Registering method, device, electronic equipment and storage medium in rotary screen printing process

Abstract

The application discloses a matching method and device in a rotary screen printing process, electronic equipment and a storage medium, which can realize more accurate and efficient matching operation in the rotary screen printing process. The method comprises the following steps: acquiring a complete printing image of a target fabric; respectively performing feature extraction on the complete printing image and a template printing image to obtain first image features and second image features; performing deviation calculation on the first image features and the second image features to obtain image deviation data, and determining an adjustment parameter according to the image deviation data; generating a control instruction corresponding to the adjustment parameter, and adjusting the position of the rotary screen by using the control instruction to realize the matching process.

Description

Technical Field

[0001] This application relates to the field of rotary screen printing technology, and in particular to a method, apparatus, electronic device, and computer-readable storage medium for matching patterns in the rotary screen printing process. Background Technology

[0002] In the textile printing and dyeing industry, rotary screen printing is widely used in the printing process due to its high production efficiency and wide adaptability. Rotary screen printing machines are typically equipped with multiple independent rotary screens. During the printing process, the fabric is firmly attached to the printing guide belt and runs continuously, passing sequentially through each rotary screen pressed tightly against the fabric surface. Magnetic rods inside the screens evenly squeeze the ink onto the fabric through the pattern mesh, completing multi-color overprinting. In this process, pattern matching is the core key to determining the printing quality. Pattern matching refers to adjusting the running position of the rotary screens of different colors to achieve precise alignment of the printed patterns on the fabric. If the pattern matching deviation is too large, defects such as "mismatched patterns" will occur, resulting in substandard products and wasting raw materials and equipment operating costs. As the textile industry continues to improve printing precision, traditional manual pattern matching methods relying on visual inspection are no longer sufficient to meet actual production needs.

[0003] Therefore, how to achieve more accurate and efficient pattern matching in rotary screen printing is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of this application is to provide a pattern matching method in the rotary screen printing process, which can achieve more accurate and efficient pattern matching operation in the rotary screen printing process; another purpose of this application is to provide a pattern matching device, electronic device and computer-readable storage medium in the rotary screen printing process, all of which have the above-mentioned beneficial effects.

[0005] In a first aspect, this application discloses a pattern matching method in the rotary screen printing process, including: Obtain a complete printed image of the target fabric; Feature extraction is performed on the complete printed image and the template printed image respectively to obtain the first image feature and the second image feature; The deviation between the first image feature and the second image feature is calculated to obtain image deviation data, and the adjustment parameters are determined based on the image deviation data. The control command corresponding to the adjustment parameter is generated, and the position of the circular mesh is adjusted using the control command to achieve the matching of patterns.

[0006] Optionally, obtain a complete printed image of the target fabric, including: The fabric printing image of the target fabric is acquired using a line scan camera; All the fabric print images are stitched together to obtain the complete print image.

[0007] Optionally, feature extraction is performed on the complete printed image and the template printed image respectively to obtain first image features and second image features, including: The complete printed image is segmented to obtain complete printed sub-images. Features are extracted from each complete printed sub-image to obtain the sub-image features of all the complete printed sub-images as the first image features. The template printing image is segmented to obtain template printing sub-images. Features are extracted from each template printing sub-image to obtain the sub-image features of all template printing sub-images as the second image features. Accordingly, the deviation between the first image feature and the second image feature is calculated to obtain image deviation data, including: The deviations between the sub-image features of the corresponding complete printed sub-images and the sub-image features of the template printed sub-images are calculated to obtain the sub-image deviation data. The image deviation data is calculated based on all the sub-image deviation data.

[0008] Optionally, the image deviation data is the image pixel deviation, and the adjustment parameters are determined based on the image deviation data, including: The physical deviation of the image is calculated based on the image pixel deviation and the unit pixel size; The image physical deviation is converted into the adjustment parameter based on the device error using a preset conversion model.

[0009] Optionally, after generating control commands corresponding to the adjustment parameters and using the control commands to adjust the position of the circular mesh to achieve the desired pattern, the process further includes: Obtain the pattern matching result, and if the pattern matching result is a failure, return to the step of obtaining the complete printed image of the target fabric; The system counts the number of failed flower pairings and outputs an alarm when the number of failed flower pairings reaches a preset number.

[0010] Optionally, after generating control commands corresponding to the adjustment parameters and using the control commands to adjust the position of the circular mesh to achieve the desired pattern, the process further includes: When the flower matching result is successful, the image deviation data corresponding to the current flower matching processing operation is statistically analyzed. The preset conversion model is optimized and updated using the image deviation data.

