A method and device for detecting glue application defects

Abstract

Embodiments of the present application provide a gluing defect detection method and device, and relate to the technical field of gluing. The method comprises: obtaining a gluing extension direction according to an original gluing image; splitting the original gluing image into a plurality of pixel columns in the gluing extension direction; obtaining servo axis motion parameters corresponding to each pixel column according to a pixel equivalent of the original gluing image; performing azimuth compensation on the corresponding pixel column according to the servo axis motion parameters to obtain a target gluing image, wherein a gluing area in the target gluing image is a straight line; and performing analysis on the target gluing image according to a visual detection mechanism to obtain a gluing detection result. In this way, the misjudgment of defects at the gluing inflection point can be reduced by analyzing the image after the gluing area is transformed into a straight line, thereby increasing the defect detection rate of the soft package battery wave-shaped gluing, reducing the misjudgment rate of the detection, and improving the production efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of gluing, in particular to a gluing defect detection method and device. BACKGROUND

[0002] Currently, after the soft package battery is glued, a blue light source is used to make the glue present a blue color, and then an image is obtained by shooting. Then, the image is analyzed to detect gluing defects. However, when the wave line gluing detection is performed, the corner is prone to misjudgment. SUMMARY

[0003] The gluing defect detection method and device provided by the embodiments of the present application can reduce the misjudgment of defects at the corner of gluing by transforming the gluing area into a straight line and then performing image analysis, thereby increasing the defect detection rate of the wave-shaped gluing of the soft package battery, reducing the misjudgment rate of detection, and improving the production efficiency.

[0004] The embodiments of the present application can be implemented as follows:

[0005] In a first aspect, the embodiments of the present application provide a gluing defect detection method, which comprises:

[0006] obtaining a gluing extension direction according to an original gluing image;

[0007] splitting the original gluing image into a plurality of pixel columns in the gluing extension direction;

[0008] obtaining servo axis motion parameters corresponding to each pixel column according to the pixel equivalent of the original gluing image;

[0009] performing azimuth compensation on the corresponding pixel column according to the servo axis motion parameters to obtain a target gluing image, wherein the gluing area in the target gluing image is a straight line;

[0010] performing analysis on the target gluing image according to a visual detection mechanism to obtain a gluing detection result.

[0011] In a second aspect, the embodiments of the present application provide a gluing defect detection device, which comprises:

[0012] a direction obtaining module configured to obtain a gluing extension direction according to an original gluing image;

[0013] a splitting module configured to split the original gluing image into a plurality of pixel columns in the gluing extension direction;

[0014] a parameter obtaining module configured to obtain servo axis motion parameters corresponding to each pixel column according to the pixel equivalent of the original gluing image;

[0015] The compensation module is used to perform orientation compensation on the corresponding pixel column according to the motion parameters of the servo axis to obtain the target glue coating image, wherein the glue coating area in the target glue coating image is a straight line;

[0016] The analysis module is used to analyze the target adhesive-coated image based on the visual inspection agency to obtain adhesive-coated detection results.

[0017] This application provides a method and apparatus for detecting adhesive coating defects. After obtaining an original adhesive coating image, the original image is divided into multiple pixel columns based on the adhesive extension direction. Servo axis motion parameters corresponding to each pixel column are obtained based on the pixel equivalent of the original image. Then, orientation compensation is performed on the corresponding pixel columns according to the servo axis motion parameters to obtain a target adhesive coating image. The adhesive coating area in the target image is a straight line. Finally, the target adhesive coating image is analyzed by a visual inspection mechanism to obtain the adhesive coating detection result. In this way, by transforming the adhesive coating area into a straight line before performing defect analysis, the misjudgment of defects at adhesive coating inflection points is reduced, thereby increasing the defect detection rate of wavy adhesive coating in soft-pack batteries, reducing the false judgment rate, and improving production efficiency. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the adhesive application area;

[0020] Figure 2 A schematic flowchart illustrating the adhesive defect detection method provided in this application embodiment;

[0021] Figure 3 This is a schematic diagram of the adhesive application area before processing, as provided in the embodiments of this application.

