A screen overprint automation control method, system and related device

Abstract

This invention provides an automated control method, system, and related equipment for screen printing, which improves the efficiency and accuracy of screen printing. The method in this invention may include: obtaining deformation parameters of a preliminary printed image, the number M of rows of arrayed primitives in the overprinted image to be overprinted from the preliminary printed image, and the height H of the image area; in the overprinted image, taking the image from height 0 to H1 as the first row of images, and successively stepping a unit pixel distance from height H1*(1-Q1) to H1*(2+Q1) to extract multiple first-type test images of height H1; wherein, 2*H / M>H1≥H / M, 0<Q1<1; calculating the similarity between the first row of images and multiple first-type test images, and determining the step distance Y1 corresponding to the first-type image with the highest similarity; using H2=Y1+H1*(1-Q1) as the primitive height, determining the true position distribution of the M rows of primitives in the height direction in the overprinted image.

Description

Technical Field

[0001] This invention relates to the field of laser imaging technology, and in particular to an automated control method, system and related equipment for screen printing. Background Technology

[0002] UV (ultraviolet) coating, also known as UV varnishing, is a term in the printing industry referring to a post-printing process. It involves precisely and evenly applying a special photosensitive adhesive to the surface or specific areas of a pre-printed product after initial printing. After being exposed to ultraviolet light, the adhesive quickly dries and hardens on the surface, creating a glossy film that protects the print, enhances the product's appearance, and serves as an alternative to lamination.

[0003] Before coating the surface of the printed material with photosensitive emulsion, a screen printing stencil needs to be made according to the shape of the graphic area to be coated with the photosensitive emulsion. In the existing stencil making process, to accommodate the deformed preliminary printed material, a film needs to be made based on the original image. Then, multiple images are cut from the complete film, and finally, the cut film is placed in the appropriate position on the screen frame using manual alignment to create the screen printing stencil. Therefore, the existing method of making and cutting film is complex, time-consuming, and labor-intensive, and the manual alignment operation has poor controllability. Summary of the Invention

[0004] This invention provides an automated control method, system, and related equipment for screen printing, which can improve the accuracy and efficiency of screen printing production.

[0005] The first aspect of this invention provides an automated control method for screen printing, which may include:

[0006] The number of rows M of arrayed primitives contained in the overprinted image required for the initial printing image, and the height H of the image area;

[0007] In the overprinted image, the image of the region from height 0 to H1 is taken as the first row of images, and multiple first-class test images with height H1 are cropped from the region of height H1*(1-Q1) to H1*(2+Q1) by stepping a unit pixel distance; where 2*H / M>H1≥H / M, 0<Q1<1;

[0008] Calculate the similarity between the first row of images and multiple first-class test images, and determine the step distance Y1 corresponding to the first-class image with the highest similarity;

[0009] Using H2=Y1+H1*(1-Q1) as the element height, the actual position distribution of M rows of elements in the overprinted image is determined;

[0010] In the overprinted image, the true position deviation of the M rows of graphic elements in the height direction is calculated based on the deformation parameters of the preliminary printed image, and the position of the graphic elements is adjusted along the same direction as the true position deviation to generate a corrected image.

[0011] Optionally, as a possible implementation, the method may further include the following steps before generating the corrected image:

[0012] Obtain the number of columns N of the arrayed primitives and the width W of the image area;

[0013] Take the image of the region with width 0 to D1 as the first column of images, and extract multiple second-type test images with width D1 from the region with width D1*(1-Q2) to D1*(2+Q2) by stepping a unit pixel distance; where 2*W / N>D1≥W / N, 0<Q2<1;

[0014] Calculate the similarity between the first column of images and multiple second-class test images, and determine the step distance Y2 corresponding to the first-class image with the highest similarity;

[0015] In the overprinted image, D2 = Y2 + D1 * (1 - Q2) is used as the width of the graphic element to determine the actual position distribution of the N columns of graphic elements;

[0016] Calculate the true horizontal position deviation of the N columns of graphic elements based on their actual position distribution.

[0017] Optionally, as one possible implementation, the method may further include the following steps before generating the corrected image:

[0018] Within the blank area at the edge of the primitive, with a height ranging from 0 to (H-4*H2), the value y2 = [0, P, 2P, ..., H-4*H2] is taken at intervals of P rows of pixels. Images within the range of y2 to y2 + H2 are taken as the third type of primitive, and images within the range of y2 + H2 to y2 + H2 * 2 are taken as the fourth type of primitive. The similarity between the third type of primitive and the fourth type of primitive corresponding to each value of y2 is calculated. The value of y2 when the first similarity is greater than the threshold is found. This value is the coarse boundary line and is denoted as y3.