[0011] Optionally, the control command is used to adjust the position of the circular mesh to achieve pattern matching, including: The control command is sent to the motor device corresponding to the circular mesh, so that the motor device drives the circular mesh to adjust its position according to the adjustment parameters, so as to achieve the matching process.

[0012] Secondly, this application discloses a pattern matching device in the rotary screen printing process, comprising: The acquisition module is used to acquire a complete printed image of the target fabric; The extraction module is used to extract features from the complete printed image and the template printed image respectively to obtain the first image features and the second image features; The calculation module is used to calculate the deviation between the first image feature and the second image feature to obtain image deviation data, and determine the adjustment parameters based on the image deviation data; The adjustment module is used to generate control commands corresponding to the adjustment parameters, and to use the control commands to adjust the position of the circular mesh to achieve the matching process.

[0013] Thirdly, this application discloses an electronic device, including: Memory, used to store computer programs; A processor, used to execute the computer program to implement the steps of the matching method in any of the rotary screen printing processes described above.

[0014] Fourthly, this application discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the matching method in any of the rotary screen printing processes described above.

[0015] This application provides a pattern matching method in rotary screen printing, comprising: acquiring a complete printed image of the target fabric; extracting features from the complete printed image and the template printed image respectively to obtain a first image feature and a second image feature; calculating the deviation between the first image feature and the second image feature to obtain image deviation data, and determining adjustment parameters based on the image deviation data; generating control instructions corresponding to the adjustment parameters, and using the control instructions to adjust the position of the rotary screen to achieve pattern matching.

[0016] By applying the technical solution provided in this application, feature deviation calculations are performed on the complete printed image of the target fabric and the printed image of the template to obtain image deviation data between the two. Based on this image deviation data, adjustment parameters for controlling the position adjustment of the rotary screen are determined, allowing for position adjustment of the rotary screen in the rotary screen printing system, thereby achieving pattern matching. Therefore, this technical solution achieves fully automated pattern matching in the rotary screen printing process, completely eliminating manual reliance and effectively improving pattern matching efficiency and accuracy.

[0017] The matching device, electronic equipment, and computer-readable storage medium in the rotary screen printing process provided in this application also have the above-mentioned technical effects, and will not be described in detail here. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the prior art and the embodiments of this application, the accompanying drawings used in the description of the prior art and the embodiments of this application will be briefly introduced below. Of course, the accompanying drawings described below with respect to the embodiments of this application are only a part of the embodiments in this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort, and such other drawings also fall within the protection scope of this application.

[0019] Figure 1 A schematic flowchart illustrating a pattern matching method in a rotary screen printing process provided in this application embodiment; Figure 2 This is a schematic diagram of the structure of a rotary screen printing system provided in an embodiment of this application; Figure 3 A schematic flowchart illustrating another pattern matching method in rotary screen printing provided in this application embodiment; Figure 4 A schematic diagram of a pattern matching device in a rotary screen printing process provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] The core of this application is to provide a pattern matching method in the rotary screen printing process, which can achieve more accurate and efficient pattern matching operation in the rotary screen printing process; another core of this application is to provide a pattern matching device, electronic device and computer-readable storage medium in the rotary screen printing process, all of which have the above-mentioned beneficial effects.

[0021] To provide a clearer and more complete description of the technical solutions in the embodiments of this application, the technical solutions in the embodiments of this application will be described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0022] This application provides a method for matching patterns in the rotary screen printing process.

[0023] Please refer to Figure 1, Figure 1 The flowchart of a pattern matching method in a rotary screen printing process provided in the embodiments of this application may include, but is not limited to, the following S101~S104.

[0024] S101: Obtain a complete printed image of the target fabric.

[0025] This step aims to acquire a complete printed image of the target fabric, which is the fabric that needs to be matched with the pattern. A complete printed image refers to the overall image of a single pattern within the field of view. The field of view of a single pattern is the visual range covered by a set of complete printed patterns. Based on this, the complete printed image of the target fabric can be obtained through an image acquisition device.

[0026] In one embodiment of this application, obtaining a complete printed image of the target fabric may include: acquiring a fabric printed image of the target fabric using a line scan camera; and stitching together all the fabric printed images to obtain a complete printed image.

