Printed matter defect inspection device, defect inspection method, program, and printing system

Abstract

Provided are a printed matter defect inspection device, a defect inspection method, a program, and a printing system for automatically and accurately inspecting all printed matter. The present invention provides a printed matter defect inspection device with which, using a scan image comparison scheme for comparing a captured image in which an item of printed matter being inspected is captured and a reference image in which an item of printed matter serving as a correct answer is captured to inspect any defect in printed matter being inspected, each item of printed matter among a plurality of items of printed matter being continuously printed is inspected whenever necessary, wherein: a defect in the printed matter is inspected using a data comparison scheme for comparing the captured image and reference data generated on the basis of original printing data for the printed matter to inspect any defect in the printed matter being inspected; the quality of the printed matter is assessed from the result of the inspection performed using the data comparison scheme; and the captured image of printed matter assessed to be of satisfactory quality is set as a reference image.

Description

Printed matter defect inspection device, defect inspection method and program, and printing system

[0001] The present invention relates to a defect inspection device, a defect inspection method and program, and a printing system for printed matter, and in particular to a technology for inspecting defects in printed matter by comparing a captured image of the printed matter to be inspected with a reference image of a correct printed matter.

[0002] Defect inspection devices that inspect defects in an object by comparing image data captured using a scanner with reference data are widely used. One application of this inspection method is a print defect inspection device that inspects prints printed by a printing press for print defects such as streaks and missing ink. Conventional print defect inspections widely use a scanned image comparison method, in which reference data, which is image data printed under the same conditions and serves as a reference, is acquired in advance and compared with image data captured during printing. However, the scanned image comparison method has a problem in that it cannot perform comparison inspections on prints in which the image changes each time, such as variable printing, or on the first sheet after changing printing conditions.

[0003] On the other hand, as a solution to the problem of not being able to inspect the first sheet, data comparison inspections are widely practiced, in which digital data input to a printing press is compared with image data. However, data comparison inspections involve differences, such as differences in data format between a four-channel CMYK (cyan, magenta, yellow, and black) color space and a three-channel RGB (red, green, and blue) color space, and therefore require preprocessing to match their characteristics. Regarding the differences between CMYK and RGB, conventional techniques use a table for matching color profiles between print data and image data to match color characteristics. However, color profiles vary depending on printing conditions, and there are a wide variety of conditions, such as differences between printing presses and paper types depending on the country, making it difficult to detect defects with high accuracy.

[0004] In contrast, Patent Document 1 describes an inspection device that inspects the quality of printed matter printed by a printing device using a reference image and a scanned image of the printed matter, and that is equipped with a selection means for selecting whether the pre-printed image or the scanned image used to print the printed matter will be used as the reference image when inspecting the quality of the printed matter.

[0005] JP 2023-39712 A

[0006] In the inspection device described in Patent Document 1, if a difference is detected as a result of comparing the pre-press image and the scanned image, a reference image selection screen including the pre-press image and the scanned image is displayed, and a user input as to whether the detected difference is a defect or not is accepted, and a reference image is selected based on the accepted user input. In this way, the inspection device described in Patent Document 1 makes a judgment based on the user input in order to unnecessarily detect an abnormality, which has the problem of requiring the user to read the detection results and enter a judgment.

[0007] The present invention has been made in view of the above circumstances, and aims to provide a defect inspection device, defect inspection method and program, and printing system for printed matter that can inspect all printed matter automatically and with high precision.

[0008] In order to achieve the above object, a printed matter defect inspection device according to a first aspect of the present disclosure is a printed matter defect inspection device that inspects each of a plurality of printed matters that are printed in succession at any time using a scan image comparison method that compares an image of the printed matter to be inspected with a reference image of a correct printed matter to inspect for defects in the printed matter to be inspected, and is equipped with one or more processors and one or more memories that store programs to be executed by the one or more processors, and the one or more processors execute instructions of the program to inspect for defects in the printed matter using a data comparison method that compares an image of the printed matter to be inspected with reference data generated based on the original printing data of the printed matter to inspect for defects in the printed matter to be inspected, and determines whether the printed matter is good or bad based on the results of the inspection using the data comparison method, and sets the image of a printed matter that is judged to be good as the reference image.

