MiniLED cold solder joint detection method, device, equipment and medium

Abstract

This application relates to the field of detection technology, and in particular to a method, apparatus, device, and medium for detecting Mini LED solder joint defects. The method includes acquiring a detection image, which is an X-ray scan of a Mini LED panel; segmenting the detection image to obtain sub-images of the corresponding region for each Mini LED chip in the detection image, each sub-image including the Mini LED chip and the corresponding soldering medium; determining the grayscale distribution information corresponding to each sub-image, the grayscale distribution information including the grayscale value of each coordinate point in the corresponding sub-image; determining the soldering quality of each Mini LED chip based on the grayscale distribution information corresponding to each sub-image, the soldering quality including acceptable and defective solder joints; and determining the location of each Mini LED chip with a defective solder joint. This application can improve the accuracy of solder joint defect detection.

Description

Technical Field

[0001] This application relates to the field of testing technology, and in particular to a method, apparatus, equipment and medium for detecting Mini LED solder joint defects. Background Technology

[0002] Mini LED technology is a new type of display technology that uses smaller LED chips as the backlight source, building upon traditional LED backlighting. Compared to traditional LED backlighting, Mini LED allows for more precise light control. Furthermore, because it uses smaller LED chips, it boasts higher pixel density and more uniform light emission, resulting in higher contrast, richer colors, and better reliability. A Mini LED panel typically consists of Mini LED chips, packaging materials, a PCB substrate, connecting lines, and driver circuitry. The Mini LED chips and other components are fixed to the PCB substrate using soldering technology. During the manufacturing process of Mini LED panels, improper control of parameters such as temperature, pressure, or time during the soldering process between the Mini LED chips and the PCB substrate can lead to problems such as missing solder joints, insufficient solder, and porosity. Poor soldering can cause the Mini LED chips to malfunction, resulting in uneven brightness or areas of the display screen that are not visible.

[0003] In related technologies, image acquisition equipment and image processing algorithms are used to detect and analyze solder joints on Mini LED panels, detecting features such as shape, color, and location of the solder joints. Combined with preset criteria for detecting cold solder joints, the presence of such issues is determined. However, the detection results are affected by factors such as image quality, lighting conditions, and camera parameters. Furthermore, the images cannot reveal potential structural problems within the solder joints, potentially leading to misjudgments or missed detections of cold solder joints. Therefore, improving the accuracy of cold solder joint detection is a pressing issue that needs to be addressed. Summary of the Invention

[0004] To improve the accuracy of solder joint detection, this application provides a method, apparatus, equipment, and medium for detecting solder joint defects in Mini LEDs.

[0005] Firstly, this application provides a method for detecting poor solder joints in Mini LEDs, employing the following technical solution:

[0006] A method for detecting poor solder joints in Mini LEDs, comprising:

[0007] Acquire a detection image, wherein the detection image is an X-ray scan of a Mini LED panel;

[0008] The detection image is segmented to obtain a sub-image of the corresponding region of each Mini LED chip in the detection image, and the sub-image includes the Mini LED chip and the corresponding welding medium.

[0009] Determine the grayscale distribution information corresponding to each of the sub-images, wherein the grayscale distribution information includes the grayscale value of each coordinate point in the corresponding sub-image;

[0010] Based on the grayscale distribution information corresponding to each sub-image, the welding quality of each Mini LED chip is determined, and the welding quality includes qualified and poor solder joints;

[0011] The location of each Mini LED chip with a poor solder joint is determined.

[0012] By employing the above technical solution, an inspection image of the Mini LED panel is acquired and segmented to obtain a sub-image of the corresponding region for each Mini LED chip in the inspection image. Then, by analyzing the grayscale value of each coordinate point in the sub-image, the grayscale distribution information corresponding to each sub-image is determined. Based on the grayscale distribution information, the welding quality of each Mini LED chip can be judged, determining whether it is qualified or has a poor weld, and the location of the poorly welded Mini LED chip can be determined. This method can detect the welding quality of each Mini LED chip on the Mini LED panel, thereby improving the accuracy of poor weld detection.

[0013] In one possible implementation, segmenting the detected image to determine a sub-image for each Mini LED chip includes:

[0014] Obtain welding information for the Mini LED panel, including the welding position and standard area of ​​each Mini LED chip, wherein the standard area is the area around the Mini LED chip where a preset welding medium is distributed;

[0015] Based on the welding information of the Mini LED panel, chip segmentation parameters are determined, which are used to characterize the segmentation area of ​​a single Mini LED chip.

[0016] Based on the chip segmentation parameters, the detected image is segmented to determine the sub-image of each Mini LED chip.

[0017] By employing the above technical solution, the welding position and standard area of ​​each Mini LED chip on the Mini LED panel are obtained. The standard area is the region around the Mini LED chip where the pre-defined welding medium is distributed. Based on this information, the segmentation region of each Mini LED chip, i.e., the chip segmentation parameters, can be determined. Then, based on these chip segmentation parameters, the detection image is segmented, thereby accurately determining the sub-image of each Mini LED chip. This allows for better segmentation of sub-images based on the welding information of the Mini LED panel, thus improving the accuracy of detection. By accurately determining the sub-image of each Mini LED chip, the grayscale distribution information of each chip can be analyzed more precisely, thereby judging the welding quality and detecting cold solder joints, improving the accuracy and reliability of Mini LED cold solder joint detection.

[0018] In one possible implementation, determining the welding quality of each Mini LED chip based on the grayscale distribution information corresponding to each sub-image includes:

[0019] Determine the standard grayscale distribution information corresponding to the sub-image;

[0020] Based on the standard grayscale distribution information and the grayscale distribution information corresponding to each sub-image, a standard similarity of each sub-image is determined. The standard similarity is used to characterize the degree of overlap between the grayscale distribution information of the corresponding sub-image and the standard grayscale distribution information.

[0021] When the standard similarity of any sub-image is greater than a preset threshold, the welding quality of the MiniLED chip corresponding to any sub-image is determined to be qualified.

[0022] If the standard similarity of any sub-image is less than or equal to a preset threshold, then the welding quality of the Mini LED chip corresponding to any sub-image is determined to be a poor weld.

[0023] By employing the above technical solution, the standard grayscale distribution information corresponding to each sub-image is determined as a reference. Then, the grayscale distribution information corresponding to each sub-image is compared and analyzed with the standard grayscale distribution information to calculate the standard similarity. For any sub-image, if its standard similarity is greater than a preset threshold, the welding quality of the Mini LED chip corresponding to that sub-image is determined to be qualified. If the standard similarity of the sub-image is less than or equal to the preset threshold, the welding quality of the Mini LED chip corresponding to that sub-image is determined to be a cold solder joint. The welding quality of the Mini LED chip can be judged based on the similarity of the grayscale distribution information, enabling more accurate detection of cold solder joints. Furthermore, by setting an appropriate threshold, the criteria for determining qualified and cold solder joints can be flexibly controlled.

[0024] In one possible implementation, determining the standard grayscale distribution information corresponding to the sub-image includes:

[0025] Based on the grayscale distribution information corresponding to each of the sub-images, a grayscale set corresponding to each of the multiple target coordinate points is determined. The grayscale set includes the grayscale value of the corresponding target coordinate point in the grayscale distribution information of each of the sub-images. The target coordinate point is determined according to the model size and standard area of ​​the Mini LED chip. The standard area is the area around the Mini LED chip where the preset welding medium is distributed.