[0019] Within the range of (y3 - P, y3 + P), take the value of each unit pixel interval, i.e., y2 = [y3-P, y3-P+1, y3-P+2, ..., y3+P]. Repeat the above similarity calculation steps to find the value of y2 when the maximum similarity is found. This value is the precise coordinate value of the upper boundary line, denoted as y4.

[0020] Using y4, y4+H2, y4+H2*2, y4+H2*3, and y4+H2*4 as dividing lines, determine the true location distribution of the boundaries of N columns of graphic elements.

[0021] Optionally, as a possible implementation, the similarity between the first row image and a plurality of first-type test images, and the similarity between the first column image and a plurality of second-type test images, are calculated using any one of Pearson correlation coefficient, structural similarity index, or normalized cross-correlation.

[0022] Optionally, as one possible implementation, the true position deviation includes at least one or both of the true position deviation in the horizontal direction of the array and the true position deviation in the vertical direction of the array.

[0023] Optionally, as a possible implementation, the step of adjusting the position of the graphic elements along the same direction as the actual position deviation to generate the corrected image may include: translating and correcting the position of the graphic elements in the image coordinate system according to the horizontal position deviation and / or vertical position deviation corresponding to each graphic element, and reconstructing the corrected image.

[0024] A second aspect of this invention provides an automated control method system for screen printing, which may include:

[0025] The image acquisition module is used to acquire the number of rows M of arrayed primitives contained in the overprinted image to be overprinted in the preliminary printing image, and the height H of the image area.

[0026] The row-size segmentation module is used to extract the image from the region of height 0 to H1 in the overprinted image as the first row image, and to extract multiple first-type test images of height H1 from the region of height H1*(1-Q1) to H1*(2+Q1) by stepping a unit pixel distance; wherein 2*H / M>H1≥H / M, 0<Q1<1; calculate the similarity between the first row image and the multiple first-type test images, and determine the step distance Y1 corresponding to the first-type image with the highest similarity; and determine the true position distribution of M rows of primitives in the overprinted image using H2=Y1+H1*(1-Q1) as the primitive height.

[0027] The correction output module is used to calculate the true position deviation of the M rows of graphic elements in the height direction based on the deformation parameters of the preliminary printed image in the overprinted image, and adjust the position of the graphic elements in the same direction as the true position deviation to generate a correction image.

[0028] Optionally, as one possible implementation, the automated control method system for screen printing may further include:

[0029] The column-oriented size segmentation module is used to obtain the number of columns N of the array-distributed primitives and the width W of the image area; it takes the image of the region with width 0 to D1 as the first column image, and successively steps the distance of unit pixel from the region with width D1*(1-Q2) to D1*(2+Q2) to extract multiple second-type test images with width D1; where 2*W / N>D1≥W / N, 0<Q2<1; it calculates the similarity between the first column image and multiple second-type test images, and determines the step distance Y2 corresponding to the first-type image with the highest similarity; in the overprinted image, it uses D2=Y2+D1*(1-Q2) as the primitive width to determine the true position distribution of N columns of primitives; it calculates the true position deviation of the N columns of primitives in the horizontal direction based on the true position distribution of the N columns of primitives.

[0030] A third aspect of the present invention provides a laser direct plate making apparatus, the laser direct plate making apparatus including a processor, the processor being configured to execute a computer program stored in a memory to implement the steps as described in the first aspect and any possible implementation thereof.

[0031] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the first aspect and any possible implementation thereof.

[0032] As can be seen from the above technical solutions, the embodiments of the present invention have the following advantages:

[0033] In this embodiment of the invention, by performing a similarity comparison between the first row of images and multiple first-type test images in the height direction, and restoring the element height based on the optimal matching result, the determination of element height no longer relies on manual experience values ​​or fixed templates. This allows for a relatively stable recovery of the true positional distribution of array elements in the height direction even when printing offsets, scanning noise, and local distortions exist, thus providing a more reliable positional basis for subsequent plate-making control. Furthermore, by performing a similarity comparison between the first column of images and multiple second-type test images in the width direction, and restoring the true positional distribution of array elements in the width direction, the positional recovery in the row and column directions forms a closed loop. This allows for the simultaneous acquisition of positional deviations in both the horizontal and vertical directions, thereby improving the completeness and usability of the quantification of array element positional deviations in screen printing. Finally, by introducing a two-level boundary search mechanism—coarse and fine boundary lines—within the blank area along the element edge, the system can quickly lock the candidate boundary range and then determine the precise coordinates of the upper boundary line within a local area. This balances boundary positioning efficiency and accuracy, thereby improving the precision of screen printing. Attached Figure Description