[0022] Figure 4 A schematic diagram of the adhesive-coated area after processing, provided in an embodiment of this application;

[0023] Figure 5 for Figure 2 A flowchart illustrating the sub-steps included in step S130;

[0024] Figure 6 for Figure 2 A flowchart illustrating the sub-steps included in step S140;

[0025] Figure 7 A block schematic diagram of a glue defect detection device provided by an embodiment of the present application is shown in FIG. 2;

[0026] Figure 8 A block schematic diagram of an electronic device provided by an embodiment of the present application is shown in FIG. 3;

[0027] Icon: 200 - glue defect detection device; 210 - direction obtaining module; 220 - splitting module; 230 - parameter obtaining module; 240 - compensation module; 250 - analysis module; 300 - electronic device; 310 - memory; 320 - processor; 330 - communication unit. DETAILED DESCRIPTION

[0028] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings can be arranged and designed in various different configurations.

[0029] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0030] It should be noted that the relational terms such as first and second and the like are used only to differentiate one entity or action from another, and do not necessarily require or imply that these entities or actions occur in any such actual relationship or order. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus that includes a list of elements does not only include those elements but also includes other elements not expressly listed or other elements inherent to such process, method, article or apparatus. Without more limitations, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article or apparatus including the element.

[0031] Currently, analysis is generally directly performed on the captured image to obtain a coating defect detection result. For example, a BOLB analysis method is used for the captured image, and a binary open operation and a close operation are directly used for processing to obtain a coating defect detection result. However, the present inventors have found through research that the manner of directly analyzing the captured image can detect straight-line coating, but when used for detecting the wave-shaped coating shown in FIG. 1, the detection rate of the position approximating the straight line is high, and misjudgment is prone to occur at the corner. Figure 1

[0032] To avoid misjudgment at the corner, the embodiment of the present application provides a coating defect detection method and device, which transforms the coating area into a straight line before image analysis, so as to reduce the misjudgment of defects at the coating corner point, thereby increasing the defect detection rate of the wave-shaped coating of the soft package battery, reducing the misjudgment rate of detection, and improving the production efficiency.

[0033] Some embodiments of the present application will be described in detail below with reference to the accompanying drawings. In the case of no conflict, the embodiments described below and the features in the embodiments can be combined with each other.

[0034] In the present embodiment, after the coating is completed, the soft package battery on which the coating is completed can be photographed by using an image shooting device, so as to obtain an original coating image, and the original coating image is sent to a detection device. The detection device can first transform the coating area in the original coating image into a straight line through image transformation processing, and then analyze the image after processing to obtain a coating defect detection result.

[0035] The coating defect detection method provided by the embodiment of the present application will be exemplarily described below with the detection device as the execution subject.

[0036] Please refer to Figure 2 , Figure 2 the flowchart of the coating defect detection method provided by the embodiment of the present application. The specific process of the coating defect detection method will be described in detail below. The method can include steps S110-S150.

[0037] Step S110, obtaining a coating extension direction according to an original coating image.

[0038] The coating extension direction represents the length extension direction of the coating in the original coating image.

[0039] Step S120, splitting the original coating image into a plurality of pixel columns in the coating extension direction.

[0040] Step S130, obtaining a servo axis motion parameter corresponding to each pixel column according to the pixel equivalent of the original coating image.

[0041] ​Wherein, the pixel equivalent is used to represent what the actual physical size represented by one pixel point in the image is, that is, the actual length represented by one pixel grid length.

[0042] Step S140, according to the servo shaft motion parameter, the corresponding pixel column is azimuthally compensated to obtain the target gluing image.

[0043] Wherein, the gluing area in the target gluing image is a straight line.

