A plate detection and conveying method and system based on visual processing

Abstract

The present application discloses a plate inspection and conveying method and system based on visual processing, which belongs to the field of plate conveying technology, and includes: receiving first data collected from a visual acquisition device, preprocessing the first data to generate second data; analyzing the second data, generating an execution signal, and sending the execution signal to a corresponding execution device; receiving third data collected from a conveying acquisition device, comparing it with the execution signal, and correcting the execution signal; performing quality inspection on the plate, and classifying and processing it according to the inspection results. In the implementation process of the technical solution of the present application, by analyzing the second data, generating an execution signal according to the analysis results, and sending the execution signal to the corresponding execution device in sequence, the adjustment of the plate conveying process is realized, and the execution signal is corrected by the third data collected by the conveying acquisition device, so as to ensure the accuracy of the adjustment process and improve production efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of plate conveying, and specifically to a plate detection and conveying method and system based on visual processing. Background Art

[0002] In some large-scale sheet production processes, it is usually necessary to use a sheet conveying line to place the sheets after hot pressing on the conveying line. Driven by the drive equipment, the sheets can be transported to other workstations or stored, and combined with the PLC controller to coordinate the feeding, discharging, grabbing and other processes. When entering the order data, the sheets can also be intelligently sorted, transported, counted, and stacked.

[0003] The existing plate conveying line is mainly composed of belt conveyors, drive devices, control systems, gripping devices and other components. Since the hot press is large in scale, it can meet the needs of hot pressing plates of different colors at the same time. After the hot pressing of the plates, the hot-pressed plates need to be transported to a storage point or transported to a conveying line for further processing, such as cooling, sanding, sawing and other operations. The size and weight of the plates after hot pressing are large. The traditional manual handling method is not only labor-intensive, but also interfered by human factors, resulting in uneven stacking and wrong placement of the plates. After the hot pressing is completed, they need to be classified according to different colors. However, for some plates, the hot pressing process may cause surface damage and poor quality. If such plates cannot be identified and sorted out after the hot pressing is completed, subsequent operations will be aggravated.

[0004] At the same time, in order to ensure production quality, it is necessary to set parameters such as the conveying speed of the plates and the spacing between the plates in advance so that there is a fixed and appropriate spacing between the plates. According to actual conditions, during normal production, it is necessary to keep the plates passing through the workstations at a uniform speed and a smaller spacing, so as to make production efficiency higher. For plates of different sizes, the corresponding parameter information needs to be set in advance to improve production efficiency.

[0005] However, in the plate conveying line, the current technology can only adjust the corresponding parameters before conveying. After the plate is put on the line, if the conveying speed, plate spacing and other parameters need to be adjusted, the machine can only be stopped for setting. When producing and processing different batches of plates, it is time-consuming and labor-intensive. In addition, during the processing of the same batch of plates, if one of the plates has a dimensional deviation, the processing time of the plate will be redundant when the processing time of each plate is fixed, and it will directly affect the subsequent plate processing process. How to adjust the corresponding parameters during the conveying process of the plate has become a problem that needs to be solved urgently.

[0006] Therefore, it is necessary to provide a plate inspection and conveying method and system based on visual processing to solve the above problems.

[0007] It should be noted that the above information disclosed in this background technology section is only for understanding the background technology of the present application concept, and therefore, it may contain information that does not constitute the prior art. Summary of the invention

[0008] Based on the above-mentioned problems existing in the prior art, the problem to be solved by the present application is: to provide a plate detection and conveying method and system based on visual processing, so as to achieve the function of automatic conveying adjustment by collecting the peripheral features and surface features of the plate, generating corresponding execution signals and sending them to the execution device.

[0009] The technical solution adopted by the present application to solve the technical problem is: a plate detection and conveying method based on visual processing, comprising:

[0010] The data center receives the first data collected by the visual collection device, and pre-processes the first data to generate second data. The collection device is set at the feeding place of the plate detection conveyor line. The first data is ordered data.

[0011] Analyze the second data, generate an execution signal according to the analysis result, and send the execution signal to the corresponding execution device in sequence;

[0012] receiving the third data collected by the conveying and collecting device, comparing the third data with the execution signal, and correcting the execution signal according to the comparison result;

[0013] Carry out quality inspection on the boards and classify them according to the inspection results.