[0026] Determine a target gray value for each of the grayscale sets, wherein the target gray value is the mode of the corresponding grayscale set;

[0027] The target grayscale values ​​corresponding to each target coordinate point are summarized to determine the standard grayscale distribution information.

[0028] By adopting the above technical solution, firstly, based on the grayscale distribution information corresponding to each sub-image, multiple grayscale sets of target coordinate points are determined. These grayscale sets include the grayscale values ​​of the corresponding target coordinate points in each sub-image. Then, the target grayscale value of each grayscale set is determined, i.e., the mode of the grayscale set. Finally, the target grayscale values ​​corresponding to each target coordinate point are summarized to obtain complete standard grayscale distribution information. This allows for a more accurate comparison of the grayscale distribution of each sub-image, thereby improving the accuracy and reliability of Mini LED cold solder joint detection.

[0029] In one possible implementation, after determining that the soldering quality of the Mini LED chip corresponding to any of the sub-images is a poor solder joint, the method further includes:

[0030] Based on the standard grayscale distribution information, the chip center coordinates are determined;

[0031] Based on the chip center coordinates, determine the target number of dividing lines and multiple coordinate points corresponding to each dividing line;

[0032] Based on multiple coordinate points corresponding to each of the segmentation lines and the grayscale distribution information of any sub-image, the type of poor solder joint of the Mini LED chip corresponding to any sub-image is determined, and the type of poor solder joint includes voids and misalignment.

[0033] By employing the above technical solution and analyzing standard grayscale distribution information, the coordinates of the center point of the Mini LED chip in the sub-image can be determined, i.e., the chip center coordinates. Using the chip center coordinates as the starting point and setting appropriate directions and spacing, multiple dividing lines can be determined, and multiple coordinate points can be identified on each dividing line. Based on the grayscale distribution characteristics and the position of the dividing lines, the types of solder joint defects present in the sub-image can be analyzed. This allows for more accurate identification of solder joint types, enabling a more detailed description of the Mini LED chip's soldering quality issues and providing accurate information for subsequent processing.

[0034] In one possible implementation, determining the target number of dividing lines and multiple coordinate points corresponding to each dividing line based on the chip center coordinates includes:

[0035] Obtain the product usage information of the Mini LED panel, and determine the detection accuracy based on the product usage information;

[0036] Based on the detection accuracy, the segmentation line density is determined;

[0037] Based on the density of the dividing lines and the coordinates of the chip center, a target number of dividing lines and multiple coordinate points corresponding to each dividing line are determined.

[0038] By adopting the above technical solution, product usage information of the Mini LED panel is obtained, and the required testing accuracy is determined based on this information. Then, based on the determined testing accuracy, an appropriate segmentation line density can be determined to accommodate Mini LED panels of different specifications. Based on the chip center coordinates and the segmentation line density, segmentation lines are determined around the chip center coordinates according to a certain direction, number, and spacing. Multiple coordinate points are determined on each segmentation line; these coordinate points are used for further detection and analysis of solder joint defects. By determining the target number of segmentation lines and the corresponding coordinate points for each segmentation line, a more accurate and comprehensive solder joint defect detection area is provided, further improving the accuracy and reliability of Mini LED solder joint defect detection.

[0039] In one possible implementation, determining the solder joint type of the Mini LED chip corresponding to any sub-image based on multiple coordinate points corresponding to each of the segmentation lines and the grayscale distribution information of any sub-image includes:

[0040] Obtain the shape of the Mini LED chip;

[0041] Based on the shape of the Mini LED chip, the center coordinate point, and multiple coordinate points corresponding to each dividing line, at least two reference sets are determined, and each reference set contains at least two coordinate sequences that are in a reference relationship.

[0042] Based on the grayscale distribution information of the at least two control sets and any sub-image, at least two grayscale control groups are determined, and each grayscale control group includes at least two grayscale value sequences that are in a control relationship.

[0043] Several abnormal control groups are determined from the at least two gray value control groups, wherein at least one gray value sequence in the abnormal control group has a change trend that is inconsistent with other gray value sequences in the group;

[0044] Based on the aforementioned abnormal control groups, the type of poor solder joint of the Mini LED chip corresponding to any sub-image is determined.

[0045] By employing the above technical solution, the shape information of the Mini LED chip, namely the shape and outline of the Mini LED, is obtained. Based on the shape of the Mini LED chip, multiple coordinate points corresponding to each dividing line, and the center coordinate point, at least two control sets are determined. Each control set consists of at least two coordinate sequences that are in a comparative relationship, and these coordinate sequences correspond to the shape and layout of the Mini LED. Then, based on the at least two control sets and the grayscale distribution information of any sub-image, at least two grayscale value control groups are determined. Each grayscale value control group consists of at least two grayscale value sequences in a comparative relationship, and these grayscale value sequences correspond one-to-one with the corresponding coordinate sequences. From the at least two grayscale value control groups, several abnormal control groups are determined. In each abnormal control group, at least one grayscale value sequence exhibits a trend inconsistent with the other grayscale value sequences within the group, i.e., it shows a significant difference from other control relationships. Finally, based on the characteristics of the abnormal control groups, it can be determined whether the Mini LED chip has voids or misaligned solder joints, or other types of poor soldering. It can more accurately determine the type of solder joint failure of the Mini LED chip corresponding to any sub-image. By comparing the changing trends in the abnormal control group, it can more reliably identify the solder joint failure of the Mini LED chip, further improving the accuracy and reliability of solder joint failure detection.

[0046] Secondly, this application provides a Mini LED cold solder joint detection device, which adopts the following technical solution:

[0047] A Mini LED cold solder joint detection device, comprising:

[0048] An image acquisition module is used to acquire an image, which is an X-ray scan of a Mini LED panel.

[0049] A sub-image determination module is used to segment the detection image to obtain a sub-image of the corresponding region of each Mini LED chip in the detection image, wherein the sub-image includes the Mini LED chip and the corresponding welding medium;

[0050] A grayscale distribution information determination module is used to determine the grayscale distribution information corresponding to each of the sub-images, wherein the grayscale distribution information includes the grayscale value of each coordinate point in the corresponding sub-image;

[0051] The welding quality determination module is used to determine the welding quality of each Mini LED chip based on the grayscale distribution information corresponding to each sub-image. The welding quality includes qualified and poor solder joints.

[0052] The cold solder joint location determination module is used to determine the location of each Mini LED chip whose soldering quality is cold solder joint.

[0053] By employing the above technical solution, an inspection image of the Mini LED panel is acquired and segmented to obtain a sub-image of the corresponding region for each Mini LED chip in the inspection image. Then, by analyzing the grayscale value of each coordinate point in the sub-image, the grayscale distribution information corresponding to each sub-image is determined. Based on the grayscale distribution information, the welding quality of each Mini LED chip can be judged, determining whether it is qualified or has a poor weld, and the location of the poorly welded Mini LED chip can be determined. This method can detect the welding quality of each Mini LED chip on the Mini LED panel, thereby improving the accuracy of poor weld detection.

[0054] In one possible implementation, when the sub-image determination module segments the detected image to determine the sub-image of each Mini LED chip, it specifically performs the following:

[0055] Obtain welding information for the Mini LED panel, including the welding position and standard area of ​​each Mini LED chip, wherein the standard area is the area around the Mini LED chip where a preset welding medium is distributed;

[0056] Based on the welding information of the Mini LED panel, chip segmentation parameters are determined, which are used to characterize the segmentation area of ​​a single Mini LED chip.

