preset lamp-off defect discrimination ratio is between 0.7 and 0.9. When the light-emitting area of ​​the Mini LED in the Mini LED backlight panel image to be tested is greater than the product of the standard lamp bead area and the preset lamp-off defect discrimination ratio, the defect type of the Mini LED is determined to be lamp-off, and the preset lamp-off area is taken as the lamp bead area corresponding to the lamp-off defect type.

[0129] Method 3: Based on the standard LED area and the preset weak brightness defect discrimination ratio, determine the preset weak brightness area, and use the preset weak brightness area as the LED area corresponding to the weak brightness defect type.

[0130] It should be noted that the preset weak brightness defect discrimination ratio is between 0.5 and 0.7. When the light-emitting area of ​​the Mini LED in the Mini LED backlight panel image to be detected is less than the product of the standard lamp bead area and the preset weak brightness defect discrimination ratio, the defect type of the Mini LED is determined to be weak brightness, and the preset weak brightness area is taken as the lamp bead area corresponding to the weak brightness defect type.

[0131] The standard LED area is the luminous area of ​​any normally emitting Mini LED in the reference template image, which is the standard LED area obtained during the process of creating the reference template image.

[0132] For any Mini LED in the differential image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type, including:

[0133] After obtaining the LED area corresponding to defect types such as bursting, extinguishing, and weak brightness, for any Mini LED in any differential image, the area of ​​any Mini LED is matched with the LED area corresponding to each defect type. Specifically, if the area of ​​any Mini LED matches the preset bursting area, bursting is taken as the defect type of any Mini LED; if the area of ​​any Mini LED matches the preset extinguishing area, extinguishing is taken as the defect type of any Mini LED; and if the area of ​​any Mini LED matches the preset weak brightness area, weak brightness is taken as the defect type of any Mini LED.

[0134] Step 203: Based on the row spacing and column spacing of the Mini LEDs corresponding to the reference template image, determine the position of any Mini LED in the difference image.

[0135] During implementation, after determining the defect type of any Mini LED in the Mini LED backlight panel image to be inspected, it is also necessary to determine the location of the Mini LED identified as defective. (See [link to relevant documentation]). Figure 6 As shown, it includes:

[0136] Step 2031: Based on row spacing, vertical distance, and reference ordinate, determine the row value of any MiniLED identified as a defect in the differential image.

[0137] During implementation, after determining the reference ordinate of the reference origin in the differential image, and the longitudinal distance of any Mini LED identified as a defect from the reference ordinate, the row value of any Mini LED identified as a defect in the differential image can be obtained by dividing the longitudinal distance by the row spacing, i.e., which row the Mini LED is located in in the differential image.

[0138] Step 2032: Based on the column spacing, horizontal distance, and reference horizontal coordinate, determine the column value of any MiniLED identified as a defect in the differential image.

[0139] During implementation, after determining the reference abscissa of the reference origin in the differential image, and the lateral distance of any Mini LED identified as a defect from the reference abscissa, the column value of any Mini LED identified as a defect in the differential image can be obtained by dividing the lateral distance by the column spacing, that is, which column the Mini LED is located in in the differential image.

[0140] The row and column values ​​mentioned above can be obtained using formula (4).

[0141]

[0142] In formula (4), DC is the column value of any Mini LED that is determined to be defective, ceil is the round-up function, DR is the row value of any Mini LED that is determined to be defective, and x 1,1 y 1,1 For reference x and y coordinates, Dx is the horizontal distance, Dy is the vertical distance, MeanH is the row spacing, and MeanW is the column spacing.

[0143] It should be noted that the row spacing and column spacing mentioned above are data obtained during the creation of the reference template image, while the horizontal distance, vertical distance, reference horizontal coordinate, and reference vertical coordinate are data obtained by the computing device in the difference image.

[0144] Specifically, the row spacing is the vertical distance between two adjacent Mini LEDs in the reference template image, the column spacing is the horizontal distance between two adjacent Mini LEDs in the reference template image, the vertical distance is the vertical distance of any Mini LED identified as a defect relative to the reference origin in the differential image, the horizontal distance is the horizontal distance of any Mini LED identified as a defect relative to the reference origin in the differential image, the reference ordinate is the ordinate of the reference origin in the differential image, and the reference abscissa is the abscissa of the reference origin in the differential image.

