Printing registration method based on machine vision, controller and storage medium

Abstract

The invention discloses a printing registration method based on machine vision, a controller and a storage medium, and relates to the field of printing device.The printing registration method comprises the steps that in response to a registration trigger signal, a sliding table is controlled to drive an image collection device to collect a registration image between any set of adjacent sprayers, and multiple registration images of each set of adjacent sprayers are obtained, identifying a nozzle identifier in the registration image and two calibration dot matrixes representing a nozzle spraying area, respectively calculating a difference value between a distance between calibration points at each corresponding position and a preset distance between a group of adjacent nozzles, and determining a deviation value of each nozzle of the group of adjacent nozzles based on a mean value of each difference value, and correcting the spraying position coordinates of the nozzle based on the deviation value of the nozzle. According to the method, the registration image between any group of adjacent nozzles can be acquired based on one image acquisition device, the system cost is reduced, the nozzle deviation value is calculated based on the difference value between the calibration dot matrix representing the spraying area of the nozzle and the preset distance between the adjacent nozzles, and the registration precision is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of printing equipment, and in particular to a printing register method based on machine vision, a controller and a storage medium. BACKGROUND

[0002] In the field of digital printing, overprint refers to a process of overlapping different patterns in a printing area to form a complex pattern in the printing process, for example, printing product patterns on the surface of a corrugated paper packaging box. The accuracy of overprint is a key factor affecting the printing quality. Therefore, during the printing process, the spraying position of each nozzle is usually adjusted by manual register to avoid pattern misregistration, deviation, ghosting and other problems.

[0003] However, the existing manual register method has the problem of poor calibration accuracy. Therefore, how to improve the register accuracy in the overprint process has become a problem to be solved. SUMMARY

[0004] In view of the above problems, the present application provides a printing register method based on machine vision, a controller and a storage medium to achieve the purpose of improving the register accuracy in the overprint process. The specific scheme is as follows:

[0005] The first aspect of the present application provides a printing register method based on machine vision, applied to a controller in a register system, the register system comprising the controller and a sliding table configured with an image acquisition device, the printing register method based on machine vision comprising:

[0006] In response to a register trigger signal, controlling the sliding table to drive the image acquisition device to collect a register image between any group of adjacent nozzles, and obtaining a plurality of register images of each group of adjacent nozzles;

[0007] Identifying a nozzle identifier and two calibration point arrays in the register image, the calibration point arrays representing the spraying area of one nozzle in the group of adjacent nozzles corresponding to the nozzle identifier;

[0008] Identifying the distance between the calibration points at corresponding positions in the two calibration point arrays, respectively calculating the difference between each distance and the preset distance of the group of adjacent nozzles, and determining the deviation value of each nozzle of the group of adjacent nozzles based on the average of each difference value;

[0009] Correcting the spraying position coordinates of the nozzle based on the deviation value of the nozzle.

[0010] In a possible implementation, before the identification of the distance between the calibration points at corresponding positions in the two calibration point arrays, the printing register method based on machine vision further comprises:

[0011] identifying whether a direction correction dot array adapted to the identifier exists in the register image;

[0012] in the absence of the direction correction dot array, performing the operation step of identifying the distance between the calibration points at the corresponding positions in the two calibration dot arrays;

[0013] in the presence of the direction correction dot array, determining an offset angle based on the direction correction dot array, correcting the coordinates of the calibration points in the two calibration dot arrays based on the offset angle, and performing the operation step of identifying the distance between the calibration points at the corresponding positions in the two calibration dot arrays after the correction is completed.

[0014] In a possible implementation, the operation of determining an offset angle based on the direction correction dot array and correcting the coordinates of the calibration points in the two calibration dot arrays based on the offset angle comprises:

[0015] identifying the direction correction dot array corresponding to the printhead identifier in the register image to obtain the coordinates of the correction points in the direction correction dot array;

[0016] based on the coordinates of the correction points, calculating the offset angle between the movement direction of the printing medium and the pointing direction represented by the direction correction dot array, the printing medium being the medium carrying the direction correction dot array;

[0017] in the case where the offset angle is not greater than a preset included angle threshold, performing the operation step of identifying the distance between the calibration points at the corresponding positions in the two calibration dot arrays;

[0018] in the case where the offset angle is greater than the preset included angle threshold, correcting the coordinates of the calibration points based on the offset angle.

[0019] In a possible implementation, the operation of determining the deviation value of each of the group of adjacent printheads based on the mean value of the difference values comprises:

[0020] performing image recognition on the calibration dot array in the register image; in the case where the image recognition result represents color registration, determining the mean value of the difference values as the deviation value of one of the group of adjacent printheads, and determining the negative value of the deviation value as the deviation value of another of the group of adjacent printheads;

[0021] in the case where the image recognition result represents color registration, determining the mean value of the difference values as the deviation value of one of the group of adjacent printheads, and determining the negative value of the deviation value as the deviation value of another of the group of adjacent printheads, and updating the deviation value of each of the printheads based on the deviation value of each of the printheads and the deviation value of the reference printhead.

[0022] In a possible implementation, the updating of the deviation value of each of the nozzles based on the deviation value of each of the nozzles and the deviation value of the reference nozzle comprises:

[0023] For each of the nozzles:

[0024] a nozzle whose installation sequence number is between the installation sequence number of the nozzle and the installation sequence number of the reference nozzle is determined as an associated nozzle;

[0025] a sum of the deviation value of each of the associated nozzles and the deviation value of the nozzle is calculated, and a difference between the sum and the deviation value of the reference nozzle is determined as the deviation value of the nozzle.

[0026] In a possible implementation, before the determining of the deviation value of each of the nozzles in the group of adjacent nozzles based on the mean value of each of the differences, the machine vision-based printing register method further comprises:

[0027] calculating a check variance based on each of the differences and the mean value;

[0028] in a case where the check variance is greater than a preset variance threshold, removing an outlier in each of the differences based on the check variance;

[0029] in a case where the check variance is not greater than the preset variance threshold, performing the operation of determining the deviation value of each of the nozzles in the group of adjacent nozzles based on the mean value of each of the differences.

[0030] In a possible implementation, the controlling of the slide table to drive the image acquisition device to acquire the register image between any group of adjacent nozzles in response to a register trigger signal comprises:

[0031] controlling the image acquisition device to acquire a print medium image at an initial position, and performing image recognition on the print medium image;

[0032] in a case where the print medium image contains a trigger identifier, performing the operation of controlling the slide table to drive the image acquisition device to acquire the register image between any group of adjacent nozzles.