[0057] Based on the chip segmentation parameters, the detected image is segmented to determine the sub-image of each Mini LED chip.

[0058] In one possible implementation, when the welding quality determination module determines the welding quality of each Mini LED chip based on the grayscale distribution information corresponding to each sub-image, it is specifically used for:

[0059] Determine the standard grayscale distribution information corresponding to the sub-image;

[0060] Based on the standard grayscale distribution information and the grayscale distribution information corresponding to each sub-image, a standard similarity of each sub-image is determined. The standard similarity is used to characterize the degree of overlap between the grayscale distribution information of the corresponding sub-image and the standard grayscale distribution information.

[0061] When the standard similarity of any sub-image is greater than a preset threshold, the welding quality of the MiniLED chip corresponding to any sub-image is determined to be qualified.

[0062] If the standard similarity of any sub-image is less than or equal to a preset threshold, then the welding quality of the Mini LED chip corresponding to any sub-image is determined to be a poor weld.

[0063] In one possible implementation, the welding quality determination module, when determining the standard grayscale distribution information corresponding to the sub-image, is specifically used for:

[0064] Based on the grayscale distribution information corresponding to each of the sub-images, a grayscale set corresponding to each of the multiple target coordinate points is determined. The grayscale set includes the grayscale value of the corresponding target coordinate point in the grayscale distribution information of each of the sub-images. The target coordinate point is determined according to the model size and standard area of ​​the Mini LED chip. The standard area is the area around the Mini LED chip where the preset welding medium is distributed.

[0065] Determine a target gray value for each of the grayscale sets, wherein the target gray value is the mode of the corresponding grayscale set;

[0066] The target grayscale values ​​corresponding to each target coordinate point are summarized to determine the standard grayscale distribution information.

[0067] In one possible implementation, a Mini LED solder joint detection device further includes:

[0068] The chip center coordinate determination module is used to determine the chip center coordinates based on the standard grayscale distribution information.

[0069] The segmentation line determination module is used to determine a target number of segmentation lines and multiple coordinate points corresponding to each segmentation line based on the chip center coordinates;

[0070] The cold solder joint type determination module is used to determine the cold solder joint type of the Mini LED chip corresponding to any sub-image based on multiple coordinate points corresponding to each of the segmentation lines and the grayscale distribution information of any sub-image. The cold solder joint type includes voids and misalignments.

[0071] In one possible implementation, when the segmentation line determination module determines the target number of segmentation lines and the multiple coordinate points corresponding to each segmentation line based on the chip center coordinates, it is specifically used for:

[0072] Obtain the product usage information of the Mini LED panel, and determine the detection accuracy based on the product usage information;

[0073] Based on the detection accuracy, the segmentation line density is determined;

[0074] Based on the density of the dividing lines and the coordinates of the chip center, a target number of dividing lines and multiple coordinate points corresponding to each dividing line are determined.

[0075] In one possible implementation, when the solder joint type determination module determines the solder joint type of the Mini LED chip corresponding to any sub-image based on multiple coordinate points corresponding to each of the segmentation lines and the grayscale distribution information of any sub-image, it is specifically used for:

[0076] Obtain the shape of the Mini LED chip;

[0077] Based on the shape of the Mini LED chip, the center coordinate point, and multiple coordinate points corresponding to each dividing line, at least two reference sets are determined, and each reference set contains at least two coordinate sequences that are in a reference relationship.

[0078] Based on the grayscale distribution information of the at least two control sets and any sub-image, at least two grayscale control groups are determined, and each grayscale control group includes at least two grayscale value sequences that are in a control relationship.

[0079] Several abnormal control groups are determined from the at least two gray value control groups, wherein at least one gray value sequence in the abnormal control group has a change trend that is inconsistent with other gray value sequences in the group;

[0080] Based on the aforementioned abnormal control groups, the type of poor solder joint of the Mini LED chip corresponding to any sub-image is determined.

[0081] Thirdly, this application provides an electronic device that adopts the following technical solution:

[0082] An electronic device comprising:

[0083] At least one processor;

[0084] Memory;

[0085] At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform the Mini LED cold solder joint detection method described above.

[0086] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution:

[0087] A computer-readable storage medium includes: a computer program stored thereon that can be loaded by a processor and executed by the Mini LED solder joint detection method described above.

[0088] In summary, this application includes at least one of the following beneficial technical effects:

[0089] 1. Acquire inspection images of the Mini LED panel and segment the images to obtain sub-images of the corresponding regions for each Mini LED chip. Then, by analyzing the grayscale values ​​of each coordinate point in the sub-images, determine the grayscale distribution information corresponding to each sub-image. Based on the grayscale distribution information, the soldering quality of each Mini LED chip can be judged, determining whether it is qualified or has a poor solder joint, and identifying the location of the poorly soldered Mini LED chip. This method can detect the soldering quality of each Mini LED chip on the Mini LED panel, thereby improving the accuracy of poor solder joint detection.

[0090] 2. By analyzing standard grayscale distribution information, the coordinates of the center point of the Mini LED chip in the sub-image can be determined, i.e., the center coordinates. Using the chip center coordinates as the starting point, and setting appropriate directions and spacing, multiple dividing lines can be determined, and multiple coordinate points can be identified on each dividing line. Based on the grayscale distribution characteristics and the position of the dividing lines, the types of solder joint defects present in the sub-image can be analyzed. This allows for more accurate identification of solder joint types, enabling a more detailed description of the Mini LED chip's soldering quality issues and providing accurate information for subsequent processing.

[0091] 3. Obtain the shape information of the Mini LED chip, i.e., the shape and outline of the Mini LED. Based on the shape of the Mini LED chip, multiple coordinate points corresponding to each segmentation line, and the center coordinate point, determine at least two control sets. Each control set consists of at least two coordinate sequences that are in a comparative relationship, and these coordinate sequences correspond to the shape and layout of the Mini LED. Then, based on the grayscale distribution information of the at least two control sets and any sub-image, determine at least two grayscale value control groups. Each grayscale value control group consists of at least two grayscale value sequences that are in a comparative relationship, and these grayscale value sequences correspond one-to-one with the corresponding coordinate sequences. From the at least two grayscale value control groups, determine several abnormal control groups. In the abnormal control groups, at least one grayscale value sequence has a trend that is inconsistent with the change trend of other grayscale value sequences in the group, that is, it has a significant difference from other control relationships. Finally, based on the characteristics of the abnormal control groups, it can be determined whether the Mini LED chip has voids or misplaced solder joints, etc. It can more accurately determine the type of solder joint failure of the Mini LED chip corresponding to any sub-image. By comparing the changing trends in the abnormal control group, it can more reliably identify the solder joint failure of the Mini LED chip, further improving the accuracy and reliability of solder joint failure detection. Attached Figure Description

[0092] Figure 1 This is a flowchart illustrating a method for detecting poor solder joints in Mini LEDs according to an embodiment of this application.