[0014] During the implementation of the technical solution of the present application, the second data is analyzed, and an execution signal is generated based on the analysis result. The execution signal is sent to the corresponding execution device in sequence, thereby achieving adjustment of the plate conveying process. The execution signal is also corrected by the third data collected by the conveying acquisition device to ensure the accuracy of the adjustment process and improve production efficiency.

[0015] Furthermore, the data center refers to a hardware module with data analysis and processing, data sending and receiving, and data temporary storage and preservation.

[0016] Furthermore, the execution device includes a speed regulator, a position adjustment device, and a display device.

[0017] Further, analyzing the second data further includes the following steps:

[0018] Extracting a peripheral feature of the plate from the second data, the peripheral feature being an edge contour of the plate, and comparing the extracted peripheral feature with a specification of the plate of the current batch;

[0019] According to the peripheral feature comparison results, determine whether the plate needs to be adjusted in spacing or classified;

[0020] Extracting surface features of the plate from the second data, and obtaining the surface complexity of each plate according to the extracted surface features, wherein the surface features include point cloud data of the plate;

[0021] Generate an execution signal and send the execution signal to the execution device.

[0022] Furthermore, the peripheral features are edge contours of the plate, and the surface features include plate point cloud data, plate surface average curvature, and plate surface texture complexity.

[0023] Furthermore, the method for obtaining the surface complexity of the plate includes: obtaining point cloud data of the plate, and using fractal geometry methods to calculate the fractal dimension of the plate surface, and then comprehensively calculating the calculated fractal dimension of the plate surface in combination with other parameters in the surface features to obtain the surface complexity.

[0024] Furthermore, the calculation process of surface complexity is as follows:

[0025] First, the three-dimensional coordinate information of the plate surface is obtained through point cloud data;

[0026] Then, the fractal dimension of the point cloud data on the plate surface is calculated using the box counting method or the sphere counting method;

[0027] Then, the fractal dimension is weighted in combination with other parameters in the plate surface characteristics to obtain the surface complexity of the plate.

[0028] Furthermore, the execution signal includes a digital signal or an analog voltage signal sent to the speed regulator, a displacement signal of the position adjustment device, a digital signal sent to the display screen, and a pulse signal.

[0029] A plate detection and conveying system based on visual processing, comprising:

[0030] An ordered data receiving module is used for receiving the first data collected by the visual collection device in the data center, and preprocessing the first data to generate second data. The collection device is set at the feeding place of the plate detection conveyor line. The first data is ordered data;

[0031] An execution signal generating module, used for analyzing the second data, generating an execution signal according to the analysis result, and sending the execution signal to the corresponding execution device in sequence;

[0032] An execution signal correction module is used to receive the third data collected from the conveying collection device, compare it with the execution signal, and correct the execution signal according to the comparison result;

[0033] The quality inspection module is used to inspect the quality of the plates and classify them according to the inspection results.

[0034] The beneficial effects of the present application are: the present application provides a plate detection and conveying method and system based on visual processing, which analyzes the second data, generates an execution signal according to the analysis result, and sends the execution signal to the corresponding execution device in sequence, thereby realizing adjustment of the plate conveying process, and also corrects the execution signal through the third data collected by the conveying acquisition device, thereby ensuring the accuracy of the adjustment process and improving production efficiency.

[0035] In addition to the above-described purposes, features and advantages, the present application also has other purposes, features and advantages. The present application will be further described in detail with reference to the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0037] Figure 1 This is a schematic diagram of the overall process of a plate detection and conveying method based on visual processing in this application;

[0038] Figure 2 This is a schematic diagram of the module structure of a plate inspection and conveying system based on visual processing in this application. DETAILED DESCRIPTION

[0039] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0040] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0041] Embodiment 1: Figure 1As shown, the present application provides a plate detection and conveying method based on visual processing, which is applied to the conveying production line of the plate, and can use visual processing and other technologies to identify the color of the plate after hot pressing, and classify the plates of different colors, and at the same time adjust the operating parameters of the conveying production line in the subsequent conveying process to adapt to plates of different sizes and types, so as to further process, sort, stack and other operations on the plates after hot pressing; in the process of hot pressing plates of different colors, the visual acquisition device can be installed on the manipulator, and after the hot pressing is completed, the manipulator automatically completes the scanning of the plate color in the process of carrying the plate, and after the scanning is completed, it is compared with the color database established in advance, so as to realize the counting, conveying, packaging, stacking and other tasks of the plates according to the color;