[0145] Furthermore, in the Mini LED backlight panel to be tested, each Mini LED is controlled by a connected LED switch. Typically, these switches are evenly distributed in the backlight panel image, and one switch controls multiple Mini LEDs. Especially when a Mini LED is identified as defective, it's possible that the Mini LED itself is not defective, but the LED switch connected to it is faulty. In this case, determining the position of the LED switch becomes even more crucial. After determining the position of any Mini LED in the differential image based on the row and column spacing of the Mini LEDs corresponding to the reference template image, refer to... Figure 7 As shown, it also includes:

[0146] Step 2041: Obtain the total number of rows and columns of LED switches. Each LED switch controls the on / off state of at least one Mini LED. The LED switches are evenly arranged within a rectangle formed by at least one LED connected to each switch on both the reference template image and the Mini LED backlight panel to be tested. (See [reference]). Figure 8 As shown.

[0147] First, it should be noted that in the Mini LED backlight panel image to be tested, each LED switch controls the on / off state of at least one Mini LED. The number of Mini LEDs controlled by the LED switch varies depending on the specifications of the Mini LED backlight panel, usually 4-9. The above multiple LEDs and LED switches form a rectangle, that is, multiple LEDs are evenly arranged in multiple rows and columns on the backlight panel.

[0148] Since the LED switches are evenly arranged on the reference template image and the Mini LED backlight panel to be tested, in order to determine the position of the LED switch corresponding to any Mini LED during the implementation process, it is necessary to first obtain the total number of rows and columns of the LED switches.

[0149] Step 2042: Determine the switch row value of any Mini LED that is determined to be defective based on the total number of rows of LED beads, the row value of any Mini LED that is determined to be defective, and the total number of rows of switches.

[0150] During implementation, after obtaining the total number of rows of LED beads and the total number of rows of switches, the row value of the switch can be determined by using the row value of any Mini LED that is determined to be defective. For example, the row value of the switch can be obtained by multiplying the total number of rows of switches by the row value of any Mini LED that is determined to be defective, and then dividing by the total number of rows of LED beads.

[0151] Step 2043: Determine the switch column value of any Mini LED that is determined to be defective based on the total number of LED columns, the column value of any Mini LED that is determined to be defective, and the total number of switch columns.

[0152] During implementation, after obtaining the total number of rows of LED beads and the total number of rows of switches, the row value of the switch can be determined by using the row value of any Mini LED that is determined to be defective. For example, the row value of the switch can be obtained by multiplying the total number of rows of switches by the row value of any Mini LED that is determined to be defective, and then dividing by the total number of rows of LED beads.

[0153] The row value and column value of the switch can be obtained by formula (5).

[0154]

[0155] In formula (5), ICR is the switch row value, ICC is the switch column value, ceil is the round-up function, DR is the row value of any Mini LED that is determined to be defective, DC is the column value of any Mini LED that is determined to be defective, M is the total number of LED rows, N is the total number of LED columns, m is the total number of switch rows, and n is the total number of switch columns.

[0156] It should be noted that the total number of rows of LED beads, the total number of columns of LED beads, and the total number of rows of switches mentioned above are data obtained by the computing device from the reference template image.

[0157] Specifically, the total number of rows of LED beads is the sum of the number of rows of each Mini LED distributed in the reference template image, and the total number of columns of LED beads is the sum of the number of columns of each Mini LED distributed in the reference template image.

[0158] Based on the same inventive concept, see [reference] Figure 9 As shown in the figure, this application provides a defect detection device for a Mini LED backlight panel, comprising:

[0159] The differential unit 910 is used to perform a differential operation on the image of the Mini LED backlight panel to be detected and the reference template image to obtain a differential image, wherein the coordinates of each Mini LED in the image of the Mini LED backlight panel to be detected are the same as the coordinates of the corresponding Mini LED in the reference template image.

[0160] The matching unit 920 is used to match the area of ​​any Mini LED in the differential image with the area of ​​the LED corresponding to each defect type. If there is a matching LED area, the defect type corresponding to the matching LED area is taken as the defect type of any Mini LED.

[0161] The determining unit 930 is used to determine the position of any Mini LED in the differential image based on the row spacing and column spacing of the Mini LEDs corresponding to the reference template image.