[0093] Figure 2 This is a schematic diagram of image segmentation in an embodiment of this application;

[0094] Figure 3 This is a schematic diagram of sub-image segmentation in an embodiment of this application;

[0095] Figure 4 This is a schematic diagram of the structure of a Mini LED cold solder joint detection device according to an embodiment of this application;

[0096] Figure 5 This is a schematic diagram of the structure of the electronic device in the embodiments of this application. Detailed Implementation

[0097] The following combination Figures 1-5 This application will be described in further detail.

[0098] After reading this specification, those skilled in the art may make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they fall within the scope of this application.

[0099] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0100] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0101] This application provides a method for detecting solder joint defects in Mini LEDs, executed by an electronic device, as described above. Figure 1 The method includes steps S101-S104, wherein:

[0102] Step S101: Obtain the detection image, which is an X-ray scan of the Mini LED panel;

[0103] Step S102: Segment the detection image to obtain a sub-image of the corresponding region of each Mini LED chip in the detection image. The sub-image includes the Mini LED chip and the corresponding welding medium.

[0104] In this embodiment of the application, the Mini LED panel is scanned using an X-ray device to obtain a detection image. The obtained detection image can be segmented using image processing algorithms to obtain a sub-image of the corresponding region for each Mini LED chip in the detection image. Commonly used image processing algorithms include edge detection, threshold segmentation, and region growing, as shown in the attached figure. Figure 2 As shown, each sub-image contains a Mini LED chip and its corresponding welding medium.

[0105] Step S103: Determine the grayscale distribution information corresponding to each sub-image. The grayscale distribution information includes the grayscale value of each coordinate point in the corresponding sub-image.

[0106] In this embodiment of the application, for each segmented sub-image, a coordinate system is established in the same way, and then the gray-level distribution information is determined based on the gray-level value of each pixel (coordinate point) in the sub-image. The gray-level of a certain coordinate point in the sub-image can be represented as (X, Y, Z), where X is the horizontal coordinate value of the position in the image coordinate system, Y is the vertical coordinate value of the position in the image coordinate system, and Z is the gray-level value of the position.

[0107] Step S104: Determine the soldering quality of each Mini LED chip based on the gray-scale distribution information corresponding to each sub-image. The soldering quality includes qualified and unsoldered.

[0108] Step S105: Determine the positions of the Mini LED chips with unsoldered soldering quality.

[0109] For the embodiments of the present application, by comparing the similarities between the gray-scale distribution information of each sub-image, it can be judged whether there is a situation where the similarity between the gray-scale distribution information of a certain sub-image and the gray-scale distribution information of the remaining proportional number of sub-images is lower than the preset similarity. If so, determine that the soldering quality of the Mini LED chip corresponding to the certain sub-image is unsoldered, and determine the position of the Mini LED chip in the Mini LED panel; if not, determine that the soldering quality of each Mini LED chip is qualified. Here, the proportional number is determined according to the number of Mini LED chips on the Mini LED panel, and the proportional number is used to represent the majority of all chips. For example, if there are 100 Mini LED chips soldered on the Mini LED panel, the proportional number can be 90.

[0110] Furthermore, each sub-image can be segmented to determine a number of sub-regions. There is a position correspondence relationship between each sub-region, that is, there is at least one of the position relationships of central symmetry, axial symmetry, point symmetry, and同位对称 (should be "homothetic symmetry" in English). Compare the gray-scale distribution information of the sub-regions with the position correspondence relationship to judge whether the gray-scale distribution is consistent. If there is inconsistency, determine that the soldering quality of the corresponding Mini LED chip is unsoldered, and determine the position of the Mini LED chip in the Mini LED panel; if they are all consistent, determine that the soldering quality of the corresponding Mini LED chip is qualified.

[0111] Obtain the detection image of the Mini LED panel, segment the image to obtain the sub-images corresponding to the regions of each Mini LED chip in the detection image, and then determine the gray-scale distribution information corresponding to each sub-image by analyzing the gray-scale values of each coordinate point in the sub-image. Based on the gray-scale distribution information, the soldering quality of each Mini LED chip can be judged, whether it is qualified or unsoldered, and the positions of the unsoldered Mini LED chips can be determined. The soldering quality of each Mini LED chip on the Mini LED panel can be detected, thereby improving the accuracy of unsoldering detection.

[0112] Furthermore, segmenting the detection image to determine the sub-images of each Mini LED chip includes steps S1021 (not shown in the figure) - steps S1023 (not shown in the figure), where:

[0113] Step S1021: Obtain the welding information of the Mini LED panel. The welding information includes the welding position and standard area of ​​each Mini LED chip. The standard area is the area around the Mini LED chip where a preset welding medium is distributed.

[0114] Specifically, during the manufacturing process of Mini LED panels, welding information of the Mini LED panel to be inspected can be obtained based on the performance of the welding equipment and the product specifications of the Mini LED panel. For example, the coordinates of the welding positions can be marked on the PCB or other markers (such as QR codes, barcodes, RFID, etc.) can be used to record relevant welding parameters of the Mini LED panel. This allows welding information to be obtained by scanning or querying these marks or records during cold solder joint detection. The welding position refers to the location where the corresponding Mini LED chip is welded on the Mini LED panel; it can be the location of a specific point on the Mini LED chip on the Mini LED panel, such as the center point of the Mini LED chip. The standard area is the area around the Mini LED chip where the welding medium is distributed when the welding is qualified / normal.

[0115] Step S1022: Based on the welding information of the Mini LED panel, determine the chip segmentation parameters. The chip segmentation parameters are used to characterize the segmentation area of ​​a single Mini LED chip.

[0116] Step S1023: Based on the chip segmentation parameters, segment the detection image to determine the sub-image of each Mini LED chip.

[0117] Specifically, chip segmentation parameters are parameters used to characterize the segmented regions of a single Mini LED chip. These parameters can be determined based on features such as the welding position, the size and shape of the standard region, etc. For example, bounding boxes and geometric features of the image (such as shape and size) can be used to characterize the segmented regions of the chip. Based on the determined chip segmentation parameters, the detection image is segmented to determine the sub-image of each Mini LED chip. Segmentation can be achieved using image processing algorithms and computer vision techniques. For example, thresholding, image connected component analysis, and morphological operations can be used to extract the sub-image of each Mini LED chip.

[0118] By acquiring the welding position and standard area of ​​each Mini LED chip on the Mini LED panel—where the standard area is the region around the Mini LED chip where the pre-defined welding medium is distributed—the segmentation region of each Mini LED chip, i.e., chip segmentation parameters, can be determined. Then, based on these chip segmentation parameters, the detection image is segmented, thereby accurately determining the sub-image of each Mini LED chip. This allows for better segmentation of sub-images based on the welding information of the Mini LED panel, thus improving detection accuracy. Accurately determining the sub-image of each Mini LED chip allows for more precise analysis of the grayscale distribution information of each chip, thereby judging welding quality and detecting cold solder joints, improving the accuracy and reliability of Mini LED cold solder joint detection.

[0119] Furthermore, based on the grayscale distribution information corresponding to each sub-image, the welding quality of each Mini LED chip is determined, including steps S1041 (not shown in the figure) - S1044 (not shown in the figure), wherein:

[0120] Step S1041: Determine the standard grayscale distribution information corresponding to the sub-image.

[0121] Specifically, based on design or standard requirements, the standard grayscale distribution information corresponding to the sub-image is determined. This can be obtained by scanning and analyzing a batch of known qualified Mini LED panels. The standard grayscale distribution information represents the typical grayscale distribution of a qualified Mini LED panel. When scanning the known qualified Mini LED panels and the Mini LED panel to be tested, the X-ray illumination intensity and angle are the same.

