Visual inspection method, system, terminal and medium for roll-to-roll coating production line

Abstract

The present application is applicable to the technical field of image detection, and provides a visual detection method, system, terminal and medium for a roll-to-roll coating production line, wherein the method comprises first using a shooting device to obtain first real-shot image information and second real-shot image information, and then generating first wrinkle feature set information based on an edge detection algorithm and the first real-shot image information, and generating second wrinkle feature set information based on the second real-shot image information, and finally accurately generating wrinkle detection result information based on the first wrinkle feature set information and the second wrinkle feature set information. The present application can not only use image detection technology to accurately detect wrinkle removal effects, ensure the flatness and consistency of workpieces, and improve the reliability of the production process, but also ensure the surface processing quality of membrane electrode assemblies and other key components, which helps to optimize electrochemical performance and improve the overall efficiency and durability of fuel cells.

Description

Technical Field

[0001] The present application relates to the technical field of image detection, and in particular, to a visual detection method, system, terminal and medium for a roll-to-roll coating production line. Background Art

[0002] Roll-to-roll coating lines play a vital role in hydrogen fuel cell production because they can continuously process thin film materials such as catalyst layers and proton exchange membranes and provide consistent coating thickness.

[0003] At present, the roll-to-roll coating production line usually operates according to pre-set parameters. However, due to the lack of a real-time wrinkle removal effect detection mechanism, when the wrinkle removal effect of the wrinkle removal and flattening roller is greatly reduced due to wear, the production defect cannot be discovered in time, resulting in low reliability and needs further improvement. Summary of the invention

[0004] Based on this, the embodiments of the present application provide a visual inspection method, system, terminal and medium for a roll-to-roll coating production line to solve the problem of low reliability in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a visual inspection method for a roll-to-roll coating production line, which is applied to a coating production line, wherein the coating production line includes a flattening roller, and the method includes:

[0006] Based on a preset shooting device, first real-shot image information and second real-shot image information are acquired, wherein the first real-shot image information is used to describe an image corresponding to the workpiece before the flattening roller contacts the workpiece, and the second real-shot image information is used to describe an image corresponding to the workpiece after the flattening roller contacts the workpiece;

[0007] Generate first wrinkle feature set information according to a preset edge detection algorithm and the first real-shot image information, and generate second wrinkle feature set information according to the edge detection algorithm and the second real-shot image information, wherein the first wrinkle feature set information includes a plurality of first wrinkle area information and first area position information corresponding to each of the first wrinkle area information, and the second wrinkle feature set information includes a plurality of second wrinkle area information and second area position information corresponding to each of the second wrinkle area information;

[0008] Wrinkle detection result information is generated according to the first wrinkle feature set information and the second wrinkle feature set information.

[0009] Compared with the prior art, the beneficial effect is as follows: in the visual inspection method for a roll-to-roll coating production line provided in the embodiment of the present application, the terminal equipment can first use a shooting device to obtain first real-shot image information and second real-shot image information, and then generate first wrinkle feature set information based on an edge detection algorithm and the first real-shot image information, and at the same time generate second wrinkle feature set information based on the edge detection algorithm and the second real-shot image information, and finally accurately generate wrinkle detection result information based on the first wrinkle feature set information and the second wrinkle feature set information, thereby realizing timely discovery of production defects of the flattening roller, greatly improving reliability, reducing the situation where the flattening roller continues to participate in production even though the wrinkle removal effect is not ideal, and to a certain extent solving the current problem of low reliability.

[0010] In a second aspect, an embodiment of the present application provides a visual inspection system for a roll-to-roll coating production line, which is applied to a coating production line, wherein the coating production line includes a flattening roller, and the system includes:

[0011] A real-shot image information acquisition module: used to acquire first real-shot image information and second real-shot image information based on a preset shooting device, wherein the first real-shot image information is used to describe an image corresponding to the workpiece before the flattening roller contacts the workpiece, and the second real-shot image information is used to describe an image corresponding to the workpiece after the flattening roller contacts the workpiece;

[0012] A wrinkle feature set information generating module: used to generate first wrinkle feature set information according to a preset edge detection algorithm and the first real-shot image information, and to generate second wrinkle feature set information according to the edge detection algorithm and the second real-shot image information, wherein the first wrinkle feature set information includes a plurality of first wrinkle area information and first area position information corresponding to each of the first wrinkle area information, and the second wrinkle feature set information includes a plurality of second wrinkle area information and second area position information corresponding to each of the second wrinkle area information;

[0013] Wrinkle detection result information generating module: used to generate wrinkle detection result information according to the first wrinkle feature set information and the second wrinkle feature set information.

[0014] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect described above when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method of the first aspect described above are implemented.