[0042] When establishing a pattern database, the pattern needs to be designed manually first. After the pattern is designed, batch proofing is performed, and one of the patterns with the highest similarity to the designed pattern is selected for scanning and storage, thereby forming a pattern database;

[0043] It should be noted that after the hot pressing of the plate is completed, it is transported by a robot. Since the robot is equipped with a visual acquisition device, the plate to be transported can be scanned and compared with the stored pattern data in the pattern database to prepare for subsequent classification. When the patterns of the same batch are the same, there is no need to classify them, and the quality of the plate to be transported can be inspected, so there is no need to add additional inspection equipment, reducing production costs;

[0044] Among them, the visual acquisition device installed on the manipulator can be a common device on the market, such as Hikvision, Daheng, etc., which is not limited in this embodiment;

[0045] The plate detection and conveying method comprises the following steps:

[0046] Step 01: The data center receives the first data collected by the visual collection device, and pre-processes the first data to generate second data. The collection device is set at the feeding place of the plate detection conveyor line. The first data is ordered data;

[0047] In the complete plate detection and conveying process, it is necessary to use modules such as plate detection conveyor line, data center, and visual acquisition equipment. The plate detection conveyor line is used to carry and convey the plates to be processed, and processing stations are set at different positions on the plate conveyor line. Each processing station has a fixed processing area. After the plate arrives at the corresponding processing station, the plate entering the processing area will be processed, such as grinding station, slotting station, cutting station, etc.

[0048] A visual acquisition device is provided at the feeding place of the plate detection conveyor line, and the visual acquisition device is used to collect data of the plates entering the plate detection conveyor line and obtain corresponding data. The visual acquisition device can be an industrial camera, a laser scanner, an optical sensor, etc., which is not limited in this embodiment, and only needs to be able to collect images of mobile objects with a certain speed;

[0049] After collecting the plate data, the visual acquisition device also needs to send the first data it has collected to the data center, where the data center refers to a hardware module with data analysis and processing, data transmission and reception, and data temporary storage and preservation. In this embodiment, it can be an industrial computer. It can be understood that there is a wired or wireless channel between the visual acquisition device and the data center for data exchange. In this embodiment, a wireless channel is taken as an example, such as WiFi, Bluetooth, ZigBee, cellular network, etc.;

[0050] After the first data collected by the visual acquisition device is received by the data center, the data center first needs to pre-process the first data and generate second data. Because the first data usually contains a large amount of original information, which may contain noise and redundant data, it is necessary to pre-process the first data to extract useful information. The pre-processing of the first data includes steps such as denoising, contrast enhancement, and edge detection. For details, reference can be made to the optimization processing process of image data in the prior art, which will not be described in detail in this embodiment.

[0051] It should be noted that the first data collected by the visual acquisition device is ordered data, and the order of sending, receiving and storing each data is consistent with the order of the plates going online, so as to facilitate data traceability and achieve a one-to-one correspondence between the plates and the collected data. At the same time, the second data after preprocessing should also be ordered data;

[0052] Step 02: Analyze the second data, generate an execution signal according to the analysis result, and send the execution signal to the corresponding execution device in sequence;

[0053] After preprocessing, the second data needs to be analyzed by the data center to determine whether the entire conveying process needs to be adjusted, wherein the adjustment of the conveying process is achieved through an execution device, which includes: a speed regulator, which is used to adjust the running speed of the plate detection conveyor line, usually by adjusting the speed of the drive motor; a position adjustment device, which is used to adjust the position of a single plate, for example, by a movable clamp, a drive cylinder, a hydraulic push rod, etc., and the specific details can refer to the prior art; a display device, such as a display screen, which can display part of the execution signal, for example, a certain plate needs to be manually turned over, manually moved, etc. The second data is analyzed and processed by the data center, and the analysis result is converted into a corresponding execution signal. After the execution signal is sent to different devices, the corresponding action can be performed on the plate on the plate detection conveyor line, and part of the execution signal can also be sent to the display device for display, so as to realize an execution method combining automatic and manual.