[0009] According to the printed matter defect inspection device of the first aspect, all printed matters can be inspected automatically and with high accuracy.

[0010] A printed matter defect inspection device according to a second aspect of the present disclosure is preferably the printed matter defect inspection device according to the first aspect, wherein one or more processors inspect each of a plurality of printed matters printed in succession using a data comparison method until a reference image is set, and then inspect each of the plurality of printed matters printed in succession using a scan image comparison method after the reference image is set.

[0011] In the printed matter defect inspection device according to the third aspect of the present disclosure, in the printed matter defect inspection device according to the second aspect, it is preferable that one or more processors perform inspection using a scanned image comparison method from the printed matter to be inspected next to the printed matter of the captured image set as the reference image.

[0012] In the printed matter defect inspection device according to the fourth aspect of the present disclosure, in the printed matter defect inspection device according to any of the first to third aspects, it is preferable that one or more processors set a reference image for each piece of original printing data.

[0013] In the printed matter defect inspection device according to the fifth aspect of the present disclosure, in the printed matter defect inspection device according to any of the first to fourth aspects, it is preferable that one or more processors perform inspection using a data comparison method using a learning model.

[0014] In the printed matter defect inspection device according to the sixth aspect of the present disclosure, in the printed matter defect inspection device according to the fifth aspect, it is preferable that the learning model is trained using reference data generated based on the original printing data of the printed matter, captured images of the printed matter, and the results of inspection of the printed matter as learning data.

[0015] A printed matter defect inspection device according to a seventh aspect of the present disclosure is the printed matter defect inspection device according to the sixth aspect, wherein the inspection results preferably include inspection results using a scan image comparison method.

[0016] In the printed matter defect inspection device according to the eighth aspect of the present disclosure, in the printed matter defect inspection device according to the sixth or seventh aspect, it is preferable that the inspection results include at least one of the presence or absence of defects, the number of defects, the position of the defects, and the size of the defects.

[0017] In order to achieve the above object, a printing system according to a ninth aspect of the present disclosure is a printing system comprising a printing device that prints a printed matter based on original printing data, an imaging device that captures an image of the printed matter by imaging it, and a defect inspection device for printed matter according to any of the first to eighth aspects.

[0018] In order to achieve the above object, a printed matter defect inspection method according to a tenth aspect of the present disclosure is a printed matter defect inspection method that inspects each of a plurality of printed matters that are printed in succession at any time using a scan image comparison method that compares an image of the printed matter being inspected with a reference image of a correct printed matter to inspect for defects in the printed matter being inspected, in which one or more processors inspect the printed matter for defects using a data comparison method that compares an image of the printed matter being inspected with reference data generated based on the original printing data of the printed matter to inspect for defects in the printed matter being inspected, and determines whether the printed matter is good or bad based on the results of the inspection using the data comparison method, and sets the image of a printed matter that is judged to be good as a reference image.

[0019] In order to achieve the above object, a program according to an eleventh aspect of the present disclosure is a program that causes a computer to execute the method for inspecting defects in printed matter according to aspect 10. A non-transitory, computer-readable storage medium on which the program according to the eleventh aspect is stored is also included in the present disclosure.

[0020] According to the present invention, all printed materials can be inspected automatically and with high accuracy.

[0021] Fig. 1 is a diagram showing the overall configuration of an inkjet printing system. Fig. 2 is a block diagram showing the internal configuration of the inkjet printing system. Fig. 3 is a diagram showing the configuration of a defect inspection device. Fig. 4 is a block diagram showing the functional configuration of the defect inspection device. Fig. 5 is a flowchart showing each step of a defect inspection method using the defect inspection device.

[0022] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0023] 1 is a diagram showing the overall configuration of an inkjet printing system 100. The inkjet printing system 100 is a printing machine that prints color images by ejecting ink of four colors, cyan (C), magenta (M), yellow (Y), and black (K), onto sheets of paper P, which are recording media.