[0044] Step S150, according to the visual detection mechanism, the target gluing image is analyzed to obtain the gluing detection result.

[0045] In this way, based on the servo shaft motion parameter, each pixel column in the original gluing image is azimuthally compensated, so as to transform the gluing area into a straight line, and then the image analysis is performed to obtain the gluing detection result. Since the gluing area is processed into a straight line before the image analysis is performed, the false judgment of defects at the inflection point of the gluing can be reduced, the defect detection rate of the soft package battery wave-shaped gluing is increased, the false judgment rate of the detection is reduced, and the production efficiency is improved.

[0046] Please refer to Figure 3 and Figure 4 Before processing, the gluing area in the original gluing image is a wave-shaped gluing as shown in Figure 3 If the wave-shaped gluing is directly detected, it is easy to misjudge at the corner. In the embodiment, the wave-shaped gluing in Figure 3 is processed into a straight line gluing as shown in Figure 4 , so that the defect detection rate of the wave-shaped gluing is increased.

[0047] In the embodiment, the original gluing image can be obtained by the image shooting device by shooting the soft package battery after gluing and sent to the detection device, or the image selected by the user from the gluing image stored in the detection device needs to be detected for gluing defect detection. Of course, it can be understood that the original gluing image that needs to be detected can also be determined by other ways, and the determination method is not limited here. Wherein, the gluing image stored in the detection device can be obtained by the image shooting device by shooting the soft package battery after gluing and sent to the detection device.

[0048] In order to avoid the inaccuracy of the gluing detection result caused by unclear image, the shooting position of the soft package battery can be set in advance, and the clear and contrast image can be obtained by shooting at this position. In this way, the clear and contrast original gluing image can be obtained.

[0049] In the case of obtaining the original glue coating image, the original glue coating image can be analyzed to obtain the glue coating extension direction. As a possible example, the original glue coating image can be binarized to detect target pixel points from the original glue coating image. It can be understood that the target pixel points are determined by the binarization method, and other methods can also be used to determine the target pixel points. Then, based on the distribution of the target pixel points in the original glue coating image, the glue coating extension direction is obtained. As shown in Figure 3 , assuming that the black part in Figure 3 is a target pixel point, it can be determined that the glue coating extension direction is from left to right.

[0050] In this embodiment, after the glue coating extension direction is determined, the original glue coating image can be split into a column of pixel columns along the glue coating extension direction. As a possible example, in the case of detecting target pixel points in the original glue coating image, only the region containing all target pixel points can be split into multiple pixel columns in the glue coating extension direction. As shown in Figure 3 , the glue coating extension direction is from left to right, i.e. the Y-axis direction, so the region containing all target pixel points can be split into multiple pixel columns on the Y-axis.

[0051] In this embodiment, step S130 can be performed during the glue coating process. Based on the pixel equivalent and the movement of the servo axis during the glue coating process, the servo axis motion parameters corresponding to each pixel column can be obtained. The servo axis motion parameters can be the coordinates of the position of the glue coating mechanism after moving on the servo axis in the XY coordinate system; that is, the servo axis motion parameters can include coordinates in the XY coordinate system, and one coordinate can include x and y values. The XY coordinate system can be as shown in Figure 3 , the Y-axis direction of the XY coordinate system is the glue coating extension direction, and the X-axis direction of the XY coordinate system is the glue coating relief direction perpendicular to the glue coating extension direction; the actual physical size of the glue coating mechanism moving on the servo axis represented by one pixel point in the original glue coating image is the pixel equivalent, based on which the pixel column in the original glue coating image can be corresponded to the position of the glue coating mechanism after moving on the servo axis, so that the pixel column in the original glue coating image is translated up and down according to the positional relationship.

[0052] As a possible example, the servo axis motion parameters corresponding to each pixel column can be obtained by Figure 5 . Please refer to Figure 5 , Figure 5 for the flowchart of the sub-steps included in step S130 in Figure 2 . In this embodiment, step S130 can include sub-steps S131-S133.