[0016] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0018] Figure 1 is a flow chart of a visual inspection method provided by an embodiment of the present application;

[0019] Figure 2 is a first schematic diagram of a workpiece provided by an embodiment of the present application;

[0020] Figure 3 is a second schematic diagram of a workpiece provided by an embodiment of the present application;

[0021] Figure 4 is a third schematic diagram of a workpiece provided by an embodiment of the present application;

[0022] Figure 5 is a flow chart of step S200 in the visual inspection method provided in one embodiment of the present application;

[0023] Figure 6 is a fourth schematic diagram of a workpiece provided by an embodiment of the present application;

[0024] Figure 7 is a flow chart of step S300 in the visual inspection method provided in one embodiment of the present application;

[0025] Figure 8 is a schematic diagram of the process after step S300 in the visual inspection method provided in one embodiment of the present application;

[0026] Fig. 9 is a schematic diagram of the process after step S420 in the visual inspection method provided in one embodiment of the present application;

[0027] Fig.10 is a fifth schematic diagram of a workpiece provided by an embodiment of the present application;

[0028] Fig.11 is a module block diagram of a visual inspection system provided by an embodiment of the present application;

[0029] Fig.12 It is a schematic diagram of a terminal device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0031] In the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0033] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0034] See also Figure 1 , Figure 1 : is a flow chart of the visual inspection method for a roll-to-roll coating production line provided in an embodiment of the present application. In this embodiment, the execution subject of the visual inspection method is a terminal device. It is understood that the types of terminal devices include but are not limited to mobile phones, tablet computers, laptop computers, ultra-mobile personal computers (Ultra-Mobile Personal Computer, UMPC), netbooks, personal digital assistants (Personal Digital Assistant, PDA), etc., and the embodiments of the present application do not impose any restrictions on the specific types of terminal devices.

[0035] See also Figure 1 The visual inspection method provided in the embodiment of the present application includes but is not limited to the following steps:

[0036] In S100 , first real-shot image information and second real-shot image information are acquired based on a preset shooting device.

[0037] Without loss of generality, the visual inspection method can be applied to a coating production line, which can include an unwinding device, a preheating device, a coating device, an oven drying device, a wrinkle removal device, a deviation correction and traction device, a load detection device, a defect detection device and a winding device in sequence according to the transport direction of the workpiece, wherein the wrinkle removal device is used to eliminate wrinkles generated during the transport of the workpiece to ensure the flatness of the workpiece. For example, see Figure 2 and Figure 3 The core component of the wrinkle removal device is the flattening roller, namely the wrinkle removal flattening roller. It should be noted that the flattening roller is located on the upper surface of the workpiece and conflicts with the upper surface of the workpiece.

[0038] Specifically, the terminal device can use a preset shooting device to quickly obtain the first real-shot image information and the second real-shot image information, wherein the shooting device can be an industrial camera, for example, see Figure 3 The camera device may be located directly above the flattening roller; the first real-shot image information is used to describe the image corresponding to the workpiece before the flattening roller contacts the workpiece, and the first real-shot image information can characterize the flattening state of the workpiece before the flattening roller contacts the workpiece; the second real-shot image information is used to describe the image corresponding to the workpiece after the flattening roller contacts the workpiece, and the second real-shot image information can characterize the flattening state of the workpiece after the flattening roller contacts the workpiece.

[0039] For example, see Figure 2 and Figure 4 , Figure 4 The first area in is used to represent the shooting range of the first real-shot image information. Figure 4 The second area in is used to represent the shooting range of the second real-shot image information.

[0040] In S200, first wrinkle feature set information is generated according to a preset edge detection algorithm and first real-shot image information, and second wrinkle feature set information is generated according to an edge detection algorithm and second real-shot image information.

[0041] Specifically, after the terminal device obtains the first real-shot image information and the second real-shot image information, the terminal device can use a preset edge detection algorithm to perform edge feature extraction processing on the first real-shot image information to quickly generate the first wrinkle feature set information, and at the same time use the edge detection algorithm to perform edge feature extraction processing on the second real-shot image information to quickly generate the second wrinkle feature set information, wherein the edge detection algorithm can be an edge detection algorithm based on a Canny operator or an edge detection algorithm based on a Roberts operator. The first wrinkle feature set information includes multiple first wrinkle area information and first area position information corresponding to each first wrinkle area information, the first wrinkle area information is used to describe the wrinkle area in the first real-shot image information, and the first area position information is used to describe the position corresponding to the wrinkle area in the first real-shot image information. The second wrinkle feature set information includes multiple second wrinkle area information and second area position information corresponding to each second wrinkle area information, the second wrinkle area information is used to describe the wrinkle area in the second real-shot image information, and the second area position information is used to describe the position corresponding to the wrinkle area in the second real-shot image information.

[0042] In some possible implementations, in order to generate reliable first wrinkle feature set information and second wrinkle feature set information, please refer to Figure 5 Step S200 includes but is not limited to the following steps:

[0043] In S210, based on a preset edge detection algorithm, edge extraction processing is performed on the first real-shot image information to generate multiple first selected area information and first flattening roller area information, and based on the edge detection algorithm, edge extraction processing is performed on the second real-shot image information to generate multiple second selected area information and second flattening roller area information.

