Door plate sleeve shell packaging system based on image recognition

Abstract

The invention discloses a door plate casing packaging system based on image recognition, and the method comprises the steps: recognizing door plate information through a high-precision digital microscopic system, and transmitting parameters to a server; the server analyzes the parameters and transmits the analyzed data to the PC end to control the pressing plate mechanism and the lifting supporting mechanism to clamp one side of the door plate; the digital microscopic system judges whether the surface of the door plate is damaged; the digital microscopic system detects whether the position of the door plate on the packaging device deviates or not; the digital microscopic system measures data of the door plate; a worker carries out casing packaging on one side of the door plate; the steps from S3-S6 are repeated to carry out casing packaging on the other side of the door plate until the whole door plate is subjected to casing packaging; and the digital microscopic system detects the quality of the door plate after the sheathing. According to the method, the casing packaging state of the door plate can be automatically recognized with high precision, respective advantages can be exerted through cooperation of manual work and a machine, the production quality is improved, and the industrial production requirement is met.

Description

Technical Field

[0001] The invention relates to the technical field of door panel shell packaging, and in particular to a door panel shell packaging system based on image recognition. Background Art

[0002] Door panels are made of solid wood or other wood materials, and are scientifically processed through processes such as drying, cutting, planing, mortising, drilling, high-speed milling, assembly, grinding, and painting. After the door panels are made, they need to be transported to the place of use. Since the materials used to make the door panels are mainly made of wood, they need to be packaged in a shell during transportation to prevent cracking and damage during transportation.

[0003] Considering the characteristics of door panels, the shell packaging of door panels on the market is mainly completed by manual and machine cooperation, that is, the door panels are clamped by machines, and then workers shell the two sides of the door panels separately. Manual packaging can optimize the user experience during transportation, sales and use. In addition, during the shell packaging of door panels, manual operation can better consider different packaging methods according to the characteristics of different door panels. In addition, for example, when packaging solid wood door panels, considering their own particularity, manual packaging can minimize damage to the door panels. Therefore, through the cooperation of manual and machine operations, the packaging process of door panels can be more accurately controlled, thereby improving the quality of door panel packaging.

[0004] Chinese invention patent CN116119127A discloses a method for identifying the packaging effect of decorative panels, including: automatically wrapping the panels with a six-sided wrapping machine to obtain a whole package of panels; photographing the whole package of panels with a photographing system to obtain an actual image of the whole package of panels; comparing the actual image with a target image in a database to obtain a comparison result; and conveying the whole package of panels to a position corresponding to the comparison result through a guide lifting roller. This invention simply realizes the packaging of panels, and cannot adopt different packaging methods according to the characteristics of the panels. Summary of the invention

[0005] The present invention provides a door panel shell packaging system based on image recognition. Through a digital microscope system, various data of the door panel during packaging can be detected, and then manual and machine packaging can be carried out to solve the technical problem that the existing packaging system needs to rely on the level of personnel and cause waste of labor.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: The present invention provides a door panel shell packaging system based on image recognition, comprising: S1 uses a high-precision digital microscope system to identify door panel information and transmit the parameters to the server;

[0007] The S2 server analyzes the parameters and transmits the analyzed data to the PC to control the pressing plate mechanism and the lifting support mechanism to clamp one side of the door panel; S3 digital microscope system determines whether the door panel surface is damaged; The S4 digital microscope system detects whether the door panel is offset on the packaging device; S5 digital microscope system measures the data of door panels; S6 staff will package one side of the door panel with a shell; S7 repeats the steps of S3-S6 to package the other side of the door panel until the entire door panel is packaged in the shell; The S8 digital microscope system inspects the quality of the door panels after shelling.

[0008] Compared with the prior art, the present invention has the following beneficial effects: 1 The present invention can help staff quickly determine whether the door panel is damaged before the shell is packaged by using a digital microscope system, and can detect slight cracks and damages that are difficult to observe with the naked eye by further processing the image during the inspection, so that the staff can quickly determine the damage condition of the damaged area of ​​the door panel.

[0009] 2 The present invention can detect whether the door panel is offset when entering the conveyor belt and being clamped by the pressure plate mechanism through a digital microscope system, so as to avoid the deflection of the door panel during the transmission process without the staff's knowledge, and to avoid the displacement of the door panel affecting the packaging quality when the door panel is subsequently packaged in a shell.

[0010] 3 The present invention can quickly measure the size of the door panel through the digital microscope system, so that when the device encounters door panels of different sizes (for example, multiple door panels are stacked), the staff can adopt different packaging methods when packaging the door panels. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 is a flow chart of a door panel shell packaging system based on image recognition provided by an embodiment of the present invention; Figure 2 It is a structural diagram of the device of the present invention; Figure 3 A schematic diagram of defective parts on the door panel surface provided by an embodiment of the present invention; Figure 4A schematic diagram of the Fourier transform characteristics provided by an embodiment of the present invention; Figure 5 It is a system structure diagram of the present invention.