[0054] Specifically, analyzing the second data further includes the following steps:

[0055] Step 02-1: extracting the peripheral feature of the plate from the second data, the peripheral feature being the edge contour of the plate, and comparing the extracted peripheral feature with the plate specification of the current batch;

[0056] The second data includes the peripheral features of the plate. In this embodiment, the peripheral features refer to the edge contour of the plate. The shape, size and other information of the plate can be obtained through the edge contour, and compared with the specifications of the current batch of plates input into the data center to determine whether they meet the requirements;

[0057] Step 02-2: Determine whether the plate needs to be adjusted in spacing or classified according to the peripheral feature comparison results;

[0058] If the peripheral features do not match the plate specifications of the current batch, it means that the plate may have a size deviation or does not belong to the current batch, which will cause the original plate spacing to change. At this time, the data center will generate a corresponding execution signal to instruct the execution equipment to adjust the size or sort it. For example, if the plate size is too large or too small, the speed regulator will adjust the conveyor line speed so that the corresponding size correction can be made at the subsequent processing station; if the plate does not belong to the current batch, the position adjustment device will move the plate to the designated area for sorting or rescheduling the production plan;

[0059] Step 02-3: extracting surface features of the plate from the second data, and calculating the surface complexity of each plate according to the extracted surface features, wherein the surface features include plate point cloud data;

[0060] After analyzing the plate through peripheral features, it is necessary to further analyze the plate from the dimension of surface features. Surface features refer to the point cloud data of the plate, which can reflect the fractal dimension of the plate surface. The fractal dimension can measure the complexity of the plate surface, and the complexity of the plate surface will be related to the running speed of the plate detection conveyor line. For example, when the complexity of the plate surface is high, it is necessary to reduce the running speed of the plate detection conveyor line so that the corresponding plate can be processed to a higher degree and reduce the probability of rework. When the complexity of the plate surface is low, it is necessary to appropriately increase the running speed of the plate detection conveyor line to speed up production efficiency.

[0061] The calculation method of the surface complexity of the plate includes: obtaining point cloud data of the plate, and calculating the fractal dimension of the plate surface by using a fractal geometry method, and then performing a comprehensive calculation on the calculated fractal dimension of the plate surface in combination with other parameters in the surface characteristics to obtain the surface complexity;

[0062] The fractal geometry method can be implemented by using the box counting method or the sphere counting method. The specific operating principle can refer to the prior art. Other parameters in the surface features include but are not limited to the average curvature of the plate surface, the complexity of the plate surface texture, the damaged area of ​​the plate surface, etc. These parameters can be directly generated by the visual acquisition device. Specifically, the calculation process of the surface complexity is as follows:

[0063] Step 02-3-1: First, obtain the three-dimensional coordinate information of the plate surface through point cloud data. These coordinate information can describe the ups and downs and concavities of the plate surface in detail;

[0064] Step 02-3-2: Then, the fractal dimension of the point cloud data on the plate surface is calculated using the box counting method or the sphere counting method; specifically, the plate surface is divided into boxes of different sizes or covered with spheres of different radii, and the number of boxes or spheres covering the point cloud data is counted, so as to obtain the fractal dimension of the plate surface. This step can refer to the prior art, such as related patents containing fractal dimension calculation, which will not be described in detail in this embodiment;

[0065] Step 02-3-3: Then, combine other parameters in the plate surface features and perform weighted processing on the fractal dimension to obtain the surface complexity of the plate; for example, if the fractal dimension D=2.6, the average curvature K=0.02, the texture complexity T=0.5, and the weights w_1=0.7, w_2=0.2, w_3=0.1, where w_1 is the weight of the fractal dimension, w_2 is the dimension of the average curvature, and w_3 is the dimension of the texture complexity, then the plate surface complexity = 2.6×0.7+0.02×0.2+0.5×0.1=1.874, which is the plate surface complexity. When selecting the weight, you can specify it according to the actual situation. For example, a plate with a larger fractal dimension may require more detailed processing, so a higher weight is given when calculating the complexity;