[0162] Optionally, the image of the Mini LED backlight panel to be tested is taken when the angle between the Mini LED backlight panel to be tested and the horizontal plane is zero.

[0163] Optionally, the area of ​​the LED corresponding to each defect type can be determined in the following ways:

[0164] Based on the standard LED bead area and the preset explosion defect discrimination ratio, the preset explosion area is determined, and the preset explosion area is used as the LED bead area corresponding to the explosion defect type.

[0165] Based on the standard LED area and the preset lamp-extinguishing defect discrimination ratio, the preset lamp-extinguishing area is determined, and the preset lamp-extinguishing area is used as the LED area corresponding to the lamp-extinguishing defect type.

[0166] Based on the standard LED bead area and the preset weak brightness defect discrimination ratio, the preset weak brightness area is determined, and the preset weak brightness area is used as the LED bead area corresponding to the weak brightness defect type.

[0167] The standard LED area is the luminous area corresponding to any normally emitting Mini LED in the reference template image.

[0168] Optionally, the image of the Mini LED backlight panel to be detected is compared with the reference template image to obtain a difference image, including:

[0169] For any defect type, the Mini LED backlight panel image to be inspected is binarized according to the grayscale threshold corresponding to the defect type to obtain the binary image to be inspected.

[0170] By performing a difference operation between the binary image to be inspected and the reference template image, a difference image corresponding to any defect type can be obtained.

[0171] Optionally, for any Mini LED in the differential image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type, including:

[0172] For any Mini LED in any differential image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type.

[0173] Optionally, a difference operation is performed based on the binary image to be inspected and the reference template image to obtain a difference image corresponding to any defect type, including:

[0174] If the grayscale threshold is the same as the grayscale threshold for a burst lamp, then the binary image to be inspected and the reference template image are subjected to forward difference operation to obtain the difference image corresponding to the burst lamp defect type.

[0175] If the grayscale threshold is the same as the grayscale threshold for lamp extinguishing, then the binary image to be inspected and the reference template image are subjected to inverse difference operation to obtain the difference image corresponding to the lamp extinguishing defect type.

[0176] If the grayscale threshold is the weak brightness grayscale threshold, then the binary image to be inspected and the difference image corresponding to the lamp-off defect type are subjected to forward difference operation to obtain the difference image corresponding to the weak brightness defect type.

[0177] Optionally, based on the row and column spacing of the Mini LEDs corresponding to the reference template image, the position of any Mini LED in the difference image is determined, including:

[0178] Based on row spacing, vertical distance, and reference ordinate, determine the row value of any Mini LED identified as defective in the differential image; and

[0179] Based on column spacing, lateral distance, and reference abscissa, determine the column value of any Mini LED identified as a defect in the differential image;

[0180] Wherein, row spacing is the vertical distance between two adjacent Mini LEDs in the reference template image, column spacing is the horizontal distance between two adjacent Mini LEDs in the reference template image, vertical distance is the vertical distance of any Mini LED determined to be defective relative to the reference origin in the differential image, horizontal distance is the horizontal distance of any Mini LED determined to be defective relative to the reference origin in the differential image, reference ordinate is the ordinate of the reference origin in the differential image, and reference abscissa is the abscissa of the reference origin in the differential image.

[0181] Optionally, after determining the position of any Mini LED in the difference image based on the row spacing and column spacing of the Mini LEDs corresponding to the reference template image, the method further includes:

[0182] Obtain the total number of rows and columns of LED switches, wherein each LED switch controls the on / off state of at least one Mini LED, and the LED switches are uniformly arranged in the rectangle formed by at least one LED connected to the LED switch on both the reference template image and the Mini LED backlight panel to be detected.

[0183] The switch row value of any Mini LED that is determined to be defective is determined based on the total number of rows of LED beads, the row value of any Mini LED that is determined to be defective, and the total number of switch rows.

[0184] The switch column value of any Mini LED that is determined to be defective is determined based on the total number of LED columns, the column value of any Mini LED that is determined to be defective, and the total number of switch columns.

[0185] The total number of rows of LED beads is the sum of the number of rows of each Mini LED distributed in the reference template image, and the total number of columns of LED beads is the sum of the number of columns of each Mini LED distributed in the reference template image.