[0122] Step S1042: Based on the standard grayscale distribution information and the grayscale distribution information corresponding to each sub-image, determine the standard similarity of each sub-image. The standard similarity is used to characterize the degree of overlap between the grayscale distribution information of the corresponding sub-image and the standard grayscale distribution information.

[0123] Step S1043: When the standard similarity of any sub-image is greater than a preset threshold, the welding quality of the Mini LED chip corresponding to any sub-image is determined to be qualified.

[0124] Step S1044: When the standard similarity of any sub-image is less than or equal to a preset threshold, the welding quality of the Mini LED chip corresponding to any sub-image is determined to be a poor weld.

[0125] Specifically, based on the standard grayscale distribution information and the grayscale distribution information of the sub-images, the standard similarity of each sub-image is calculated. The standard similarity measures the degree of overlap between the grayscale distribution of the sub-image and the standard grayscale distribution. Various similarity calculation methods can be used, such as correlation coefficient, cosine similarity, and Euclidean distance. A preset standard similarity threshold is determined according to the specific application requirements. This threshold is used to judge the degree of overlap between the grayscale distribution information of the sub-image and the standard grayscale distribution information, thereby determining whether the welding quality is qualified. The threshold can be determined based on experimental, empirical, or statistical analysis methods.

[0126] Furthermore, for each sub-image, it is determined whether its standard similarity is greater than a preset threshold. If the standard similarity is greater than the threshold, the welding quality of the corresponding Mini LED chip is determined to be qualified; if the standard similarity is less than or equal to the threshold, the welding quality of the corresponding Mini LED chip is determined to be poor.

[0127] The standard grayscale distribution information corresponding to each sub-image is used as a reference. The grayscale distribution information of each sub-image is then compared and analyzed with the standard grayscale distribution information to calculate the standard similarity. For any sub-image, if its standard similarity is greater than a preset threshold, the welding quality of the Mini LED chip corresponding to that sub-image is determined to be acceptable. If the standard similarity of a sub-image is less than or equal to the preset threshold, the welding quality of the Mini LED chip corresponding to that sub-image is determined to be a cold solder joint. Judging the welding quality of Mini LED chips based on the similarity of grayscale distribution information can more accurately detect cold solder joints. Furthermore, by setting appropriate thresholds, the criteria for judging acceptable and cold solder joints can be flexibly controlled.

[0128] Further, the standard grayscale distribution information corresponding to the sub-image is determined, including steps SA1 (not shown in the figure) - SA3 (not shown in the figure), wherein:

[0129] Step SA1: Based on the grayscale distribution information corresponding to each sub-image, determine the grayscale set corresponding to each of the multiple target coordinate points. The grayscale set includes the grayscale value of the corresponding target coordinate point in the grayscale distribution information of each sub-image. The target coordinate points are determined according to the model, size and standard area of ​​the Mini LED chip.

[0130] Specifically, based on the model and size of the Mini LED chip and the standard area, multiple target coordinate points are determined. These target coordinate points can be located at the center, corners, or other representative positions of the standard area. Based on the grayscale distribution information of each sub-image, a grayscale set is determined for each target coordinate point. This grayscale set is the collection of grayscale values ​​corresponding to the target coordinate point in the grayscale distribution information of each sub-image, obtained by extracting the grayscale values ​​of the corresponding pixels and collecting them into the set.

[0131] Step SA2: Determine the target gray value for each gray set. The target gray value is the mode of the corresponding gray set.

[0132] Step SA3: Summarize the target grayscale values ​​corresponding to each target coordinate point to determine the standard grayscale distribution information.

[0133] Specifically, for each grayscale set, a target grayscale value is determined. This target grayscale value can be determined by finding the mode of the set, i.e., the grayscale value that appears most frequently in the set. Each target grayscale value is associated with its corresponding target coordinate point, forming a key-value pair structure. When using standard grayscale distribution information for grayscale comparison, the corresponding target grayscale value can be quickly found through the target coordinate point.

[0134] First, based on the grayscale distribution information corresponding to each sub-image, multiple grayscale sets of target coordinate points are determined. These grayscale sets include the grayscale values ​​of the corresponding target coordinate points in each sub-image. Then, the target grayscale value, i.e., the mode, of each grayscale set is determined. Finally, the target grayscale values ​​corresponding to each target coordinate point are aggregated to obtain complete standard grayscale distribution information. This allows for a more accurate comparison of the grayscale distribution of each sub-image, thereby improving the accuracy and reliability of Mini LED solder joint detection.

[0135] Furthermore, after determining that the welding quality of the Mini LED chip corresponding to any sub-image is a poor solder joint, the process further includes steps S201 (not shown in the figure) - S203 (not shown in the figure), wherein:

[0136] Step S201: Determine the chip center coordinates based on standard grayscale distribution information;

[0137] Step S202: Based on the chip center coordinates, determine the target number of dividing lines and the multiple coordinate points corresponding to each dividing line.

[0138] In this embodiment of the application, the coordinate region corresponding to the Mini LED chip is determined based on standard grayscale distribution information, and then the coordinates of the center point of the Mini LED chip in the sub-image are determined. For example, morphological operations, object detection algorithms, or contour analysis can be used to determine the center coordinates of the chip. Figure 3 As shown, by taking the chip center coordinates as the starting point and setting appropriate directions and spacing, the target number of dividing lines can be determined, and multiple coordinate points can be determined on each dividing line. The distribution density and number of dividing lines and coordinate points can be flexibly adjusted according to the size, layout and characteristics of the Mini LED chip.

[0139] Step S203: Based on the multiple coordinate points corresponding to each segmentation line and the grayscale distribution information of any sub-image, determine the type of poor solder joint of the Mini LED chip corresponding to any sub-image. The types of poor solder joint include voids and misalignment.

[0140] In this embodiment, based on multiple coordinate points corresponding to each segmentation line and the grayscale distribution information of the sub-image, a grayscale value sequence corresponding to each segmentation line is determined. The grayscale value sequence is arranged in ascending order of straight-line distance between each coordinate point in the segmentation line and the center coordinate point. Then, each grayscale value sequence is analyzed to determine the grayscale change trend of the segmentation line at the corresponding position. Based on the grayscale change trend corresponding to the segmentation line at each position, the type of poor solder joint of the Mini LED chip corresponding to the sub-image is determined, where the poor solder joint type includes voids and misalignments.

[0141] Furthermore, void solder joints refer to omissions or deficiencies within the soldering medium, resulting in voids inside the chip. In terms of grayscale trends, this manifests as a trend where the grayscale value decreases and then increases again. Displacement solder joints refer to offset soldering medium distribution within a pre-defined soldering area (standard area). In terms of grayscale trends, this manifests as a decrease in grayscale value before or after a pre-defined coordinate point, which represents the edge of the soldering medium at the location of the dividing line under normal soldering conditions.

[0142] By analyzing standard grayscale distribution information, the coordinates of the center point of the Mini LED chip in the sub-image can be determined, i.e., the chip center coordinates. Using the chip center coordinates as the starting point, and setting appropriate directions and spacing, multiple dividing lines can be determined, and multiple coordinate points can be identified on each dividing line. Based on the grayscale distribution characteristics and the position of the dividing lines, the types of solder joint defects present in the sub-image can be analyzed. This allows for more accurate identification of solder joint types, enabling a more detailed description of the Mini LED chip's soldering quality issues and providing accurate information for subsequent processing.