[0033] The second aspect of the present application provides a controller applied to a register system, the controller comprising:

[0034] an image acquisition control unit configured to control a slide table to drive an image acquisition device to acquire a register image between any group of adjacent nozzles in response to a register trigger signal, and obtain a plurality of register images of each group of the adjacent nozzles;

[0035] an image recognition unit configured to recognize a printhead identifier and two calibration dot arrays in the register image, the calibration dot arrays representing a spraying area of a printhead in the group of adjacent printheads corresponding to the printhead identifier;

[0036] a deviation confirmation unit configured to identify a distance between calibration dots at corresponding positions in the two calibration dot arrays, calculate a difference between each of the distances and a preset distance of the group of adjacent printheads, and determine a deviation value of each of the printheads in the group of adjacent printheads based on an average of the differences;

[0037] a deviation correction unit configured to correct a spraying position coordinate of the printhead based on the deviation value of the printhead.

[0038] In a possible implementation, the controller further includes:

[0039] a direction correction unit configured to identify whether a direction correction dot array adapted to the identifier exists in the register image before the deviation confirmation unit identifies the distance between the calibration dots at the corresponding positions in the two calibration dot arrays, and trigger the deviation confirmation unit to perform the operation of identifying the distance between the calibration dots at the corresponding positions in the two calibration dot arrays when the direction correction dot array does not exist.

[0040] The direction correction unit is further configured to determine an offset angle based on the direction correction dot array, correct the coordinates of the calibration dots in the two calibration dot arrays based on the offset angle, and trigger the deviation confirmation unit to perform the operation of identifying the distance between the calibration dots at the corresponding positions in the two calibration dot arrays after the correction.

[0041] In a possible implementation, the direction correction unit is configured to:

[0042] identify a direction correction dot array corresponding to the printhead identifier in the register image to obtain correction dot coordinates in the direction correction dot array;

[0043] calculate the offset angle between a movement direction of a printing medium and a pointing direction represented by the direction correction dot array based on the correction dot coordinates, the printing medium being a medium carrying the direction correction dot array.

[0044] perform the operation of identifying the distance between the calibration dots at the corresponding positions in the two calibration dot arrays when the offset angle is not greater than a preset included angle threshold.

[0045] correct the coordinates of the calibration dots based on the offset angle when the offset angle is greater than the preset included angle threshold.

[0046] In a possible implementation, the deviation confirmation unit is configured to determine the deviation value of each of the group of adjacent printheads based on the mean value of each of the difference values when determining the deviation value of each of the group of adjacent printheads based on the mean value of each of the difference values.

[0047] perform image recognition on the calibration dot array in the register image; in a case where the image recognition result represents color-to-color overprint, determine the mean value of each of the difference values as the deviation value of one of the group of adjacent printheads, and determine the negative value of the deviation value as the deviation value of another of the group of adjacent printheads;

[0048] in a case where the image recognition result represents color-to-color overprint, determine the mean value of each of the difference values as the deviation value of one of the group of adjacent printheads, and determine the negative value of the deviation value as the deviation value of another of the group of adjacent printheads, and update the deviation value of each of the printheads based on the deviation value of each of the printheads and the deviation value of the reference printhead.

[0049] In a possible implementation, the deviation confirmation unit is configured to update the deviation value of each of the printheads based on the deviation value of each of the printheads and the deviation value of the reference printhead when determining the deviation value of each of the group of adjacent printheads based on the mean value of each of the difference values.

[0050] for each of the printheads:

[0051] determine, as an associated printhead, the printhead whose installation serial number is between the installation serial number of the printhead and the installation serial number of the reference printhead;

[0052] calculate the sum of the deviation value of each of the associated printheads and the deviation value of the printhead, and determine, as the deviation value of the printhead, the difference between the sum and the deviation value of the reference printhead.

[0053] In a possible implementation, the deviation confirmation unit is further configured to:

[0054] before determining the deviation value of each of the group of adjacent printheads based on the mean value of each of the difference values, calculate a check variance based on each of the difference values and the mean value;

[0055] in a case where the check variance is greater than a preset variance threshold, eliminate an outlier in each of the difference values based on the check variance;

[0056] in a case where the check variance is not greater than the preset variance threshold, perform the operation of determining the deviation value of each of the group of adjacent printheads based on the mean value of each of the difference values.

[0057] In a possible implementation, the image acquisition control unit, when controlling the slide table to drive the image acquisition device to acquire the registration image between any adjacent nozzle group in response to the registration trigger signal, is configured to include the following steps:

[0058] controlling the image acquisition device to acquire an image of the printing medium at an initial position, and performing image recognition on the image of the printing medium;

[0059] in the case where the trigger identifier exists in the image of the printing medium, performing the operation step of controlling the slide table to drive the image acquisition device to acquire the registration image between any adjacent nozzle group.

[0060] The third aspect of the present application provides a controller, comprising at least one processor and a memory connected to the processor, wherein:

[0061] the memory is configured to store a computer program;

[0062] the processor is configured to execute the computer program, so that the controller can implement the machine vision-based printing registration method of the first aspect or any implementation manner of the first aspect.

[0063] The fourth aspect of the present application provides a computer storage medium, which carries one or more computer programs, and when the one or more computer programs are executed by a controller, the controller can implement the machine vision-based printing registration method of the first aspect or any implementation manner of the first aspect.

[0064] By means of the above technical solutions, the machine vision-based printing registration method, controller and storage medium provided by the present application are configured to apply the machine vision-based printing registration method to a registration system comprising a slide table configured with an image acquisition device, and are configured to control the slide table to drive the image acquisition device to acquire a registration image between any adjacent nozzle group in response to a registration trigger signal, so that the acquisition of the registration image between any adjacent nozzle group can be realized by configuring only one image acquisition device, thereby reducing the system cost. Subsequently, by configuring to identify the nozzle identifier and the two calibration point arrays in the registration image, the spraying area of one nozzle in a group of adjacent nozzles corresponding to the nozzle identifier is represented by the calibration point array, so as to limit the correction reference. And by configuring to identify the distance between the calibration points at the corresponding positions in the two calibration point arrays, the difference between each distance and the preset distance of a group of adjacent nozzles is calculated respectively, and the deviation value of each nozzle of a group of adjacent nozzles is determined based on the average of each difference value, so as to realize the determination of the deviation of the spraying position of each nozzle compared with the spraying area represented by the calibration point array. Finally, by configuring to correct the spraying position coordinates of the nozzle based on the deviation value of the nozzle, the registration is completed. It can be seen that the present application reduces the system cost while improving the registration accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0065] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0066] Figure 1 A flowchart of a machine vision-based printing registration method provided for this application;

[0067] Figure 2 A schematic diagram of a registration system provided in this application;

[0068] Figure 3 A schematic diagram of a registration image provided for this application;

[0069] Figure 4 A schematic diagram of a calibration dot matrix provided in this application;

[0070] Figure 5 A schematic diagram of another calibration dot matrix provided in this application;

[0071] Figure 6 A schematic diagram of a preset coordinate system for the shooting plane provided in this application;

[0072] Figure 7 A schematic diagram illustrating the acquisition of a registration image using a registration system provided in this application;

[0073] Figure 8 A flowchart of image acquisition for an image acquisition device provided in this application;

[0074] Figure 9 A flowchart of a machine vision-based printing registration method provided for this application;

[0075] Figure 10 A block diagram of a controller provided in this application;

[0076] Figure 11 This is a schematic diagram of the structure of a controller provided in this application. Detailed Implementation

[0077] The embodiments of this application are described below with reference to the accompanying drawings. The terminology used in the implementation section of this application is for explaining specific embodiments only and is not intended to limit the scope of this application.

