Inspection system for printed matter, processing device used in the inspection system, and inspection method

Abstract

To improve accuracy of inspection of printed matter.SOLUTION: An inspection system is used in combination with a printing machine that includes a print controller converting input print source data into head data, and a print head that performs printing on the basis of the head data. The inspection system includes a camera that images printed matter printed by the printing machine to generate a camera image, and a processing device that determines the quality of the printed matter on the basis of the camera image and outputs the determination result. The processing device acquires identification information specifying at least one of the model and the mode of the printing machine, performs spatial filtering processing on the print source data or the head data to generate a filter image, and compares the filter image with the camera image. The processing device determines the filter parameters used in the spatial filtering processing on the basis of the identification information.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a printed matter inspection system, a processing device used in the inspection system, and an inspection method. [Background technology]

[0002] 2. Description of the Related Art Various inspection devices have been developed and are in use for inspecting the quality of a print by comparing image data acquired by photographing a print with a camera with the original print data.

[0003] For example, Patent Document 1 discloses an inspection device that performs inspection based on the difference between a master image generated from print data and a read image generated by reading a printed matter with a reading device. It describes that by generating a master image from print data, it is possible to efficiently inspect printed matter, for example, by variable data printing (VDP).

[0004] Patent Document 2 discloses an inspection method in which an inspection image obtained by photographing a printed matter is read out and compared with a previously generated reference image for each unit of the printed matter, and if a mismatch is found, it is determined that an error has occurred in the printing.

[0005] Patent Document 3 discloses an inspection device that inspects the print contents and print condition of color prints in which different data is printed on a page-by-page basis. This inspection device inspects the print contents and print condition by comparing the background pattern common to the prints and the variable data that differs for each print with a reference image.

[0006] Patent Document 4 discloses an inspection method for determining the quality of a printed matter by comparing comparative reference data generated by converting reference data according to the conditions of the printed matter with comparative image data based on image data acquired by imaging the printed matter. The comparative reference data is converted from the reference data using a learning model generated by applying deep learning. It is described that this makes it possible to determine the quality of a printed matter using the reference data according to the conditions of the printed matter. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2015-174307 A [Patent Document 2] JP 2019-132661 A [Patent Document 3] JP 2003-54096 A [Patent Document 4] JP 2020-186938 A Summary of the Invention [Problem to be solved by the invention]

[0008] In conventional print inspection methods, the accuracy of inspection can be reduced due to differences in the format of image data acquired by photographing a print and the data that was the basis for the print, ink bleeding during printing, paper deformation, etc. Also, in an environment where multiple printing machines of different models are mixed, or when a printing machine operates in multiple modes according to the printing target, it is difficult to properly inspect each of the multiple printing machines or multiple modes.

[0009] The present disclosure provides a new inspection technology that can improve the accuracy of image inspection of printed materials in an environment where multiple printing machines of different models are mixed or when a printing machine operates in multiple modes depending on the printing subject. [Means for solving the problem]

[0010] An inspection system according to one aspect of the present invention is used in combination with a printing machine having a print controller that converts inputted original printing data into head data, and a print head that performs printing based on the head data. The inspection system includes a camera that captures a printed matter printed by the printing machine and generates a camera image, and a processing device. The processing device acquires identification information that identifies at least one of the model of the printing machine and the mode of the printing machine, and executes, based on the identification information, either (a) a first process that judges the quality of the printed matter by comparing a first filtered image generated by performing a first spatial filtering process using a first filter on the original printing data with the camera image, or (b) a second process that judges the quality of the printed matter by comparing a second filtered image generated by performing a second spatial filtering process using a second filter on the head data with the camera image. The processing device determines parameters of the first filter and parameters of the second filter based on the identification information.

[0011] A processing device according to another aspect of the present invention is used in combination with a printing machine including a print controller that converts input original printing data into head data, and a print head that performs printing based on the head data. The processing device acquires identification information that identifies at least one of the model of the printing machine and the mode of the printing machine, and determines, based on the identification information, parameters of a first filter used in a first spatial filtering process to be applied to the original printing data and parameters of a second filter used in a second spatial filtering process to be applied to the head data. The processing device compares a first filter image generated by performing the first spatial filtering process on the original printing data with a second filter image generated by performing the second spatial filtering process on the head data, and outputs the comparison result.

[0012] A general or specific aspect of the present invention may be realized by an apparatus, a system, an integrated circuit, a computer program, a recording medium, or any combination thereof. Effect of the Invention

[0013] According to the present invention, it is possible to improve the accuracy of image inspection of printed matter. [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram illustrating an example of a conventional inspection system. [Diagram 2] 1A and 1B are diagrams illustrating the deformation of paper and printed portions caused by printing; [Diagram 3] FIG. 1 is a diagram illustrating a configuration of an inspection system according to an exemplary embodiment of the present invention. [Figure 4] FIG. 2 is a schematic diagram for explaining an overview of a determination process performed by a processing device. [Diagram 5] FIG. 1 is a schematic diagram illustrating an example of a system including multiple printing machines. [Figure 6A] FIG. 13 is a diagram for explaining another example of the inspection system. [Figure 6B] FIG. 13 is a diagram for explaining yet another example of the inspection system. [Figure 7A] FIG. 10 is a diagram showing a schematic flow of an inspection based on an image that has been printed and filtered. [Figure 7B] FIG. 1 is a diagram illustrating an outline of a color conversion process. [Figure 8] 10 is a flowchart illustrating an example of a process executed by the processing device. [Figure 9A] FIG. 13 is a diagram showing an example of a table showing the relationship between printing machines and output data formats, etc. [Figure 9B] FIG. 13 is a diagram showing an example of a table showing the relationship between the mode of the printing machine and the filter to be used. [Figure 10] 10 is a flowchart showing another example of the process executed by the processing device. [Figure 11] FIG. 11 is a diagram showing a flow of a process for converting head data into a first filter image. [Figure 12A]1A and 1B are diagrams illustrating examples of a Gaussian filter and an averaging filter. [Figure 12B] FIG. 13 is a diagram illustrating an example of a color conversion table. [Figure 13] 1A and 1B are diagrams illustrating an example of a spatial filter and a method of adjusting parameters of the spatial filter. [Figure 14] 1A and 1B are diagrams illustrating an example of a color conversion table and an example of a method for adjusting parameters thereof. [Figure 15] 11A and 11B are diagrams illustrating an example of a process of matching a first filter image with a camera image. [Figure 16] 1 is a flowchart showing the flow of a method for generating a trained model. [Figure 17A] FIG. 1 is a diagram showing an example of a test chart. [Figure 17B] FIG. 13 is a diagram showing another example of the test chart. [Figure 17C] FIG. 13 is a diagram showing yet another example of the test chart. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Before describing the embodiments of the present invention, the findings on which the present invention is based will be described.

[0016] A digital printing press that performs variable data printing prints different content on each page. Such a printing press is widely used for various purposes such as printing addresses, invoices, and statements.

[0017] In variable printing, different content is printed on each page, so inspection cannot be performed using a simple method such as comparing with a single image prepared in advance. For this reason, a method of inspection can be considered that compares and collates the image data of the original print with the image data obtained by capturing the printout.

[0018] However, the method of matching two images has the following problems, for example: Generally, printing processes subtractive color data (YMCK) and cameras process additive color data (RGB), so the data from the two cannot be directly compared. The image displayed in the printing press does not necessarily match the image displayed in the inspection device, and differences arise. Due to the characteristics of the paper or ink, etc., ink bleeding or paper deformation may occur, resulting in differences between the image you are trying to print and the image that is actually printed.

[0019] Due to these issues, it has been difficult for conventional inspection devices to inspect color printed materials with high accuracy, and so inspection systems that focus on matching the colors of important parts, such as characters, have often been used.

[0020] FIG. 1 is a diagram showing a schematic diagram of an example of a conventional inspection system. The inspection system shown in FIG. 1 includes a printing machine 100 (printer) having a print controller 110 and a print head 120, a processing device 210, and a camera 220 (imaging device). The print head 120 includes four types of heads corresponding to four colors, cyan (C), magenta (M), yellow (Y), and black (K). The print controller 110 converts the original print data (e.g., a PDF file, etc.) input from an external computer 300 into head data and outputs it to each print head 120. The head data is, for example, data of halftone images of each color of CMYK. Each print head 120 executes printing on the paper 10 being conveyed according to the head data. The printed paper 10 is photographed by the camera 220. The camera 220 photographs the printed paper 10 to generate camera image data (hereinafter, also referred to as "camera image"). The processor 210 extracts data of a specific color (for example, the color of an important part such as a character) from each of the head data and the camera image, and compares them to determine the quality of the print.

[0021] In such a system, the inspection target is limited to a specific color component of the printed matter, and other color components cannot be inspected. In addition, it is difficult to detect defects in the printed matter caused by ink bleeding or paper deformation during printing with high accuracy.

[0022] Generally, paper used for printing expands and contracts as it absorbs moisture and oil. When ink containing moisture or oil is sprayed or applied onto paper, the paper expands and contracts, and the printed matter may be distorted relative to the original digital data. For example, A4 size paper may be distorted by about 1 mm.