[0034] Figure 1This is a schematic diagram of an embodiment of the automated control method for screen printing according to the present invention;

[0035] Figure 2 This is a schematic diagram of one embodiment of the laser direct plate making equipment in this invention. Detailed Implementation

[0036] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0037] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0038] It should be noted that any embodiment described as "exemplary" or "for example" in this application should not be construed as having an advantage over other embodiments. Rather, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0039] For ease of understanding, the specific processes in the embodiments of the present invention are described below. Please refer to [link / reference]. Figure 1 One embodiment of the automated control method for screen printing according to the present invention may include:

[0040] S101: Obtain the overprinted image and array basic parameters required for the preliminary printed image.

[0041] This step involves obtaining a preliminary printed image (used to detect deformation parameters) after printing from the original image, as well as the number of rows M, the height H, and / or the number of columns N, and the width W of the arrayed primitives in the overprinted image to be printed from the preliminary printed image. The purpose of this step is to establish the input basis for subsequent primitive size restoration and positional deviation calculation, avoiding the need for manual alignment of the M*N primitives sequentially.

[0042] S102: Determine the true size and row position of the primitive in the height direction

[0043] Take the image in the area from height 0 to H1 as the first row image, and sequentially step by unit pixel distance in the area from height H1*(1 - Q1) to H1*(2 + Q1) to intercept multiple first-class test images with a height of H1. Calculate the similarity between the first row image and the multiple first-class test images, and determine the step distance Y1 corresponding to the first-class image with the highest similarity. Subsequently, in the overprinted image, take H2 = Y1 + H1*(1 - Q1) as the primitive height to determine the true position distribution of M rows of primitives. The purpose of setting this step is to restore the true size of the primitive in the height direction in a similarity search manner, facilitating subsequent independent correction of the primitives after block division. For example, based on the height direction, the number of rows M of the primitives distributed in an array in the overprinted image can be divided into M row areas in the height direction, and the position correction is performed on the M row areas respectively to obtain the corrected image.

[0044] In an optional implementation, H1 is the estimated value of the primitive height, satisfying H1 ≥ H / M, and Q1 is the search window ratio parameter, satisfying 0 < Q1 < 1. The similarity calculation can adopt any one of the Pearson correlation coefficient, the structural similarity index, or the normalized cross-correlation.

[0045] S103: Restore the true size and column position of the primitive in the horizontal direction

[0046] Optionally, as a possible implementation, before generating the corrected image, the number of columns N of the primitives distributed in an array and the width W of the image format can also be obtained. Take the image in the area from width 0 to D1 as the first column image, and sequentially step by unit pixel distance in the area from width D1*(1 - Q2) to D1*(2 + Q2) to intercept multiple second-class test images with a width of D1. Calculate the similarity between the first column image and the multiple second-class test images, and determine the step distance Y2 corresponding to the first-class image with the highest similarity. Subsequently, in the overprinted image, take D2 = Y2 + D1*(1 - Q2) as the primitive width to determine the true position distribution of N columns of primitives in the horizontal direction.

[0047] The purpose of setting this step is to further restore the true size and column position of the array primitives in the width direction, so that the true position distribution of the primitives can be restored completely in both the row direction and the column direction.

[0048] In one implementation, D1 is an estimated value of the primitive width, satisfying D1≥W / N, and Q2 is a search window ratio parameter in the width direction, satisfying 0<Q2<1. Through the optimal matching of similarity in the width direction, the true position distribution in the column direction that matches the row direction restoration result can be obtained.

[0049] S104: Perform rough check boundary line and fine check boundary line positioning

[0050] Optionally, based on the embodiments composed of S101 to S102 and / or S101 to S103 above, a two-level search method of "rough positioning + fine positioning" can also be adopted to improve the boundary positioning accuracy while ensuring the search efficiency, providing a stable boundary basis for the subsequent automatic segmentation of array primitives.