[0186] Based on the same inventive concept, see [reference] Figure 10 As shown, this disclosure provides a terminal, including:

[0187] Memory 1001 is used to store executable instructions;

[0188] Processor 1002 is configured to read and execute executable instructions stored in memory to implement the method as described in any of the first aspects.

[0189] Among them, Figure 10 In this context, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits together, represented by one or more processors (processor 1002) and memory (memory 1001). The bus architecture may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver may be multiple components, including transmitters and transceivers, providing a unit for communicating with various other devices over a transmission medium. Processor 1002 is responsible for managing the bus architecture and general processing, and memory 1001 may store data used by processor 1002 during operation.

[0190] The processor 1002 is responsible for managing the bus architecture and general processing, while the memory 1001 can store the data used by the processor 1000 when performing operations.

[0191] The memory 1001 and processor 1002 cooperate with each other to implement any one of the methods executed by the computing device in steps 201-203 of the above embodiments, which will not be described in detail here.

[0192] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium that, when the instructions in the storage medium are executed by a processor, enables the processor to perform the method described in any of the first aspects above.

[0193] In summary, this application discloses a defect detection method for a Mini LED backlight panel, applied to a computing device. The method includes: performing a difference operation between an image of the Mini LED backlight panel to be detected and a reference template image to obtain a difference image. It should be noted that the coordinates of each Mini LED in the image of the Mini LED backlight panel to be detected and the corresponding Mini LED in the reference template image are the same. Thus, for any Mini LED in the difference image, the area of ​​any Mini LED is matched with the area of ​​the LED corresponding to each defect type. If a matching LED area exists, the defect type corresponding to the matching LED area is taken as the defect type of any Mini LED. Furthermore, based on the row and column spacing of the Mini LEDs corresponding to the Mini LEDs in the reference template image, the position of any Mini LED in the difference image is determined. This allows for the rapid and accurate acquisition of the defect type and position of the defective Mini LED in the image of the Mini LED backlight panel to be detected, thereby improving the defect detection efficiency and accuracy.

[0194] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program product systems. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product system implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0195] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program product systems according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0196] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0197] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0198] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for defect detection of a Mini LED backlight panel, characterized in that, Applied to a computing device, the method comprises: For any one defect type, the Mini LED backlight panel image to be detected is binarized according to the gray threshold corresponding to the defect type to obtain a to-be-detected binary image; if the gray threshold is a blown lamp gray threshold, the to-be-detected binary image is subjected to forward difference operation with the reference template image to obtain the difference image corresponding to the blown lamp defect type; if the gray threshold is an extinguished lamp gray threshold, the to-be-detected binary image is subjected to reverse difference operation with the reference template image to obtain the difference image corresponding to the extinguished lamp defect type; if the gray threshold is a weak light gray threshold, the to-be-detected binary image corresponding to the extinguished lamp defect type is subjected to forward difference operation with the reference template image to obtain a result image, and then the to-be-detected binary image is subjected to forward difference operation with the result image to obtain the difference image corresponding to the weak light defect type, wherein the coordinates of each Mini LED in the Mini LED backlight panel image to be detected and the corresponding Mini LED in the reference template image are the same; For any one Mini LED in the difference image, the area of the Mini LED is matched with the lamp bead area corresponding to each defect type, and if there is a matching lamp bead area, the defect type corresponding to the matching lamp bead area is taken as the defect type of the Mini LED; Based on the row spacing and column spacing of the Mini LED corresponding to the reference template image, the position of the Mini LED in the difference image is determined.

2. The method of claim 1, wherein, The Mini LED backlight panel image to be detected is obtained when the angle between the Mini LED backlight panel to be detected and the horizontal plane is zero.

3. The method of claim 1, wherein, The lamp bead area corresponding to each defect type is determined in the following manner: Based on the standard lamp bead area and a preset blown lamp defect discrimination ratio, a preset blown lamp area is determined, and the preset blown lamp area is taken as the lamp bead area corresponding to the blown lamp defect type; Based on the standard lamp bead area and a preset extinguished lamp defect discrimination ratio, a preset extinguished lamp area is determined, and the preset extinguished lamp area is taken as the lamp bead area corresponding to the extinguished lamp defect type; Based on the standard lamp bead area and a preset weak light defect discrimination ratio, a preset weak light area is determined, and the preset weak light area is taken as the lamp bead area corresponding to the weak light defect type; The standard lamp bead area is the light-emitting area corresponding to any one Mini LED with normal light emission in the reference template image.