[0044] Specifically, the terminal device can perform edge extraction processing on the first real-shot image information based on a preset edge detection algorithm to generate multiple first selected area information and first flattening roller area information. At the same time, based on the edge detection algorithm, the terminal device can perform edge extraction processing on the second real-shot image information to generate multiple second selected area information and second flattening roller area information, wherein the first selected area information is used to describe the contour area to be selected in the first real-shot image information, and the first selected area information can simultaneously include the contour area that is in contact with the first flattening roller area information and the contour area that is not in contact with the first flattening roller area information; the first flattening roller area information is used to describe the area belonging to the flattening roller in the first real-shot image information.

[0045] Without loss of generality, the second selected area information is used to describe the contour area to be selected in the second real-shot image information, and the second selected area information can include both the contour area in contact with the second flattening roller area information and the contour area not in contact with the second flattening roller area information; the second flattening roller area information is used to describe the area belonging to the flattening roller in the second real-shot image information. It should be noted that the terminal device can determine the first flattening roller area information and the second flattening roller area information using existing classification algorithms such as convolutional neural networks, so it is not repeated.

[0046] In S220, all first wrinkle region information is determined based on the plurality of first candidate region information and the first flattening roller region information, and all second wrinkle region information is determined based on the plurality of second candidate region information and the second flattening roller region information.

[0047] Specifically, after the terminal device generates the first selected area information, the first flattening roller area information, the second selected area information and the second flattening roller area information, the terminal device can quickly determine all the first wrinkle area information based on the multiple first selected area information and the first flattening roller area information, and at the same time quickly determine all the second wrinkle area information based on the multiple second selected area information and the second flattening roller area information, wherein the first wrinkle area information is used to describe the first selected area information that is in contact with the first flattening roller area information, and the second wrinkle area information is used to describe the second selected area information that is in contact with the second flattening roller area information.

[0048] In S230, for each first wrinkle area information: determine the first area position information according to a preset position coordinate system and the first wrinkle area information, and for each second wrinkle area information: determine the second area position information according to the position coordinate system and the second wrinkle area information.

[0049] Specifically, after the terminal device determines all the first wrinkle area information and the second wrinkle area information, the terminal device can perform this processing on each first wrinkle area information: according to the preset position coordinate system and the first wrinkle area information, the first area position information is effectively determined; and at the same time, perform this processing on each second wrinkle area information: according to the position coordinate system and the second wrinkle area information, the second area position information is effectively determined, thereby generating reliable first wrinkle feature set information and second wrinkle feature set information, thereby improving the reliability of precise detection.

[0050] In S300, wrinkle detection result information is generated according to the first wrinkle feature set information and the second wrinkle feature set information.

[0051] Specifically, after the terminal device generates the first wrinkle feature set information and the second wrinkle feature set information, the terminal device can accurately generate wrinkle detection result information based on the first wrinkle feature set information and the second wrinkle feature set information, wherein the wrinkle detection result information includes normal state information or abnormal state information, the normal state information is used to describe that the flattening state corresponding to the workpiece after contact with the flattening roller is a normal state, and the abnormal state information is used to describe that the flattening state corresponding to the workpiece after contact with the flattening roller is an abnormal state.

[0052] In some possible implementations, in order to facilitate the generation of reliable wrinkle detection result information, before step S300, the method further includes but is not limited to the following steps:

[0053] In S301 , first maximum measured width information is generated according to an edge detection algorithm and first real-shot image information, and second maximum measured width information is generated according to an edge detection algorithm and second real-shot image information.

[0054] For example, see Figure 6 The terminal device can determine the width of the workpiece in the first real-shot image information according to the edge detection algorithm and the first real-shot image information, and calculate the length of the workpiece width by using a preset Euclidean distance formula to generate the first maximum measured width information. At the same time, according to the edge detection algorithm and the second real-shot image information, the second maximum measured width information is generated. The specific process of generating the second maximum measured width information is similar to the specific process of generating the first maximum measured width information, so it is not repeated here. The first maximum measured width information is used to describe the maximum width corresponding to the workpiece in the first real-shot image information; the second maximum measured width information is used to describe the maximum width corresponding to the workpiece in the second real-shot image information.

[0055] In some possible implementations, in order to generate reliable wrinkle detection results, see Figure 7 Step S300 includes but is not limited to the following steps:

[0056] In S310 , the second maximum measured width information is compared with the first maximum measured width information.

[0057] Specifically, after the terminal device generates the first maximum measured width information and the second maximum measured width information, the terminal device may compare the second maximum measured width information with the first maximum measured width information.

[0058] In S320, if the second maximum measured width information is greater than the first maximum measured width information, it is determined whether the second real-shot image information contains at least one second wrinkle area information.

[0059] Specifically, if the second maximum measured width information is greater than the first maximum measured width information, the terminal device can determine whether there is at least one second wrinkle area information in the second real-shot image information. It should be noted that when the wrinkle removal effect of the flattening roller is not significantly reduced due to wear, that is, when the flattening roller is in normal working conditions, the second wrinkle area information may not exist in the second real-shot image information.