[0053] Sub-step S131, obtaining a pixel equivalent of the original gluing image.

[0054] The actual physical size of the gluing mechanism represented by a pixel point in the original gluing image moving on the servo shaft is the pixel equivalent. The resolution of the image capturing device can be obtained, and the imaging field size information of the image capturing device can be obtained by measuring with a ruler. The image capturing device is used to obtain the original gluing image by shooting. The imaging field size information can include the actual length and the actual width of the imaging field. Then, the pixel equivalent can be calculated according to the resolution and the imaging field size information.

[0055] For example, a feature point can be specified, and after the servo shaft moves a fixed distance, the single-pixel precision is calculated according to the change of the pixel coordinates of the feature point in the field of view and the fixed distance, that is, the pixel equivalent is obtained.

[0056] It should be noted that the above-mentioned pixel equivalent obtaining method is only for illustration, and other methods can be used to obtain the pixel equivalent according to actual conditions, and the pixel equivalent obtaining method is not limited herein.

[0057] Sub-step S132, taking the starting position of the servo shaft when gluing as a reference point, and setting the coordinates of the reference point in the XY coordinate system.

[0058] Optionally, the coordinates of the reference point in the XY coordinate system can be set as (0, 0), or other values can be set, which can be set according to actual needs. The coordinates of subsequent gluing can be obtained according to the specific movement distance, movement direction and coordinates of the reference point. The reference point corresponds to the first pixel column in the gluing region of the original gluing image in the gluing extension direction.

[0059] Sub-step S133, during the gluing process of the servo shaft, whenever the servo shaft moves a pixel equivalent in the gluing extension direction, the current coordinates in the XY coordinate system are obtained until the gluing is completed.

[0060] When gluing with the servo shaft, the current coordinates of the servo shaft in the XY coordinate system can be obtained whenever the servo shaft moves a pixel equivalent in the Y-axis direction of the XY coordinate system; that is, the x value and the y value at this time are recorded as the current coordinates of the servo shaft in the XY coordinate system whenever the servo shaft moves a pixel equivalent in the Y-axis direction. Similarly, until the gluing is completed, a plurality of coordinates are obtained.

[0061] In this process, the pixel columns corresponding to the coordinates obtained during the glue application are the pixel columns arranged sequentially in the glue application direction within the glue application area of ​​the original glue application image. For example, assuming the glue application direction of the original glue application image is from left to right, and the pixel columns arranged sequentially from left to right in the glue application area of ​​the original glue application image are pixel columns a, b, c, and d, then the coordinates of the reference point obtained during the glue application process correspond to pixel column a, the second coordinate corresponds to pixel column b, the third coordinate corresponds to pixel column c, and the fourth coordinate corresponds to pixel column d. Thus, by utilizing the motion trajectory of the servo axis of the glue application mechanism, at least the servo axis motion parameters corresponding to each pixel column with glue application can be obtained.

[0062] Having obtained the servo axis motion parameters, it is possible to... Figure 6 The azimuth compensation is performed as shown. Please refer to... Figure 6 , Figure 6 for Figure 2 A flowchart illustrating the sub-steps included in step S140. In this embodiment, step S140 may include sub-steps S141 to S143.

[0063] Sub-step S141: Determine the coordinates corresponding to the reference pixel column from the coordinates corresponding to each pixel column.

[0064] The reference pixel column is one of the pixel columns corresponding to the obtained servo axis motion parameters. Optionally, the user can specify one pixel column as the reference pixel column, or the reference pixel column can be randomly selected, or as follows: Figure 3 and Figure 4 The first pixel column (the pixel column containing point P) in the adhesive extension direction of the original adhesive coating area is fixed as the reference pixel column. After determining the reference pixel column, its corresponding coordinates can be determined. The reference pixel column does not need to be translated, i.e., no orientation compensation is required, and the offset information of the coordinates corresponding to the reference pixel column is 0.