[0024] General-purpose printing paper is used for the paper P. General-purpose printing paper is not so-called inkjet paper, but paper made primarily of cellulose, such as coated paper used for general offset printing. Furthermore, water-based ink is used for the ink. Water-based ink is ink in which coloring materials such as dyes and pigments are dissolved or dispersed in water and a water-soluble solvent.

[0025] As shown in FIG. 1, the inkjet printing system 100 includes a transport unit 110 , a printing unit 120 , an imaging unit 130 , a drying unit 140 , a sorting unit 150 , and a paper discharge unit 160 .

[0026] [Conveying Section] The conveying section 110 conveys the paper P fed from a paper feeding section (not shown) in a conveying direction. The conveying section 110 includes an upstream pulley 112, a downstream pulley 114, and a conveying belt 116.

[0027] The upstream pulley 112 has a rotation shaft (not shown) that extends horizontally and is rotatably supported. The downstream pulley 114 has a rotation shaft (not shown) that is parallel to the rotation shaft of the upstream pulley 112 and is rotatably supported.

[0028] The conveyor belt 116 is an endless belt made of stainless steel and is stretched between an upstream pulley 112 and a downstream pulley 114. By using the stainless steel conveyor belt 116, the flatness of the paper P can be maintained in a good condition.

[0029] The downstream pulley 114 has a motor (not shown) as a driving means. When the motor is driven, the downstream pulley 114 rotates counterclockwise in Fig. 1. The upstream pulley 112 rotates counterclockwise in Fig. 1 following the rotation of the downstream pulley 114. The conveyor belt 116 travels between the upstream pulley 112 and the downstream pulley 114 along a travel path due to the rotation of the upstream pulley 112 and the downstream pulley 114.

[0030] Paper P supplied from a paper feed unit (not shown) is placed on the conveying surface of the conveyor belt 116. The conveying unit 110 conveys the paper P placed on the conveyor belt 116 along a conveying path from the upstream pulley 112 to the downstream pulley 114, and delivers it to the paper discharge unit 160. At positions on this conveying path facing the printing unit 120, the imaging unit 130, the drying unit 140, and the sorting unit 150, the paper P is conveyed with its printed surface held horizontal.

[0031] The conveying belt 116 may be provided with a plurality of suction holes (not shown), and the paper P placed on the conveying surface of the conveying belt 116 may be adsorbed and held on the conveying surface by sucking the suction holes of the conveying belt 116 with a pump (not shown).

[0032] [Printing Unit] The printing unit 120 is an example of a "printing device" in the present disclosure, and forms (prints) an image on paper P based on original print data. The printing unit 120 is equipped with inkjet heads 122C, 122M, 122Y, and 122K. The inkjet head 122C ejects cyan ink droplets using an inkjet system. Similarly, the inkjet heads 122M, 122Y, and 122K eject magenta, yellow, and black ink droplets using an inkjet system, respectively.

[0033] Inkjet heads 122C, 122M, 122Y, and 122K are arranged at regular intervals along the transport path of paper P, which is carried by transport belt 116. Inkjet heads 122C, 122M, 122Y, and 122K are each a line head, and are formed with a length corresponding to the paper width. Inkjet heads 122C, 122M, 122Y, and 122K are arranged so that the nozzle surfaces, on which nozzles (not shown) are arranged, face the transport belt 116.

[0034] The inkjet heads 122C, 122M, 122Y, and 122K form an image on the printing surface of the paper P using a predetermined screen type by ejecting ink droplets from nozzles formed on the nozzle surface toward the paper P being transported by the transport belt 116.

[0035] In this way, the printing unit 120 forms an image by a so-called single pass method in one scan on the paper P transported by the transport belt 116. As a result, a color image is formed on the printing surface of the paper P, and the paper P becomes a "printed matter."

[0036] The imaging unit 130 is an example of an "imaging device" in the present disclosure, and acquires an image of the printing surface of the paper P, i.e., a scanned image of the printed matter. The imaging unit 130 is disposed downstream of the printing unit 120 in the transport direction of the paper P. The imaging unit 130 includes a scanner 132.