[0078] The embodiments of this application will now be described with reference to the accompanying drawings. Those skilled in the art will recognize that, with technological advancements and the emergence of new scenarios, the technical solutions provided in the embodiments of this application are equally applicable to similar technical problems.

[0079] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such terms are interchangeable where appropriate; this is merely a way of distinguishing objects with the same attributes in the embodiments of this application. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, so that a process, method, system, product, or apparatus that comprises a series of elements is not necessarily limited to those elements, but may include other elements not explicitly listed or inherent to those processes, methods, products, or apparatuses.

[0080] It should be noted that, in practical applications, the machine vision-based printing registration method provided in this application improves registration accuracy and reduces system production costs compared to existing technologies. Specifically, to address the problem of poor registration accuracy in traditional manual registration, existing technologies often use area scan cameras to determine and register relevant offsets. The principle is to place an area scan camera between any two printheads to capture the registration marks at the joint between two adjacent printheads for registration. However, when the printhead joint distance is narrow, the area scan camera's field of view is limited, preventing it from capturing the registration marks and thus reducing registration accuracy. To solve the accuracy degradation problem, existing technologies can only address this by adding an area scan camera to each joint, which increases printer costs and setup complexity. This application applies a machine vision-based printing registration method to a registration system including a slide equipped with an image acquisition device. It configures the slide to move the image acquisition device to acquire registration images between any group of adjacent printheads in response to a registration trigger signal. This allows for the acquisition of registration images between any two adjacent printheads with only one image acquisition device, reducing system costs. Subsequently, by identifying printhead identifiers and two calibration dot matrices in the registration image, the calibration dot matrices characterize the spraying area of ​​one printhead in a group of adjacent printheads corresponding to the printhead identifier, thus defining a correction reference. Furthermore, by identifying the spacing between corresponding calibration points in the two calibration dot matrices, the differences between each spacing and a preset spacing of a group of adjacent printheads are calculated. The average of these differences determines the deviation value of each printhead in a group of adjacent printheads, thus determining the deviation of the spraying position of each printhead from the spraying area characterized by the calibration dot matrices. Finally, by correcting the printhead spraying position coordinates based on the printhead deviation value, registration is completed. Therefore, this application improves registration accuracy while reducing system costs.

[0081] The first aspect of this application provides a machine vision-based printing registration method, applied to a controller in a registration system. The registration system includes a controller and a slide equipped with an image acquisition device, such as... Figure 1 As shown, this machine vision-based printing registration method includes:

[0082] S101. In response to the registration trigger signal, control the slide to drive the image acquisition device to acquire the registration image between any group of adjacent nozzles, and obtain multiple registration images of each group of adjacent nozzles.

[0083] It should be noted that, in practical applications, the aforementioned registration system can be integrated into the printer system for registration purposes. There are several possible structural configurations for the registration system; one is provided as an example:

[0084] likeFigure 2 The diagram shows a registration system, which includes an image acquisition device 201, a slide 202, and a controller 203. The slide 202 may include a first slide rail 2021, a first slider 2022, a second slide rail 2023, and a second slider 2024. The slide 202 can be mounted on the slide mounting plane of the printer. This slide mounting plane is parallel to or perpendicular to the printhead mounting plane of the printer, and the slide 202 does not obstruct the printhead's spray path.

[0085] The first slider 2022 is movably connected to the first slide rail 2021, and the first slider 2022 slides along the extension direction of the first slide rail 2021. One end of the second slide rail 2023 is fixedly connected to the first slider 2022, and the second slider 2024 is movably connected to the second slide rail 2023, and the second slider 2024 slides along the extension direction of the second slide rail 2023.

[0086] The image acquisition device 201 is movably mounted on the second slider 2024, and the imaging plane of the image acquisition device 201 is the printing plane; the image acquisition device 201, the slider 202 and the printer are all communicatively connected to the controller 203;

[0087] In the registration state, the slide 202 drives the image acquisition device 201 to move to the target position between any two printheads of the printer.

[0088] In one possible implementation, the first slide rail 2021 and the second slide rail 2023 can be rails of various shapes such as curved rails, straight rails, and circular rails. This application does not impose too many restrictions on the specific rail type.

[0089] In one possible implementation, the first slider 2022 and the second slider 2024 mentioned above can be self-driven sliders (equipped with a drive motor), or sliders driven by the slide rails they are mounted on through the slide rails' built-in drive device (such as a lead screw). This application does not impose too many restrictions on the specific slider type.

[0090] It should be noted that, in practical applications, the aforementioned registration trigger signal can be triggered externally by the operator or by the image acquisition device recognizing a special pattern pre-printed on the printing medium.

[0091] It should be noted that in practical applications, there are multiple ways to implement the above-mentioned control slide to drive the image acquisition device to acquire the overlay image between any group of adjacent nozzles. Here, one example is provided:

[0092] The identification of each nozzle in a group of adjacent nozzles in the alignment trigger signal is analyzed, the target spatial coordinates corresponding to the identification of both nozzles are found, and the slide is controlled to move the image acquisition device to the target spatial coordinates to acquire an alignment image. The target spatial coordinates can be obtained by calibrating the positions between each nozzle in advance.

[0093] It should be noted that, in practical application scenarios, this application configures a registration system including a controller and a slide table equipped with an image acquisition device, and configures the slide table to drive the image acquisition device to acquire the registration image between any group of adjacent nozzles in response to the registration trigger signal. This enables the acquisition of the registration image between any group of adjacent nozzles with only one image acquisition device, thereby reducing the complexity and cost of the registration system.

[0094] S102. Identify the nozzle identifier and two calibration dot matrix in the registration image. The calibration dot matrix represents the spraying area of ​​one of the nozzles in a group of adjacent nozzles corresponding to the nozzle identifier.

[0095] It should be noted that, in practical applications, the aforementioned registration image can be an image of the registration diagram captured by an image acquisition device at a position between a group of adjacent printheads. This registration diagram is a printing medium that at least prints printhead markings and calibration dots. The printing medium can be of the same material and size as the object being printed after registration; for example, the printing medium can be corrugated paper printed with multiple printhead markings and calibration dots.