[0065] Sub-step S142: Obtain the offset information of the x-value in the coordinates corresponding to each other pixel column relative to the x-value in the coordinates corresponding to the reference pixel column.

[0066] For each other pixel column that has already obtained the corresponding servo axis motion parameters, the offset information corresponding to the coordinates of that other pixel column can be calculated based on the x-values ​​in the coordinates of the other pixel column and the x-values ​​in the coordinates of the reference pixel column. Optionally, the specific method for obtaining the offset information can be determined in conjunction with the requirements for the transformed straight line. For example, if the requirement is that the straight line has an angle greater than 0° with the Y-axis direction, the offset information corresponding to each coordinate can be calculated based on this requirement.

[0067] As a possible example, the straight line after transformation is parallel to the Y-axis direction. In the embodiment, the offset information includes an offset distance and an offset direction. For each other pixel column, the x value in the coordinates corresponding to the other pixel column is subtracted from the x value in the coordinates corresponding to the reference pixel column to obtain a calculation result. When the calculation result is 0, it is determined that the offset information is no offset. When the calculation result is positive, the calculation result is taken as the offset distance, and it is determined that the offset direction is upward. When the calculation result is negative, the absolute value of the calculation result is taken as the offset distance, and it is determined that the offset direction is downward. In this way, the offset information corresponding to each coordinate can be quickly obtained while ensuring that the glue application area is processed as a straight line.

[0068] In sub-step S143, the pixel columns corresponding to each of the coordinates are azimuthally compensated according to the offset information corresponding to each of the coordinates.

[0069] When the offset information corresponding to each coordinate is obtained, the pixel columns corresponding to each coordinate can be translated based on the offset direction and the offset distance in the offset information, so as to realize azimuthal compensation. For example, if the offset information corresponding to the coordinates corresponding to the pixel column b is that the offset is 2 pixel distances upward, the pixel column b can be translated downward by 2 pixel distances.

[0070] It can be understood that if the original glue application image is directly split into a plurality of pixel columns, and only part of the pixel columns are pixel columns with glue, only the pixel columns with glue can be azimuthally compensated, and other pixel columns without glue are not translated.

[0071] After the azimuthal compensation, a target glue application image in which the glue application area is a straight line can be obtained. The target glue application image can be analyzed by a visual detection mechanism to obtain a glue detection result. The specific analysis method can be determined according to actual needs.

[0072] Optionally, the target glue application image can be analyzed based on a BLOB detection algorithm to obtain the glue detection result. In the algorithm, the glue application area is first determined by binarization. If there is a large defect, the defect area where the large defect is located is determined by feature extraction. If there are some small defects, a binary image is obtained by opening operation and closing operation respectively, and then a new image is obtained by subtracting the two images. Feature extraction is then performed on the new image to obtain the defect area of the glue. The glue detection result is generated based on the defect area.

[0073] In the embodiment, the gluing track is evenly divided in the Y-axis direction, and then each column of pixels is translated in the X-axis direction according to the number and direction of pixels to be translated, so that a new straight gluing track is obtained. The number and direction of pixels to be translated are obtained based on the motion track of the servo axis. In this way, the wavy gluing area can be converted into a straight gluing area based on the gluing track of the servo axis, so as to reduce the false detection caused by the detection at the inflection point and improve the detection rate.

[0074] To perform the corresponding steps in the above embodiments and various possible manners, an implementation of a gluing defect detection device 200 is given below, please refer to Figure 7 , Figure 7 A block diagram of the gluing defect detection device 200 provided in the embodiment is shown. It should be noted that the gluing defect detection device 200 provided in the embodiment has the same basic principle and technical effects as the above embodiments, and for brief description, the part not mentioned in the embodiment can refer to the corresponding content in the above embodiments. The gluing defect detection device 200 can include a direction obtaining module 210, a splitting module 220, a parameter obtaining module 230, a compensation module 240, and an analysis module 250.