[0066] Step 02-4: Generate an execution signal and send it to the execution device. The execution signal includes a digital signal or an analog voltage signal sent to the speed regulator, a displacement signal of the position adjustment device, a digital signal sent to the display screen, a pulse signal, etc. Specifically, if the surface complexity of the plate is high, the execution signal is a digital signal to reduce the conveying speed. If the size of the plate is abnormal, the execution signal is a displacement signal of the position adjustment device, and a pulse signal can be generated and sent to the display screen at the same time. The display screen displays the adjustment process or recommended operations in real time to ensure that the plate is fully detected and processed in the subsequent processing station; on the contrary, if the surface complexity of the plate is low, the conveyor line speed will be appropriately increased to improve the overall production efficiency.

[0067] Step 03: receiving the third data collected from the transmission collection device, and comparing it with the execution signal, and correcting the execution signal according to the comparison result;

[0068] During the operation of the plate inspection conveyor line, real-time monitoring is crucial. Through the conveying acquisition equipment installed at various positions of the conveyor line, such as photoelectric sensors, laser rangefinders, etc., the position, speed, direction and other information of the plate can be obtained in real time. This information will be transmitted to the data center as the third data and compared with the previously generated execution signal to ensure that the running status of the plate on the conveyor line meets expectations;

[0069] If the position or speed of the plate is detected to be deviant, the data center will immediately generate a new execution signal to instruct the corresponding execution equipment to make corrections. For example, if the plate deviates from the predetermined path, the position adjustment device will make fine adjustments based on the new execution signal to ensure that the plate can return to the correct path; if the plate speed is too fast or too slow, the speed regulator will adjust the conveyor line speed based on the new execution signal to ensure that the plate can achieve the best effect during the inspection and processing of the subsequent processing station.

[0070] Step 04: Conduct quality inspection on the panels and classify them according to the inspection results.

[0071] After the plate has been subjected to surface feature analysis and real-time execution signal correction, it is also necessary to conduct quality inspection. Quality inspection can be achieved through visual inspection systems, ultrasonic inspection equipment, infrared inspection equipment, etc. For details, please refer to the existing technology. These devices can detect defects, cracks, uneven thickness and other problems of the plate after hot pressing, and transmit the inspection results to the data center. The data center will generate corresponding execution signals according to the quality inspection results to instruct the classification processing equipment to classify the plate; for example, for defect-free plates, the execution signal indicates that they will be directly sent to the next processing station; for plates with slight defects, the execution signal indicates that they will be sent to the repair station for repair; for plates with serious defects, the execution signal indicates that they will be moved to the waste area for processing, and the processing process will be sent to the display device for display at the same time;

[0072] Although in the aforementioned process, the visual inspection equipment on the robot can be used to inspect the quality of the hot-pressed plates, the subsequent processing steps may also affect the quality of the plates after passing through the conveyor line, so the quality of the plates still needs to be inspected.

[0073] Embodiment 2: Figure 2 As shown, the present application also provides a plate detection and conveying system based on visual processing, which runs the plate detection and conveying method in Example 1 to adjust and optimize the conveying process of the plate, specifically including the adjustment of the conveying line speed and the plate spacing, and the system includes:

[0074] An ordered data receiving module is used for receiving the first data collected by the visual collection device in the data center, and preprocessing the first data to generate second data. The collection device is set at the feeding place of the plate detection conveyor line. The first data is ordered data;

[0075] An execution signal generating module, used for analyzing the second data, generating an execution signal according to the analysis result, and sending the execution signal to the corresponding execution device in sequence;

[0076] An execution signal correction module is used to receive the third data collected from the conveying collection device, compare it with the execution signal, and correct the execution signal according to the comparison result;

[0077] The quality inspection module is used to inspect the quality of the plates and classify them according to the inspection results.