[0096] It should be noted that, in practical application scenarios, the above-mentioned nozzle identification can be a nozzle identification that carries at least the associated calibration dot matrix identification information, the corresponding adjacent nozzle identification, and a machine-readable identification (such as a QR code or barcode) that shows the correspondence between the nozzle identification and the calibration station.

[0097] It should be noted that, in practical applications, the arrangement and drawing format of the nozzle markers and calibration dots in the above-mentioned registered image can be varied. One example is provided here:

[0098] like Figure 3The diagram illustrates a registration image, comprising: a trigger identifier 301, a nozzle identifier 302, a first calibration dot matrix 303, and a second calibration dot matrix 304. The trigger identifier 301 stores the target spatial coordinates of the shooting positions between a set of adjacent nozzles. The nozzle identifier 302 stores identification information of the associated calibration dot matrix (first calibration dot matrix 303 and second calibration dot matrix 304) (e.g., a dot matrix composed of diagonal circles represents the first calibration dot matrix, and a dot matrix composed of blank circles represents the second calibration dot matrix), nozzle identifiers corresponding to adjacent nozzles (e.g., adjacent first and second nozzles), and the correspondence between the nozzle identifiers and calibration points (e.g., the first nozzle corresponds to the first calibration dot matrix, and the second nozzle corresponds to the second calibration dot matrix). The first calibration dot matrix 303 and the second calibration dot matrix 304 characterize the spraying area of ​​each nozzle in a set of adjacent nozzles during registration.

[0099] It should be noted that, in practical application scenarios, this application identifies the actual spraying area of ​​each nozzle by configuring and recognizing the nozzle identifier in the registration image, as well as the calibration dot matrix representing the spraying area of ​​each nozzle in a group of adjacent nozzles, thereby providing a correction benchmark for subsequent registration.

[0100] S103. Identify the spacing between corresponding calibration points in two calibration point matrices, calculate the difference between each spacing and the preset spacing of a group of adjacent nozzles, and determine the deviation value of each nozzle in a group of adjacent nozzles based on the mean of each difference.

[0101] It should be noted that, in practical applications, the aforementioned corresponding positions can be set based on the specific form of the calibration dot matrix, indicating the location of a set of calibration points that calibrate the boundary distance of a group of adjacent nozzles during spraying. The preset spacing of the aforementioned group of adjacent nozzles is the initial spray boundary spacing of the nozzles before spraying. This application, by configuring and identifying the spacing of calibration points at corresponding positions in two calibration dot matrices, calculates the difference between each spacing and the preset spacing of a group of adjacent nozzles, thereby obtaining the boundary spacing of each spraying position of a group of adjacent nozzles during spraying, and the deviation amount from the current preset spacing of the nozzles. Furthermore, by configuring the deviation value of each nozzle in a group of adjacent nozzles based on the mean of each difference, the impact of abnormal differences on the calculation accuracy of the nozzle deviation value is weakened, thereby improving the registration accuracy.

[0102] To facilitate understanding of the identification of the spacing between corresponding calibration points in the two calibration dot matrices, the following explanation is provided in conjunction with possible implementations of this application:

[0103] In one possible implementation, such as Figure 4The diagram shows a calibration dot matrix, including a first calibration dot matrix 303 and a second calibration dot matrix 304. The calibration points at the corresponding positions comprise fifteen groups. Two groups are selected for description below. The first group consists of the first calibration point 401 located in the first calibration dot matrix 303 and the first calibration point 501 located in the second calibration dot matrix 304. The second group consists of the twelfth calibration point 412 located in the first calibration dot matrix 303 and the twelfth calibration point 512 located in the second calibration dot matrix 304. The first calibration dot matrix 303 corresponds to the first printhead, and the second calibration dot matrix 304 corresponds to the second printhead. It is assumed that when the first and second printheads print, they both execute a right-to-left, top-to-bottom printing sequence (top, bottom, left, and right are...). Figure 4 (Relative positions). The position of the first calibration point 401 relative to the first calibration point matrix 303 is the same as the position of the first calibration point 501 relative to the second calibration point matrix 304, and the position of the twelfth calibration point 412 relative to the first calibration point matrix 303 is the same as the position of the twelfth calibration point 512 relative to the second calibration point matrix 304. Therefore, the spacing corresponding to the first group is d1, and the spacing corresponding to the second group is d12.

[0104] In one possible implementation, such as Figure 5 The diagram shows a calibration dot matrix, including a first calibration dot matrix 601 (containing only one calibration point) corresponding to a first nozzle and a second calibration dot matrix 701 (approximately a ring-shaped dot matrix composed of multiple calibration points) corresponding to a second nozzle. The aforementioned corresponding positions can be the relative positions of the calibration point in the first calibration dot matrix 601 and the calibration points that make up the second calibration dot matrix 701, and the aforementioned spacing is the distance d between the calibration point in the first calibration dot matrix 601 and the calibration points that make up the second calibration dot matrix 701.

[0105] S104. Correct the spraying position coordinates of the nozzle based on the nozzle deviation value.

[0106] It should be noted that in practical applications, the aforementioned printhead deviation value can be a correction value in the direction of print media movement (such as the paper output direction). For example, assuming the print media movement direction is the x-direction, located on the print media plane, and perpendicular to the print media movement direction is the y-direction, then the aforementioned correction value is the correction amount in the x-direction. For the y-direction correction amount, in the case of same-color overprinting, the printhead seams can be adjusted manually without calculation; in the case of different-color overprinting, the starting spray position of each color spraying unit can be adjusted manually without calculation.

[0107] This application configures a registration system including a controller and a slide with an image acquisition device. Responding to a registration trigger signal, the slide is controlled to drive the image acquisition device to acquire registration images between any group of adjacent nozzles. This achieves the acquisition of registration images between any group of adjacent nozzles with only one image acquisition device, reducing the complexity and cost of the registration system. Subsequently, by configuring the identification of nozzle identifiers in the registration images and a calibration point matrix representing the spraying area of ​​each nozzle in a group of adjacent nozzles, the actual spraying area of ​​each nozzle is identified, providing a correction reference for subsequent registration. Furthermore, by configuring the identification of the spacing between corresponding calibration points in the two calibration point matrices, the difference between each spacing and the preset spacing of a group of adjacent nozzles is calculated, thereby obtaining the boundary spacing of each spraying position of a group of adjacent nozzles during spraying, and the deviation from the current preset spacing of the nozzle. Further, by configuring the determination of the deviation value of each nozzle in a group of adjacent nozzles based on the mean of each difference, the impact of abnormal differences on the calculation accuracy of the nozzle deviation value is weakened, thereby improving the registration accuracy. Finally, the spraying position coordinates of the nozzle are corrected by configuring the nozzle-based deviation value, thus completing the registration. It is evident that this application improves registration accuracy while reducing system costs.