[0023] FIG. 2 is a schematic diagram showing deformation of paper and printed parts due to printing. As shown in FIG. 2, parts with a large amount of ink shrink more, and parts with a small amount of ink shrink less. The degree and form of deformation vary depending on the print content, so it is difficult to predict the deformation in advance. In particular, in variable printing, where different contents are printed on each page, the amount of ink differs from page to page, so the way of shrinkage may change irregularly from page to page. As a result, it may be difficult to match the camera image with the original data. In addition, the optical characteristics of the lens in the camera (mainly distortion aberration) may cause the captured image to deform. In this case, the deformation is regular, but it may also be difficult to match the original data.

[0024] In addition, in the system shown in FIG. 1, the inspection is performed by comparing the image shown by the head data with the camera image, but some printers output original data instead of head data. In an environment where printers that output original data and printers that output head data coexist, it is required to be able to perform the inspection appropriately regardless of the printer model. Furthermore, the characteristics of the ink discharged from the print head 120 (ejection amount, thickness, etc.) may differ depending on the printer model and mode. For example, in a printer that selects one mode from a plurality of modes according to the type of object to be printed (e.g., paper, film, etc.), when the mode is changed, the head data generated by the print controller 110 changes. As a result, the color tone and bleeding of the printed image may also change depending on the mode. Therefore, it is required to be able to perform accurate inspection regardless of the printer model and mode.

[0025] In order to solve the above problems, the inventors have come up with the configuration of the embodiment of the present invention described below. An exemplary embodiment of the present invention will be described below. However, more detailed explanation than necessary may be omitted. For example, detailed explanation of already well-known matters or duplicate explanation of substantially the same configuration may be omitted. This is to avoid the following explanation becoming unnecessarily redundant and to facilitate understanding by those skilled in the art. Note that the inventor provides the attached drawings and the following description so that those skilled in the art can fully understand this disclosure, and does not intend to limit the subject matter described in the claims by them. In this specification, the same reference symbols are used for the same or similar components.

[0026] (Embodiment 1) FIG. 3 is a diagram showing a schematic configuration of an inspection system according to an exemplary embodiment of the present invention. The inspection system includes a printing machine 100 and an inspection device 200. FIG. 3 also shows a computer 300 connected to the printing machine 100 and the inspection device 200. The computer 300 is any information processing device, such as a server computer, a personal computer (PC), or a mobile terminal. The computer 300 may be included in the inspection system, or may be an external element of the inspection system. The printing machine 100 may also be an external element of the inspection system.

[0027] The printer 100 shown in FIG. 3 includes a print controller 110, a print head 120, and a conveyor 130. The conveyor 130 conveys the rolled paper 10. The print controller 110 is a device that controls the overall operation of the printer 100. The print controller 110 includes an integrated circuit including a processor and a memory, such as a microcontroller unit. The print controller 110 receives a print instruction including original print data input from the computer 300 and drives the conveyor 130 and the print head 120. As a result, the printer 100 performs printing while conveying the paper 10. The print controller 110, the print head 120, and the conveyor 130 do not have to be integrated into one device, and may be configured as independent devices.

[0028] The printing machine 100 is a digital printing machine that performs printing using a known method such as an inkjet method or an electrophotographic method. The printing machine 100 prints on paper 10 based on original print data input from a computer 300. The printing may be color printing or monochrome printing. In the following description, as an example, color printing is performed using four colors of ink: cyan (C), magenta (M), yellow (Y), and black (K). The printing machine 100 may perform printing using inks of other colors, not limited to CMYK.

[0029] The printer 100 in this embodiment is capable of performing variable printing. In variable printing, different characters, figures, images, etc. are continuously printed on each page of the paper 10. The paper 10 in this embodiment is roll paper, but printing may also be performed on other printing media such as film.

[0030] The print controller 110 converts the input original print data into head data and outputs it to the print head 120. The original print data may be vector-format data including image and character information such as PDF (Portable Document Format). The head data may be bitmap (raster) data representing a halftone image expressed with a small number of gradations, such as about 2 to 4 gradations per color pixel. The print controller 110 has a function of RIP (Raster Image Processor) that converts original print data, such as vector format, into head data representing a raster image expressed as a set of points with a smaller number of gradations. The RIP process may include various processes such as a process of converting original print data such as PDF into raster data, a process of converting RGB (red, green, blue) to CMYK (cyan, magenta, yellow, black), and a halftone process that expresses the shade of each color with halftone dots (halftone). At least a part of the RIP function may be executed by a device (such as the computer 300) different from the print controller 110. The original print data is not limited to PDF, and may be image data such as JPEG (Joint Photographic Experts Group) or PNG (Portable Network Graphics).

[0031] The print head 120 is a device including components for performing printing based on input head data and circuits for controlling these components. Although one print head 120 is illustrated in FIG. 3, when color printing is performed, multiple types of print heads corresponding to multiple colors of ink may be provided. For example, four print heads corresponding to four colors of ink, cyan (C), magenta (M), yellow (Y), and black (K), respectively, may be provided. When the printing machine 100 is an inkjet printer, the print heads of each color may include multiple inkjet heads arranged in a direction perpendicular to the conveying direction (the direction of the arrow shown in FIG. 1) along the surface of the paper 10. Each inkjet head includes, for example, a nozzle that pressurizes or heats the ink and ejects it. Note that when the printing machine 100 is an electrophotographic printer, the print head 120 may include a light source such as a laser or LED, an optical system such as a polygon mirror, components such as a photosensitive drum, and circuits for controlling the light source and the optical system.

[0032] The inspection device 200 operates in conjunction with the printing machine 100, inspects the printed paper 10, and outputs the inspection results. The inspection device 200 is connected to the printing machine 100 and a computer 300. The inspection device 200 includes a camera 220 and a processing device 210.

[0033] The camera 220 is disposed on a transport path of the printed paper 10. The camera 220 captures an image of the printed paper 10 to generate image data (referred to as a "camera image"). The camera 220 can be configured to output the camera image for each page, for example.

[0034] The camera 220 includes an image sensor such as a CCD or CMOS and an optical system such as a lens. The camera 220 may include a two-dimensional image sensor, or a linear image sensor (line sensor) such as a contact image sensor (CIS). When the camera 220 includes a linear image sensor, the camera 220 may capture the conveyed paper 10 line by line, and output the data of the multiple lines as a camera image by page. Alternatively, the camera 220 may output data line by line, and the processing device 210 may generate the data of the two-dimensional camera image by collecting the data of the multiple lines for each page. The camera 220 may be provided not only on the front side of the paper 10 but also on the back side. By providing two cameras 220 on both sides of the paper 10, the printing state of both sides of the paper 10 can be inspected.

[0035] The processing device 210 includes a processor 212, storage media (memories) such as a RAM 214 and a ROM 216, and an input / output interface (I / F) 218. The processor 212 includes an arithmetic processing circuit such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The ROM 216 stores a computer program executed by the processor 212. The program includes a set of instructions for causing the processor 212 to execute processes described below. The RAM 214 is a work memory for expanding the program when the processor 212 executes the program. The processor 212 is connected to the computer 300, the print controller 110, and the camera 220 via the interface 218.

[0036] The processor 212 of the processing device 210 performs a comparison process based on the original print data or head data and the camera image data to determine the quality of the printed matter. The processor 212 of the processing device 210 can also perform a comparison process based on the original print data and head data to determine the normality of the print controller 110. The processing device 210 can arbitrarily select the comparison data to be compared from a pair of original print data and a camera image, a pair of head data and a camera image, or a pair of original print data and head data. Details of this determination process will be described below with reference to Figs. 4 to 6B.

[0037] FIG. 4 is a schematic diagram for explaining an example of the judgment process by the processing device 210. The processing device 210 in this example acquires at least one of the original printing data and the head data, performs necessary conversion processes such as spatial filtering and color conversion on the acquired original printing data or the head data, and generates image data for comparison (hereinafter, sometimes referred to as "printer filter image"). The processing device 210 also acquires a camera image from the camera 220, performs necessary conversion processes such as spatial filtering and color conversion on the camera image, and generates a camera image for comparison (hereinafter, sometimes referred to as "camera filter image"). The processing device 210 compares the printer filter image with the camera filter image, and outputs the comparison result. For example, the processing device 210 executes a process of comparing the printer filter image with the camera filter image for each relatively small area over the entire image, and judges the quality of the print based on the degree of match between the two. The processing device 210 outputs the judgment result to an output device or storage device such as a display or speaker connected to the processing device 210.

[0038] In the example shown in FIG. 4, the processing device 210 can select whether to use the original print data or the head data for matching. The processing device 210 can be configured to select whether to use the original print data or the head data for matching based on, for example, a mode setting specified by a user. In this case, the user can use an input device connected to the processing device 210 to switch between a first mode using the original print data and a second mode using the head data. Alternatively, the processing device 210 may be configured to obtain model information of the printing machine 100 from a device such as the computer 300 or the print controller 100, and select whether to use the original print data or the head data for matching according to the model information. Such a function makes it possible to perform an appropriate inspection according to the model of the printing machine 100.