[0051] As a possible implementation, in the range where the height of the blank area at the edge of the primitive is from `0` to `(H - 4*H2)`, take pixel values at intervals of `P` rows each time, i.e., `y2=[0, P, 2P,..., H - 4*H2]`. Successively take the images in the range from `y2` to `y2 + H2` as the third type of primitive, and take the images in the range from `y2 + H2` to `y2 + H2*2` as the fourth type of primitive. Calculate the similarity between the third type of primitive and the fourth type of primitive corresponding to each `y2` value, find the value of `y2` when the first similarity is greater than the threshold, and use this value as the rough check boundary line `y3`.

[0052] Subsequently, take values at unit pixel intervals each time in the range of `(y3 - P, y3 + P)`, i.e., `y2=[y3 - P, y3 - P + 1, y3 - P + 2,..., y3 + P]`. Repeat the above similarity calculation steps, find the value of `y2` when the maximum similarity is obtained, and use this value as the exact coordinate value `y4` of the upper boundary line. Taking `y4`, `y4 + H2`, `y4 + H2*2`, `y4 + H2*3`, `y4 + H2*4` as the dividing lines, the 4-row primitives can be segmented in the height direction.

[0053] S105: Calculate the true position deviation, and adjust the position of the primitive in the same direction as the true position deviation to generate a corrected image.

[0054] Based on the actual positional distribution of the `M` row primitives and `N` column primitives, and the deformation parameters of the preliminary printed image, the actual positional deviations in the horizontal and vertical directions of the array are calculated respectively. For example, the origin of the coordinate system of the preliminary printed image can be aligned with the origin of the overprinted image. The actual positional deviation can then be calculated based on the deviation between the reserved coordinates of the overprinted image in the preliminary printed image and the actual position coordinates of the overprinted image. The actual positional deviation may include only the horizontal deviation, or it may include both the horizontal and vertical deviations.

[0055] Based on the actual positional deviation, the positions of the graphic elements are adjusted along the same direction as the actual positional deviation to generate a corrected image. Alternatively, the actual positional deviation can be converted into positional adjustment parameters required for subsequent exposure compensation, stitching correction, or alignment control in the laser-to-plate (Laser Direct Plate Making) equipment. In one implementation, the corrected image can be obtained by translating and correcting the positions of each graphic element in the image coordinate system and then reconstructing it. For scenarios where control parameters are directly output, the control parameters can be sent to the control module of the Laser Direct Plate Making equipment to drive subsequent exposure or alignment actions to perform compensation.

[0056] This invention compares the similarity of the first row of images with multiple first-type test images in the height direction, and recovers the element height based on the optimal matching result. This eliminates reliance on manual experience or fixed templates for element height determination, enabling a more stable recovery of the true positional distribution of array elements in the height direction even with printing offsets, scanning noise, and local distortions. This provides a more reliable positional basis for subsequent plate-making control. Furthermore, this invention compares the similarity of the first column of images with multiple second-type test images in the width direction, recovering the true positional distribution of array elements in the width direction. This creates a closed loop between row and column position recovery, allowing simultaneous acquisition of horizontal and vertical positional deviations, thus improving the completeness and usability of array element positional deviation quantification. Finally, this invention introduces a two-level boundary search mechanism—coarse and fine boundary lines—within the blank areas along element edges. This allows the system to quickly lock onto candidate boundary ranges and then determine the precise coordinates of the upper boundary line within a local area. This balances boundary positioning efficiency and accuracy, thereby improving the precision of screen printing.

[0057] It is understood that, in the various embodiments of this application, the sequence number of the above steps does not imply the order of execution. The execution order of each step should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. For example, steps S102 and S103 can be interchanged.

[0058] This invention also provides an automated control system for screen printing, which may include:

[0059] The image acquisition module is used to acquire the deformation parameters of the preliminary printed image, as well as the number of rows M of arrayed primitives contained in the overprinted image to be overprinted from the preliminary printed image, and the height H of the image area.

[0060] The row-size segmentation module is used to extract the image from the region of height 0 to H1 in the overprinted image as the first row image, and to extract multiple first-class test images of height H1 from the region of height H1*(1-Q1) to H1*(2+Q1) by stepping a unit pixel distance; where 2*H / M>H1≥H / M, 0<Q1<1; calculate the similarity between the first row image and multiple first-class test images, and determine the step distance Y1 corresponding to the first-class image with the highest similarity; and determine the true position distribution of M rows of primitives in the overprinted image using H2=Y1+H1*(1-Q1) as the primitive height.

[0061] The correction output module is used to calculate the true position deviation of the M rows of graphic elements in the height direction based on the deformation parameters of the preliminary printed image in the overprinted image, and adjust the position of the graphic elements in the same direction as the true position deviation to generate a correction image.