[0060] In S330, if the second real-shot image information contains at least one second wrinkle region information, abnormal state information is generated; otherwise, normal state information is generated.

[0061] Specifically, if there is at least one second wrinkle area information in the second real-shot image information, it indicates that the flattening roller may be worn due to long-term use, resulting in a significant reduction in the wrinkle removal effect. The terminal device can generate abnormal status information, otherwise the terminal device can generate normal status information, thereby realizing timely discovery of the production defect when the wrinkle removal effect of the flattening roller is not ideal, thereby improving reliability.

[0062] In S340 , if the second maximum measured width information is equal to the first maximum measured width information, the second maximum measured width information is compared with the preset workpiece width information.

[0063] Specifically, if the second maximum measured width information is equal to the first maximum measured width information, the terminal device can compare the second maximum measured width information with the preset workpiece width information, where the workpiece width information is a preset value, and the workpiece width information can be the ideal width after the workpiece contacts the flattening roller.

[0064] In S350, if the second maximum measured width information is equal to the workpiece width information, normal state information is generated, otherwise abnormal state information is generated.

[0065] Specifically, if the second maximum measured width information is equal to the workpiece width information, the terminal device can generate normal status information, otherwise the terminal device can generate abnormal status information, thereby improving applicability, which is suitable for distinguishing application scenarios in which the workpiece is in a flattened state with wrinkles before contacting the flattening roller, and because the flattening roller does not effectively contact the workpiece, the workpiece is still in a flattened state with wrinkles after contacting the flattening roller.

[0066] In some possible implementations, in order to further detect the flattening state of the workpiece, the abnormal state information includes common abnormality information or severe abnormality information, wherein the common abnormality information is used to describe that the flattening state corresponding to the workpiece after contacting the flattening roller is a common abnormal state; the severe abnormality information is used to describe that the flattening state corresponding to the workpiece after contacting the flattening roller is a severe abnormal state, please refer to Figure 8If abnormal status information is generated, after step S300, the method further includes but is not limited to the following steps:

[0067] In S400, first total quantity information of the first wrinkle region information is obtained, and second total quantity information of the second wrinkle region information is obtained.

[0068] Specifically, the terminal device can obtain the first total quantity information of the first fold area information and the second total quantity information of the second fold area information, wherein the first total quantity information is used to describe the total quantity of the first fold area information; the second total quantity information is used to describe the total quantity of the second fold area information.

[0069] In S410, the first total quantity information and the second total quantity information are compared.

[0070] Specifically, after the terminal device obtains the first total quantity information and the second total quantity information, the terminal device may compare the first total quantity information and the second total quantity information.

[0071] In S420, if the second total quantity information is greater than the first total quantity information, it is determined that the abnormal state information is serious abnormal state information.

[0072] Specifically, if the second total quantity information is greater than the first total quantity information, it indicates that after the workpiece contacts the flattening roller, more wrinkles are formed due to a serious decrease in the smoothness of the flattening roller. The terminal device can accurately determine that the abnormal status information is serious abnormal information.

[0073] In S430, if the second total quantity information is less than or equal to the first total quantity information, it is determined that the abnormal state information is common abnormal state information.

[0074] Specifically, if the second total quantity information is less than or equal to the first total quantity information, it indicates that the wrinkle removal effect of the flattening roller is not as expected or has no wrinkle removal effect at all, and the terminal device can determine that the abnormal state information is common abnormal state information.

[0075] Among some possible implementations, in order to facilitate the precise repair of the flattening rollers of the coating line, please refer to Fig. 9 After step S420, the method further includes but is not limited to the following steps:

[0076] In S421, first target contour point set information is determined based on the first wrinkle region information and the first flattening roller region information, and second target contour point set information is determined based on the second wrinkle region information and the second flattening roller region information.

[0077] Specifically, the terminal device can quickly determine the first target contour point set information based on the first wrinkle area information and the first flattening roller area information, and quickly determine the second target contour point set information based on the second wrinkle area information and the second flattening roller area information.

[0078] For example, see Fig.10 , Fig.10 It is used to demonstrate the application scenario that the workpiece is in a flattened state with wrinkles before contacting the flattening roller, and the workpiece is still in a flattened state with wrinkles after contacting the flattening roller. Fig.10 The wrinkle shapes and numbers in the figure are only examples. The first target contour point set information includes a plurality of first target contour points, which are used to describe contour points where the first wrinkle area information contacts the first flattening roller area information, and the second target contour point set information includes a plurality of second target contour points, which are used to describe contour points where the second wrinkle area information contacts the second flattening roller area information.

[0079] In S422, for each first target contour point: the shortest distance between the first target contour point and each second target contour point is calculated to generate shortest distance set information.

[0080] Specifically, after the terminal device determines the first target contour point set information and the second target contour point set information, the terminal device can perform this processing for each first target contour point: using the Euclidean calculation formula, calculate the shortest distance between the first target contour point and each second target contour point, and generate the shortest distance set information, wherein the shortest distance set information includes multiple shortest distance information to be selected, and the shortest distance information to be selected is used to describe the shortest distance between the first target contour point and the second target contour point.