[0039] When the print controller 110 outputs head data, the contents of the head data may differ depending on the model and print mode of the printer 100. For example, if the printer 100 is a model capable of printing in a plurality of print modes according to the type of paper 10, the thickness or color setting of the ink used, the print speed, or the image quality, the head data may differ depending on the print mode. This is because the optimal halftone dot processing differs depending on various factors such as the type of paper 10 and the type of ink used by the printer 100. In such a printer 100, the optimal mode is selected from the plurality of print modes according to the type of paper 10, the thickness or color setting of the ink used, the print speed, or the image quality, and printing is performed.

[0040] Therefore, the processing device 210 in this embodiment is configured to acquire identification information that identifies at least one of the model and mode of the printing press 100, and switch filter parameters (e.g., values ​​that determine the filter size and coefficients, etc.) to be applied to the original print data or head data according to the identification information. This allows the filter parameters to be adjusted to optimal values ​​according to the identification information. The processing device 210 acquires identification information of the printing press 100 from an external device, such as the computer 300, the print controller 110, or an input device used by the user. The identification information may include at least one of model information that identifies the model of the printing press 100 and mode information that identifies the mode of the printing press 100.

[0041] The processing device 210 may further be configured to change the parameters of the filter used in the spatial filtering process applied to the camera image according to the identification information. The processing device 210 may also be configured to change the parameters of the color conversion process applied to the original print data or the head data according to the identification information. The processing device 210 may further be configured to change the parameters of the color conversion process applied to the camera image according to the identification information.

[0042] The identification information may include both model information that identifies the model of the printing press 100 and mode information that identifies the mode of the printing press 100. The mode information has a different data format for each model of the printing press 100. The processing device 210 can read the mode information that has a different data format for each model of the printing press 100 based on the model information. The processing device 210 may be configured to select matching data based on the model information and to determine parameters of a filter to be used in each spatial filtering process based on the mode information.

[0043] In the example shown in Fig. 4, the print head 120 includes four types of print heads corresponding to four colors: cyan (C), magenta (M), yellow (Y), and black (K). This allows color printing. The print head 120 may be configured to perform monochrome printing. When monochrome printing is performed, color adjustment processing for the original print data or head data and the camera image data may be omitted.

[0044] According to this embodiment, the processing device 210 judges the quality of the print based on a printer filter image generated by performing spatial filtering on the original print data or head data, and a camera filter image generated by performing spatial filtering on a camera image acquired by photographing the print. As the spatial filtering process, a process that reflects the influence of ink bleeding and paper deformation during printing is performed. This makes it possible to detect defects in the print with high accuracy even if ink bleeding and paper deformation occur during printing. In addition, in this embodiment, a color adjustment process according to the characteristics of the original print data or head data and the camera image is also performed. This makes it possible to perform inspection with high accuracy regardless of the difference in color expression between the two.

[0045] Furthermore, the processing device 210 in this embodiment switches between a first process in which a first spatial filtering process using a first filter is performed on the original print data to generate a first filtered image, and a second process in which a second spatial filtering process using a second filter is performed on the head data to generate a second filtered image, according to identification information that specifies at least one of the model of the printing machine 100 and the mode of the printing machine 100. That is, the processing device 210 selects collation data based on the identification information of the printing machine 100. The processing device 210 also sets the parameters of the first filter and the second filter, and various parameters in the color conversion process, to optimal values ​​based on the identification information. This makes it possible to perform appropriate inspection according to the model or mode of the printing machine 100, even in an environment where multiple printing machines 100 of different models are mixed, or when the printing machine 100 has multiple printing modes according to the printing target (e.g., paper, film, etc.).

[0046] FIG. 5 is a diagram showing a schematic example of a system including a plurality of printers of different models. In FIG. 5, two printers 100A and 100B are shown as examples. The number of printers is not limited to two, and may be three or more. In this example, the printer 100A is configured to output original print data and identification information of the printer 100A. Meanwhile, the printer 100B is configured to output head data and identification information of the printer 100B. The user can select whether to print using the printer 100A or the printer 100B. When the printer 100A is used, the processing device 210 acquires original print data and identification information from the printer 100A, and performs spatial filtering processing and color conversion processing according to the model or mode of the printer 100A indicated by the identification information to generate a first filter image. On the other hand, when the printing press 100B is used, the processing device 210 acquires the head data and identification information from the printing press 100B, performs spatial filtering processing and color conversion processing according to the model or mode of the printing press 100B indicated by the identification information, and generates a second filter image. The processing device 210 judges the quality of the print by comparing the first filter image or the second filter image with a camera filter image converted from a camera image.

[0047] 5 can acquire the identification information of the printer 100A or 100B, and switch between a first process of performing spatial filtering and color conversion on the original print data and a second process of performing spatial filtering and color conversion on the head data, depending on the identification information. Also, the processor 210 can adjust parameters such as the size and coefficient of the filter used in the spatial filtering process, as well as parameters of the color conversion process, depending on the identification information. This enables appropriate inspection depending on the model and mode of the printer.

[0048] 5, the printing machine 100A is configured to transmit the original print data and the identification information to the processing device 210. Instead of the printing machine 100A, the computer 300 may be configured to transmit the original print data and the identification information to the processing device 210. Also, instead of the printing machine 100B, the computer 300 may be configured to transmit the identification information of the printing machine 100B to the processing device 210.

[0049] The processing device 210 may omit the spatial filtering process and color adjustment process for the camera image, and directly compare the camera image with a filter image based on the original print data or head data. Fig. 6A shows an example of a system configuration in this case. By performing appropriate spatial filtering and other processes on the original print data or head data (hereinafter, collectively referred to as "print data"), it is possible to perform inspection with the same degree of accuracy as when a person visually inspects.

[0050] As described above, after acquiring the identification information of the printing press 100, the processing device 210 in this embodiment executes either the following first process (a) or second process (b). (a) The quality of the print is determined by comparing a first filter image generated by performing a first spatial filtering process on the original printing data using a first filter with a camera image generated by a camera that photographs the printout printed by the printing press. (b) The quality of the print is judged by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image.

[0051] The processing device 210 selects whether to execute the first process or the second process based on the identification information. Also, the processing device 210 adjusts the parameters of the first filter and the second filter based on the identification information. Through such operations, an optimal image inspection according to the model or mode of the printing press is realized.

[0052] Instead of performing the above first process (a) or second process (b), the processing device 210 may perform the following third process (c). (c) The normality of the print controller is determined by comparing a first filter image generated by performing a first spatial filtering process on the original print data using a first filter with a second filter image generated by performing a second spatial filtering process on the head data using a second filter.

[0053] In this case, the processing device 210 compares the original print data with the head data without using the camera image. The processing device 210 may select which of the first process, the second process, and the third process to execute based on the identification information.

[0054] 6B is a diagram showing an example of the processing device 210 performing the above-mentioned third process (c), that is, matching between the original print data and the head data. In this example, the camera 220 is not used, and the processing device 210 matches a first filter image generated by performing a conversion process such as spatial filtering on the original print data with a second filter image generated by performing a conversion process such as spatial filtering on the head data, and outputs the matching result (for example, information indicating whether the print controller 110 is normal or not). With this configuration, it is possible to detect printing defects caused by a failure or malfunction of the print controller 110 without using the camera 220. This function may be used alone or in combination with matching using a camera image.

[0055] FIG. 7A is a diagram showing a schematic flow of an inspection based on an image subjected to printing and filtering processing in this embodiment. Here, an example of a case where a filter image generated by filtering an image indicated by head data using a spatial filter is compared with a camera image is described. As shown in FIG. 7A, the print controller 110 performs halftone processing such as dithering on the original print data to generate head data. The head data is halftone data in which the shading in the original print data is expressed as dot density. Such head data can be generated for each color, for example, cyan, magenta, yellow, and black. The print head 120 drives the head corresponding to each color based on such head data to print on paper. On the paper, the image changes due to the effects of ink bleeding and mixing. In addition, when a print is photographed with a camera, the photographed image changes depending on the characteristics of the camera, the photographing environment, and the like. As a result, the camera image does not match the image indicated by the head data, and the two cannot be directly compared. Therefore, in the example of FIG. 7A, the processing device 210 converts the head data into a filter image using a spatial filter that simulates the effects of ink bleeding on paper and deformation of the paper during printing, and compares the filter image with the camera image. This makes it possible to compare the head data with the camera image, and can greatly improve the accuracy of the inspection. The size and density of the dots in the head data and the degree of ink bleeding on the paper change depending on the model and mode of the printing machine. In this embodiment, by switching the spatial filter to be used depending on the model and mode of the printing machine, appropriate inspection is possible regardless of the model and mode.

[0056] In the example of FIG. 7A, the head data is subjected to spatial filtering to generate a filter image for comparison, but as described above, the original print data may be subjected to processing such as spatial filtering to generate a filter image for comparison. When the original print data is vector format data such as PDF, the processing device 210 may perform necessary processing such as rasterization and color conversion on the original print data before performing spatial filtering. Since the original print data is also different from the camera image, the two cannot be compared as they are. By performing appropriate spatial filtering processing on the original print data according to the model and mode of the printing machine, the accuracy of the inspection can be improved.