[0075] The direction obtaining module 210 is configured to obtain a gluing extension direction according to an original gluing image.

[0076] The splitting module 220 is configured to split the original gluing image into a plurality of pixel columns in the gluing extension direction.

[0077] The parameter obtaining module 230 is configured to obtain servo axis motion parameters corresponding to each pixel column according to the pixel equivalent of the original gluing image.

[0078] The compensation module 240 is configured to perform orientation compensation on the corresponding pixel column according to the servo axis motion parameters to obtain a target gluing image. The gluing area in the target gluing image is a straight line.

[0079] The analysis module 250 is configured to analyze the target gluing image according to a visual detection mechanism to obtain a gluing detection result.

[0080] Optionally, in the embodiment, the servo shaft motion parameter includes coordinates in an XY coordinate system, a direction of an X axis of the XY coordinate system is the glue applying extension direction, a direction of a Y axis of the XY coordinate system is a glue applying fluctuation direction perpendicular to the glue applying extension direction, a unit length of the XY coordinate system is equal to the pixel equivalent, and the coordinates include x values and y values. The compensation module 240 is specifically configured to: determine coordinates corresponding to a reference pixel column from coordinates corresponding to each pixel column, wherein the reference pixel column is one of the pixel columns; obtain offset information of x values in the coordinates corresponding to each other pixel column relative to an x value in the coordinates corresponding to the reference pixel column; and perform orientation compensation on the pixel columns corresponding to the coordinates according to the offset information corresponding to the coordinates.

[0081] Optionally, in the embodiment, the offset information includes an offset distance and an offset direction; and the compensation module 240 is specifically configured to: for each other pixel column, subtract the x value in the coordinates corresponding to the other pixel column from the x value in the coordinates corresponding to the reference pixel column to obtain a calculation result; when the calculation result is 0, determine that the offset information is no offset; when the calculation result is positive, take the calculation result as the offset distance and determine that the offset direction is upward; and when the calculation result is negative, take an absolute value of the calculation result as the offset distance and determine that the offset direction is downward.

[0082] Optionally, in the embodiment, the parameter acquisition module 230 is specifically configured to: obtain a pixel equivalent of the original glue applying image; take a starting position when a servo shaft starts to apply glue as a reference point and set coordinates of the reference point in the XY coordinate system, wherein the reference point corresponds to a first pixel column in a glue applying region of the original glue applying image in the glue applying extension direction; and during glue applying of the servo shaft, obtain a current coordinate in the XY coordinate system each time the servo shaft moves one pixel equivalent in the glue applying extension direction until glue applying is completed, wherein pixel columns corresponding to the obtained coordinates during glue applying are pixel columns arranged in sequence in the glue applying region of the original glue applying image in the glue applying extension direction.

[0083] Optionally, in the embodiment, the parameter acquisition module 230 is specifically configured to: obtain resolution of an image capturing device and imaging field of view size information of the image capturing device, wherein the image capturing device is used to obtain the original glue applying image by capturing; and calculate the pixel equivalent according to the resolution and the imaging field of view size information.

[0084] Optionally, in this embodiment, the direction acquisition module 210 is specifically used to: detect target pixels from the original glue-coated image, wherein the target pixels are pixels with glue coating; and obtain the glue coating extension direction based on the distribution of the target pixels in the original glue-coated image.

[0085] Optionally, in this embodiment, the analysis module 250 is specifically used to: analyze the target adhesive-coated image based on the BLOB detection algorithm to obtain the adhesive-coated detection result.

[0086] Please refer to Figure 8 , Figure 8 This is a block diagram of an electronic device 300 that can implement the above-described adhesive defect detection method according to an embodiment of this application. The electronic device 300 may include a memory 310, a processor 320, and a communication unit 330. The memory 310, processor 320, and communication unit 330 are electrically connected to each other directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines.

[0087] The memory 310 is used to store programs or data. The memory may be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc.