4. The method of claim 3, wherein, The matching of the area of any one Mini LED in the difference image with the lamp bead area corresponding to each defect type comprises: For any one Mini LED in any one difference image, the area of the Mini LED is matched with the lamp bead area corresponding to each defect type.

5. The method according to any one of claims 1 to 4, characterized in that, The position of the arbitrary Mini LED in the differential image is determined based on the row spacing and the column spacing of the Mini LED corresponding to the reference template image, including: determining the row value of the arbitrary Mini LED determined as a defect in the differential image based on the row spacing, the vertical distance, and the reference vertical coordinate; and determining the column value of the arbitrary Mini LED determined as a defect in the differential image based on the column spacing, the horizontal distance, and the reference horizontal coordinate; wherein the row spacing is the vertical distance between two adjacent Mini LEDs in the reference template image, the column spacing is the horizontal distance between two adjacent Mini LEDs in the reference template image, the vertical distance is the vertical distance of the arbitrary Mini LED determined as a defect in the differential image relative to the reference origin, the horizontal distance is the horizontal distance of the arbitrary Mini LED determined as a defect in the differential image relative to the reference origin, the reference vertical coordinate is the vertical coordinate of the reference origin in the differential image, and the reference horizontal coordinate is the horizontal coordinate of the reference origin in the differential image.

6. The method of any one of claims 1 to 4, wherein, After determining the position of the arbitrary Mini LED in the differential image based on the row spacing and the column spacing of the Mini LED corresponding to the reference template image, the method further includes: obtaining the total number of rows and the total number of columns of the lamp bead switches, wherein each lamp bead switch controls the on-off of at least one Mini LED, and the lamp bead switches are uniformly arranged in the rectangle formed by the at least one lamp bead in the reference template image and the Mini LED backlight panel to be detected; determining the switch row value to which the arbitrary Mini LED determined as a defect belongs based on the total number of rows of the lamp bead, the row value of the arbitrary Mini LED determined as a defect, and the total number of rows of the switch; determining the switch column value to which the arbitrary Mini LED determined as a defect belongs based on the total number of columns of the lamp bead, the column value of the arbitrary Mini LED determined as a defect, and the total number of columns of the switch; wherein the total number of rows of the lamp bead is the total number of rows of the lamp bead distributed by each Mini LED in the reference template image, and the total number of columns of the lamp bead is the total number of columns of the lamp bead distributed by each Mini LED in the reference template image. 7.A defect detection device of a Mini LED backlight panel, characterized in that, including: The difference unit is configured to, for any one defect type, perform binaryzation processing on the Mini LED backlight panel image to be detected according to a gray threshold corresponding to the defect type, to obtain a to-be-detected binary image, if the gray threshold is a lamp explosion gray threshold, perform forward difference operation on the to-be-detected binary image and the reference template image, to obtain the difference image corresponding to the lamp explosion defect type, if the gray threshold is an extinguished lamp gray threshold, perform reverse difference operation on the to-be-detected binary image and the reference template image, to obtain the difference image corresponding to the extinguished lamp defect type, if the gray threshold is a weak light gray threshold, perform forward difference operation on the to-be-detected binary image corresponding to the extinguished lamp defect type and the reference template image, to obtain a result image, and then perform forward difference operation on the to-be-detected binary image and the result image, to obtain the difference image corresponding to the weak light defect type, wherein coordinates of each Mini LED in the Mini LED backlight panel image to be detected and coordinates of a corresponding Mini LED in the reference template image are the same. The matching unit is configured to, for any one Mini LED in the difference image, match an area of the any one Mini LED with areas of lamp beads corresponding to each defect type respectively, if there is a matched lamp bead area, take a defect type corresponding to the matched lamp bead area as a defect type of the any one Mini LED. The determination unit is configured to determine a position of the any one Mini LED in the difference image based on row spacing and column spacing of Mini LEDs corresponding to the reference template image.

8. A terminal, characterized by comprising: The memory is configured to store executable instructions. The processor is configured to read and execute the executable instructions stored in the memory, to implement the method in any one of claims 1-6. When the instructions in the storage medium are executed by the processor, the processor can execute the method in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, ​

Images