[0081] In S423, target shortest distance information is determined based on the shortest distance set information.

[0082] Specifically, after the terminal device generates the shortest distance set information, the terminal device can quickly determine the target shortest distance information based on the shortest distance set information, wherein the target shortest distance information is used to describe the smallest candidate shortest distance information in the shortest distance set information.

[0083] In S424, the collection range information is generated according to the target shortest distance information and the preset collection extension value information.

[0084] Specifically, after the terminal device determines the target shortest distance information, the terminal device can generate collection range information based on the target shortest distance information and the preset collection extension value information, wherein the collection range information is used to describe a perfect circular area with the first target contour point as the center and the sum of the target shortest distance information and the collection extension value information as the radius.

[0085] In S425, it is determined whether a specified number of second target contour points exist within the acquisition range information.

[0086] Specifically, after the terminal device generates the collection range information, the terminal device can determine whether there is a specified number of second target contour points in the collection range information, wherein the specific value of the specified number is a preset value, and the specified number is preferably 6, 10 or 12.

[0087] In S426, if a specified number of second target contour points exist within the acquisition range information, the first contour point position information corresponding to the first target contour point is determined based on the first area position information corresponding to the first wrinkle area information, and the second contour point position information corresponding to each second target contour point is determined based on the second area position information corresponding to the second wrinkle area information.

[0088] Specifically, if there are a specified number of second target contour points within the acquisition range information, the terminal device can quickly determine the first contour point position information corresponding to the first target contour point based on the first area position information corresponding to the first wrinkle area information, and at the same time quickly determine the second contour point position information corresponding to each second target contour point based on the second area position information corresponding to the second wrinkle area information, wherein the first contour point position information is used to describe the position of the first target contour point; and the second contour point position information is used to describe the position of the second target contour point.

[0089] In S427, the serious abnormal region information is determined according to the first contour point position information and the plurality of second contour point position information.

[0090] Specifically, after the terminal device determines the first contour point position information and the second contour point position information, the terminal device can accurately determine the severe abnormal area information based on the first contour point position information and the multiple second contour point position information, thereby facilitating maintenance personnel to accurately repair the flattening roller portion corresponding to the severe abnormal area information, wherein the severe abnormal area information is used to describe the polygonal area surrounded by the first contour point position information and the multiple second contour point position information. Exemplarily, the terminal device can sequentially connect the first contour point position information and the multiple second contour point positions to generate multiple line segments, such as the starting point of the first line segment is the first contour point position information, and the end point of the first line segment is the second contour point position adjacent to the first contour point position information, and then the starting point of the second line segment is the second contour point position, and the end point of the second line segment is another second contour point position, and so on, until a closed polygonal area is formed; the side length of the polygonal area coincides with the first contour point position information and coincides with all the second contour point position information.

[0091] The implementation principle of the visual inspection method for the roll-to-roll coating production line of the embodiment of the present application is as follows: the terminal equipment can first use the shooting device to obtain the first real-shot image information and the second real-shot image information, and then quickly generate the first wrinkle feature set information according to the edge detection algorithm and the first real-shot image information, and at the same time quickly generate the second wrinkle feature set information according to the edge detection algorithm and the second real-shot image information, and finally accurately generate the wrinkle detection result information according to the first wrinkle feature set information and the second wrinkle feature set information, so as to realize timely discovery of the production defect of the unsatisfactory wrinkle removal effect of the flattening roller and greatly improve the reliability.

[0092] It should be noted that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0093] The embodiment of the present application also provides a visual inspection system for a roll-to-roll coating production line, which is applied to the coating production line. The coating production line includes a flattening roller. For ease of description, only the parts related to the present application are shown, such as Fig.11 As shown, the system 110 includes:

[0094] The real-shot image information acquisition module 111 is used to acquire first real-shot image information and second real-shot image information based on a preset shooting device, wherein the first real-shot image information is used to describe an image corresponding to the workpiece before the flattening roller contacts the workpiece, and the second real-shot image information is used to describe an image corresponding to the workpiece after the flattening roller contacts the workpiece;

[0095] The wrinkle feature set information generating module 112 is used to generate first wrinkle feature set information according to a preset edge detection algorithm and the first real-shot image information, and to generate second wrinkle feature set information according to the edge detection algorithm and the second real-shot image information, wherein the first wrinkle feature set information includes a plurality of first wrinkle region information and first region position information corresponding to each first wrinkle region information, and the second wrinkle feature set information includes a plurality of second wrinkle region information and second region position information corresponding to each second wrinkle region information;

[0096] The wrinkle detection result information generating module 113 is used to generate wrinkle detection result information according to the first wrinkle feature set information and the second wrinkle feature set information.