[0143] Further, based on the chip center coordinates, the target number of dividing lines and multiple coordinate points corresponding to each dividing line are determined, including steps S2021 (not shown in the figure) - S2023 (not shown in the figure), wherein:

[0144] Step S2021: Obtain product usage information for the Mini LED panel and determine the testing accuracy based on the product usage information;

[0145] Step S2022: Determine the segmentation line density based on the detection accuracy.

[0146] Specifically, product usage information for Mini LED panels is obtained. This information can include parameters such as the model, size, layout, and spacing of the Mini LED chips, as well as relevant information such as the usage scenarios and parameters of the Mini LED panels. This information can be obtained from product specification sheets, CAD design data, or other relevant documents. Based on this product usage information, the detection accuracy for Mini LED solder joint defects is determined. The detection accuracy can be determined according to specific requirements, such as detecting minute solder joint defects or focusing only on large solder joint defects. The detection accuracy needs to be adjusted according to the actual application to meet the requirements for detecting solder joint defects. The detection accuracy is then converted into an appropriate dividing line density, which can be represented by the number of dividing lines. For example, if the requirement is to detect a minute solder joint defect of 0.005mm, the detection accuracy is 0.005mm. If the length of the welding medium edge is 1mm under the condition of qualified welding, then the number of intersection points between the dividing lines and the welding medium edge = welding medium edge length / (detection accuracy * preset ratio value), where the preset ratio value is greater than 0 and less than 1. The intersection points are distributed at the same spacing on the welding medium edge, and the number of intersection points is used to characterize the dividing line density.

[0147] Step S2023: Based on the segmentation line density and chip center coordinates, determine the target number of segmentation lines and the multiple coordinate points corresponding to each segmentation line.

[0148] Specifically, based on the determined segmentation line density and the chip center coordinates, a number of target segmentation lines are drawn around the chip center, with the number of targets corresponding to the segmentation line density. Simultaneously, multiple coordinate points are determined for each segmentation line, evenly distributed along the line. The number of coordinate points is determined by the segmentation line density or detection accuracy; higher density and detection accuracy result in a greater number of coordinate points.

[0149] The process involves acquiring product usage information for Mini LED panels and determining the required testing accuracy based on this information. Then, based on the determined testing accuracy, an appropriate segmentation line density can be determined to accommodate Mini LED panels of different specifications. Based on the chip center coordinates and the segmentation line density, segmentation lines are defined around the chip center coordinates according to a specific direction, number, and spacing. Multiple coordinate points are then defined on each segmentation line for further detection and analysis of solder joint defects. By defining the target number of segmentation lines and the corresponding coordinate points for each segmentation line, a more accurate and comprehensive solder joint defect detection area is provided, further improving the accuracy and reliability of Mini LED solder joint defect detection.

[0150] Furthermore, based on multiple coordinate points corresponding to each segmentation line and the grayscale distribution information of any sub-image, the type of poor soldering of the Mini LED chip corresponding to any sub-image is determined, including steps S2031 (not shown in the figure) - S2035 (not shown in the figure), wherein:

[0151] Step S2031: Obtain the shape of the Mini LED chip.

[0152] Specifically, Mini LED chips achieve higher pixel density and higher brightness through miniaturized LED devices. They are typically smaller than traditional LED chips, ranging in size from tens to hundreds of micrometers. Mini LED chips can usually be square, rectangular, hexagonal, or circular, as these regular shapes make it easier to lay them out on a real-world panel. Therefore, the shape of a Mini LED chip can be obtained from product specifications, CAD design data, or other relevant documents; the shape represents the chip's outline.

[0153] Step S2032: Based on the shape of the Mini LED chip, the center coordinate point, and multiple coordinate points corresponding to each dividing line, determine at least two reference sets, each reference set containing at least two coordinate sequences that are in a reference relationship;

[0154] Step S2033: Based on at least two control sets and the gray distribution information of any sub-image, determine at least two gray value control groups, each gray value control group including at least two gray value sequences that are in a control relationship.

[0155] Specifically, based on the shape of the Mini LED chip, several dividing lines are determined within each reference set, for example, using... Figure 3 For example, when the Mini LED chip is a regular polygon, each control set can contain four dividing lines. Dividing lines a, c, e, and g form one control set, and dividing lines b, d, f, and h form another. The angle between each dividing line and its adjacent dividing line in the control set is 90 degrees. Then, based on the multiple coordinate points corresponding to each dividing line and the center coordinate point, at least two coordinate sequences with a control relationship are determined within each control set. The first coordinate point in each sequence is the center coordinate point, and the remaining coordinate points are arranged sequentially according to the extension direction of the dividing lines. Combining this with the correspondence between gray values ​​and coordinate points in the gray-scale distribution information of any sub-image, at least two gray-scale control groups are determined.

[0156] Step S2034: Determine several abnormal control groups from at least two gray value control groups. In the abnormal control groups, there is at least one gray value sequence whose change trend is inconsistent with other gray value sequences in the group.

[0157] Specifically, for each grayscale control group, the similarity of at least two grayscale sequences within the group is compared. If the changing trend of a certain grayscale sequence is inconsistent with that of other grayscale sequences within the group, then the corresponding grayscale control group is determined to be an abnormal control group. This can be determined by calculating the Manhattan distance or Pearson correlation coefficient between each grayscale sequence, and by setting corresponding thresholds for these calculation methods. If the changing trends of the grayscale sequences exceed the threshold range, then the corresponding grayscale control group can be determined to be an abnormal control group.

[0158] Step S2035: Based on several abnormal control groups, determine the type of poor soldering of the Mini LED chip corresponding to any sub-image.

[0159] Specifically, for each abnormal control group, several abnormal gray-value sequences within each group whose changing trends are inconsistent with other gray-value sequences are identified, and the segmentation line corresponding to each abnormal gray-value sequence is determined. Based on the segmentation line corresponding to each abnormal gray-value sequence and the position of each segmentation line in the sub-image, the positional relationship between each abnormal gray-value sequence is determined. Furthermore, based on the positional relationship between each abnormal gray-value sequence, the abnormal gray-value sequences are grouped to determine several abnormal subgroups, and the corresponding positions of the abnormal gray-value sequences within each abnormal subgroup are adjacent. Positional adjacency is indicated by the presence of only the segmentation line corresponding to the abnormal gray-value sequence within the region corresponding to the corresponding abnormal subgroup.

[0160] Furthermore, anomaly trend analysis is performed on several abnormal grayscale value sequences within each anomaly group to determine the anomaly type corresponding to each anomaly group. Based on the anomaly type, the type of solder joint failure corresponding to the Mini LED chip is then determined. Each Mini LED chip can correspond to one, two, or more solder joint failure types. For example, if each abnormal grayscale value sequence within an anomaly group exhibits a pattern of grayscale value decreasing from high to low, maintaining a low grayscale value, and then increasing again, then the anomaly type corresponding to that anomaly group can be determined as void. When the grayscale value decreasing node of each abnormal grayscale value sequence within an anomaly group is closer to the chip center coordinates than the grayscale value decreasing nodes of other normal grayscale value sequences in its corresponding anomaly control group, then the anomaly type corresponding to that anomaly group can be determined as misalignment, where the grayscale value decreasing node corresponds to the outer edge of the chip soldering medium.