[0088] The processor 320 is used to read / write data or programs stored in memory and to perform corresponding functions.

[0089] The communication unit 330 is used to establish a communication connection between the electronic device 300 and other communication terminals through the network, and to send and receive data through the network.

[0090] It should be understood that, Figure 8 The structure shown is only a schematic diagram of the electronic device 300. The electronic device may also include components that are larger than... Figure 8 The more or fewer components shown, or having the same Figure 8 The different configurations shown. Figure 8 The components shown can be implemented using hardware, software, or a combination thereof.

[0091] The application further provides a readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the glue defect detection method.

[0092] To sum up, the application provides a glue defect detection method and device. In the case of obtaining an original glue image, the original glue image is split into a plurality of pixel columns based on the glue extension direction in the original glue image, and the servo axis motion parameters corresponding to each pixel column are obtained based on the pixel equivalent of the original glue image. Then, the corresponding pixel column is azimuthally compensated according to the servo axis motion parameters to obtain a target glue image, and the glue area in the target glue image is a straight line. Finally, the target glue image is analyzed according to a visual detection mechanism to obtain a glue detection result. In this way, the defect analysis can be performed after the glue area is transformed into a straight line, reducing the misjudgment of defects at the glue inflection points, thereby increasing the defect detection rate of the soft package battery wave-shaped glue, reducing the misjudgment rate of the detection, and improving the production efficiency.

[0093] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only schematic, for example, the flowcharts and block diagrams in the drawings show the possible implementation architectures, functions and operations of the devices, methods and computer program products according to the embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than that shown in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0094] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0095] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts of the prior art that make contributions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0096] The above only describes optional embodiments of the present application and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for detecting adhesive coating defects, characterized in that, The method includes: Based on the original adhesive application image, obtain the adhesive application extension direction; The original adhesive-coated image is divided into multiple pixel columns along the adhesive extension direction; Based on the pixel equivalent of the original glue coating image, obtain the servo axis motion parameters corresponding to each pixel column; Based on the motion parameters of the servo axis, the orientation compensation of the corresponding pixel column is performed to obtain the target adhesive coating image, wherein the adhesive coating area in the target adhesive coating image is a straight line; The adhesive coating image of the target is analyzed by a visual inspection agency to obtain the adhesive coating detection result; The servo axis motion parameters include coordinates in an XY coordinate system. The Y-axis of the XY coordinate system is oriented along the adhesive application extension direction, and the X-axis is oriented along the adhesive application undulation direction perpendicular to the adhesive application extension direction. The unit length of the XY coordinate system is equal to the pixel equivalent, and the coordinates include x and y values. The step of performing orientation compensation on the corresponding pixel column based on the servo axis motion parameters to obtain the target adhesive application image includes: The coordinates corresponding to the reference pixel column are determined from the coordinates corresponding to each pixel column, wherein the reference pixel column is one of the pixel columns; Obtain the offset information of the x-value in the coordinates corresponding to each other pixel column relative to the x-value in the coordinates corresponding to the reference pixel column; Based on the offset information corresponding to each coordinate, orientation compensation is performed on the pixel column corresponding to each coordinate.

2. The method according to claim 1, characterized in that, The offset information includes the offset distance and offset direction; obtaining the offset information of the x-values ​​in the coordinates corresponding to each other pixel column relative to the x-values ​​in the coordinates corresponding to the reference pixel column includes: For each other pixel column, subtract the x-value of the coordinates corresponding to the reference pixel column from the x-value of the coordinates corresponding to the other pixel column to obtain the calculation result; When the calculation result is 0, the offset information is determined to be without offset; When the calculation result is positive, the calculation result is used as the offset distance, and the offset direction is determined to be upward; When the calculation result is negative, the absolute value of the calculation result is used as the offset distance, and the offset direction is determined to be downward.