[0027] This application provides a method for acquiring a complete printed image of a target fabric. It is understood that target fabrics vary in size, and the size of the complete printed image on the target fabric also varies. Conventional cameras may not be able to capture a complete printed image, but only a partial one, meaning the printed image is incomplete, making pattern matching impossible. Therefore, this application proposes a method for acquiring a complete printed image of a target fabric using a line scan camera. Even if each camera in the line scan camera can only capture a partial printed image of the target fabric, a complete printed image can still be obtained through image stitching. The image stitching can be implemented using registration algorithms such as phase correlation.

[0028] In one possible implementation, the line scan camera can be an industrial-grade high-definition line scan camera, equipped with an LED strip light source. The line scan camera specifications are as follows: sensor RGB true color, resolution ≥ 16384 pixels / line, line frequency ≥ 40K, data bandwidth ≥ 20Gbps; the LED strip light source specifications are as follows: luminous length ≥ 2000mm, white light (5500-6500K), adjustable brightness. Furthermore, the acquisition frequency of the line scan camera can be controlled according to actual conditions.

[0029] S102: Extract features from the complete printed image and the template printed image respectively to obtain the first image features and the second image features.

[0030] S103: Calculate the deviation between the first image feature and the second image feature to obtain image deviation data, and determine the adjustment parameters based on the image deviation data.

[0031] The above steps aim to extract features and calculate feature deviations between the complete printed image and the template printed image. In other words, the image features of the complete printed image and the template printed image are extracted and compared to calculate the feature deviation between them. Based on the result of the feature deviation calculation (i.e., the image deviation data mentioned above), the corresponding adjustment parameters can be determined to facilitate the matching operation.

[0032] In one embodiment of this application, feature extraction is performed on the complete printed image and the template printed image to obtain a first image feature and a second image feature. This may include: segmenting the complete printed image to obtain complete printed sub-images, extracting features from each complete printed sub-image to obtain sub-image features of all complete printed sub-images as the first image feature; segmenting the template printed image to obtain template printed sub-images, extracting features from each template printed sub-image to obtain sub-image features of all template printed sub-images as the second image feature. Accordingly, the deviation calculation of the first image feature and the second image feature to obtain image deviation data may include: calculating the deviation of the sub-image features of the corresponding complete printed sub-image and the sub-image features of the template printed sub-image to obtain sub-image deviation data; and calculating the image deviation data based on all sub-image deviation data.

[0033] This application provides a method for feature extraction and feature deviation calculation of complete printed images and template printed images, aiming to further improve the matching efficiency in rotary screen printing. Specifically, the complete printed image and the template printed image can be segmented according to the same segmentation rules to obtain multiple complete printed sub-images and multiple template printed sub-images. Then, by calculating the deviation between the corresponding features of the complete printed sub-images and the template printed sub-images, and combining all the sub-image deviation data, the image deviation data between the complete printed image and the template printed image can be calculated. The deviation calculation of the corresponding features of the complete printed sub-images and the template printed sub-images can be performed using a parallel computing method to improve work efficiency.

[0034] In one possible implementation, the extraction of sub-image features and the calculation of deviations can be achieved using a high-performance Graphics Processing Unit (GPU) paired with GPU parallel computing software. The GPU specifications are as follows: ≥8192 cores, ≥24GB of video memory, and ≥512GB / s bandwidth. Furthermore, the template printing image can be pre-stored in the GPU. Therefore, by employing a CPU (for sub-image segmentation and sub-image deviation data fusion calculation) + GPU collaborative working mode, the complex computational task can be decomposed into parallel sub-tasks, significantly improving computational efficiency and meeting the real-time requirements of high-definition, high-speed printing.

[0035] In one embodiment of this application, the image deviation data is the image pixel deviation. Determining the adjustment parameter based on the image deviation data may include: calculating the image physical deviation based on the image pixel deviation and the unit pixel size; and converting the image physical deviation into an adjustment parameter based on device error using a preset conversion model.

[0036] This application provides a method for determining adjustment parameters based on image deviation data. Specifically, the image deviation data can be converted into physical image deviation, and then the physical image deviation can be converted into adjustment parameters. The image deviation data can specifically be image pixel deviation, i.e., the deviation between corresponding pixels in the complete printed sub-image and the template printed sub-image. The physical image deviation between the complete printed image and the template printed image can then be calculated based on the unit pixel size. Further, a preset conversion model can be retrieved from an industrial database to convert the physical image deviation into corresponding adjustment parameters. In one possible implementation, the industrial database can be an industrial-grade database hardware device used to store the preset conversion model. This preset conversion model can be used to provide feedback on the adjustment parameters corresponding to specific physical deviations (0.1mm level). For example, when the physical image deviation is 0.12mm, the corresponding adjustment parameter can be 0.15mm or 0.11mm, thus taking into account the influence of equipment errors to effectively ensure the accuracy of the pattern matching results.