[0057] In the example shown in Fig. 7A, the camera image is used as is as the data for comparison, but as in the example of Fig. 4, the camera image may also be subjected to conversion processing such as spatial filtering and color conversion to facilitate comparison between the two. In this case, too, the spatial filtering processing and color conversion processing may be appropriately adjusted according to the identification information (model or mode) of the printing press.

[0058] Thus, in this embodiment, the print data (and the camera image, if necessary) are processed before matching, assuming factors of image changes due to printing. The processing may be performed using a spatial filter (i.e., a low-pass filter) that performs smoothing, such as a Gaussian filter. The spatial filter used is not limited to a linear filter such as a Gaussian filter, but may be a nonlinear filter. In addition, a plurality of spatial filters may be combined to generate an appropriate filter image for matching. The spatial filter is created in advance according to the model and mode of the printing machine 100 and the characteristics of the paper 10. The spatial filter may be generated as a learned model trained using machine learning, for example. The processing device 210 itself may generate the spatial filter before inspection. The processing device 210 may generate an optimal spatial filter (learned model) by learning the deformation of known print data during printing, for example, using a machine learning algorithm using a neural network. An example of the neural network used is a convolutional neural network (CNN) using an error backpropagation method. The processing device 210 may generate an optimal spatial filter for each model or mode of a printing press, for example, using a learning algorithm (such as pix2pix) based on a Generative Adversarial Network (GAN).

[0059] In the embodiment shown in Figures 4 to 6, the processing device 210 performs a color conversion process in addition to a spatial filtering process on the print data. This makes it easier to compare colors between the print data and the camera image. Below, an overview of the color conversion process in this embodiment will be described with reference to Figure 7B.

[0060] FIG. 7B is a diagram showing a schematic overview of the color conversion process. Here, as in the example shown in FIG. 7A, an example in which a filter image is generated from head data will be described. In this example, the original print data is expressed in an additive RGB color space, and the head data is expressed in a subtractive CMYK color space. Since the image captured by the camera is expressed in the RGB color space, the head data cannot be directly compared with the camera image. Therefore, the processing device 210 generates a filter image by performing a conversion process from the CMYK color space to the RGB color space in addition to the above-mentioned spatial filtering process on the head data. By performing such a conversion, the image captured by the camera can be reproduced in a pseudo manner from the head data, and the accuracy of the inspection can be improved.

[0061] Color conversion is not limited to conversion from CMYK to RGB, but may be other conversions. For example, in order to make the sensitivity to color changes closer to that of the human eye, the print data (print source data or head data) and the camera image are converted into the CIE-L color space in which each color is weighted equally. * a * b * Such a conversion enables inspection closer to that of the naked eye. Also, a learned model trained by a machine learning algorithm such as CNN using backpropagation may be used to convert the color of the print data using known print data and camera images. The processing device 210 may generate a model that simultaneously performs the spatial filtering and color conversion described above using an algorithm such as pix2pix. Such a model may be generated for each model or mode of the printing machine.

[0062] The processing performed by processing unit 210 will now be described in more detail with reference to FIG.

[0063] 8 is a flowchart showing an example of processing executed by the processor 212 of the processing device 210. In this example, after starting printing, the processing device 210 repeats the processing of steps S101 to S108 for each page of the printed matter until receiving an instruction to end printing (step S109) from the print controller 110. Note that the instruction to end printing may be input from a device other than the print controller 110, such as the computer 300.

[0064] In step S100, the processing device 210 acquires identification information of the printing machine 100. The identification information includes model information that identifies the model of the printing machine 100. The identification information may further include mode information that identifies the mode of the printing machine 100. The mode information may include, for example, information regarding at least one of the type of object (paper, film, etc.) on which printing is performed, the density of ink ejected from the print head, the printing speed, color settings, and print image quality. The processing device 200 may be configured to acquire the identification information from the printing machine 100, the computer 300, or an external device such as an input device used by a user.

[0065] The data format of the mode information differs depending on the model of the printing press 100. The processing device 200 can read mode information having a data format that differs depending on the model, based on the acquired model information. For example, data indicating the relationship between the model information of the printing press 100 and the data format of the corresponding mode information can be stored in advance in the memory of the processing device 200 (for example, the ROM 216 shown in FIG. 3). The processing device 200 can refer to the data to identify the data format corresponding to the model of the printing press 100, and read the mode information in accordance with the reading rules according to the data format.

[0066] Fig. 9A shows an example of data showing the relationship between model information of the printing press 100 and the data format of the corresponding mode information. The data shown in Fig. 9A is a table showing the correspondence between the identifiers (IDs) of multiple printing presses 100 used at the site where printing and inspection are performed, the model information, the type of output data (head data or original print data), and the data format of the mode information. The processing device 200 can identify the data format of the mode information corresponding to the model information by referring to a table such as that shown in Fig. 9A.

[0067] In step S101, the processing device 210 determines whether or not the printing machine 100 is a model that outputs head data based on the identification information. The processing device 210 determines whether or not the printing machine 100 corresponding to the acquired identification information is a model that outputs head data, for example, by referring to a table such as that shown in FIG. 9A. If the printing machine 100 is a model that outputs head data (the determination result is Yes), the process proceeds to step S102. If the printing machine 100 is a model that outputs original print data (the determination result is No), the process proceeds to step S103.

[0068] 9A is an example, and data in a format different from that of the illustrated table may be used as long as it contains similar information. For example, the information shown in FIG. 9A may be distributed between a table that stores model information for each printing press ID and a table that stores information on the type of output data and the data format of mode information for each model.

[0069] In step S102, the processing device 210 acquires the head data from the print controller 110. After that, the process proceeds to step S104.

[0070] In step S103, the processing device 210 acquires the source print data from the print controller 110. After that, the process proceeds to step S104. The source print data may be sent from the computer 300 to the processing device 210.

[0071] The head data or the original print data may be acquired simultaneously with the acquisition of the identification information in step S100. For example, in step S100, the processing device 210 may be configured to acquire data in which the head data or the original print data and the identification information are integrated from the print controller 110 or the computer 300. In such a case, the processes of steps S101, S102, and S103 are omitted, and the process proceeds to step S104 after step S100.

[0072] In step S104, the processing device 210 performs spatial filtering and color conversion on the acquired original printing data or head data to generate a printer filter image.

[0073] The spatial filtering process may include, for example, a process using a smoothing filter such as a weighted averaging filter (e.g., a Gaussian filter). The spatial filtering process may include a size compression process using an averaging filter. The spatial filtering process can simulate the effects of ink bleeding and paper deformation, making it easier to match with a camera image. When processing original print data in vector format, the processing device 210 may perform a rasterization process before the spatial filtering process to convert the data into an image in raster (bitmap) format.

[0074] The processing device 210 in this embodiment determines one or more filters to be used in the spatial filtering process based on the identification information. For example, the processing device 210 refers to the table illustrated in FIG. 9B and selects and uses a filter or a group of filter parameters corresponding to the model and mode of the printing machine indicated by the identification information. This allows the spatial filtering process to be appropriately performed using a filter according to the type and mode of the printing machine.

[0075] In the example shown in FIG. 8, the processing device 210 performs a color conversion process to adjust the color of each pixel of the printer filter image in addition to the spatial filtering process. When the printer filter image is expressed in a four-color color space of CMYK, the processing device 210 may be configured to perform color conversion from CMYK to RGB, which is the color space of the camera image, for the printer filter image. The color conversion may be performed based on a color conversion table created in advance. Alternatively, the processing device 210 may convert the original print data or head data into a filter image for matching using a learned model that has been trained in advance using a learning algorithm that utilizes an error backpropagation method or the like. The processing device 210 may determine a color conversion table or model based on the identification information of the printing machine 100. This makes it possible to perform color conversion processing appropriately according to the type and mode of the printing machine.

[0076] In step S105, the processing device 210 acquires a camera image from the camera 220. The camera image is, for example, RGB image data.

[0077] In step S106, the processing device 210 performs spatial filtering on the camera image acquired in step S105 to generate a camera filter image. The spatial filtering may include processing using a smoothing filter such as a weighted averaging filter (e.g., a Gaussian filter). The spatial filtering may include size compression processing using an averaging filter. By performing spatial filtering, for example, it is possible to generate a camera filter image having the same number of pixels and degree of blur as the printer filter image. This makes it easier to match the camera filter image with the printer filter image.

[0078] The processing device 210 may change one or more filters used in the spatial filtering process for the camera image according to the identification information. For example, the processing device 210 may refer to a table prepared in advance and select and use a filter or a group of filter parameters corresponding to the model and mode of the printing press indicated by the identification information. This allows the spatial filtering process to be appropriately performed using a filter according to the type and mode of the printing press.