[0097] Optionally, the wrinkle feature set information generating module 112 includes:

[0098] The submodule for generating the information of the selected area is used to perform edge extraction processing on the first real-shot image information based on a preset edge detection algorithm to generate a plurality of first information of the selected area and first flattening roller area information, and to perform edge extraction processing on the second real-shot image information based on the edge detection algorithm to generate a plurality of second information of the selected area and second flattening roller area information;

[0099] The wrinkle region information determination submodule is used to determine all first wrinkle region information according to a plurality of first candidate region information and first flattening roller region information, and to determine all second wrinkle region information according to a plurality of second candidate region information and second flattening roller region information, wherein the first wrinkle region information is used to describe the first candidate region information in contact with the first flattening roller region information, and the second wrinkle region information is used to describe the second candidate region information in contact with the second flattening roller region information;

[0100] The regional position information determination submodule is used to determine the first regional position information for each first wrinkle regional information according to the preset position coordinate system and the first wrinkle regional information, and to determine the second regional position information for each second wrinkle regional information according to the position coordinate system and the second wrinkle regional information.

[0101] Optionally, the wrinkle detection result information includes normal state information or abnormal state information; the system 110 further includes:

[0102] Maximum measured width information generation module: used to generate first maximum measured width information according to the edge detection algorithm and the first real-shot image information, and to generate second maximum measured width information according to the edge detection algorithm and the second real-shot image information;

[0103] Optionally, the wrinkle detection result information generating module 113 includes:

[0104] Maximum measured width information comparison submodule: used to compare the second maximum measured width information with the first maximum measured width information;

[0105] The second real shot image information judgment submodule is used to judge whether the second real shot image information contains at least one second wrinkle area information if the second maximum measured width information is greater than the first maximum measured width information;

[0106] Abnormal state information generating submodule: used for generating abnormal state information if the second real shot image information contains at least one second wrinkle region information, and generating normal state information otherwise;

[0107] Second maximum measured width information comparison submodule: used for comparing the second maximum measured width information with the preset workpiece width information if the second maximum measured width information is equal to the first maximum measured width information;

[0108] Normal state information generating submodule: used to generate normal state information if the second maximum measured width information is equal to the workpiece width information, otherwise generate abnormal state information.

[0109] Optionally, the abnormal state information includes common abnormal state information or serious abnormal state information; if the abnormal state information is generated, the system 110 further includes:

[0110] Total quantity information acquisition module: used to acquire first total quantity information of first wrinkle area information, and acquire second total quantity information of second wrinkle area information;

[0111] Total quantity information comparison module: used to compare the first total quantity information and the second total quantity information;

[0112] A serious abnormality information determination module: used for determining that the abnormal state information is serious abnormality information if the second total quantity information is greater than the first total quantity information;

[0113] Common abnormal information determination module: used to determine that the abnormal status information is common abnormal information if the second total quantity information is less than or equal to the first total quantity information.

[0114] Optionally, the system 110 further includes:

[0115] A target contour point set information determination module: used to determine the first target contour point set information based on the first wrinkle area information and the first flattening roller area information, and to determine the second target contour point set information based on the second wrinkle area information and the second flattening roller area information, wherein the first target contour point set information includes a plurality of first target contour points, and the second target contour point set information includes a plurality of second target contour points, the first target contour points are used to describe contour points where the first wrinkle area information contacts the first flattening roller area information, and the second target contour points are used to describe contour points where the second wrinkle area information contacts the second flattening roller area information;

[0116] The shortest distance set information generating module is used for calculating the shortest distance between the first target contour point and each second target contour point for each first target contour point, and generating the shortest distance set information, wherein the shortest distance set information includes a plurality of shortest distance information to be selected;

[0117] A target shortest distance information determination module is used to determine the target shortest distance information based on the shortest distance set information, wherein the target shortest distance information is used to describe the smallest shortest distance information to be selected in the shortest distance set information;

[0118] The acquisition range information generation module is used to generate acquisition range information according to the target shortest distance information and the preset acquisition extension value information, wherein the acquisition range information is used to describe a perfect circular area with the first target contour point as the center and the sum of the target shortest distance information and the acquisition extension value information as the radius;

[0119] Collection range information judgment module: used to judge whether there are a specified number of second target contour points within the collection range information;

[0120] A contour point position information determination module: used for determining first contour point position information corresponding to the first target contour point according to the first area position information corresponding to the first wrinkle area information if a specified number of second target contour points exist within the acquisition range information, and determining second contour point position information corresponding to each second target contour point according to the second area position information corresponding to the second wrinkle area information;

[0121] Severe abnormal area information determination module: used to determine severe abnormal area information based on the first contour point position information and multiple second contour point position information, wherein the severe abnormal area information is used to describe the polygonal area surrounded by the first contour point position information and multiple second contour point position information.

[0122] It should be noted that the information interaction, execution process and other contents between the above-mentioned modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0123] The present application also provides a terminal device, such as Fig.12 As shown, the terminal device 120 of this embodiment includes: a processor 121, a memory 122, and a computer program 123 stored in the memory 122 and executable on the processor 121. When the processor 121 executes the computer program 123, the steps in the above-mentioned visual detection method embodiment are implemented, for example Figure 1 Steps S100 to S300 shown; or, when the processor 121 executes the computer program 123, the functions of each module in the above device are realized, for example Fig.11 The functions of modules 111 to 113 are shown.