[0013] Among them: 1 support frame, 2 fixed support mechanism, 3 fixed conveyor belt, 4 servo pressure plate mechanism, 5 lifting support mechanism, 6 lifting conveyor belt, 7 rotating shaft, 8 rotating roller, 9 driving motor, 10 servo cylinder. DETAILED DESCRIPTION

[0014] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0015] A door panel shell packaging system based on image recognition.

[0016] Please refer to Figure 1 It is a flow chart of a door panel shell packaging system based on image recognition provided by an embodiment of the present invention.

[0017] S1 uses a high-precision digital microscope system to identify door panel information and transmit the parameters to the server; S101, the high-precision digital microscope system adopts VH-Z100 high-definition RZ lens; It should be noted that there are three digital microscope systems here. One is installed at the entrance of the conveyor belt to detect whether the surface of the door panel is damaged; one is installed above the side of the conveyor belt to detect whether the door panel is offset; and one is installed above the middle of the conveyor belt to detect the size and position of the door panel.

[0018] S102, the server serves as a receiving and transmitting middle end, and is used to receive data generated by the digital microscope system, analyze the data into parameters, and transmit them to the PC end.

[0019] It should be noted that due to the large amount of parallel computing used by image processing and model building devices, RTX4070 GPU is used as the main computing device in this embodiment. In actual production, RTX3080 GPU or above computing power can also be used as image processing equipment.

[0020] The S2 server analyzes the parameters and transmits the analyzed data to the PC to control the pressing plate mechanism and the lifting support mechanism to clamp one side of the door panel; S201, the PC determines the position of the door panel on the conveyor belt according to the parameters of the digital microscope system, and when the door panel reaches the position designated by the PC, the pressing plate mechanism is controlled to move downward to fix one end of the door panel; S202, the PC determines the position of the door panel on the conveyor belt according to the parameters of the digital microscope system, and controls the lifting support mechanism to move downward, so that the unclamped end of the door panel leaks out, so that subsequent staff can pack the door panel into a shell.

[0021] Please refer to Figure 2 It is a structural diagram of a device provided by an embodiment of the present invention.

[0022] S3 digital microscope system determines whether the door panel is damaged; S301, the door panel is damaged including breakage, cracking, and bubbling; S302, using Fourier transform to enhance the feature extraction of the image, as shown in formula (1) to formula (3); Formula (1) Formula (2) Formula (3) in, and represents a function of two independent and uncorrelated variables, and represents the frequency domain variable, represents the spectrum, and Represents spatial frequency.

[0023] Please refer to Figure 4 It is a schematic diagram of Fourier transform characteristics provided by an embodiment of the present invention.

[0024] S303, making a template of a Gaussian filter, and using the Gaussian filter to smooth the image, as shown in formula (4); Formula (4) in, is the point coordinate, is the standard deviation.

[0025] S304, a threshold segmentation algorithm based on grayscale curve fluctuation, specifically as shown in formula (5)-formula (6); Formula (5) Formula (6) in, is the average value of the peaks in the horizontal direction, is the average value of the trough in the horizontal direction, is the dynamic segmentation threshold in the horizontal direction, is the dynamic segmentation threshold in the vertical direction, is the final threshold.

[0026] Please refer to Figure 3 It is a schematic diagram of the surface defect location provided by an embodiment of the present invention.

[0027] After the digital microscope system detects that the door panel is damaged, it will transmit the parameters to the PC, and the PC will control the whole device to stop running; After the device stops running, the staff will further judge the damage of the door panel. If the manual inspection fails, the door panel will not be packaged in a shell; After the digital microscope system determines that the surface damage of the door panel is acceptable, the staff will turn the door panel over, and the digital microscope system determines whether the other side of the door panel is acceptable.

[0028] It should be noted that whether the door panel damage detection is qualified needs to be referenced based on the characteristics of different door panels. In actual production, it is necessary to refer to the test results of the digital microscope system and the work experience of the construction personnel to make a judgment.

[0029] The S4 digital microscope system determines whether the door panel is offset on the conveyor belt; S401, the digital microscope system detects whether the position of the door panel is offset when it moves on the conveyor belt, and determines the angle offset threshold of the door panel axis relative to the conveyor belt; S402, the digital microscope system uses the Canny operator to detect the edge movement path of the door panel, as shown in formulas (7) to (10); Formula (7) Formula (8) Formula (9) Formula (10) in, are edge coordinates, represents the gradient amplitude, Indicates the gradient direction; S403, the offset threshold is within 10 degrees, if it exceeds the threshold, the PC will stop the device and alarm.