[0037] S104: Generate control commands corresponding to the adjustment parameters, and use the control commands to adjust the position of the circular mesh to achieve pattern matching.

[0038] This step aims to adjust the position of the rotary screen in the rotary screen printing system based on adjustment parameters. First, control instructions corresponding to the adjustment parameters are generated. Then, the position of the rotary screen is adjusted using these control instructions, thereby achieving pattern matching. In one possible implementation, the control instructions corresponding to the adjustment parameters can be generated using an industrial-grade programmable logic controller (PLC) and an encoder. The PLC has a single-point maximum frequency ≥100kHz-200kHz, and the encoder can be an incremental differential encoder with a frequency ≥2500ppr.

[0039] In one embodiment of this application, adjusting the position of the circular mesh using control commands to achieve pattern matching can include: sending control commands to the corresponding motor device of the circular mesh so that the motor device drives the circular mesh to adjust its position according to the adjustment parameters to achieve pattern matching.

[0040] In other words, the adjustment of the circular mesh position can be achieved through a motor device. This motor device can be connected to the end of the circular mesh, and the rotation of the motor drives the circular mesh to adjust its position. Based on this, the control commands can specifically control the rotation direction, rotation angle, and rotation speed of the motor device. In one possible implementation, the motor device can be a servo motor with the following specifications: rotor inertia ≥ 0.1-0.2 times the load inertia, minimum adjustment step ≤ 0.01mm.

[0041] In addition, after generating the control instructions corresponding to the above-mentioned adjustment parameters and using the control instructions to adjust the position of the rotary screen to achieve the pattern matching process, it may also include: obtaining the pattern matching result, and when the pattern matching result is a failure, returning to obtain the complete printed image of the target fabric; counting the number of pattern matching failures, and outputting an alarm prompt when the number of pattern matching failures reaches a preset number.

[0042] Specifically, after the flower matching operation is completed, a cyclic detection operation can be initiated to check whether the matching was successful. If multiple matching attempts fail, an alarm will be triggered to alert the operator to assist in troubleshooting. The detection of successful matching involves determining whether the matching deviation is below a preset threshold. If so, the matching is considered successful; otherwise, it is considered a failure. Of course, the specific values ​​of the preset number of attempts and the preset threshold do not affect the implementation of this technical solution and can be set by technical personnel according to actual conditions; this application does not impose any limitations on them.

[0043] Furthermore, the pattern matching method in the rotary screen printing process can also include: when the pattern matching result is successful, statistically analyzing the image deviation data corresponding to the current pattern matching operation; and using the image deviation data to optimize and update the preset conversion model. In other words, to effectively ensure pattern matching accuracy, the preset conversion model can be optimized and updated using the image deviation data after successful pattern matching. This optimization and update operation can be performed periodically or in real time; this application does not limit this. Therefore, the model accuracy can be effectively guaranteed, thereby ensuring the accuracy of the pattern matching result.

[0044] As can be seen, the pattern matching method in the rotary screen printing process provided in this application calculates the feature deviation between the complete printed image of the target fabric and the template printed image to obtain image deviation data between the two. Based on this image deviation data, adjustment parameters for controlling the position adjustment of the rotary screen can be determined, allowing for position adjustment of the rotary screen in the rotary screen printing system based on these adjustment parameters, thereby achieving pattern matching. Therefore, this technical solution achieves fully automated pattern matching in the rotary screen printing process, completely eliminating manual reliance and effectively improving pattern matching efficiency and accuracy.

[0045] Based on the above embodiments, this application proposes another method for matching patterns in the rotary screen printing process.

[0046] First, please refer to Figure 2 , Figure 2 The schematic diagram of a rotary screen printing system provided in this application embodiment mainly includes an image acquisition unit, an image storage unit, a high-performance computing unit, a deviation calculation unit, an industrial database, a control unit, and an execution unit, forming a closed loop. The functions of each component are implemented as follows: 1. Image Acquisition Unit: The core component is an industrial-grade high-definition line scan camera, whose acquisition frequency can be controlled by the encoder of the control unit, and it is equipped with an LED strip light source. The image acquisition unit can acquire high-definition printed images of the fabric on the printing guide belt in real time, and the acquired raw image data (fabric printed image) is transmitted to the image storage unit in real time.