[0037] Scanner 132 is a device that optically reads an image formed on paper P using inkjet heads 122C, 122M, 122Y, and 122K. Scanner 132 includes an imaging device that captures an image printed on paper P and converts it into an electrical signal. The imaging device may be a color CCD (charge coupled device) linear image sensor having an array of light receiving elements for each of RGB, each equipped with a color filter for each of R (red), G (green), and B (blue), or may be a color CMOS (complementary metal oxide semiconductor) linear image sensor.

[0038] In addition to the imaging device, the scanner 132 may include an illumination optical system that illuminates the object to be read, and a signal processing circuit that processes signals obtained from the imaging device to generate digital image data.

[0039] Drying Section The drying section 140 dries the ink on the paper P. The drying section 140 is disposed downstream of the imaging section 130 in the transport direction of the paper P.

[0040] The drying unit 140 includes a heater 142. For example, at least one of a halogen heater and an infrared heater is used as the heater 142. The heater 142 heats the printing surface of the paper P to dry the ink on the paper P. The drying unit 140 may include air blowing means such as a fan or a blower.

[0041] [Sorting Unit] The sorting unit 150 sorts printed matter according to a pass / fail judgment of the paper P transported by the transport belt 116. The sorting unit 150 is disposed downstream of the drying unit 140 in the transport direction of the paper P. The sorting unit 150 includes a stamper 152.

[0042] The stamper 152 performs a stamping process of applying ink to the leading edge of the paper P determined to be defective in accordance with the pass / fail judgment of the paper P being transported by the transport belt 116 .

[0043] [Paper Discharge Section] The paper discharge section 160 collects the paper P on which an image has been formed and dried. The paper discharge section 160 is located downstream of the sorting section 150 in the conveying direction of the paper P, at the end point of the conveying path of the conveying section 110. The paper discharge section 160 includes a paper discharge tray 162.

[0044] The paper discharge tray 162 stacks and collects the paper sheets P transported by the transport belt 116. The paper discharge tray 162 is provided with a front paper stopper, a rear paper stopper, and a side paper stopper (not shown), and stacks the paper sheets P in an orderly manner.

[0045] The paper ejection tray 162 is provided so as to be movable up and down by a lifting device (not shown). The drive of the lifting device is controlled in conjunction with an increase or decrease in the number of sheets P stacked on the paper ejection tray 162. As a result, the topmost sheet P among the sheets P stacked on the paper ejection tray 162 is always at a constant height.

[0046] 2 is a block diagram showing the internal configuration of the inkjet printing system 100. The inkjet printing system 100 includes a defect inspection device 10, an input unit 170, a display unit 171, a storage unit 172, an integrated control unit 174, a conveyance control unit 176, a print control unit 178, an imaging control unit 180, a drying control unit 182, a sorting control unit 184, and a paper discharge control unit 186.

[0047] The defect inspection device 10 is an apparatus for detecting streak defects that occur on printed materials printed using a single-pass printing method by using a scanner 132 mounted perpendicular to the conveyance direction to capture images of the printed material during printing, and then follows the printing from the captured images to inspect and display defects on the printed material in real time. Hereinafter, inspecting defects on a printed material may be simply referred to as "inspecting a printed material." "During printing" refers to, for example, the period from when an image is printed on paper P by the printing unit 120 until the paper P is collected by the paper discharge unit 160. "During printing" may also include a certain period of time after the paper P is collected by the paper discharge unit 160. Herein, the defect inspection device 10 inspects each of multiple printed materials continuously printed by the inkjet printing system 100 at any time. Details of the defect inspection device 10 will be described later.

[0048] The input unit 170 is, for example, an operation panel that accepts input from a user for operating the inkjet printing system 100. The display unit 171 is, for example, a display that displays a scanned image and various information. The input unit 170 and the display unit 171 are arranged in close proximity, and the user can interactively control various processes of the inkjet printing system 100 and print a desired image by operating the input unit 170 while viewing the display unit 171.

[0049] The storage unit 172 stores programs for controlling the inkjet printing system 100 and information necessary for executing the programs. The storage unit 172 is configured by a non-transitory storage medium such as a hard disk (not shown) or various semiconductor memories.