[0030] It should be noted that the offset angle of the door panel is obtained by comparing the axis and edge of the door panel with the axis and edge of the conveyor belt. The offset of the door panel includes lateral offset and longitudinal offset. If any of the two offset angles exceeds the threshold, the device will stop running.

[0031] S5 digital microscope system measures the data of the door panel itself; S501, the measured door panel data includes length, width and thickness; S502, the digital microscope system obtains the endpoint coordinates of the wooden board skeleton by a vertex positioning method, as shown in formula (11)-formula (12); Formula (11) Formula (12) in, , represent the horizontal and vertical coordinates of the first point respectively, , Represent the horizontal and vertical coordinates of the second point respectively.

[0032] S503, the digital microscope system determines the size of the wooden board by the distance between the end point coordinates, as shown in formula (13); Formula (13) in, Represents the distance between two points.

[0033] S503, the PC converts the data measured by the digital microscope system into parameters and outputs them to a display.

[0034] It should be noted that the digital microscope system for detecting the size of the door panel is installed on a universal shaft or a mechanical arm to measure the size of each surface of the door panel. At the same time, angle parameters can be set in the digital microscope system to determine whether the end surface of the door panel is flat.

[0035] S6 staff will package one side of the door panel with a shell; S601, the staff selects the appropriate packaging method based on the parameters of the door panels, their dimensions and damage conditions.

[0036] S7 repeats the steps of S3-S6 to package the other side of the door panel until the entire door panel is packaged in the shell; S701, two packaging devices are provided, and the two packaging devices are placed symmetrically along the axis of the movement direction of the door transfer plate; S702, after the staff has wrapped one side of the door panel with a shell, they start the conveyor belt to transport the packaged door panel on one side to another packaging device for packaging.

[0037] S8S8 digital microscope system detects the quality of door panels after shell assembly.

[0038] S801, the digital microscope system takes photos of the packaged door panels for sampling and transmits the data to the PC; S802, the PC stores the detection parameters of the digital microscope system in the cloud for subsequent analysis of the quality of door panels of different batches and the packaging quality of the staff.

[0039] Please refer to Figure 5 It is a system structure diagram provided by an embodiment of the present invention.

[0040] In addition, it should be noted that the present invention can be provided as a method, an apparatus or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0041] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0042] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0043] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0044] Finally, it should be noted that the above is a preferred embodiment of the present invention. It should be pointed out that although the preferred embodiment of the present invention has been described, for those skilled in the art, once the basic creative concept of the present invention is known, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A door panel shell packaging system based on image recognition, comprising: A support frame (1), wherein a lifting support mechanism (5) and a fixed support mechanism (2) are fixedly installed on the left and right sides of the upper end of the support frame (1), respectively; a pressing plate mechanism (4) is fixedly installed on the upper end of the fixed support mechanism (2), and the pressing plate mechanism (4) is controlled to move up and down by a servo cylinder (10) fixedly installed on the fixed support mechanism (2); two rotating shafts (7) are fixedly installed on the upper end of the fixed support mechanism (2), and the two rotating shafts (7) are connected to each other through a fixed conveyor belt (3); two rotating rollers (8) are fixedly installed on the upper end of the lifting support mechanism (3), and the two rotating rollers (8) are connected to each other through a lifting conveyor belt (6); and the rotating shafts (7) and the rotating rollers (8) are synchronously driven by two identical driving motors (9) respectively; It is characterized in that it also includes the following steps: S1 uses a high-precision digital microscope system to identify door panel information and transmit the parameters to the server; The S2 server analyzes the parameters and transmits the analyzed data to the PC to control the pressing plate mechanism and the lifting support mechanism to clamp one side of the door panel; S3 digital microscope system determines whether the door panel surface is damaged; The S4 digital microscope system detects whether the door panel is offset on the packaging device; S5 digital microscope system measures the data of door panels; S6 staff will package one side of the door panel with a shell; S7 repeats the steps of S3-S6 to package the other side of the door panel until the entire door panel is packaged in the shell; The S8 digital microscope system inspects the quality of the door panels after shelling.

2. The door panel shell packaging system based on image recognition according to claim 1, characterized in that: The S1 uses a high-precision digital microscope system to identify door panel information and transmits parameters to the server, where: S101, the high-precision digital microscope system adopts VH-Z100 high-definition RZ lens; S102, the server serves as a receiving and transmitting middle end, and is used to receive data generated by the digital microscope system, analyze the data into parameters, and transmit them to the PC end.