[0079] In addition to the spatial filtering process, the processing device 210 may perform a color conversion process to adjust the color of each pixel of the camera image. In addition to the spatial filtering process and the color conversion process, a process such as rotation correction may be performed to facilitate matching with the printer filter image. Alternatively, the processing device 210 may convert the camera image into a camera filter image for matching using a learned model that has been trained in advance using a learning algorithm that utilizes an error backpropagation method or the like. The processing device 210 may determine a color conversion table or model based on the identification information of the printer 100. This allows the color conversion process to be performed appropriately depending on the type and mode of the printer.

[0080] The processes of steps S105 and S106 may be performed before step S102 or S103, or may be performed in parallel with the processes of steps S102 or S103.

[0081] In step S107, the processing device 210 compares the printer filter image with the camera filter image to determine whether the printing is good or bad. The processing device 210 determines whether the printing is good or bad based on the difference between the printer filter image and the camera filter image. For example, the processing device 210 can compare the printer filter image and the camera filter image for each corresponding small area, and determine that a printing error has occurred when a location where pixel values ​​are significantly different is detected.

[0082] In step S108, the processing device 210 outputs the judgment result. For example, the processing device 210 outputs information indicating whether or not there is a defect in the print, and if there is a defect, which location in the image the defect is located, as the judgment result. The judgment result may be output to, for example, an output device such as a display connected to the processing device 210 or a storage device. By looking at this output, the user can know that a defect has occurred in the print. The processing device 210 may create a list of the inspection results in which the judgment result is recorded for each page, and record the list in the storage device. This makes it possible to keep a history of printing and inspection.

[0083] In step S109, the processing device 210 judges whether or not there is an instruction to end printing. If there is no instruction to end printing, the process returns to step S101 and the next page is inspected. The instruction to end printing can be input from the print controller 110 or the computer 300, for example.

[0084] Through the above operations, the processing device 210 can compare the original print image and the camera image for each page of the printed matter and determine whether there are any abnormalities in the printing. In this embodiment, in steps S104 and S105, spatial filtering and color conversion are performed on the original print data or head data and the camera image. These processes facilitate the matching of the original print data or head data with the camera image, improving the accuracy of the inspection.

[0085] In the example of FIG. 8, conversion from the camera image to a camera filter image is performed in step S106, but this process may be omitted.

[0086] FIG. 10 is a flowchart showing another example of the process executed by the processor 212 of the processing device 210. In the flowchart shown in FIG. 10, steps S106 and S107 in the flowchart shown in FIG. 8 are replaced with step S117. The process other than step S117 is the same as the example of FIG. 8. In the example of FIG. 10, the processing device 210 does not perform spatial filtering and color conversion on the camera image, and uses the camera image as it is as data for comparison. In step S117, the processing device 210 compares the printer filter image with the camera image to determine whether the printing is good or bad. Even in this case, the model (spatial filter and color conversion table) used to generate the printer filter image from the printing data is appropriately created for each model or mode of the printer, so that the quality of the printing can be determined with high accuracy.

[0087] Here, a specific example of the data conversion process in step S104 will be described with reference to FIG. 11. FIG. 11 shows the flow of the process of converting the head data into a printer filter image. As an example, a process example in which a printer filter image is generated from head data (a) including image information of four colors, cyan (C), magenta (M), yellow (Y), and black (K), having a resolution of 1200 dpi (dots per inch) will be described. In the example of FIG. 11, pixel values ​​in an image indicated by the head data are expressed by 2 bits for each color (8 bits in total). Pixel value 0 (00 in binary) represents "no ink", pixel value 1 (01 in binary) represents "small" ink amount, pixel value 2 (10 in binary) represents "medium" ink amount, and pixel value 3 (11 in binary) represents "large" ink amount. For example, if the pixel value is 3 (11) for cyan, 1 (01) for magenta, 0 (00) for yellow, and 2 (00) for black, the amount of cyan ink is "large," the amount of magenta ink is "small," yellow is "no ink," and the amount of black ink is "medium." In this way, the ink amount of each color of CMYK is expressed by 2 bits, and the larger the value of the 2 bits, the greater the amount of ink. In this embodiment, the pixel value in the head data and the print density have a nonlinear relationship, and the print density is not proportional to the pixel value.

[0088] In the example of FIG. 11, the processing device 210 refers to a gray-scale conversion table recorded in advance in memory for each color of CMYK, and converts the head data having a pixel value of 2 bits for each color into image data (b) having a pixel value of 8 bits for each color (total of 32 bits). The pixel value and density in this image data have a linear relationship, and the density is proportional to the pixel value. The processing device 210 performs a filtering process (convolution operation) on this image data using a spatial filter such as a Gaussian filter and an averaging filter (for example, a filter that averages 16 pixels). As a result, the processing device 210 smoothes the image of each color of CMYK, and generates image data (c) in which the number of pixels is reduced to 1 / 16 (300 dpi).

[0089] FIG. 12A shows examples of a Gaussian filter and an averaging filter. The values ​​of the elements (coefficients) of these filters (kernels) are determined so as to appropriately reflect the effects of ink bleeding and paper deformation due to printing. The sizes (kernel sizes) of these filters and each coefficient are appropriately adjusted according to the model or mode of the printing machine 100. For example, when a mode corresponding to a combination of an ink that is prone to bleeding and a printing object (e.g., paper or film) is selected, the kernel size may be increased and the gradient of the coefficients may be made gentle. Conversely, when a mode corresponding to a combination of an ink that is unlikely to bleed and a printing object is selected, the kernel size of the Gaussian filter may be decreased and the gradient of the coefficients may be made large.

[0090] The processing device 210 performs gain adjustment on the image data (c). The gain adjustment is a process for approximating the color of the image indicated by the original print data, and may be performed for each of the colors C, M, Y, and K based on a gain adjustment table previously recorded in a storage medium such as a memory. Since the optimal gain value differs depending on the model of the printing machine and the printing mode, a gain adjustment table may be created for each model of the printing machine and for each mode. The processing device 210 may be configured to determine the gain adjustment table to be used based on identification information indicating the model or mode of the printing machine.

[0091] The processing device 210 further performs color conversion from CMYK to RGB based on a color conversion table previously recorded in a storage medium such as a memory, and generates a printer filter image (d).

[0092] FIG. 12B shows an example of a color conversion table. This color conversion table specifies the correspondence between a combination of four CMYK values ​​and a combination of three RGB values. Each numerical value in the color conversion table is set to an appropriate value according to the characteristics of the ink, paper, camera, etc. For example, a plurality of color conversion tables may be created in advance for each model or mode of the printing machine. The processing device 210 may be configured to determine the color conversion table to be used based on identification information indicating the model or mode of the printing machine.

[0093] The printer filter image in the example of Fig. 11 is a 300 dpi image in which the pixel values ​​of each color of RGB are expressed in 8 bits (total of 24 bits). The processing device 210 checks the print quality by comparing this printer filter image with a camera image or a camera filter image converted from a camera image. Note that in this specification, the expression "comparison with a camera image" may refer not only to comparison with the camera image itself, but also to comparison with a camera filter image converted from a camera image.

[0094] The resolution of each image and the number of bits of each pixel in the example of Figure 11, as well as the values ​​in each filter and each table, are merely examples, and these values ​​are set to appropriate values ​​depending on the system (e.g., the model or mode of the printing machine).

[0095] 11, the printer filter image is generated from the head data, but the printer filter image may be generated based on original printing data such as PDF. In that case, the processing device 210 may convert the original printing data into bitmap image data expressed in a predetermined color space such as RGB, and then perform spatial filtering (and color conversion as necessary) using a spatial filter such as a Gaussian filter or an averaging filter to generate the printer filter image.

[0096] Next, examples of spatial filters used in this embodiment will be described in more detail.

[0097] 13 is a diagram showing an example of a spatial filter applied to print data and a schematic diagram showing a method of adjusting the parameters of the spatial filter. In this example, the spatial filter is a Gaussian filter based on the following two-dimensional Gaussian distribution function.

number

[0098] The kernel size of the Gaussian filter illustrated in FIG. 13 is 5×5. The kernel size may be other sizes (e.g., 3×3, 7×7, etc.). Parameters such as the kernel size and standard deviation σ are set to appropriate values ​​depending on the model of the printing press used in the inspection, the mode of the printing press, and the characteristics of the camera, etc. In this example, a Gaussian filter is used, but even when another spatial filter is used, the filter parameters (values ​​of each element) can be adjusted depending on the characteristics of the printing press, camera, etc.

[0099] Here, the pixel values ​​of coordinates (i,j) in the print data, filtered image, and camera image are denoted as A[i,j], B[i,j], and C[i,j], respectively. The pixel value B[i,j] of the filtered image is approximated by the following formula using the above two-dimensional Gaussian distribution function.

number

[0100] The deviation d between the camera image and the filtered image is expressed by the following formula:

number

[0101] Each parameter of the spatial filter is determined in advance to an appropriate value so as to minimize this deviation d. Each parameter of the spatial filter may be determined using machine learning. For example, each parameter of the spatial filter may be determined by performing supervised learning using a large number of learning data sets corresponding to pairs of print data A[i,j] and camera images C[i,j] and a predetermined machine learning algorithm. As a result of this learning, the spatial filter actually used in the inspection may be a filter different from the Gaussian filter.