[0047] 2. Image Storage Unit: The core component is an industrial-grade high-speed memory card, connected to the image acquisition unit and high-performance computing unit. Its specifications are as follows: total bandwidth ≥ 40Gbps, connected to the motherboard of the server where the deviation calculation unit is located via a PCIe 3.0 or higher slot. The image storage unit can receive raw image data from the image acquisition unit, temporarily store and preprocess it (stitching the raw image data into a single-flower back-view field of view, which can reach 2×3×16K×16K≈1.6 billion pixels, which can be called billion-pixel level), and then send the high-definition image data (complete printed image) to the high-performance computing unit.

[0048] 3. High-performance computing unit: The core component is a high-performance graphics processing unit (GPU), along with GPU parallel computing software, which connects to the image storage unit and the deviation calculation unit. The high-performance computing unit receives high-definition image data with billions of pixels transmitted from the image storage unit, combines it with the pre-stored printing artwork (template printing image), quickly completes parallel calculations of the image data, and transmits the calculated image feature data to the deviation calculation unit.

[0049] 4. Deviation Calculation Unit: The core component is the Central Processing Unit (CPU), which can share a server with the GPU of the High-Performance Computing Unit. The Deviation Calculation Unit can receive image feature data transmitted from the High-Performance Computing Unit to complete deviation calculation, form numerical deviation (image deviation data), and complete physical deviation conversion. Then, based on the artificial intelligence pre-trained model (preset conversion new model) in the industrial database, it completes the intelligent conversion between image physical deviation and adjustment parameters. Finally, the obtained physical deviation data is transmitted to the control unit and simultaneously fed back to the industrial database.

[0050] 5. Industrial Database: Employing industrial-grade database hardware, the system provides process data and pre-trained models to the deviation calculation unit. The pre-trained model is used to provide feedback on the adjustment parameters corresponding to specific physical deviations (0.1mm level), which are then retrieved by the control unit. Simultaneously, the industrial database can iteratively optimize the pre-trained model using new deviation data and adjustment results, improving the accuracy of subsequent adjustments. Furthermore, the database supports real-time data updates and queries, ensuring the accuracy and adaptability of control commands.

[0051] 6. Control Unit: The core is an industrial-grade programmable logic controller (PLC), which connects to an industrial database and execution units. It generates control commands based on the execution unit adjustment parameters obtained from the industrial database and sends them to the execution units. Simultaneously, it receives adjustment feedback signals from the execution units. If adjustment fails, it triggers an alarm module and transmits the abnormal information to the industrial database for subsequent model optimization. Furthermore, the encoder can acquire the printing spindle's rotational speed parameters in real time, establish a communication connection with the image acquisition unit, convert the data into pulse signals, and send them to the image acquisition unit to control the image acquisition frequency.

[0052] 7. Execution Unit: The core component is a motor, which can receive control commands from the control unit to adjust the end cap of the circular mesh connected to it, thereby driving the circular mesh to make precise adjustments.

[0053] For further information, please refer to [link / reference]. Figure 3 , Figure 3 The flowchart illustrates another pattern matching method in rotary screen printing provided in this application embodiment, and its specific implementation process is as follows: S1: System initialization.

[0054] The system starts up the seven core components (image acquisition unit, image storage unit, high-performance computing unit, deviation calculation unit, industrial database, control unit, and execution unit), performs a self-test, and checks the communication status and operating parameters of each component through the control unit. If an abnormality is detected during the self-test, an alarm is triggered. If the self-test is normal, the parameters of each component are configured through the control unit to complete the initialization.

[0055] S2: Image acquisition and transmission.

[0056] The encoder of the execution unit collects the printing spindle speed parameters in real time and transmits them to the line scan camera of the image acquisition unit. This allows the line scan camera to adjust its acquisition frequency according to the parameters (the encoder is installed on the printing spindle; the faster the printing speed, the higher the pulse frequency emitted by the encoder, showing a positive correlation; for example, if the printed fabric moves 1m, and the camera needs to take 100,000 shots based on accuracy requirements, but the actual pulse frequency emitted by the encoder is 160,000, then it needs to be adjusted to the acquisition frequency of 100,000 shots based on the parameters—the actual pulse frequency is 160,000). At the same time, the matching supplementary light source is turned on synchronously to perform multi-exposure acquisition of the printing area of ​​the running fabric, acquiring a certain number of rows of images, and transmitting the original image data to the image storage unit for buffering in real time.