[0062] Optionally, as one possible implementation, the automated screen printing control system of the present invention may further include:

[0063] The column-oriented size segmentation module is used to obtain the number of columns N of the array-distributed primitives and the width W of the image area; it takes the image of the region with width 0 to D1 as the first column image, and successively steps the distance of unit pixel from the region with width D1*(1-Q2) to D1*(2+Q2) to extract multiple second-type test images with width D1; where 2*W / N>D1≥W / N, 0<Q2<1; it calculates the similarity between the first column image and multiple second-type test images, and determines the step distance Y2 corresponding to the first-type image with the highest similarity; in the overprinted image, it uses D2=Y2+D1*(1-Q2) as the primitive width to determine the true position distribution of N columns of primitives; it calculates the true position deviation of the N columns of primitives in the horizontal direction based on the true position distribution of the N columns of primitives.

[0064] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0065] The automated control method system for screen printing in this embodiment of the invention has been described above from the perspective of modular functional entities. Please refer to [link to relevant documentation]. Figure 2 The laser direct plate-making equipment in this embodiment of the invention will now be described from the perspective of hardware processing:

[0066] The laser-to-plate (Laser Direct Printing) device 1 may include a memory 11, a processor 12, and an input / output bus 13. The processor 11 executes the computer program to implement the above-mentioned... Figure 1 The screen printing automation control method shown is, for example Figure 1 Steps 101 to 105 are shown. Alternatively, the processor executes a computer program to implement the functions of each module or unit in the above-described device embodiments.

[0067] In some embodiments of the present invention, the processor is specifically used to implement the following steps:

[0068] The memory 11 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the laser-to-plate (Laser Direct Plate Making) apparatus 1, such as the hard disk of the Laser Direct Plate Making apparatus 1. In other embodiments, the memory 11 can also be an external storage device of the Laser Direct Plate Making apparatus 1, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the Laser Direct Plate Making apparatus 1. Furthermore, the memory 11 can include both internal storage units and external storage devices of the Laser Direct Plate Making apparatus 1. The memory 11 can be used not only to store application software and various types of data installed on the Laser Direct Plate Making apparatus 1, such as computer program code, but also to temporarily store data that has been output or will be output.

[0069] In some embodiments, processor 12 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 11 or process data, such as executing computer programs.

[0070] The input / output bus 13 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc.

[0071] Furthermore, the laser direct plate making equipment may also include a wired or wireless network interface 14. The network interface 14 may optionally include a wired interface and / or a wireless interface (such as a WI-FI interface, Bluetooth interface, etc.), which is typically used to establish a communication connection between the laser direct plate making equipment 1 and other electronic devices.

[0072] Figure 2 Only the laser-to-plate apparatus 1 with components 11-14 and computer programs is shown; those skilled in the art will understand that... Figure 2 The structure shown does not constitute a limitation on the laser direct printing equipment 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0073] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the functions described above. Figure 1 The screen printing automation control method shown is, for example Figure 1 Steps 101 to 105 are shown. Alternatively, the processor executes a computer program to implement the functions of each module or unit in the above-described device embodiments.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0077] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes 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.

[0078] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An automated control method for screen printing, characterized in that, include: The number of rows M of arrayed primitives contained in the overprinted image required for the initial printing image, and the height H of the image area; In the overprinted image, the image of the region from height 0 to H1 is taken as the first row of images, and multiple first-class test images with height H1 are cropped from the region of height H1*(1-Q1) to H1*(2+Q1) by stepping a unit pixel distance; where 2*H / M>H1≥H / M, 0<Q1<1; Calculate the similarity between the first row of images and multiple first-class test images, and determine the step distance Y1 corresponding to the first-class image with the highest similarity; Using H2=Y1+H1*(1-Q1) as the element height, the actual position distribution of M rows of elements in the overprinted image is determined; In the overprinted image, the true position deviation of the M rows of graphic elements in the height direction is calculated based on the deformation parameters of the preliminary printed image, and the position of the graphic elements is adjusted along the same direction as the true position deviation to generate a corrected image.