[0050] The overall control unit 174 performs various processes in accordance with the programs stored in the storage unit 172, and performs overall control of the overall operation of the inkjet printing system 100. The defect inspection apparatus 10 is also under the overall control of the overall control unit 174.

[0051] The conveyance control unit 176 controls a motor (not shown) of the conveyance unit 110 to convey the paper P in the conveyance direction by the conveyance unit 110. As a result, the paper P supplied from a paper feed unit (not shown) passes through positions facing the printing unit 120, the imaging unit 130, the drying unit 140, and the sorting unit 150, and is finally discharged to the paper discharge unit 160.

[0052] The print control unit 178 controls the ejection of ink from the inkjet heads 122C, 122M, 122Y, and 122K based on the original print data. The original print data may be stored in the storage unit 172. The print control unit 178 causes the inkjet heads 122C, 122M, 122Y, and 122K to eject cyan, magenta, yellow, and black ink droplets onto the paper P when the paper P passes a position facing each nozzle surface.

[0053] The print control unit 178 may output information about the location of the nozzle with the ejection failure to the overall control unit 174. The defect inspection device 10 may obtain information about the location of the nozzle with the ejection failure from the print control unit 178.

[0054] The print control unit 178 may also have a compensation function that corrects the original print data to compensate for printing by a nozzle with a discharge defect. One example is a compensation function that compensates for a nozzle with a discharge defect by increasing the volume of ink droplets from multiple adjacent nozzles. The print control unit 178 outputs information about the areas of the printed material that have been compensated for by the compensation function to the overall control unit 174. The defect inspection device 10 may obtain information about the areas of the printed material that have been compensated for by the compensation function from the print control unit 178.

[0055] The imaging control unit 180 causes the imaging unit 130 to capture an image of the printed matter. The imaging control unit 180 causes the scanner 132 to read the image formed on the printing surface of the paper P at the timing when the paper P passes a position facing the scanner 132.

[0056] The drying control unit 182 controls the heating by the heater 142, thereby causing the drying unit 140 to dry the paper P. The heater 142 heats the paper P when the paper P passes a position facing the heater 142.

[0057] The sorting control unit 184 controls the stamping process by the stamper 152, thereby causing the sorting unit 150 to sort the paper P. The sorting control unit 184 classifies printed matter into good products and defective products according to the inspection results output from the defect inspection device 10. If the paper P passing through a position opposite the stamper 152 is determined to be defective, the sorting control unit 184 performs the stamping process by the stamper 152.

[0058] The paper discharge control unit 186 controls the stacking of the paper P by the paper discharge tray 162. The paper P is discharged onto the paper discharge tray 162 and stacked. Defective paper P has ink adhering to the leading edge. This allows the user to identify defective paper P from among the papers P stacked on the paper discharge tray 162.

[0059] <Configuration of Defect Inspection Apparatus> The defect inspection apparatus 10 is realized by at least one computer. Fig. 3 is a diagram showing the configuration of the defect inspection apparatus 10. As shown in Fig. 3, the defect inspection apparatus 10 includes a processor 10A, a memory 10B, and a communication interface 10C.

[0060] The processor 10A executes instructions stored in the memory 10B. The hardware structure of the processor 10A is various processors as shown below. The various processors include a CPU (Central Processing Unit), which is a general-purpose processor that executes software (programs) and functions as various functional units, a GPU (Graphics Processing Unit), which is a processor specialized for image processing, a PLD (Programmable Logic Device), which is a processor whose circuit configuration can be changed after manufacture such as an FPGA (Field Programmable Gate Array), and a dedicated electrical circuit, which is a processor having a circuit configuration designed specifically for executing specific processing such as an ASIC (Application Specific Integrated Circuit).

[0061] A single processing unit may be configured with one of these various processors, or may be configured with two or more processors of the same or different types (e.g., multiple FPGAs, a combination of a CPU and an FPGA, or a combination of a CPU and a GPU). Multiple functional units may also be configured with a single processor. Examples of multiple functional units configured with a single processor include: a first configuration, as typified by a client or server computer, in which a single processor is configured with a combination of one or more CPUs and software, and this processor operates as multiple functional units; and a second configuration, as typified by a SoC (System on Chip), in which a processor is used to realize the functions of an entire system including multiple functional units on a single IC (Integrated Circuit) chip. In this way, the various functional units are configured with one or more of the above-mentioned various processors as a hardware structure.