[0124] The terminal device 120 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server, and the terminal device 120 includes but is not limited to a processor 121 and a memory 122. Those skilled in the art will appreciate that Fig.12It is only an example of the terminal device 120 and does not constitute a limitation of the terminal device 120. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device 120 may also include input and output devices, network access devices, buses, etc.

[0125] Among them, the processor 121 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.; the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0126] The memory 122 may be an internal storage unit of the terminal device 120, such as a hard disk or memory of the terminal device 120, or the memory 122 may be an external storage device of the terminal device 120, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the terminal device 120; further, the memory 122 may also include both an internal storage unit and an external storage device of the terminal device 120, and the memory 122 may also store a computer program 123 and other programs and data required by the terminal device 120, and the memory 122 may also be used to temporarily store data that has been output or is to be output.

[0127] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form, etc.; the computer-readable medium may include: any entity or device that can carry computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0128] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, all equivalent changes made according to the methods, principles, and structures of the present application should be included in the protection scope of the present application.

Claims

1. A visual inspection method for a roll-to-roll coating production line, applied to a coating production line, wherein the coating production line includes a flattening roller, characterized in that: The method comprises: Based on a preset shooting device, first real-shot image information and second real-shot image information are acquired, wherein the first real-shot image information is used to describe an image corresponding to the workpiece before the flattening roller contacts the workpiece, and the second real-shot image information is used to describe an image corresponding to the workpiece after the flattening roller contacts the workpiece; Generate first wrinkle feature set information according to a preset edge detection algorithm and the first real-shot image information, and generate second wrinkle feature set information according to the edge detection algorithm and the second real-shot image information, wherein the first wrinkle feature set information includes a plurality of first wrinkle area information and first area position information corresponding to each of the first wrinkle area information, and the second wrinkle feature set information includes a plurality of second wrinkle area information and second area position information corresponding to each of the second wrinkle area information; Generate wrinkle detection result information according to the first wrinkle feature set information and the second wrinkle feature set information, wherein the wrinkle detection result information includes normal state information or abnormal state information; Before generating wrinkle detection result information according to the first wrinkle feature set information and the second wrinkle feature set information, the method further includes: Generate first maximum measured width information according to the edge detection algorithm and the first real-shot image information, and generate second maximum measured width information according to the edge detection algorithm and the second real-shot image information; The generating wrinkle detection result information according to the first wrinkle feature set information and the second wrinkle feature set information includes: comparing the second maximum measured width information with the first maximum measured width information; If the second maximum measured width information is greater than the first maximum measured width information, determining whether the second real-shot image information contains at least one second wrinkle area information; If the second real-shot image information contains at least one piece of the second wrinkle region information, the abnormal state information is generated; otherwise, the normal state information is generated; If the second maximum measured width information is equal to the first maximum measured width information, comparing the second maximum measured width information with the preset workpiece width information; If the second maximum measured width information is equal to the workpiece width information, the normal state information is generated; otherwise, the abnormal state information is generated.

2. The method according to claim 1, characterized in that The step of generating first wrinkle feature set information according to a preset edge detection algorithm and the first real-shot image information, and generating second wrinkle feature set information according to the edge detection algorithm and the second real-shot image information, includes: Based on a preset edge detection algorithm, edge extraction processing is performed on the first real-shot image information to generate a plurality of first to-be-selected area information and first flattening roller area information; and based on the edge detection algorithm, edge extraction processing is performed on the second real-shot image information to generate a plurality of second to-be-selected area information and second flattening roller area information; Determine all the first wrinkle region information according to the plurality of first candidate region information and the first flattening roller region information, and determine all the second wrinkle region information according to the plurality of second candidate region information and the second flattening roller region information, wherein the first wrinkle region information is used to describe the first candidate region information in contact with the first flattening roller region information, and the second wrinkle region information is used to describe the second candidate region information in contact with the second flattening roller region information; For each first wrinkle area information: determine the first area position information according to a preset position coordinate system and the first wrinkle area information, and for each second wrinkle area information: determine the second area position information according to the position coordinate system and the second wrinkle area information.

3. The method according to claim 2, characterized in that The abnormal state information includes common abnormal state information or serious abnormal state information; if the abnormal state information is generated, after generating wrinkle detection result information according to the first wrinkle feature set information and the second wrinkle feature set information, the method further includes: Acquire first total quantity information of the first wrinkle region information, and acquire second total quantity information of the second wrinkle region information; comparing the first total quantity information and the second total quantity information; If the second total quantity information is greater than the first total quantity information, determining that the abnormal state information is serious abnormal state information; If the second total quantity information is less than or equal to the first total quantity information, it is determined that the abnormal state information is common abnormal state information.