2. The automated control method for screen printing according to claim 1, characterized in that, Before generating the corrected image, the method further includes: Obtain the number of columns N of the arrayed primitives and the width W of the image area; Take the image of the region with width 0 to D1 as the first column of images, and extract multiple second-type test images with width D1 from the region with width D1*(1-Q2) to D1*(2+Q2) by stepping a unit pixel distance; where 2*W / N>D1≥W / N, 0<Q2<1; Calculate the similarity between the first column of images and multiple second-class test images, and determine the step distance Y2 corresponding to the first-class image with the highest similarity; In the overprinted image, D2 = Y2 + D1 * (1 - Q2) is used as the width of the graphic element to determine the actual position distribution of the N columns of graphic elements; Calculate the true horizontal position deviation of the N columns of graphic elements based on their actual position distribution.

3. The automated control method for screen printing according to claim 1 or 2, characterized in that, Before generating the corrected image, the method further includes: Within the blank area at the edge of the primitive, the height is between 0 and (H-4*H2). Each time, the value y2 = [0, P, 2P, ..., H-4*H2] is taken at intervals of P rows of pixels. Images in the range of y2 to (y2 + H2) are taken as the third type of primitive, and images in the range of y2 + H2 to y2 + H2* 2 are taken as the fourth type of primitive. The similarity between the third type of primitive and the fourth type of primitive corresponding to each value of y2 is calculated. The value of y2 when the first similarity is greater than the threshold is found. This value is the coarse boundary line and is denoted as y3. Within the range (y3 - P, y3 + P), take the value of each unit pixel interval, i.e., y2 = [y3-P, y3-P+1, y3-P+2, ..., y3+P]. Repeat the above similarity calculation steps to find the value of y2 when the maximum similarity is found. This value is the precise coordinate value of the upper boundary line, denoted as y4. Using y4, y4+H2, y4+H2*2, y4+H2*3, and y4+H2*4 as dividing lines, determine the true location distribution of the boundaries of N columns of graphic elements.

4. The automated control method for screen printing according to claim 1 or 2, characterized in that, The similarity between the first row image and multiple test images of the first type, and the similarity between the first column image and multiple test images of the second type, are calculated using any one of the Pearson correlation coefficient, structural similarity index, or normalized cross-correlation.

5. The automated control method for screen printing according to claim 1 or 2, characterized in that, The true position deviation includes at least one or both of the true position deviation in the horizontal direction of the array and the true position deviation in the vertical direction of the array.

6. The automated control method for screen printing according to claim 1, 2, or 5, characterized in that, The step of adjusting the position of the graphic elements along the same direction as the actual position deviation to generate a corrected image includes: translating and correcting the position of the graphic elements in the image coordinate system according to the horizontal position deviation and / or vertical position deviation corresponding to each graphic element, and reconstructing the corrected image.

7. An automated control system for screen printing, characterized in that, include: The image acquisition module is used to acquire the number of rows M of arrayed primitives contained in the overprinted image to be overprinted in the preliminary printing image, and the height H of the image area. The row-size segmentation module is used to extract the image from the region of height 0 to H1 in the overprinted image as the first row image, and to extract multiple first-type test images of height H1 from the region of height H1*(1-Q1) to H1*(2+Q1) by stepping a unit pixel distance; wherein 2*H / M>H1≥H / M, 0<Q1<1; calculate the similarity between the first row image and the multiple first-type test images, and determine the step distance Y1 corresponding to the first-type image with the highest similarity; and determine the true position distribution of M rows of primitives in the overprinted image using H2=Y1+H1*(1-Q1) as the primitive height. The correction output module is used to calculate the true position deviation of the M rows of graphic elements in the height direction based on the deformation parameters of the preliminary printed image in the overprinted image, and adjust the position of the graphic elements in the same direction as the true position deviation to generate a correction image.

8. The system according to claim 7, characterized in that, Also includes: The column-oriented size segmentation module is used to obtain the number of columns N of the array-distributed primitives and the width W of the image area; it takes the image of the region with width 0 to D1 as the first column image, and successively steps the distance unit pixel from the region with width D1*(1-Q2) to D1*(2+Q2) to extract multiple second-type test images with width D1; where 2*W / N>D1≥W / N, 0<Q2<1; it calculates the similarity between the first column image and the multiple second-type test images, and determines the step distance Y2 corresponding to the first-type image with the highest similarity. In the overprinted image, D2=Y2+ D1*(1-Q2) is used as the width of the graphic element to determine the actual position distribution of the N columns of graphic elements; the actual position deviation of the N columns of graphic elements in the horizontal direction is calculated based on the actual position distribution of the N columns of graphic elements.

9. An electronic device, characterized in that, The method includes a memory and a processor, the processor being configured to implement the method of any one of claims 1 to 6 when executing a computer program stored in the memory.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1 to 6.

Images