[0062] Furthermore, the hardware structure of these various processors is, more specifically, an electric circuit made up of a combination of circuit elements such as semiconductor elements.

[0063] The memory 10B stores instructions to be executed by the processor 10A. The memory 10B includes a RAM (Random Access Memory) and a ROM (Read Only Memory), not shown. The processor 10A uses the RAM as a working area, executes software using various programs and parameters, including a defect inspection program, stored in the ROM, and also executes various processes of the defect inspection apparatus 10 by using the parameters stored in the ROM, etc.

[0064] The communication interface 10C controls communication with the general control unit 174. The defect inspection device 10 is connected to the general control unit 174 via the communication interface 10C. The defect inspection device 10 and the inkjet printing system 100 may be connected via a LAN (Local Area Network) or the like.

[0065] [Functional Configuration of Defect Inspection Apparatus] The defect inspection apparatus 10 is an apparatus that inspects printed matter to be inspected for defects and determines the quality of the printed matter to be inspected. Fig. 4 is a block diagram showing the functional configuration of the defect inspection apparatus 10. The defect inspection apparatus 10 includes a reference data acquisition unit 12, a scanned image acquisition unit 14, a data comparison inspection unit 16, a reference image acquisition unit 18, a scanned image comparison inspection unit 20, and an output unit 22.

[0066] The reference data acquisition unit 12 acquires reference data 12A generated based on original printing data of a printed matter to be printed by the inkjet printing system 100. The reference data 12A may be image data of the original printing data before RIP (Raster Image Processor) processing, or may be image data after RIP processing. The reference data 12A may be stored in the storage unit 172.

[0067] The scanned image acquisition unit 14 acquires a scanned image 14A (an example of a "captured image") obtained by capturing an image of a printed material printed in the inkjet printing system 100. The scanned image acquisition unit 14 may acquire the scanned image 14A from the scanner 132 via the imaging control unit 180. The scanned image acquisition unit 14 may acquire the scanned image 14A by performing signal processing on the scanned image acquired from the scanner 132. The scanned image 14A is, for example, bitmap data.

[0068] The data comparison inspection unit 16 performs an inspection using a data comparison method, in which a scanned image of the print to be inspected is compared with reference data generated based on the original print data of the print, and thereby inspects the print for defects. Here, the data comparison inspection unit 16 compares the reference data 12A with the scan image 14A to inspect the print of the scan image 14A. The data comparison inspection unit 16 also judges the quality of the print from the results of the data comparison inspection.

[0069] The data comparison and inspection unit 16 includes a learning model 16A. The learning model 16A is configured, for example, by a convolutional neural network (CNN). When the reference data 12A and the scanned image 14A are input, the learning model 16A outputs information about defects in the scanned image 14A. The defect information includes at least one of the presence or absence of defects, the number of defects, the positions of defects, and the sizes of defects.

[0070] The learning model 16A is trained using reference data generated based on the original print data of the printed matter, scanned images of the printed matter, and inspection results of the printed matter as training data. The inspection results of the training data include at least one of the presence or absence of defects, the number of defects, the positions of defects, and the sizes of defects. The inspection results of the training data include the results of inspection using a scanned image comparison method described below. The inspection results of the training data may also include the results of inspection using a data comparison method.

[0071] For example, the data comparison and inspection unit 16 acquires whether or not there are defects in the printed matter, and determines the printed matter as non-defective if there are no defects, and determines the printed matter as defective if there are defects.

[0072] The data comparison and inspection unit 16 may acquire the number of defects on the printed matter, and may determine that the printed matter is good if the number of defects is relatively small, and may determine that the printed matter is defective if the number of defects is relatively large.

[0073] The data comparison inspection unit 16 may acquire the location of a defect in the printed matter, and judge the printed matter to be good if the location of the defect is relatively far from the center of the printed matter, and judge the printed matter to be defective if the location of the defect is relatively close to the center of the printed matter.