4. The method according to claim 3, characterized in that After determining that the abnormal state information is serious abnormal state information if the second total quantity information is greater than the first total quantity information, the method further includes: Determine first target contour point set information based on the first wrinkle region information and the first flattening roller region information, and determine second target contour point set information based on the second wrinkle region information and the second flattening roller region information, wherein the first target contour point set information includes a plurality of first target contour points, and the second target contour point set information includes a plurality of second target contour points, the first target contour points are used to describe contour points where the first wrinkle region information contacts the first flattening roller region information, and the second target contour points are used to describe contour points where the second wrinkle region information contacts the second flattening roller region information; For each of the first target contour points: calculating the shortest distance between the first target contour point and each of the second target contour points, and generating shortest distance set information, wherein the shortest distance set information includes a plurality of shortest distance information to be selected; Based on the shortest distance set information, determine the target shortest distance information, wherein the target shortest distance information is used to describe the smallest shortest distance information to be selected in the shortest distance set information; Generate acquisition range information according to the target shortest distance information and the preset acquisition extension value information, wherein the acquisition range information is used to describe a perfect circular area with the first target contour point as the center and the sum of the target shortest distance information and the acquisition extension value information as the radius; Determining whether a specified number of the second target contour points exist within the acquisition range information; If a specified number of the second target contour points exist within the acquisition range information, first contour point position information corresponding to the first target contour point is determined according to the first area position information corresponding to the first wrinkle area information, and second contour point position information corresponding to each of the second target contour points is determined according to the second area position information corresponding to the second wrinkle area information; Severe abnormality region information is determined according to the first contour point position information and the plurality of second contour point position information, wherein the severe abnormality region information is used to describe a polygonal region enclosed by the first contour point position information and the plurality of second contour point position information.

5. A visual inspection system for a roll-to-roll coating production line, applied to a coating production line, wherein the coating production line includes a flattening roller, characterized in that: The system comprises: A real-shot image information acquisition module: used to acquire first real-shot image information and second real-shot image information based on a preset shooting device, wherein the first real-shot image information is used to describe an image corresponding to the workpiece before the flattening roller contacts the workpiece, and the second real-shot image information is used to describe an image corresponding to the workpiece after the flattening roller contacts the workpiece; A wrinkle feature set information generating module: used to generate first wrinkle feature set information according to a preset edge detection algorithm and the first real-shot image information, and to generate second wrinkle feature set information according to the edge detection algorithm and the second real-shot image information, wherein the first wrinkle feature set information includes a plurality of first wrinkle area information and first area position information corresponding to each of the first wrinkle area information, and the second wrinkle feature set information includes a plurality of second wrinkle area information and second area position information corresponding to each of the second wrinkle area information; A wrinkle detection result information generating module: used for generating wrinkle detection result information according to the first wrinkle feature set information and the second wrinkle feature set information, wherein the wrinkle detection result information includes normal state information or abnormal state information; Wherein, the system further comprises: A maximum measured width information generating module: used to generate first maximum measured width information according to the edge detection algorithm and the first real-shot image information, and to generate second maximum measured width information according to the edge detection algorithm and the second real-shot image information; Wherein, the wrinkle detection result information generating module includes: Maximum measured width information comparison submodule: used to compare the second maximum measured width information with the first maximum measured width information; A second real shot image information judgment submodule: configured to judge whether the second real shot image information contains at least one second wrinkle area information if the second maximum measured width information is greater than the first maximum measured width information; Abnormal state information generating submodule: used for generating the abnormal state information if the second real shot image information contains at least one of the second wrinkle region information, and generating the normal state information otherwise; A second maximum measured width information comparison submodule: used for comparing the second maximum measured width information with the preset workpiece width information if the second maximum measured width information is equal to the first maximum measured width information; Normal state information generating submodule: used for generating the normal state information if the second maximum measured width information is equal to the workpiece width information, and generating the abnormal state information otherwise.

6. The system according to claim 5, characterized in that The wrinkle feature set information generation module includes: A submodule for generating information of the region to be selected: used for performing edge extraction processing on the first real-shot image information based on a preset edge detection algorithm to generate a plurality of first information of the region to be selected and first information of the region of the flattening roller, and performing edge extraction processing on the second real-shot image information based on the edge detection algorithm to generate a plurality of second information of the region to be selected and second information of the region of the flattening roller; A wrinkle region information determination submodule: used to determine all of the first wrinkle region information according to a plurality of the first candidate region information and the first flattening roller region information, and to determine all of the second wrinkle region information according to a plurality of the second candidate region information and the second flattening roller region information, wherein the first wrinkle region information is used to describe the first candidate region information in contact with the first flattening roller region information, and the second wrinkle region information is used to describe the second candidate region information in contact with the second flattening roller region information; The area position information determination submodule is used to determine the first area position information for each of the first wrinkle area information according to a preset position coordinate system and the first wrinkle area information, and to determine the second area position information for each of the second wrinkle area information according to the position coordinate system and the second wrinkle area information.

7. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images