[0102] Next, the color conversion process in this embodiment and an example of a method for adjusting the color conversion table will be described in more detail.

[0103] FIG. 14 is a diagram showing an example of a color conversion table and an example of a method for adjusting the parameters. In this example, the processing device 210 converts the CMYK print data into an RGB filter image based on the color conversion table recorded in a storage medium such as a memory. This color conversion table is data that specifies the relationship between a combination of four CMYK color values ​​and a combination of three RGB color values. Instead of the color conversion table, a function or model that realizes a similar conversion may be used. Each parameter in the color conversion table is determined so as to minimize the deviation between the camera image and the filter image. The processing device 210 may adjust the parameters of the color conversion table by performing supervised learning using a large number of learning data sets corresponding to pairs of the print data A[i,j] and the camera image C[i,j] and a predetermined machine learning algorithm.

[0104] In this embodiment, the spatial filtering process and the color conversion process are performed separately, but a conversion process including these processes may be performed. Such a conversion process may be a conversion using a trained model trained using a machine learning algorithm such as a neural network. The processing device 210 may generate a trained model for generating a pseudo camera image from print data using an algorithm such as a GAN.

[0105] Next, an example of a process for matching a printer filter image converted from print data with a camera image will be described.

[0106] FIG. 15 is a diagram showing an example of a process for matching a printer filter image with a camera image. In this example, the processing device 210 divides the printer filter image and the camera image into a plurality of regions and matches the two for each region. In the example of FIG. 15, each image is divided into 12 regions. An overlapping region is provided between the regions. The processing device 210 may perform matching multiple times while moving a region to be cut out from the printer filter image by one pixel in each direction, for example, vertically and horizontally, to determine a cut-out region that has the highest degree of agreement with the camera image, and compare that region with a corresponding region in the camera image. An offset may be provided in advance to the coordinates in order to compensate for the effect of predictable deformation, such as deformation of the camera image caused by aberration of the lens in the camera. The processing device 210 may calculate the difference between the pixel value of the printer filter image and the corresponding pixel value of the camera image for each pixel, and detect printing defects based on the difference in pixel value. The processing device 210 calculates an index value indicating the image difference such as SSD (Sum of Squared Difference) or SAD (Sum of Absolute Difference) for each of the above regions, and if the value exceeds a threshold, it can detect that there is a defect in the printing of that region. It is also possible to determine the quality of the printing in a similar manner when comparing a camera filter image, which has been subjected to spatial filtering or color conversion processing on a camera image, with a printer filter image.

[0107] As described above, the inspection system in this embodiment is used in combination with a printer 100 that includes a print controller 110 that converts inputted original print data into head data, and a print head 120 that prints based on the head data. The inspection system includes a camera 220 that captures a printed matter printed by the printer 100 and generates a camera image, and a processing device 210. The processing device 210 acquires identification information that identifies at least one of the model of the printer and the mode of the printer, and executes either (a) a first process in which a first filter image generated by performing a first spatial filtering process using a first filter on the original print data is compared with a camera image generated by a camera that captures the printed matter printed by the printer to determine whether the printed matter is good or bad, or (b) a second process in which a second filter image generated by performing a second spatial filtering process using a second filter on the head data is compared with the camera image to determine whether the printed matter is good or bad. The processing device 210 determines the parameters of the first filter and the parameters of the second filter based on the identification information.

[0108] This configuration makes it possible to compensate for the effects of ink bleeding and paper deformation during printing, which depend on the model and mode of the printer, or the aberration of the camera lens, etc. Therefore, even in an environment where multiple printers of different models are mixed, or when using a printer with multiple printing modes according to the type of paper or film, the accuracy of image inspection of printed matter can be improved regardless of the model or mode.

[0109] In this embodiment, spatial filtering and color conversion are performed on the original print data or head data, but the color conversion may be omitted depending on the printed matter. For example, when monochrome printing is inspected, the color conversion may be omitted. This also applies to the color conversion process for the camera image. In addition, the printing device 100 in this embodiment is an inkjet printer, but the technology of this embodiment may be applied to an electrophotographic printer such as a laser printer, or a printing machine that performs plate printing.

[0110] Furthermore, the processing device 210 may determine the parameters of the first filter used in the first spatial filtering process applied to the original print data and the parameters of the second filter used in the second spatial filtering process applied to the head data based on the printer identification information, compare the first filter image generated by performing the first spatial filtering process on the original print data with the second filter image generated by performing the second spatial filtering process on the head data, and output the comparison result. By performing such comparison, defects in the print head of the printer can be detected without using a camera.

[0111] (Embodiment 2) Next, an example of a method for generating a trained model by machine learning to be used for performing conversion processes such as the spatial filtering and color conversion described above will be described.

[0112] FIG. 16 is a flowchart showing a flow of a method for generating a trained model in this embodiment. This method includes a step of generating a training dataset (step S200) and a step of generating a trained model based on the training dataset (step S210). Step S200 includes steps S201 to S205. Step S210 includes steps S211 to S213. Steps S200 and S210 may be executed by the same device or different devices. In the following description, as an example, the computer 300 shown in FIG. 3 executes step S200, and the processing device 210 executes step S210. Note that the processes of steps S200 and S210 may be executed by other devices, not limited to the computer 300 and the processing device 210.

[0113] In step S201, the computer 300 acquires learning print data from a storage device. The learning print data may be, for example, data showing an image similar to a printed matter to be actually inspected, or data showing an image of a test chart including a pattern of multiple colors created specifically for learning. The learning print data is created in advance and recorded in a storage device in the computer 300 or an external storage device. The learning print data corresponds to the original print data shown in FIG. 3. The learning print data may be data in the same format as the head data.

[0114] In step S202, the computer 300 instructs the printing press 100 to execute printing based on the learning print data.

[0115] In step S203, computer 300 instructs camera 220 to capture an image of a printed matter printed based on the learning print data. In response to this, camera 220 generates image data of the printed matter (hereinafter referred to as a "learning camera image").

[0116] In step S204, the computer 300 records the learning camera image and the learning print data in association with each other in the storage device.

[0117] In step S205, computer 300 determines whether an instruction to end the generation of learning data has been issued. The instruction to end may be input to computer 300 based on, for example, a user's operation. Alternatively, the instruction to end may be issued when a preset number of printing and photographing operations have been completed. Until the instruction to end is issued, computer 300 repeats the operations of steps S201 to S205 for different learning print data.

[0118] Through the above operations, a learning data set including one or more pairs of learning print data and learning camera images is generated and recorded in a storage device. This learning data set is used to train a machine learning model for converting print data into a pseudo camera image (hereinafter, sometimes referred to as a "verification print image"). In order to enhance the effect of learning, it is preferable to prepare as many pairs of learning print data and learning camera images as possible. A pair of print data used in an actual inspection and its corresponding camera image may be included in the learning data set.

[0119] Next, step S210 of generating a trained model using the training data set will be described in detail.

[0120] In step S211, the processing device 210 acquires a learning data set from the storage device. If the learning data set includes a plurality of pairs of learning print data and learning camera images, data for all pairs is acquired.

[0121] In step S212, the processing device 210 uses a predetermined machine learning algorithm to perform machine learning based on the learning data set, thereby generating a model (trained model) for converting the print data into a matching print image. As the machine learning algorithm, for example, various algorithms used for converting an input image into another image using deep learning can be used. For example, an algorithm using a convolutional neural network (CNN), such as GAN or NST (Neural Style Transfer), can be used. The generated trained model can be, for example, a model that executes the spatial filtering process and the color conversion process described in the first embodiment. The generation of the trained model includes adjusting multiple parameters in the model so as to reduce the deviation between the learning print data and the corresponding learning camera image.

[0122] In step S213, the processing device 210 records the generated trained model in a storage device (for example, the ROM 216).

[0123] The above operations can generate a trained model for converting print data into a print image for comparison. As described above, the optimal spatial filtering process and color conversion process differ depending on the model or mode of the printing machine. For this reason, a trained model can be generated for each model or mode of the printing machine. When performing an inspection based on the generated trained model, the processing device 210 executes an image conversion program that implements the trained model to convert the print data to be inspected into a print image for comparison. The image conversion program can be configured to apply different trained models depending on the model or mode of the printing machine. The processing device 210 compares and collates the print image for comparison with a camera image or an image that has been subjected to processing such as rotation correction and color correction on the camera image (collectively referred to as a "camera image for comparison") to determine whether the printed matter is good or bad.

[0124] Next, an example of a test chart used as learning print data for model generation will be described. The test chart may include a pattern in which multiple areas of different colors are arranged one-dimensionally or two-dimensionally. In this specification, "color" refers to a combination of hue, brightness, and saturation.