[0074] The data comparison inspection unit 16 may acquire the size of the defect in the printed matter, and judge the printed matter to be good if the size of the defect is relatively small, and judge the printed matter to be defective if the size of the defect is relatively large.

[0075] The data comparison and inspection unit 16 may obtain at least two of the presence or absence of defects, the number of defects, the positions of defects, and the sizes of defects, and determine the quality of the printed matter.

[0076] The reference image acquisition unit 18 acquires a reference image 18A obtained by capturing an image of a print that is a correct answer for defect inspection. That is, the reference image 18A is a scanned image of the correct print, and is, for example, bitmap data. The reference image 18A may be stored in the storage unit 172.

[0077] The scanned image comparison inspection unit 20 inspects defects in printed matter using a scanned image comparison method, which compares a scanned image of the printed matter to be inspected with a reference image of the correct printed matter to inspect the printed matter. Here, the scanned image comparison inspection unit 20 compares the reference image 18A with the scanned image 14A to inspect the printed matter of the scanned image 14A. For example, the scanned image comparison inspection unit 20 aligns the reference image 18A with the scanned image 14A and identifies the presence or absence of defects based on the difference between the reference image 18A and the scanned image 14A. The scanned image comparison inspection unit 20 may include a learning model 16A.

[0078] The output unit 22 outputs the inspection results of the data comparison inspection unit 16 and the scan image comparison inspection unit 20. The inspection results are input to the sorting control unit 184. The inspection results may be displayed on the display unit 171 or stored in the memory unit 172.

[0079] <Defect Inspection Method> Figure 5 is a flowchart showing the steps of a defect inspection method performed by the defect inspection apparatus 10. The defect inspection method is realized by the processor 10A executing a defect inspection program stored in the memory 10B. The defect inspection program may be provided by a computer-readable non-transitory storage medium. In this case, the defect inspection apparatus 10 may read the defect inspection program from the non-transitory storage medium and store it in the memory 10B.

[0080] Here, an example will be described in which multiple printed materials that have been successively printed based on a single set of original printing data are inspected. First, the inkjet printing system 100 sequentially prints multiple printed materials based on the original printing data. The defect inspection device 10 inspects each of the multiple printed materials while they are being printed.

[0081] In step S1, the defect inspection device 10 acquires a scanned image 14A of the first printed matter. That is, the printing unit 120 of the inkjet printing system 100 forms an image on the first sheet of paper P transported by the transport unit 110, thereby generating the first printed matter. The imaging unit 130 captures an image of the first printed matter. The scanned image acquisition unit 14 of the defect inspection device 10 acquires the scanned image 14A of the first printed matter from the imaging unit 130.

[0082] In step S2, the defect inspection device 10 determines whether or not a reference image 18A corresponding to the original print data exists in the storage unit 172. The reference image 18A is not set at the start of printing and is not stored in the storage unit 172. In this case, it is determined that the reference image 18A does not exist, and the process proceeds to step S4.

[0083] In step S4, the defect inspection device 10 inspects the first printed material using a data comparison inspection method. That is, the reference data acquisition unit 12 acquires reference data 12A corresponding to the original print data from the memory unit 172. The data comparison inspection unit 16 inputs the reference data 12A and the scanned image 14A into a learning model 16A and acquires information about defects in the first printed material. Here, the data comparison inspection unit 16 acquires whether or not there are defects in the first printed material, and determines that the first printed material is good if no defects are present, and determines that the first printed material is defective if defects are present. The output unit 22 outputs the inspection results of the data comparison inspection unit 16. The overall control unit 174 of the inkjet printing system 100 displays the inspection results on the display unit 171.

[0084] In step S5, the defect inspection device 10 determines whether the first printed sheet is a non-defective product. If the first printed sheet is a non-defective product, the process proceeds to step S6. If the first printed sheet is a defective product, the process proceeds to step S7.

[0085] In step S6, the defect inspection device 10 sets a reference image 18A. Here, since the first printed matter is determined to be a non-defective product, the reference image acquisition unit 18 sets the scanned image 14A of the first printed matter as the reference image 18A. The reference image acquisition unit 18 also stores the set reference image 18A in the storage unit 172.