[0078] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A plate detection and conveying method based on visual processing, characterized in that: include: The data center receives the first data collected by the visual collection device, and pre-processes the first data to generate second data. The collection device is set at the feeding place of the plate detection conveyor line. The first data is ordered data. The second data is analyzed, and an execution signal is generated according to the analysis result, and the execution signal is sent to the corresponding execution device in sequence. If the surface complexity of the plate is high, the execution signal is a digital signal for reducing the conveying speed. On the contrary, if the surface complexity of the plate is low, the conveying line speed is appropriately increased. The analysis of the second data further includes the following steps: Extracting a peripheral feature of the plate from the second data, the peripheral feature being an edge contour of the plate, and comparing the extracted peripheral feature with a specification of the plate of the current batch; According to the peripheral feature comparison results, determine whether the plate needs to be adjusted in spacing or classified; Extracting surface features of the plate from the second data, and obtaining the surface complexity of each plate according to the extracted surface features, wherein the surface features include point cloud data of the plate; The method for obtaining the surface complexity of the plate includes: obtaining point cloud data of the plate, and calculating the fractal dimension of the plate surface using a fractal geometry method, and then performing a comprehensive calculation on the calculated fractal dimension of the plate surface in combination with other parameters in the surface characteristics to obtain the surface complexity; Generate an execution signal and send the execution signal to the execution device; The peripheral features are the edge contours of the plate, and the surface features include plate point cloud data, plate surface average curvature, and plate surface texture complexity; receiving the third data collected by the conveying and collecting device, comparing the third data with the execution signal, and correcting the execution signal according to the comparison result; Carry out quality inspection on the boards and classify them according to the inspection results.

2. According to the method for plate inspection and conveying based on visual processing according to claim 1, it is characterized in that: The data center refers to a hardware module with data analysis and processing, data sending and receiving, and data temporary storage and preservation.

3. The plate detection and conveying method based on visual processing according to claim 1 is characterized in that: The execution device includes a speed regulator, a position adjustment device, and a display device.

4. The plate detection and conveying method based on visual processing according to claim 1 is characterized in that: The calculation process of surface complexity is as follows: First, the three-dimensional coordinate information of the plate surface is obtained through point cloud data; Then, the fractal dimension of the point cloud data on the plate surface is calculated using the box counting method or the sphere counting method; Then, the fractal dimension is weighted in combination with other parameters in the surface characteristics of the plate to obtain the surface complexity of the plate.

5. The plate detection and conveying method based on visual processing according to claim 3 is characterized in that: The execution signal includes a digital signal or an analog voltage signal sent to the speed regulator, a displacement signal of the position adjustment device, a digital signal sent to the display screen, and a pulse signal.

6. A plate inspection and conveying system based on visual processing, characterized in that: include: An ordered data receiving module is used for receiving the first data collected by the visual collection device in the data center, and preprocessing the first data to generate second data. The collection device is set at the feeding place of the plate detection conveyor line. The first data is ordered data; The execution signal generation module is used to analyze the second data, generate an execution signal according to the analysis result, and send the execution signal to the corresponding execution device in sequence. If the surface complexity of the plate is high, the execution signal is a digital signal for reducing the conveying speed. On the contrary, if the surface complexity of the plate is low, the conveying line speed is appropriately increased. The analysis of the second data further includes the following steps: Extracting a peripheral feature of the plate from the second data, the peripheral feature being an edge contour of the plate, and comparing the extracted peripheral feature with a specification of the plate of the current batch; According to the peripheral feature comparison results, determine whether the plate needs to be adjusted in spacing or classified; Extracting surface features of the plate from the second data, and obtaining the surface complexity of each plate according to the extracted surface features, wherein the surface features include point cloud data of the plate; The method for obtaining the surface complexity of the plate includes: obtaining point cloud data of the plate, and calculating the fractal dimension of the plate surface using a fractal geometry method, and then performing a comprehensive calculation on the calculated fractal dimension of the plate surface in combination with other parameters in the surface characteristics to obtain the surface complexity; Generate an execution signal and send the execution signal to the execution device; The peripheral features are the edge contours of the plate, and the surface features include plate point cloud data, plate surface average curvature, and plate surface texture complexity; An execution signal correction module is used to receive the third data collected from the conveying collection device, compare it with the execution signal, and correct the execution signal according to the comparison result; The quality inspection module is used to inspect the quality of the plates and classify them according to the inspection results.

7. The plate inspection and conveying system based on visual processing according to claim 6 is characterized by: Used to implement the plate detection and conveying method based on visual processing as described in any one of claims 1 to 5.

Images