3. The door panel shell packaging system based on image recognition according to claim 1, characterized in that: The S2 server analyzes the parameters and transmits the analyzed data to the PC to control the pressing plate mechanism and the lifting support mechanism to clamp one side of the door panel, wherein: S201, the PC determines the position of the door panel on the conveyor belt according to the parameters of the digital microscope system, and when the door panel reaches the position designated by the PC, the pressing plate mechanism is controlled to move downward to fix one end of the door panel; S202, the PC determines the position of the door panel on the conveyor belt according to the parameters of the digital microscope system, and controls the lifting support mechanism to move downward, so that the unclamped end of the door panel leaks out, so that subsequent staff can pack the door panel into a shell.

4. The door panel shell packaging system based on image recognition according to claim 1, characterized in that: The S3 digital microscope system determines whether the door panel is damaged, wherein: S301, the door panel is damaged including breakage, cracking, and bubbling; S302, using Fourier transform to enhance the feature extraction of the image, as shown in formula (1) to formula (3); Formula (1) Formula (2) Formula (3) in, and represents a function of two independent and uncorrelated variables, and represents the frequency domain variable, represents the spectrum, and represents the spatial frequency; S303, making a template of a Gaussian filter, and using the Gaussian filter to smooth the image, as shown in formula (4); Formula (4) in, is the point coordinate, is the standard deviation; S304, a threshold segmentation algorithm based on grayscale curve fluctuation, specifically as shown in formula (5)-formula (6); Formula (5) Formula (6) in, is the average value of the peaks in the horizontal direction, is the average value of the trough in the horizontal direction, is the dynamic segmentation threshold in the horizontal direction, is the dynamic segmentation threshold in the vertical direction, is the final threshold.

5. The door panel damage according to claim 4 includes breakage, cracking, and blistering, characterized in that: After the digital microscope system detects that the door panel is damaged, it will transmit the parameters to the PC, and the PC will control the whole device to stop running; After the device stops running, the staff will further judge the damage of the door panel. If the manual inspection fails, the door panel will not be packaged in a shell; After the digital microscope system determines that the surface damage of the door panel is acceptable, the staff will turn the door panel over, and the digital microscope system will determine whether the other side of the door panel is acceptable.

6. The door panel shell packaging system based on image recognition according to claim 1, characterized in that: The S4 digital microscope system determines whether the position of the door panel on the conveyor belt is offset, wherein: S401, the digital microscope system detects whether the position of the door panel is offset when it moves on the conveyor belt, and determines the angle offset threshold of the door panel axis relative to the conveyor belt; S402, the digital microscope system uses the Canny operator to detect the edge movement path of the door panel, as shown in formulas (7) to (10); Formula (7) Formula (8) Formula (9) Formula (10) in, are edge coordinates, represents the gradient amplitude, Indicates the gradient direction; S403, the offset threshold is within 10 degrees, if it exceeds the threshold, the PC will stop the device and alarm.

7. The door panel shell packaging system based on image recognition according to claim 1, characterized in that: The S5 digital microscope system measures the data of the door panel itself, including: S501, the measured door panel data includes length, width and thickness; S502, the digital microscope system obtains the endpoint coordinates of the wooden board skeleton by a vertex positioning method, as shown in formula (11)-formula (12); Formula (11) Formula (12) in, , Represent the horizontal and vertical coordinates of the first point respectively, , Respectively represent the abscissa and ordinate of the second point; S503, the digital microscope system determines the size of the wooden board by the distance between the end point coordinates, as shown in formula (13); Formula (13) in, Indicates the distance between two points; S503, the PC converts the data measured by the digital microscope system into parameters and outputs them to a display.

8. The door panel shell packaging system based on image recognition according to claim 1, characterized in that: The S6 staff performs shell packaging on one side of the door panel, which is characterized by: S601, the staff selects the appropriate packaging method based on the parameters of the door panels, their dimensions and damage conditions.

9. The door panel shell packaging system based on image recognition according to claim 1, characterized in that: In step S7, the steps S3 to S6 are repeated to package the other side of the door panel in a shell until the entire door panel is packaged in a shell, wherein: S701, two packaging devices are provided, and the two packaging devices are placed symmetrically along the axis of the movement direction of the door transfer plate; S702, after the staff has wrapped one side of the door panel with a shell, they start the conveyor belt to transport the packaged door panel on one side to another packaging device for packaging.

10. The door panel shell packaging system based on image recognition according to claim 1, characterized in that: The S8 digital microscope system detects the quality of the door panels after shelling, where: S801, the digital microscope system takes photos of the packaged door panels for sampling and transmits the data to the PC; S802, the PC stores the detection parameters of the digital microscope system in the cloud for subsequent analysis of the quality of door panels of different batches and the packaging quality of the staff.

Images