[0057] S3: Image storage and preprocessing.

[0058] After receiving the original image data, the image storage unit forms a complete high-definition image with a single-view field of view of one billion pixels. That is, it stitches the linear array image into an overall two-dimensional image, which can be achieved by using registration algorithms such as phase correlation. Then, the image data is transmitted to the high-performance computing unit.

[0059] S4: High-performance computing.

[0060] The high-performance computing unit receives image data transmitted from the image storage unit, performs calculations based on GPU parallel computing software, compares real-time image features with printing draft features at the pixel level to calculate the sub-image numerical deviation between the two (the sub-image level numerical offset obtained by convolution after cutting a billion-pixel image into sub-images), and then transmits the calculated sub-image numerical deviation to the deviation calculation unit.

[0061] S5: Deviation Calculation and Label Definition.

[0062] The deviation calculation unit receives data from the high-performance computing unit. It automatically generates a misprint label based on the number of print sets in the batch (i.e., the number of rotary screens used in the batch) and transmits the label to the control unit. The misprint label generation process includes: associating the deviation of each pattern with the corresponding rotary screen number based on the data from the high-performance computing unit, and combining this with the deviation type (e.g., warp, weft, diagonal, etc.) to generate a misprint label. This label contains information such as the rotary screen number, relative position, and deviation type.

[0063] S6: Retrieve industrial database.

[0064] The system provides a built-in AI pre-trained model for the control unit, which is then called up by the control unit. After obtaining the physical parameters that can be adjusted by the execution unit based on the calculated numerical deviation, the system outputs matching adjustment parameters based on the AI ​​pre-trained model and feeds them back to the control unit in real time.

[0065] S7: Control command generation and transmission.

[0066] The control unit receives adjustment parameters from the industrial database and converts them into control commands to specify the motor's rotation direction, rotation angle, etc. Then, it sends the control commands to the corresponding motor in the execution unit to adjust the rotation speed of the circular mesh spindle.

[0067] S8: Perform adjustment and alarm judgment.

[0068] After receiving the control command, the motor of the execution unit starts closed-loop control and drives the circular mesh to make fine adjustments. When the physical accuracy reaches 0.10mm, the motor transmits the adjustment feedback signal to the control unit and enters the cyclic detection step. If the deviation is still greater than 0.15mm after N adjustments, an alarm is triggered to remind the operator to assist in troubleshooting. N is a settable parameter.

[0069] S9: Loop detection.

[0070] The control unit collects the real-time operating status of the printing production line and determines whether to continue printing. If printing continues, it returns to S2 and repeats the above process to form a closed-loop control, ensuring the accuracy of pattern matching throughout the process. If printing stops (e.g., when the fabric is exhausted, the task is completed, or the fault cannot be resolved), after confirmation by the operator, the control unit shuts down each component in sequence, automatically saves the pattern matching data (such as deviation values, adjustment parameters, alarm records, etc.) to the industrial database, and ends the process.

[0071] As can be seen, the pattern matching method in the rotary screen printing process provided in this application calculates the feature deviation between the complete printed image of the target fabric and the template printed image to obtain image deviation data between the two. Based on this image deviation data, adjustment parameters for controlling the position adjustment of the rotary screen can be determined, allowing for position adjustment of the rotary screen in the rotary screen printing system based on these adjustment parameters, thereby achieving pattern matching. Therefore, this technical solution achieves fully automated pattern matching in the rotary screen printing process, completely eliminating manual reliance and effectively improving pattern matching efficiency and accuracy.

[0072] This application provides a pattern matching device in the rotary screen printing process.

[0073] Please refer to Figure 4 , Figure 4 This is a schematic diagram of the structure of a pattern matching device in a rotary screen printing process provided in an embodiment of this application. The pattern matching device in the rotary screen printing process may include: Module 1 is used to acquire a complete printed image of the target fabric; Extraction module 2 is used to extract features from the complete printed image and the template printed image respectively to obtain the first image features and the second image features; The calculation module 3 is used to calculate the deviation between the first image feature and the second image feature to obtain image deviation data, and to determine the adjustment parameters based on the image deviation data. Adjustment module 4 is used to generate control commands corresponding to the adjustment parameters, and to use the control commands to adjust the position of the circular mesh in order to achieve pattern matching.