[0108] In one possible implementation, before identifying the spacing between calibration points at corresponding positions in the two calibration dot matrices, the machine vision-based printing registration method provided in the first aspect of this application further includes:

[0109] Identify whether there is an orientation correction matrix in the registered image that matches the identifier;

[0110] In the absence of an orientation correction dot matrix, perform the operation step of identifying the spacing between corresponding calibration points in two calibration dot matrices;

[0111] In the presence of an orientation correction point matrix, the offset angle is determined based on the orientation correction point matrix, and the coordinates of each calibration point in the two calibration point matrices are corrected based on the offset angle; after the correction is completed, the operation steps of identifying the spacing between corresponding calibration points in the two calibration point matrices are performed.

[0112] It should be noted that, in practical applications, the aforementioned orientation correction dot matrix represents the correction point matrix pointing to the registered image. When the image acquisition device can acquire and calculate accurate spacing, the aforementioned registered image points to any preset coordinate axis parallel to the preset coordinate system containing the image acquisition device's shooting plane. A schematic diagram of the preset coordinate system containing the shooting plane is shown below. Figure 6 As shown, the preset coordinate system (composed of the x-axis and y-axis) where the shooting plane 61 is located is as follows: Figure 6As shown, the orientation correction dot matrix 62 is parallel to calibration point matrix 63 (No. 1) and calibration point matrix 64 (No. 2), respectively. The orientation correction dot matrix 62 represents the alignment of the registered image with the x-axis (the direction of printing media movement) in a way that allows for accurate spacing calculation. During registration, the spacing between the calibration points at the corresponding positions is determined by the image acquisition device identifying the registered image and converting the calibration points to a spatial coordinate system to obtain their coordinates. If the registered image is no longer parallel to the x-axis, the distance and angle between each calibration point in calibration point matrix 63 (No. 1) and calibration point matrix 64 and the lens of the image acquisition device will change, causing the identified calibration point coordinates to shift, thus reducing the accuracy of the calculated spacing. Therefore, this application improves the accuracy of the obtained calibration point coordinates by configuring the identification of whether an orientation correction dot matrix exists in the registered image, and, if so, determining the offset angle based on the orientation correction dot matrix, and correcting the coordinates of each calibration point in the two calibration dot matrices based on the offset angle, thereby improving the accuracy of the final calculated spacing.

[0113] It should be noted that in practical application scenarios, there are multiple ways to determine the offset angle based on the orientation correction matrix and correct the coordinates of each calibration point in the two calibration matrices based on the offset angle. Here, one is provided as an example, including the following steps A1 to A3.

[0114] Step A1: Identify the coordinates of each correction point in the orientation correction point matrix. Then trigger step A2.

[0115] Step A2: Use the preset least squares algorithm to fit the coordinates of each correction point in step A1 to obtain the first direction vector representing the direction of the registered image. Then trigger step A3.

[0116] Step A3: Obtain the first angle corresponding to the slope of the first direction vector, obtain the second angle corresponding to the slope of the preset reference direction vector, and determine the difference between the first angle and the second angle as the offset angle. Then trigger step A4.

[0117] In one possible implementation, the preset reference direction vector in step A3 above can be the direction vector of the printing medium movement direction under the condition of accurately calculating the spacing, and the second angle corresponding to its slope is 0. The first angle mentioned above is the arctangent value of the slope of the first direction vector.

[0118] Step A4: Construct a rotation matrix based on the offset angle obtained in step A3, and substitute the coordinates of each calibration point into the rotation matrix to obtain the corrected coordinates of each calibration point.

[0119] In one possible implementation, the rotation matrix M(x, y) described above could be: .

[0120] In one possible implementation, the offset angle is determined based on the orientation correction matrix, and the coordinates of each calibration point in the two calibration matrices are corrected based on the offset angle, including:

[0121] Identify the direction correction point matrix corresponding to the nozzle identifier in the registered image and obtain the coordinates of each correction point in the direction correction point matrix;

[0122] Based on the coordinates of each correction point, the offset angle between the movement direction of the printing medium and the pointing direction represented by the orientation correction dot matrix is ​​calculated. The printing medium is the medium that carries the orientation correction dot matrix.

[0123] If the offset angle is not greater than the preset included angle threshold, perform the operation step of identifying the spacing between corresponding calibration points in the two calibration point matrices;

[0124] If the offset angle is greater than the preset included angle threshold, the coordinates of each calibration point are corrected based on the offset angle.

[0125] Those skilled in the art will understand that, in practical applications, the acquisition of point coordinates and corresponding calculations through image recognition, as described in this application, can be achieved by configuring an image recognition algorithm or a neural network model. The types of such image recognition algorithms or neural network models can be varied, including but not limited to: blob detection algorithms, contour detection algorithms, point spacing calculation algorithms, and object detection models (YOLO). This application does not impose excessive limitations or elaborate on the specific types and construction processes of the aforementioned algorithms or models.

[0126] In one possible implementation, determining the deviation value of each nozzle in a set of adjacent nozzles based on the mean of the differences includes:

[0127] Image recognition is performed on the calibration dot matrix in the registered image; when the image recognition result represents mismatched printing, the mean of each difference is determined as the deviation value of one printhead in a set of adjacent printheads, and the negative value of the deviation value is determined as the deviation value of another printhead in a set of adjacent printheads.

[0128] When the image recognition result represents overprinting of the same color, the mean of each difference is determined as the deviation value of one printhead in a set of adjacent printheads, and the negative value of the deviation value is determined as the deviation value of another printhead in a set of adjacent printheads. Based on the deviation value of each printhead and the deviation value of the reference printhead, the deviation value of each printhead is updated.

[0129] It should be noted that in practical applications, the aforementioned dissimilar color overprinting refers to the sequential spraying of different colors by different nozzles, while the aforementioned same-color overprinting refers to the sequential spraying of the same color by different nozzles. The dissimilar and same-color overprinting can be distinguished by differences in the calibration dot pattern, calibration dot matrix shape, and calibration dot color within the calibration dot matrix.