[0161] The process involves acquiring the shape information of the Mini LED chip, i.e., its shape and outline. Based on the shape of the Mini LED chip, multiple coordinate points corresponding to each segmentation line, and the center coordinate point, at least two control sets are determined. Each control set consists of at least two coordinate sequences that are in a comparative relationship, corresponding to the shape and layout of the Mini LED. Then, based on the grayscale distribution information of the at least two control sets and any sub-image, at least two grayscale value control groups are determined. Each grayscale value control group consists of at least two grayscale value sequences in a comparative relationship, with each sequence corresponding to a specific coordinate sequence. From the at least two grayscale value control groups, several abnormal control groups are identified. In each abnormal control group, at least one grayscale value sequence exhibits a trend inconsistent with the other grayscale value sequences within the group, i.e., a significant difference from the other control groups. Finally, based on the characteristics of the abnormal control groups, it can be determined whether the Mini LED chip has voids or misaligned solder joints, or other types of poor soldering. It can more accurately determine the type of solder joint failure of the Mini LED chip corresponding to any sub-image. By comparing the changing trends in the abnormal control group, it can more reliably identify the solder joint failure of the Mini LED chip, further improving the accuracy and reliability of solder joint failure detection.

[0162] The above embodiments describe a method for detecting Mini LED solder joint defects from the perspective of process flow. The following embodiments describe a device for detecting Mini LED solder joint defects from the perspective of virtual modules or virtual units. For details, please refer to the following embodiments.

[0163] This application provides a device for detecting Mini LED solder joint defects, such as... Figure 2 As shown, the device for detecting Mini LED cold solder joints may specifically include a detection image acquisition module 201, a sub-image determination module 202, a grayscale distribution information determination module 203, a soldering quality determination module 204, and a cold solder joint location determination module 205, wherein:

[0164] The detection image acquisition module 201 is used to acquire the detection image, which is an X-ray scan of the Mini LED panel;

[0165] The sub-image determination module 202 is used to segment the detection image to obtain a sub-image of the corresponding region of each Mini LED chip in the detection image. The sub-image includes the Mini LED chip and the corresponding welding medium.

[0166] The grayscale distribution information determination module 203 is used to determine the grayscale distribution information corresponding to each sub-image. The grayscale distribution information includes the grayscale value of each coordinate point in the corresponding sub-image.

[0167] The welding quality determination module 204 is used to determine the welding quality of each MiniLED chip based on the grayscale distribution information corresponding to each sub-image. The welding quality includes qualified and poor solder joints.

[0168] The cold solder joint location determination module 205 is used to determine the location of each Mini LED chip whose soldering quality is cold solder joint.

[0169] By employing the above technical solution, an inspection image of the Mini LED panel is acquired and segmented to obtain a sub-image of the corresponding region for each Mini LED chip in the inspection image. Then, by analyzing the grayscale value of each coordinate point in the sub-image, the grayscale distribution information corresponding to each sub-image is determined. Based on the grayscale distribution information, the welding quality of each Mini LED chip can be judged, determining whether it is qualified or has a poor weld, and the location of the poorly welded Mini LED chip can be determined. This method can detect the welding quality of each Mini LED chip on the Mini LED panel, thereby improving the accuracy of poor weld detection.

[0170] In one possible implementation, the sub-image determination module 202, when segmenting the detected image and determining the sub-image for each Mini LED chip, specifically performs the following:

[0171] Obtain the welding information of the Mini LED panel, which includes the welding position and standard area of ​​each Mini LED chip. The standard area is the area around the Mini LED chip where the preset welding medium is distributed.

[0172] Based on the welding information of the Mini LED panel, the chip segmentation parameters are determined. The chip segmentation parameters are used to characterize the segmentation area of ​​a single Mini LED chip.

[0173] Based on chip segmentation parameters, the detected image is segmented to determine the sub-image of each Mini LED chip.

[0174] In one possible implementation, when determining the welding quality of each Mini LED chip based on the grayscale distribution information corresponding to each sub-image, the welding quality determination module 204 is specifically used for:

[0175] Determine the standard grayscale distribution information corresponding to the sub-image;

[0176] Based on the standard grayscale distribution information and the grayscale distribution information corresponding to each sub-image, the standard similarity of each sub-image is determined. The standard similarity is used to characterize the degree of overlap between the grayscale distribution information of the corresponding sub-image and the standard grayscale distribution information.

[0177] When the standard similarity of any sub-image is greater than a preset threshold, the welding quality of the Mini LED chip corresponding to any sub-image is determined to be qualified.

[0178] If the standard similarity of any sub-image is less than or equal to a preset threshold, then the welding quality of the Mini LED chip corresponding to any sub-image is determined to be a poor weld.

[0179] In one possible implementation, the welding quality determination module 204, when determining the standard grayscale distribution information corresponding to the sub-image, is specifically used for:

[0180] Based on the grayscale distribution information corresponding to each sub-image, the grayscale set corresponding to each of the multiple target coordinate points is determined. The grayscale set includes the grayscale value of the corresponding target coordinate point in the grayscale distribution information of each sub-image. The target coordinate points are determined according to the model size and standard area of ​​the Mini LED chip. The standard area is the area around the Mini LED chip where the preset welding medium is distributed.

[0181] Determine the target gray value for each grayscale set. The target gray value is the mode of the corresponding grayscale set.

[0182] The target grayscale values ​​corresponding to each target coordinate point are summarized to determine the standard grayscale distribution information.

[0183] In one possible implementation, a Mini LED solder joint detection device further includes:

[0184] The chip center coordinate determination module is used to determine the chip center coordinates based on standard grayscale distribution information.

[0185] The segmentation line determination module is used to determine the target number of segmentation lines and the multiple coordinate points corresponding to each segmentation line based on the chip center coordinates;

[0186] The cold solder joint type determination module is used to determine the cold solder joint type of the Mini LED chip corresponding to any sub-image based on multiple coordinate points corresponding to each segmentation line and the grayscale distribution information of any sub-image. The cold solder joint types include voids and misalignments.

[0187] In one possible implementation, the segmentation line determination module, when determining the target number of segmentation lines and the multiple coordinate points corresponding to each segmentation line based on the chip center coordinates, is specifically used for:

[0188] Obtain product usage information for Mini LED panels and determine the testing accuracy based on this information.

[0189] Determine the segmentation line density based on detection accuracy;

[0190] Based on the segmentation line density and the chip center coordinates, the target number of segmentation lines and the multiple coordinate points corresponding to each segmentation line are determined.

[0191] In one possible implementation, when the solder joint type determination module determines the solder joint type of the Mini LED chip corresponding to any sub-image based on multiple coordinate points corresponding to each segmentation line and the grayscale distribution information of any sub-image, it is specifically used for:

[0192] Obtain the shape of the Mini LED chip;

[0193] Based on the shape of the Mini LED chip, the center coordinate point, and multiple coordinate points corresponding to each dividing line, at least two control sets are determined, and each control set contains at least two coordinate sequences that are in a control relationship.

[0194] Based on at least two control sets and the grayscale distribution information of any sub-image, at least two grayscale control groups are determined, and each grayscale control group includes at least two grayscale value sequences that are in a control relationship.