[0074] As can be seen, the pattern matching device in the rotary screen printing process provided in this application calculates the feature deviation between the complete printed image of the target fabric and the printed image of the template, thereby obtaining image deviation data between the two. Based on this image deviation data, adjustment parameters for controlling the position adjustment of the rotary screen can be determined, facilitating the position adjustment of the rotary screen in the rotary screen printing system, thus achieving pattern matching. Therefore, this technical solution achieves fully automated pattern matching in the rotary screen printing process, completely eliminating manual reliance and effectively improving pattern matching efficiency and accuracy.

[0075] In one embodiment of this application, the acquisition module 1 can be specifically used to acquire fabric printing images of the target fabric using a line scan camera; and to stitch together all the fabric printing images to obtain a complete printing image.

[0076] In one embodiment of this application, the extraction module 2 described above can be specifically used to segment the complete printed image to obtain complete printed sub-images, extract features from each complete printed sub-image, and obtain the sub-image features of all complete printed sub-images as first image features; and to segment the template printed image to obtain template printed sub-images, extract features from each template printed sub-image, and obtain the sub-image features of all template printed sub-images as second image features. Accordingly, the above calculation module 3 can be specifically used to calculate the deviation between the sub-image features of the corresponding complete printed sub-image and the sub-image features of the template printed sub-image to obtain sub-image deviation data; and to calculate image deviation data based on all sub-image deviation data.

[0077] In one embodiment of this application, the image deviation data is the image pixel deviation. The above-mentioned calculation module 3 can be specifically used to calculate the image physical deviation based on the image pixel deviation and the unit pixel size; and to convert the image physical deviation into an adjustment parameter based on the device error using a preset conversion model.

[0078] In one embodiment of this application, the pattern matching device in the rotary screen printing process may further include an alarm module, which is used to generate control commands corresponding to the above-mentioned adjustment parameters, and use the control commands to adjust the position of the rotary screen so as to obtain the pattern matching result after the pattern matching process, and when the pattern matching result is a pattern matching failure, return to the step of obtaining the complete printed image of the target fabric; count the number of pattern matching failures, and when the number of pattern matching failures reaches a preset number, output an alarm prompt.

[0079] In one embodiment of this application, the matching device in the rotary screen printing process may further include an update module, which is used to generate control commands corresponding to the adjustment parameters and use the control commands to adjust the position of the rotary screen so that after the matching process, when the matching result is successful, the image deviation data corresponding to the current matching process is statistically analyzed; and the preset conversion model is optimized and updated using the image deviation data.

[0080] In one embodiment of this application, the adjustment module 4 can be specifically used to send control commands to the corresponding motor device of the circular mesh, so that the motor device drives the circular mesh to adjust its position according to the adjustment parameters, so as to achieve the matching process.

[0081] For a description of the apparatus provided in the embodiments of this application, please refer to the above method embodiments; further details will not be repeated here.

[0082] This application provides an electronic device.

[0083] Please refer to Figure 5 , Figure 5 This application provides a schematic diagram of the structure of an electronic device, which may include: Memory 11 is used to store computer programs; The processor 10 is used to execute computer programs to implement the steps of the matching method in any of the rotary screen printing processes described above.

[0084] like Figure 5 The diagram shows the structural composition of an electronic device, which may include a processor 10, a memory 11, a communication interface 12, and a communication bus 13. The processor 10, memory 11, and communication interface 12 all communicate with each other through the communication bus 13.

[0085] In this embodiment, the processor 10 may be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field-programmable gate array, or other programmable logic devices.

[0086] The processor 10 can call the program stored in the memory 11. Specifically, the processor 10 can execute the operations in the embodiment of the matching method in the rotary screen printing process.

[0087] The memory 11 is used to store one or more programs. The programs may include program code, which includes computer operation instructions. In this embodiment, the memory 11 stores at least a program for implementing the following functions: Acquire a complete printed image of the target fabric; extract features from the complete printed image and the template printed image to obtain a first image feature and a second image feature; calculate the deviation between the first image feature and the second image feature to obtain image deviation data, and determine the adjustment parameters based on the image deviation data; generate control commands corresponding to the adjustment parameters, and use the control commands to adjust the position of the rotary screen to achieve pattern matching.

[0088] In one possible implementation, the memory 11 may include a program storage area and a data storage area, wherein the program storage area may store the operating system and applications required for at least one function; and the data storage area may store data created during use.

[0089] In addition, memory 11 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device or other volatile solid-state storage device.

[0090] Communication interface 12 can be an interface for the communication module, used to connect with other devices or systems.