[0130] It should be noted that in practical applications, the aforementioned reference printhead is a pre-selected printhead among multiple printheads spraying the same color. In the case of dissimilar color overprinting, only the spraying distance between different colors needs to be considered. However, in the case of same-color overprinting, to ensure overprinting quality and avoid overlap or shadows, the spraying positions of each printhead of the same color need to be adjusted using the reference printhead as a reference point. Therefore, this application configures image recognition of the calibration dot matrix in the registration image. In the case of dissimilar color overprinting, the average of each difference is determined as the deviation value of one printhead in a group of adjacent printheads, and the negative value of the deviation value is determined as the deviation value of another printhead in the group of adjacent printheads. In the case of same-color overprinting, the average of each difference is determined as the deviation value of one printhead in a group of adjacent printheads, and the negative value of the deviation value is determined as the deviation value of another printhead in the group of adjacent printheads. Based on the deviation values ​​of each printhead and the reference printhead, the deviation values ​​of each printhead are updated. This process handles the differences in printhead deviation values ​​under different overprinting types to ensure registration accuracy under different overprinting types.

[0131] In one possible implementation, the deviation values ​​of each nozzle are updated based on the deviation values ​​of each nozzle and the deviation value of the reference nozzle, including:

[0132] For each nozzle:

[0133] The nozzles whose installation serial numbers are between the installation serial numbers of the nozzle and the reference nozzle are identified as associated nozzles.

[0134] Calculate the sum of the deviation values ​​of each associated nozzle and the deviation value of the nozzle itself, and determine the difference between the sum and the deviation value of the reference nozzle as the deviation value of the nozzle.

[0135] It should be noted that in practical applications, for adjacent printheads in same-color overprinting, any change in the spraying position of any printhead will cause a change in the spraying position deviation of adjacent printheads, and this change accumulates as the number of printheads between the current printhead and the reference printhead increases. Therefore, this application eliminates accumulated errors and improves the accuracy of updating the deviation values ​​of each printhead by configuring the calculation of the deviation value of each associated printhead and the sum of the deviation values ​​of that printhead, and determines the deviation value of that printhead as the difference between the sum and the deviation value of the reference printhead. This improves the accuracy of the final overprinting accuracy.

[0136] In one possible implementation, before determining the deviation values ​​of each printhead in a set of adjacent printheads based on the mean of the differences, the machine vision-based printing registration method further includes:

[0137] The verification variance is calculated based on each difference and the mean.

[0138] If the verification variance is greater than a preset variance threshold, outliers are removed from each difference based on the verification variance.

[0139] If the variance of the test is not greater than the preset variance threshold, perform the operation step of determining the deviation value of each nozzle of a group of adjacent nozzles based on the mean of each difference.

[0140] It should be noted that in practical applications, external interference factors such as equipment vibration, lighting fluctuations during shooting, and dust can cause outliers (extremely large or small) in the aforementioned differences. If the mean of each difference is directly determined as the nozzle deviation, the presence of outliers will affect the accuracy of the deviation determination. Therefore, this application improves the accuracy of the determined nozzle deviation by configuring the calculation of the verification variance based on each difference and the mean, and by removing outliers from each difference when the verification variance exceeds a preset variance threshold. This improves the accuracy of the determined nozzle deviation and ultimately enhances the registration accuracy.

[0141] In one possible implementation, in response to a registration trigger signal, the slide is controlled to move the image acquisition device to acquire registration images between any set of adjacent nozzles, including:

[0142] The system controls the image acquisition device to acquire an image of the printing medium at the initial position and performs image recognition on the printing medium image.

[0143] If a trigger identifier exists in the printed media image, execute the operation steps of controlling the slide to drive the image acquisition device to acquire the registration image between any group of adjacent printheads.

[0144] To facilitate understanding of the process by which the aforementioned image acquisition device acquires an image of the printing medium at its initial position, an explanation is provided here in conjunction with one possible implementation of this application:

[0145] like Figure 7The diagram illustrates a registration system for acquiring registration images. Image acquisition device 71 periodically acquires images of the printing medium from an initial position and performs image recognition on these images. Upon detecting trigger identifier 73, the image acquisition device moves to the starting position (which can be a pre-set position between two printheads 72) to acquire a registration image (including at least one printhead identifier 74 and at least one calibration dot matrix 75). Since image acquisition device 71 acquires wide-angle images, after acquiring the registration image at the current position, it can identify the nearest printhead identifier (excluding the printhead identifier corresponding to the current position) in the currently acquired registration image and move to the acquisition position corresponding to that printhead identifier for the next acquisition. The direction of movement of the printing medium is X, and the acquisition direction of the image acquisition device is Y.

[0146] In one possible implementation, the flowchart for image acquisition by the aforementioned image acquisition device can be as follows: Figure 8 As shown, it includes the following steps S801 to S804.

[0147] Step S801: The image acquisition device moves along the direction of motion to the position corresponding to the current nozzle mark and acquires the current registration image. Step S802 is then triggered.

[0148] Step S802: If the current registered image is successfully acquired, determine whether there are other nozzle markers. If yes, trigger step S803; otherwise, trigger step S804.

[0149] Step S803: Identify the nozzle identifier closest to the current position, excluding the current nozzle identifier, and update the current position to the position corresponding to that nozzle identifier. Then, trigger step S801.

[0150] Step S804: Control the image acquisition device to move to the initial position and stop image acquisition.

[0151] To facilitate understanding of the machine vision-based printing registration method provided by the first aspect and any implementation thereof of this application, one possible implementation of this application is described herein:

[0152] like Figure 9 The diagram shows a flowchart of a machine vision-based printing registration method. The specific operation steps are as follows:

[0153] Step S901: In response to the registration trigger signal, the slide table is controlled to drive the image acquisition device to acquire the registration images between any group of adjacent nozzles, obtaining multiple registration images of each group of adjacent nozzles. Step S902 is then triggered.

[0154] Step S902: Identify the nozzle identifier and two calibration points in the registration image. Then trigger step S903.

[0155] Step S903: Identify whether there is an orientation correction dot matrix in the registered image that matches the identifier. If yes, then trigger step S904; otherwise, trigger step S906.

[0156] Step S904: Determine the offset angle based on the orientation correction dot matrix, and determine whether the offset angle is greater than a preset included angle threshold. If yes, then trigger step S905; otherwise, trigger step S906.

[0157] Step S905: Correct the coordinates of each calibration point in the calibration matrix based on the offset angle. Then trigger step S906.

[0158] Step S906: Based on the coordinates of the calibration points, obtain the distance between corresponding positions of the calibration points in the two calibration point arrays, and calculate the difference between each distance and the preset distance of a set of adjacent nozzles. Then trigger step S907.

[0159] Step S907: Perform image recognition on the calibration dots in the registered image and determine whether the image recognition result indicates mismatched color overprinting. If yes, trigger step S908; otherwise, trigger step S909.

[0160] Step S908: The mean of all differences is determined as the deviation value of one nozzle in a group of adjacent nozzles, and the negative value of the deviation value is determined as the deviation value of another nozzle in the group of adjacent nozzles. Step S910 is then triggered.