[0125] 17A to 17C show examples of test chart images. FIG. 17A shows an example of a test chart in which a plurality of color blocks of different colors are arranged two-dimensionally. This test chart includes a large number of square color block areas arranged in a direction corresponding to the transport direction of the printed matter (vertical direction in the figure) and a direction corresponding to a direction perpendicular to the transport direction (horizontal direction in the figure). Each color block is small, for example, smaller than 10 mm×10 mm. The number of color blocks is, for example, 1000 or more. The colors of these color blocks can be selected so that most of the colors that can be printed by the printing machine 100 are covered, for example. It is not necessary for all of the colors of the color blocks to be different, and blocks of the same color may be included.

[0126] FIG. 17B shows an example of a test chart in which a plurality of color bars of different colors are arranged one-dimensionally. This test chart includes a plurality of color bars of different colors extending in a direction (horizontal direction in the figure) perpendicular to the transport direction of the printed matter. The plurality of color bars are arranged along a direction (vertical direction in the figure) corresponding to the transport direction. The width (dimension in the vertical direction) of each color bar is small, for example, less than 10 mm. The number of color bars is, for example, 30 or more. The colors of these color bars can be selected so that most of the colors that can be printed by the printing machine 100 are covered, for example. It is not necessary for all the colors of the color bars to be different, and color bars of the same color may be included.

[0127] When the printing machine 100 is an inkjet printer, the print head 120 may include multiple heads for each color, for example, CMYK. The multiple heads for each color may be arranged along a direction perpendicular to the transport direction. Since the ink ejection condition may differ depending on the head, the ink density and spread may differ depending on the position of the head, even for the same color. Therefore, in the example of FIG. 17B, a test chart including multiple color bars extending along a direction corresponding to the head arrangement direction is used. By using such a test chart, it is possible to effectively learn how each color changes depending on the position in the head arrangement direction.

[0128] The test chart illustrated in FIG. 17A and FIG. 17B includes a plurality of two-dimensional codes 70 including information indicating the type of the test chart. The two-dimensional code 70 is a code in which information is expressed as two-dimensional shading information according to a predetermined rule, such as a QR (Quick Response) code. The two-dimensional code 70 can be used to identify the type of the test chart and the position of each color area in a device that learns a model. In the example of FIG. 17A and FIG. 17B, a plurality of two-dimensional codes 70 are arranged at predetermined positions around a color block or a color bar. By arranging the two-dimensional codes 70 in this manner, positioning during matching can be made easy. At least a part of the two-dimensional code 70 can be arranged along a direction (horizontal direction) corresponding to a direction perpendicular to the conveying direction of the printed matter. Such a two-dimensional code 70 functions as a marker during matching, making it easy to identify the area of ​​each color. The two-dimensional code 70 can include information for identifying the position of each color area included in the color chart. For example, the two-dimensional code 70 can include information indicating the correspondence between position coordinates in a coordinate system set in the color chart and the color at the position coordinates. 17A and 17B, when a color chart includes multiple two-dimensional codes 70, each two-dimensional code 70 may include, in addition to its own position coordinate information, information on the position coordinates of multiple color areas associated with that two-dimensional code 70. By referring to such information, the processing device 210 can specify the position of each color area using the two-dimensional code 70 as a landmark. This makes positioning easier and improves the accuracy of learning.

[0129] Instead of the two-dimensional code, a one-dimensional code (barcode) may be provided on the color chart. The same function can be realized even when a barcode is used. Also, instead of the two-dimensional code and one-dimensional code, for example, a distinctive mark, character, or symbol may be used to realize the same function.

[0130] 17C is a diagram showing yet another example of a test chart. This test chart includes a plurality of color bars of different colors. The brightness of each color bar changes continuously along a direction (horizontal direction) corresponding to a direction perpendicular to the transport direction. By using such a test chart, it is possible to efficiently learn a plurality of colors of different brightness.

[0131] The test charts exemplified in Figures 17A to 17C are not limited to one type, and multiple types of test charts may be used. In this case, for example, the operations of steps S201 to S205 shown in Figure 16 are repeated for each test chart. A model capable of image conversion with higher accuracy may be generated by combining learning using a test chart and learning using test data similar to a normal inspection target.

[0132] As described above, the present disclosure includes the systems, devices, methods, and programs described in the following items.

[0133] [Item 1] An inspection system used in combination with a printing machine including a print controller that converts input print source data into head data, and a print head that prints based on the head data, a camera for capturing an image of a printed matter printed by the printing machine and generating a camera image; A processing device; Equipped with The processing device includes: acquiring identification information that identifies at least one of the model of the printing press and the mode of the printing press; (a) a first process for judging the quality of the printed matter by comparing a first filtered image generated by performing a first spatial filtering process on the original printing data using a first filter with a camera image generated by a camera that photographs the printed matter printed by the printing machine, and (b) a second process for judging the quality of the printed matter by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image, determining a parameter of the first filter and a parameter of the second filter based on the identification information; Inspection system.

[0134] [Item 2] 2. The inspection system of claim 1, wherein the processing device selects whether to perform the first process or the second process based on the identification information.

[0135] [Item 3] The processing device is capable of (c) executing a third process of determining the normality of the print controller by comparing a first filter image generated by performing a first spatial filtering process on the original print data using a first filter with a second filter image generated by performing a second spatial filtering process on the head data using a second filter; selecting which of the first process, the second process, and the third process is to be executed based on the identification information; Item 1. The inspection system according to item 1.

[0136] [Item 4] 2. The inspection system of claim 1, wherein the parameters include at least one of a filter size and a coefficient.

[0137] [Item 5] 2. The inspection system of claim 1, wherein the identification information includes model information that identifies a model of the printing press and mode information that identifies a mode of the printing press.

[0138] [Item 6] The processing device includes: reading the mode information, which has a data format that differs for each model of the printing press, based on the model information; Item 5. The inspection system according to item 5.

[0139] [Item 7] The processing device includes: Selecting either the first mode or the second mode based on the model information; determining parameters of the first filter and parameters of the second filter based on the mode information; 7. The inspection system according to item 5 or 6.

[0140] [Item 8] 7. The inspection system of claim 5 or 6, wherein the mode information of the printing press includes information regarding at least one of the type of object to be printed on, the thickness of the ink ejected from the print head, the printing speed, color settings, and print image quality.

[0141] [Item 9] 7. The inspection system according to any one of items 1 to 6, wherein the processing device learns parameters of the first filter and the second filter that are suitable for each model and each mode of the printing press using machine learning.

[0142] [Item 10] 7. The inspection system according to any one of items 1 to 6, wherein the processing device matches the first filtered image or the second filtered image with the camera image by comparing the first filtered image or the second filtered image with an image generated by performing spatial filtering processing on the camera image.

[0143] [Item 11] 11. The inspection system of claim 10, wherein the processing device determines filter parameters to be used in the spatial filtering process performed on the camera image based on the identification information.

[0144] [Item 12] The processing device includes: In the first mode, the first spatial filtering process and the first color conversion process are performed on the original print data to generate the first filtered image; In the second mode, the second spatial filtering process and the second color conversion process are performed on the head data to generate the second filtered image; determining parameters of the first color conversion process and the second color conversion process based on the identification information; 7. An inspection system according to any one of items 1 to 6.

[0145] [Item 13] The processing device includes: comparing the first filtered image or the second filtered image with an image generated by performing spatial filtering processing and color conversion processing on the camera image, thereby matching the first filtered image or the second filtered image with the camera image; 7. An inspection system according to any one of items 1 to 6, further comprising: determining a filter to be used in the spatial filtering process performed on the camera image and parameters of the color conversion process performed on the camera image based on the identification information.

[0146] [Item 14] A printing machine including a print controller that converts input print source data into head data, and a print head that performs printing based on the head data; a camera for capturing an image of a printed matter printed by the printing machine and generating a camera image; A processing device; A processing device for use in an inspection system comprising: acquiring identification information that identifies at least one of the model of the printing press and the mode of the printing press; Based on the identification information, the method executes either (a) a first process for judging the quality of the printed matter by comparing a first filtered image generated by performing a first spatial filtering process on the original print data using a first filter with the camera image, or (b) a second process for judging the quality of the printed matter by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image, determining a parameter of the first filter and a parameter of the second filter based on the identification information; Processing unit.

[0147] [Item 15] A processing device used in combination with a printing machine including a print controller that converts input print source data into head data, and a print head that prints based on the head data, acquiring identification information that identifies at least one of the model of the printing press and the mode of the printing press; determining a parameter of a first filter used in a first spatial filtering process applied to the original print data and a parameter of a second filter used in a second spatial filtering process applied to the head data based on the identification information; comparing a first filtered image generated by performing the first spatial filtering process on the original print data with a second filtered image generated by performing the second spatial filtering process on the head data, and outputting a comparison result; Processing unit.