3. The method according to claim 1, characterized in that, The step of obtaining the servo axis motion parameters corresponding to each pixel column based on the pixel equivalent of the original adhesive coating image includes: Obtain the pixel equivalent of the original adhesive-coated image; The starting position when the servo axis starts applying glue is taken as the reference point, and the coordinates of the reference point in the XY coordinate system are set, wherein the reference point corresponds to the first pixel column in the glue application area of ​​the original glue application image in the glue application extension direction. During the servo axis adhesive application process, whenever the servo axis moves by one pixel equivalent in the adhesive application extension direction, the current coordinates in the XY coordinate system are obtained until the adhesive application is completed. The pixel column corresponding to the coordinates obtained during the adhesive application process is the pixel column arranged sequentially in the adhesive application extension direction in the adhesive application area of ​​the original adhesive application image.

4. The method according to claim 3, characterized in that, Obtaining the pixel equivalent of the original adhesive-coated image includes: The resolution of the image capturing device and the imaging field of view of the image capturing device are obtained, wherein the image capturing device is used to obtain the original adhesive coating image by capturing the image. The pixel equivalent is calculated based on the resolution and imaging field of view information.

5. The method according to claim 1, characterized in that, The step of obtaining the adhesive extension direction based on the original adhesive coating image includes: Target pixels are detected from the original glue-coated image, wherein the target pixels are pixels with glue coating. The adhesive extension direction is obtained based on the distribution of target pixels in the original adhesive coating image.

6. The method according to any one of claims 1-5, characterized in that, The step of analyzing the target adhesive-coated image based on a visual inspection agency to obtain adhesive-coated detection results includes: The target adhesive-coated image is analyzed based on the BLOB detection algorithm to obtain the adhesive-coated detection result.

7. A device for detecting adhesive defects, characterized in that, The device includes: The direction acquisition module is used to obtain the adhesive extension direction based on the original adhesive coating image; A splitting module is used to split the original adhesive-coated image into multiple pixel columns in the adhesive extension direction; The parameter acquisition module is used to acquire the servo axis motion parameters corresponding to each pixel column based on the pixel equivalent of the original glue coating image. The compensation module is used to perform orientation compensation on the corresponding pixel column according to the motion parameters of the servo axis to obtain the target glue coating image, wherein the glue coating area in the target glue coating image is a straight line; The analysis module is used to analyze the target adhesive-coated image based on the visual inspection agency to obtain adhesive-coated detection results; The servo axis motion parameters include coordinates in the XY coordinate system. The X-axis of the XY coordinate system is oriented along the adhesive application extension direction, and the X-axis is also oriented along the adhesive application undulation direction perpendicular to the adhesive application extension direction. The unit length of the XY coordinate system is equal to the pixel equivalent, and the coordinates include x and y values. The compensation module is specifically used for: The coordinates corresponding to the reference pixel column are determined from the coordinates corresponding to each pixel column, wherein the reference pixel column is one of the pixel columns; Obtain the offset information of the x-value in the coordinates corresponding to each other pixel column relative to the x-value in the coordinates corresponding to the reference pixel column; Based on the offset information corresponding to each coordinate, orientation compensation is performed on the pixel column corresponding to each coordinate.

8. The apparatus according to claim 7, characterized in that, The parameter acquisition module is specifically used for: Obtain the pixel equivalent of the original adhesive-coated image; The starting position when the servo axis starts applying glue is taken as the reference point, and the coordinates of the reference point in the XY coordinate system are set, wherein the reference point corresponds to the first pixel column in the glue application area of ​​the original glue application image in the glue application extension direction. During the servo axis adhesive application process, whenever the servo axis moves by one pixel equivalent in the adhesive application extension direction, the current coordinates in the XY coordinate system are obtained until the adhesive application is completed. The pixel column corresponding to the coordinates obtained during the adhesive application process is the pixel column arranged sequentially in the adhesive application extension direction in the adhesive application area of ​​the original adhesive application image.

Images