[0161] In step S909, the mean of each difference is determined as the deviation value of one nozzle in a group of adjacent nozzles, and the negative value of the deviation value is determined as the deviation value of another nozzle in the group of adjacent nozzles. Based on the deviation values ​​of each nozzle and the deviation value of the reference nozzle, the deviation values ​​of each nozzle are updated. Step S910 is then triggered.

[0162] Step S910: Based on the deviation value of each nozzle, correct the spraying position coordinates of each nozzle.

[0163] A second aspect of this application provides a controller applied to a registration system, such as... Figure 10 The controller shown includes:

[0164] The image acquisition control unit 1001 is used to respond to the registration trigger signal, control the slide to drive the image acquisition device to acquire the registration image between any group of adjacent nozzles, and obtain multiple registration images of each group of adjacent nozzles.

[0165] The image recognition unit 1002 is used to recognize the nozzle identifier and two calibration dot matrix in the registration image. The calibration dot matrix represents the spraying area of ​​one of the nozzles in a group of adjacent nozzles corresponding to the nozzle identifier.

[0166] The deviation confirmation unit 1003 is used to identify the spacing between corresponding calibration points in two calibration point matrices, calculate the difference between each spacing and the preset spacing of a group of adjacent nozzles, and determine the deviation value of each nozzle in a group of adjacent nozzles based on the mean of each difference.

[0167] Deviation correction unit 1004 is used to correct the spraying position coordinates of the nozzle based on the nozzle deviation value.

[0168] In one possible implementation, the controller provided in the second aspect of this application further includes:

[0169] The orientation correction unit is used to identify whether there is an orientation correction matrix in the registered image that matches the identifier before the deviation confirmation unit 1003 identifies the distance between corresponding calibration points in the two calibration matrixes; it is also used to trigger the deviation confirmation unit 1003 to perform the operation step of identifying the distance between corresponding calibration points in the two calibration matrixes if there is no orientation correction matrix.

[0170] It is also used to determine the offset angle based on the orientation correction point matrix when an orientation correction point matrix exists, correct the coordinates of each calibration point in the two calibration point matrices based on the offset angle, and trigger the deviation confirmation unit 1003 to perform the operation step of identifying the distance between the calibration points at corresponding positions in the two calibration point matrices after the correction is completed.

[0171] In one possible implementation, the orientation correction unit is set to determine the offset angle based on the orientation correction matrix and correct the coordinates of each calibration point in the two calibration matrices based on the offset angle:

[0172] Identify the direction correction point matrix corresponding to the nozzle identifier in the registered image and obtain the coordinates of each correction point in the direction correction point matrix;

[0173] Based on the coordinates of each correction point, the offset angle between the movement direction of the printing medium and the pointing direction represented by the orientation correction dot matrix is ​​calculated. The printing medium is the medium that carries the orientation correction dot matrix.

[0174] If the offset angle is not greater than the preset included angle threshold, perform the operation step of identifying the spacing between corresponding calibration points in the two calibration point matrices;

[0175] If the offset angle is greater than the preset included angle threshold, the coordinates of each calibration point are corrected based on the offset angle.

[0176] In one possible implementation, the deviation verification unit 1003 is configured to determine the deviation value of each nozzle in a set of adjacent nozzles based on the mean of the differences:

[0177] Image recognition is performed on the calibration dot matrix in the registered image; when the image recognition result represents mismatched printing, the mean of each difference is determined as the deviation value of one printhead in a set of adjacent printheads, and the negative value of the deviation value is determined as the deviation value of another printhead in a set of adjacent printheads.

[0178] When the image recognition result represents overprinting of the same color, the mean of each difference is determined as the deviation value of one printhead in a set of adjacent printheads, and the negative value of the deviation value is determined as the deviation value of another printhead in a set of adjacent printheads. Based on the deviation value of each printhead and the deviation value of the reference printhead, the deviation value of each printhead is updated.

[0179] In one possible implementation, the deviation verification unit 1003 is configured to update the deviation values ​​of each nozzle based on the deviation values ​​of each nozzle and the deviation value of the reference nozzle:

[0180] For each nozzle:

[0181] The nozzles whose installation serial numbers are between the installation serial numbers of the nozzle and the reference nozzle are identified as associated nozzles.

[0182] Calculate the sum of the deviation values ​​of each associated nozzle and the deviation value of the nozzle itself, and determine the difference between the sum and the deviation value of the reference nozzle as the deviation value of the nozzle.

[0183] In one possible implementation, the deviation verification unit 1003 is further configured as follows:

[0184] Before determining the deviation value of each nozzle in a set of adjacent nozzles based on the mean of each difference, the verification variance is calculated based on each difference and the mean.

[0185] If the verification variance is greater than a preset variance threshold, outliers are removed from each difference based on the verification variance.

[0186] If the variance of the test is not greater than the preset variance threshold, perform the operation step of determining the deviation value of each nozzle of a group of adjacent nozzles based on the mean of each difference.

[0187] In one possible implementation, the image acquisition control unit 1001, in response to a registration trigger signal, controls the slide to drive the image acquisition device to acquire a registration image between any set of adjacent nozzles, and is configured to include:

[0188] The system controls the image acquisition device to acquire an image of the printing medium at the initial position and performs image recognition on the printing medium image.

[0189] If a trigger identifier exists in the printed media image, execute the operation steps of controlling the slide to drive the image acquisition device to acquire the registration image between any group of adjacent printheads.

[0190] A third aspect of this application provides a controller, including at least one processor and a memory connected to the processor, wherein:

[0191] Memory is used to store computer programs;

[0192] The processor is used to execute a computer program to enable the controller to implement the machine vision-based printing registration method of the first aspect or any implementation thereof described above.

[0193] The structural diagram of the controller provided in the third aspect of this application is as follows: Figure 11 As shown. The controller in the embodiments of this application may include, but is not limited to, fixed terminals such as desktop computers, laptops, PDAs (personal digital assistants), PADs (tablet computers), printer controllers, etc. Figure 11 The controller shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0194] like Figure 11 As shown, the controller may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1102 or a program loaded from storage device 1108 into random access memory (RAM) 1103. When the controller is powered on, RAM 1103 also stores various programs and data required for controller operation. The processing device 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. Input / output (I / O) interface 1105 is also connected to bus 1104.

[0195] Typically, the following devices can be connected to I / O interface 1105: input devices 1106 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 1107 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1108 including, for example, memory card, hard disk, etc.; and communication devices 1109. Communication device 1109 allows the controller to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 11 A controller with various devices is shown; however, it should be understood that implementation or possession of all the devices shown is not required. More or fewer devices may be implemented alternatively.

[0196] The fourth aspect of this application provides a computer storage medium carrying one or more computer programs, which, when executed by a controller, enable the controller to perform a machine vision-based printing registration method as described in the first aspect or any implementation thereof.