[0091] Of course, it should be noted that, Figure 5 The structure shown does not constitute a limitation on the electronic device in the embodiments of this application. In practical applications, the electronic device may include more than Figure 5 More or fewer components as shown, or combinations of certain components.

[0092] This application provides a computer-readable storage medium.

[0093] The computer-readable storage medium provided in this application embodiment stores a computer program, which, when executed by a processor, can implement the steps of the matching method in any of the above-described rotary screen printing processes.

[0094] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0095] For a description of the computer-readable storage medium provided in this application, please refer to the above method embodiments; further details will not be repeated here.

[0096] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to the method section.

[0097] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0098] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0099] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are only for the purpose of helping to understand the methods and core ideas of this application. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of this application.

Claims

1. A method for matching patterns in a rotary screen printing process, characterized in that, include: Obtain a complete printed image of the target fabric; Feature extraction is performed on the complete printed image and the template printed image respectively to obtain the first image feature and the second image feature; The deviation between the first image feature and the second image feature is calculated to obtain image deviation data, and the adjustment parameters are determined based on the image deviation data. The control command corresponding to the adjustment parameter is generated, and the position of the circular mesh is adjusted using the control command to achieve the matching of patterns.

2. The pattern matching method in the rotary screen printing process according to claim 1, characterized in that, Obtain a complete printed image of the target fabric, including: The fabric printing image of the target fabric is acquired using a line scan camera; All the fabric print images are stitched together to obtain the complete print image.

3. The pattern matching method in the rotary screen printing process according to claim 1, characterized in that, Feature extraction is performed on the complete printed image and the template printed image respectively to obtain the first image feature and the second image feature, including: The complete printed image is segmented to obtain complete printed sub-images. Features are extracted from each complete printed sub-image to obtain the sub-image features of all the complete printed sub-images as the first image features. The template printing image is segmented to obtain template printing sub-images. Features are extracted from each template printing sub-image to obtain the sub-image features of all template printing sub-images as the second image features. Accordingly, the deviation between the first image feature and the second image feature is calculated to obtain image deviation data, including: The deviations between the sub-image features of the corresponding complete printed sub-images and the sub-image features of the template printed sub-images are calculated to obtain the sub-image deviation data. The image deviation data is calculated based on all the sub-image deviation data.

4. The pattern matching method in the rotary screen printing process according to claim 1, characterized in that, The image deviation data is the image pixel deviation. Adjustment parameters are determined based on the image deviation data, including: The physical deviation of the image is calculated based on the image pixel deviation and the unit pixel size; The image physical deviation is converted into the adjustment parameter based on the device error using a preset conversion model.

5. The pattern matching method in the rotary screen printing process according to claim 4, characterized in that, The process includes generating control commands corresponding to the adjustment parameters, and using these commands to adjust the position of the circular mesh to achieve the desired pattern alignment. Following this, the process also includes: Obtain the pattern matching result, and if the pattern matching result is a failure, return to the step of obtaining the complete printed image of the target fabric; The system counts the number of failed flower pairings and outputs an alarm when the number of failed flower pairings reaches a preset number.

6. The pattern matching method in the rotary screen printing process according to claim 5, characterized in that, The process includes generating control commands corresponding to the adjustment parameters, and using these commands to adjust the position of the circular mesh to achieve the desired pattern alignment. Following this, the process also includes: When the flower matching result is successful, the image deviation data corresponding to the current flower matching processing operation is statistically analyzed. The preset conversion model is optimized and updated using the image deviation data.

7. The pattern matching method in the rotary screen printing process according to claim 1, characterized in that, The control commands are used to adjust the position of the circular mesh to achieve pattern matching, including: The control command is sent to the motor device corresponding to the circular mesh, so that the motor device drives the circular mesh to adjust its position according to the adjustment parameters, so as to achieve the matching process.

8. A pattern matching device in a rotary screen printing process, characterized in that, include: The acquisition module is used to acquire a complete printed image of the target fabric; The extraction module is used to extract features from the complete printed image and the template printed image respectively to obtain the first image features and the second image features; The calculation module is used to calculate the deviation between the first image feature and the second image feature to obtain image deviation data, and determine the adjustment parameters based on the image deviation data; The adjustment module is used to generate control commands corresponding to the adjustment parameters, and to use the control commands to adjust the position of the circular mesh to achieve the matching process.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the steps of the pattern matching method in the rotary screen printing process as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the matching method in the rotary screen printing process as described in any one of claims 1 to 7.

Images