[0195] Several abnormal control groups are determined from at least two gray value control groups. In the abnormal control groups, at least one gray value sequence has a change trend that is inconsistent with other gray value sequences in the group.

[0196] Based on several abnormal control groups, the type of poor solder joint of the Mini LED chip corresponding to any sub-image is determined.

[0197] This application provides an electronic device, such as... Figure 5 As shown, Figure 5 The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0198] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0199] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0200] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0201] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0202] Electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers can also be included. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0203] This application provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0204] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified 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 of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0205] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for detecting poor solder joints in Mini LEDs, characterized in that, include: Acquire a detection image, wherein the detection image is an X-ray scan of a Mini LED panel; Obtain the welding information of the MiniLED panel, which includes the welding position and standard area of ​​each MiniLED chip. The standard area is the area around the MiniLED chip where a preset welding medium is distributed. Based on the welding information of the MiniLED panel, the detection image is segmented to obtain a sub-image of the corresponding region of each MiniLED chip in the detection image. The sub-image includes the MiniLED chip and the corresponding welding medium. Determine the grayscale distribution information corresponding to each of the sub-images, wherein the grayscale distribution information includes the grayscale value of each coordinate point in the corresponding sub-image; Based on the grayscale distribution information corresponding to each sub-image, the welding quality of each Mini LED chip is determined, and the welding quality includes qualified and poor solder joints; Determine the location of each Mini LED chip whose soldering quality is considered poor; Based on the gray value change trend in the gray value distribution information, the abnormal distribution area of ​​the welding medium in the poorly soldered Mini LED chip is identified. The abnormal distribution area includes gray value abrupt change area and gray value continuously low area. Based on the shape and location characteristics of the abnormal distribution area, the type of poor soldering of the Mini LED chip is determined, including voids and misalignment.

2. The method for detecting poor solder joints in MiniLEDs according to claim 1, characterized in that, Based on the welding information of the MiniLED panel, the detection image is segmented to obtain a sub-image of the corresponding region of each MiniLED chip in the detection image, including: Based on the welding information of the Mini LED panel, chip segmentation parameters are determined, which are used to characterize the segmentation area of ​​a single Mini LED chip. Based on the chip segmentation parameters, the detected image is segmented to determine the sub-image of each Mini LED chip.

3. The method for detecting poor solder joints in Mini LEDs according to claim 1, characterized in that, Determining the welding quality of each Mini LED chip based on the grayscale distribution information corresponding to each sub-image includes: Determine the standard grayscale distribution information corresponding to the sub-image; Based on the standard grayscale distribution information and the grayscale distribution information corresponding to each sub-image, a standard similarity of each sub-image is determined. The standard similarity is used to characterize the degree of overlap between the grayscale distribution information of the corresponding sub-image and the standard grayscale distribution information. When the standard similarity of any sub-image is greater than a preset threshold, the welding quality of the Mini LED chip corresponding to any sub-image is determined to be qualified. If the standard similarity of any sub-image is less than or equal to a preset threshold, then the welding quality of the Mini LED chip corresponding to any sub-image is determined to be a poor weld.

4. The method for detecting poor solder joints in Mini LEDs according to claim 3, characterized in that, Determining the standard grayscale distribution information corresponding to the sub-image includes: Based on the grayscale distribution information corresponding to each of the sub-images, a grayscale set corresponding to each of the multiple target coordinate points is determined. The grayscale set includes the grayscale value of the corresponding target coordinate point in the grayscale distribution information of each of the sub-images. The target coordinate points are determined according to the model size and standard area of ​​the Mini LED chip. Determine a target gray value for each of the grayscale sets, wherein the target gray value is the mode of the corresponding grayscale set; The target grayscale values ​​corresponding to each target coordinate point are summarized to determine the standard grayscale distribution information.

5. The method for detecting poor solder joints in Mini LEDs according to claim 3, characterized in that, After determining that the soldering quality of the Mini LED chip corresponding to any of the sub-images is a poor solder joint, the process further includes: Based on the standard grayscale distribution information, the chip center coordinates are determined; Based on the chip center coordinates, determine the target number of dividing lines and multiple coordinate points corresponding to each dividing line; Based on the multiple coordinate points corresponding to each of the segmentation lines and the grayscale distribution information of any sub-image, the type of poor soldering of the Mini LED chip corresponding to any sub-image is determined.

6. The method for detecting poor solder joints in Mini LEDs according to claim 5, characterized in that, The step of determining the target number of dividing lines and the multiple coordinate points corresponding to each dividing line based on the chip center coordinates includes: Obtain the product usage information of the Mini LED panel, and determine the detection accuracy based on the product usage information; Based on the detection accuracy, the segmentation line density is determined; Based on the density of the dividing lines and the coordinates of the chip center, a target number of dividing lines and multiple coordinate points corresponding to each dividing line are determined.

7. The method for detecting poor solder joints in Mini LEDs according to claim 5, characterized in that, The step of determining the solder joint type of the Mini LED chip corresponding to any sub-image based on multiple coordinate points corresponding to each of the segmentation lines and the grayscale distribution information of any sub-image includes: Obtain the shape of the Mini LED chip; Based on the shape of the Mini LED chip, the center coordinate point, and multiple coordinate points corresponding to each dividing line, at least two reference sets are determined, and each reference set contains at least two coordinate sequences that are in a comparative relationship. Based on the grayscale distribution information of the at least two control sets and any sub-image, at least two grayscale control groups are determined, and each grayscale control group includes at least two grayscale value sequences that are in a control relationship. Several abnormal control groups are determined from the at least two gray value control groups, wherein at least one gray value sequence in the abnormal control group has a change trend that is inconsistent with other gray value sequences in the group; Based on the aforementioned abnormal control groups, the type of poor solder joint of the Mini LED chip corresponding to any sub-image is determined.

8. A Mini LED cold solder joint detection device, characterized in that, include: An image acquisition module is used to acquire an image, which is an X-ray scan of a Mini LED panel. The sub-image determination module is used for: Obtain the welding information of the Mini LED panel. The welding information includes the welding position and standard area of ​​each Mini LED chip. The standard area is the area around the Mini LED chip where a preset welding medium is distributed. Based on the welding information of the MiniLED panel, the detection image is segmented to obtain a sub-image of the corresponding region of each MiniLED chip in the detection image. The sub-image includes the MiniLED chip and the corresponding welding medium. A grayscale distribution information determination module is used to determine the grayscale distribution information corresponding to each of the sub-images, wherein the grayscale distribution information includes the grayscale value of each coordinate point in the corresponding sub-image; The welding quality determination module is used to determine the welding quality of each Mini LED chip based on the grayscale distribution information corresponding to each sub-image. The welding quality includes qualified and poor solder joints. A cold solder joint location determination module is used to determine the location of each Mini LED chip whose soldering quality is considered to be a cold solder joint. The module for determining the type of cold solder joint is used for: Based on the gray value change trend in the gray value distribution information, the abnormal distribution area of ​​the welding medium in the poorly soldered Mini LED chip is identified. The abnormal distribution area includes gray value abrupt change area and gray value continuously low area. Based on the shape and location characteristics of the abnormal distribution area, the type of poor soldering of the Mini LED chip is determined, including voids and misalignment.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: perform the MiniLED solder joint detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, include: The system stores a computer program that can be loaded by a processor and executed as described in any one of claims 1-7 for detecting Mini LED solder joint defects.

Images