[0148] [Item 16] A printing machine including a print controller that converts input print source data into head data, and a print head that performs printing based on the head data; a camera for capturing an image of a printed matter printed by the printing machine and generating a camera image; A processing device; An inspection method performed by the processing device in an inspection system comprising: obtaining identification information that identifies at least one of a model of the printing press and a mode of the printing press; Based on the identification information, executing either (a) a first process for judging the quality of the printed matter by comparing a first filtered image generated by performing a first spatial filtering process on the original print data using a first filter with the camera image, or (b) a second process for judging the quality of the printed matter by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image; determining parameters of the first filter and parameters of the second filter based on the identification information; The inspection method includes:

[0149] [Item 17] A printing machine including a print controller that converts input print source data into head data, and a print head that performs printing based on the head data; a camera for capturing an image of a printed matter printed by the printing machine and generating a camera image; A processing device; A program for use in an inspection system comprising: obtaining identification information that identifies at least one of a model of the printing press and a mode of the printing press; Selecting one mode from a plurality of modes based on the identification information, including: (a) a first mode in which the quality of the printed matter is judged by comparing a first filtered image generated by performing a first spatial filtering process on the original print data using a first filter with the camera image; and (b) a second mode in which the quality of the printed matter is judged by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image; determining parameters of the first filter and parameters of the second filter based on the identification information; A program that executes the following.

[0150] [Item 18] A method executed by a processing device used in combination with a printing machine having a print controller that converts input print source data into head data, and a print head that performs printing based on the head data, comprising: obtaining identification information that identifies at least one of a model of the printing press and a mode of the printing press; determining a parameter of a first filter used in a first spatial filtering process applied to the original print data and a parameter of a second filter used in a second spatial filtering process applied to the head data based on the identification information; comparing a first filtered image generated by performing the first spatial filtering process on the original print data with a second filtered image generated by performing the second spatial filtering process on the head data, and outputting a comparison result; The method includes:

[0151] [Item 19] A program used in a system including a printing machine having a print controller that converts input print source data into head data, a print head that prints based on the head data, and a processing device, the processing device comprising: obtaining identification information that identifies at least one of a model of the printing press and a mode of the printing press; determining a parameter of a first filter used in a first spatial filtering process applied to the original print data and a parameter of a second filter used in a second spatial filtering process applied to the head data based on the identification information; comparing a first filtered image generated by performing the first spatial filtering process on the original print data with a second filtered image generated by performing the second spatial filtering process on the head data, and outputting a comparison result; A program that executes the following. [Industrial Applicability]

[0152] The technology disclosed herein can be used to inspect whether the print result of a printed matter is correct or not. For example, the technology can be suitably used to inspect a printed matter printed by a digital printing machine that performs variable color printing. [Explanation of symbols]

[0153] 10 Paper 100 printing machines 110 Print Controller 120 Print Head 130 Conveyor 200 Inspection Equipment 210 Processing equipment 212 processors 214 RAM 216 ROM 220 Camera 300 Computers

Claims

1. An inspection system used in combination with a printing machine including a print controller that converts input print source data into head data, and a print head that prints based on the head data, a camera for capturing an image of a printed matter printed by the printing machine and generating a camera image; A processing device; Equipped with The processing device includes: acquiring identification information that identifies at least one of the model of the printing press and the mode of the printing press; (a) a first process for judging the quality of the printed matter by comparing a first filtered image generated by performing a first spatial filtering process on the original printing data using a first filter with a camera image generated by a camera that photographs a printed matter printed by the printing press, and (b) a second process for judging the quality of the printed matter by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image, determining a parameter of the first filter and a parameter of the second filter based on the identification information; Inspection system.

2. The inspection system according to claim 1 , wherein the processing device selects whether to execute the first process or the second process based on the identification information.

3. The processing device is capable of (c) executing a third process of determining the normality of the print controller by comparing a first filter image generated by performing a first spatial filtering process on the original print data using a first filter with a second filter image generated by performing a second spatial filtering process on the head data using a second filter; selecting which of the first process, the second process, and the third process is to be executed based on the identification information; The inspection system of claim 1 .

4. The inspection system of claim 1 , wherein the parameter is a value that determines at least one of a size and a coefficient of a filter.

5. The inspection system according to claim 1 , wherein the identification information includes model information that identifies a model of the printing press, and mode information that identifies a mode of the printing press.

6. The processing device includes: reading the mode information, which has a data format that differs for each model of the printing press, based on the model information; The inspection system of claim 5 .

7. The processing device includes: selecting one of the first mode and the second mode based on the model information; determining parameters of the first filter and parameters of the second filter based on the mode information; 7. The inspection system according to claim 5 or 6.

8. 7. The inspection system of claim 5, wherein the mode information of the printing press includes information regarding at least one of the type of object to be printed on, the thickness of the ink ejected from the print head, the printing speed, color settings, and print image quality.

9. The inspection system according to claim 1 , wherein the processing device learns parameters of the first filter and the second filter that are suitable for each model and each mode of the printing press using machine learning.

10. 7. The inspection system according to claim 1, wherein the processing device matches the first filtered image or the second filtered image with the camera image by comparing the first filtered image or the second filtered image with an image generated by performing spatial filtering processing on the camera image.

11. The inspection system according to claim 10 , wherein the processing device determines filter parameters to be used in the spatial filtering process performed on the camera image based on the identification information.

12. The processing device includes: In the first mode, the first spatial filtering process and the first color conversion process are performed on the original print data to generate the first filtered image; In the second mode, the head data is subjected to the second spatial filtering process and the second color conversion process to generate the second filtered image; determining parameters of the first color conversion process and the second color conversion process based on the identification information; 7. An inspection system according to claim 1.

13. The processing device includes: comparing the first filtered image or the second filtered image with an image generated by performing spatial filtering processing and color conversion processing on the camera image, thereby matching the first filtered image or the second filtered image with the camera image; determining a filter to be used in the spatial filtering process to be performed on the camera image and parameters of the color conversion process to be performed on the camera image based on the identification information; 7. An inspection system according to claim 1.

14. A printing machine including a print controller that converts input print source data into head data, and a print head that performs printing based on the head data; a camera for capturing an image of a printed matter printed by the printing machine and generating a camera image; A processing device; A processing device for use in an inspection system comprising: acquiring identification information that identifies at least one of the model of the printing press and the mode of the printing press; Based on the identification information, the method executes either (a) a first process for judging the quality of the print by comparing a first filtered image generated by performing a first spatial filtering process on the original print data using a first filter with the camera image, or (b) a second process for judging the quality of the print by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image, determining a parameter of the first filter and a parameter of the second filter based on the identification information; Processing unit.

15. A processing device used in combination with a printing machine including a print controller that converts input print source data into head data, and a print head that performs printing based on the head data, acquiring identification information that identifies at least one of the model of the printing press and the mode of the printing press; determining a parameter of a first filter used in a first spatial filtering process applied to the original print data and a parameter of a second filter used in a second spatial filtering process applied to the head data based on the identification information; comparing a first filtered image generated by performing the first spatial filtering process on the original print data with a second filtered image generated by performing the second spatial filtering process on the head data, and outputting a comparison result; Processing unit.

16. A printing machine including a print controller that converts input print source data into head data, and a print head that performs printing based on the head data; a camera for capturing an image of a printed matter printed by the printing machine and generating a camera image; A processing device; An inspection method performed by the processing device in an inspection system comprising: obtaining identification information that identifies at least one of a model of the printing press and a mode of the printing press; Based on the identification information, executing either (a) a first process for judging the quality of the print by comparing a first filtered image generated by performing a first spatial filtering process on the original print data using a first filter with the camera image, or (b) a second process for judging the quality of the print by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image; determining parameters of the first filter and parameters of the second filter based on the identification information; The inspection method includes:

17. A printing machine including a print controller that converts input print source data into head data, and a print head that performs printing based on the head data; a camera for capturing an image of a printed matter printed by the printing machine and generating a camera image; A processing device; A program for use in an inspection system comprising: obtaining identification information that identifies at least one of a model of the printing press and a mode of the printing press; Selecting one mode from a plurality of modes based on the identification information, including: (a) a first mode in which the quality of the print is judged by comparing a first filtered image generated by performing a first spatial filtering process on the original print data using a first filter with the camera image; and (b) a second mode in which the quality of the print is judged by comparing a second filtered image generated by performing a second spatial filtering process on the head data using a second filter with the camera image; determining parameters of the first filter and parameters of the second filter based on the identification information; A program that executes the following.

18. A method executed by a processing device used in combination with a printing machine having a print controller that converts input print source data into head data, and a print head that performs printing based on the head data, comprising: obtaining identification information that identifies at least one of a model of the printing press and a mode of the printing press; determining parameters of a first filter used in a first spatial filtering process applied to the original print data and parameters of a second filter used in a second spatial filtering process applied to the head data based on the identification information; comparing a first filtered image generated by performing the first spatial filtering process on the original print data with a second filtered image generated by performing the second spatial filtering process on the head data, and outputting a comparison result; The method includes:

19. A program used in a system including a printing machine having a print controller that converts input print source data into head data, a print head that prints based on the head data, and a processing device, the processing device comprising: obtaining identification information that identifies at least one of a model of the printing press and a mode of the printing press; determining parameters of a first filter used in a first spatial filtering process applied to the original print data and parameters of a second filter used in a second spatial filtering process applied to the head data based on the identification information; comparing a first filtered image generated by performing the first spatial filtering process on the original print data with a second filtered image generated by performing the second spatial filtering process on the head data, and outputting a comparison result; A program that executes the following.

Images