[0197] It should also be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. In addition, in the device embodiment drawings provided in this application, the connection relationship between modules indicates that they have a communication connection, which can be implemented as one or more communication buses or signal lines.

[0198] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware, or it can be implemented by special-purpose hardware including application-specific integrated circuits, special-purpose CPUs, special-purpose memory, special-purpose components, etc. Generally, any function performed by a computer program can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be diverse, such as analog circuits, digital circuits, or special-purpose circuits. However, for this application, software program implementation is more often the preferred implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium, such as a computer floppy disk, USB flash drive, mobile hard disk, ROM, RAM, magnetic disk, or optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, training equipment, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0199] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0200] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, training device, or data center to another website, computer, training device, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

Claims

1. A machine vision based print register method, characterized by, A controller applied to a register system, the register system comprising the controller and a slide table configured with an image acquisition device, the machine vision-based printing register method comprising: in response to a register trigger signal, controlling the slide table to drive the image acquisition device to acquire a register image between any group of adjacent nozzles, to obtain a plurality of register images of each group of the adjacent nozzles; identifying a nozzle identifier and two calibration dot arrays in the register image, the calibration dot arrays representing a spraying area of one nozzle in the group of the adjacent nozzles corresponding to the nozzle identifier; identifying a distance between calibration dots at corresponding positions in the two calibration dot arrays, respectively calculating a difference between each of the distances and a preset distance of the group of the adjacent nozzles, and determining a deviation value of each of the nozzles in the group of the adjacent nozzles based on a mean value of each of the differences; correcting a spraying position coordinate of the nozzle based on the deviation value of the nozzle.

2. The machine vision-based print registration method of claim 1, wherein, Before the step of identifying the distance between calibration dots at corresponding positions in the two calibration dot arrays, the machine vision-based printing register method further comprises: identifying whether a direction correction dot array adapted to the identifier exists in the register image; in the case where the direction correction dot array does not exist, performing the operation step of identifying the distance between calibration dots at corresponding positions in the two calibration dot arrays; in the case where the direction correction dot array exists, determining an offset angle based on the direction correction dot array, correcting coordinates of each of the calibration dots in the two calibration dot arrays based on the offset angle, and performing the operation step of identifying the distance between calibration dots at corresponding positions in the two calibration dot arrays after the correction is completed.

3. The machine vision-based print registration method according to claim 2, characterized in that, The step of determining the offset angle based on the direction correction dot array, and correcting the coordinates of each of the calibration dots in the two calibration dot arrays based on the offset angle, comprises: identifying a direction correction dot array corresponding to the nozzle identifier in the register image, to obtain each correction dot coordinate in the direction correction dot array; based on each of the correction dot coordinates, calculating the offset angle between a movement direction of a printing medium and a pointing direction represented by the direction correction dot array, the printing medium being a medium carrying the direction correction dot array; in the case where the offset angle is not greater than a preset included angle threshold, performing the operation step of identifying the distance between calibration dots at corresponding positions in the two calibration dot arrays; in the case where the offset angle is greater than the preset included angle threshold, correcting the coordinates of each of the calibration dots based on the offset angle.

4. The machine vision-based print registration method according to any one of claims 1 or 2, characterized in that, The step of determining the deviation value of each of the nozzles in the group of the adjacent nozzles based on the mean value of each of the differences, comprises: performing image recognition on the calibration dot arrays in the register image; in the case where an image recognition result represents a color misregistration, determining a mean value of each of the differences as a deviation value of one of the nozzles in the group of the adjacent nozzles, and determining a negative value of the deviation value as a deviation value of another of the nozzles in the group of the adjacent nozzles. In a case where the image recognition result represents the same color overprint, the mean value of each of the difference values is determined as a deviation value of one of the nozzles in the group of adjacent nozzles, and the negative value of the deviation value is determined as a deviation value of another of the nozzles in the group of adjacent nozzles, and the deviation value of each of the nozzles is updated based on the deviation value of each of the nozzles and the deviation value of the reference nozzle.

5. The machine vision-based print registration method according to claim 4, characterized in that, The updating of the deviation value of each of the nozzles based on the deviation value of each of the nozzles and the deviation value of the reference nozzle comprises: for each of the nozzles: a nozzle having an installation serial number between the installation serial number of the nozzle and the installation serial number of the reference nozzle is determined as an associated nozzle; a sum of the deviation value of each of the associated nozzles and the deviation value of the nozzle is calculated, and a difference between the sum and the deviation value of the reference nozzle is determined as the deviation value of the nozzle.

6. The machine vision-based print registration method of claim 1, wherein, Before the determination of the deviation value of each of the nozzles in the group of adjacent nozzles based on the mean value of each of the difference values, the machine vision-based printing register method further comprises: calculating a check variance based on each of the difference values and the mean value; in a case where the check variance is greater than a preset variance threshold, eliminating an abnormal value in each of the difference values based on the check variance; in a case where the check variance is not greater than the preset variance threshold, performing the operation of determining the deviation value of each of the nozzles in the group of adjacent nozzles based on the mean value of each of the difference values.

7. The machine vision-based print registration method of claim 1, wherein, The control of the slide table to drive the image acquisition device to acquire a register image between any group of adjacent nozzles in response to a register trigger signal comprises: controlling the image acquisition device to acquire a print medium image at an initial position, and performing image recognition on the print medium image; in a case where a trigger identifier exists in the print medium image, performing the operation of controlling the slide table to drive the image acquisition device to acquire a register image between any group of adjacent nozzles.

8. A controller characterized by comprising: The controller is applied to a register system, and the controller comprises: an image acquisition control unit configured to control a slide table to drive an image acquisition device to acquire a register image between any group of adjacent nozzles in response to a register trigger signal, and to obtain a plurality of register images of each group of adjacent nozzles; an image recognition unit configured to recognize a nozzle identifier and two calibration dot arrays in the register image, the calibration dot arrays representing a printing area of one nozzle in the group of adjacent nozzles corresponding to the nozzle identifier; a deviation confirmation unit configured to recognize a distance between calibration points at corresponding positions in the two calibration dot arrays, to calculate a difference between each of the distances and a preset distance of the group of adjacent nozzles, and to determine a deviation value of each of the nozzles in the group of adjacent nozzles based on a mean value of each of the difference values; a deviation correction unit configured to correct a printing position coordinate of the nozzle based on the deviation value of the nozzle.

9. A controller characterized by comprising: The controller comprises at least one processor and a memory connected to the processor, wherein: the memory is configured to store a computer program; and the processor is configured to execute the computer program stored in the memory. The processor is configured to execute the computer program to enable the controller to implement the machine vision based print register method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that The storage medium has one or more computer programs carried thereon, which, when executed by the controller, enable the controller to implement the machine vision based print register method according to any one of claims 1 to 7.

Images