[0086] If the reference image 18A is set in step S6, or if the first printed sheet is found to be defective in step S5, it is determined in step S7 whether all printing has been completed. If not, the process returns to step S1. If all printing has been completed, the process of this flowchart ends.

[0087] In step S1, the defect inspection device 10 acquires a scanned image 14A of the second printed material. That is, the printing unit 120 of the inkjet printing system 100 forms an image on the second sheet of paper P transported by the transport unit 110, thereby generating a second printed material. The imaging unit 130 captures an image of the second printed material. The scanned image acquisition unit 14 of the defect inspection device 10 acquires the scanned image 14A of the second printed material from the imaging unit 130.

[0088] In step S2, the defect inspection device 10 determines whether or not a reference image 18A exists. If the first printed product is a non-defective product, in step S6, the scanned image 14A of the first printed product is set as the reference image 18A. Therefore, in this case, the process proceeds to step S3.

[0089] In step S3, the defect inspection device 10 inspects the second printed material using the scan image comparison inspection method. That is, the reference image acquisition unit 18 acquires the reference image 18A from the memory unit 172. The scan image comparison inspection unit 20 compares the reference image 18A with the scan image 14A to acquire information about defects in the second printed material. Here, the scan image comparison inspection unit 20 acquires whether or not there are defects in the second printed material, and determines that the second printed material is good if no defects are present, and determines that the second printed material is defective if defects are present. The output unit 22 outputs the inspection results of the data comparison inspection unit 16. The overall control unit 174 of the inkjet printing system 100 displays the inspection results on the display unit 171. Then, the process proceeds to step S7.

[0090] After the reference image 18A is set in this way, the defect inspection device 10 inspects the printed matter for defects by the scan image comparison method using the reference image 18A. Here, the defect inspection device 10 performs inspection by the scan image comparison method on the printed matter to be inspected next to the printed matter of the scan image set as the reference image 18A.

[0091] On the other hand, if the first printed sheet is defective, there is no reference image 18A, and in this case, the process moves from step S2 to step S4.

[0092] In step S4, the defect inspection device 10 inspects the second printed material using a data comparison inspection method. That is, the data comparison inspection unit 16 inputs the reference data 12A and the scanned image 14A into the learning model 16A and obtains information about defects in the second printed material. Here, the data comparison inspection unit 16 obtains whether or not there are defects in the second printed material, and determines that the second printed material is good if no defects are present, and determines that the second printed material is defective if defects are present.

[0093] In step S5, the defect inspection device 10 determines whether the second printed sheet is a non-defective product. If the second printed sheet is a non-defective product, the process proceeds to step S6.

[0094] In step S6, the defect inspection device 10 sets a reference image 18A. Here, since the second printed matter is determined to be a non-defective product, the reference image acquisition unit 18 sets the scanned image 14A of the second printed matter as the reference image 18A. The reference image acquisition unit 18 also stores the set reference image 18A in the storage unit 172. Thereafter, the process proceeds to step S7. The subsequent processes are similar.

[0095] In this way, the defect inspection device 10 sets the scanned image 14A of the second printed item as the reference image 18A, and then inspects the third and subsequent printed items using the scanned image comparison method. On the other hand, if the second printed item is defective, the defect inspection device 10 inspects the third printed item again using the data comparison method. In other words, the defect inspection device 10 inspects printed items using the data comparison method until the reference image is set, sets the scanned image of a good printed item as the reference image in the data comparison inspection, and then performs inspection using the scanned image comparison method using the reference image. In this way, inspection is performed automatically for all printed items.

[0096] Here, an example has been described in which a printed material is printed and inspected, and then the next printed material is printed and inspected. However, the inkjet printing system 100 only needs to inspect the printed materials printed in sequence, and the timing of printing and inspection can be arbitrary. For example, the printing unit 120 may start printing the second printed material before the defect inspection device 10 inspects the first printed material. Even in this case, inspection using the scanned image comparison method can be performed on the printed material to be inspected next to the printed material of the captured image set as the reference image 18A.

[0097] Although the example described here is one in which multiple printed materials are successively printed based on a single source data set, it is also possible to inspect multiple types of printed materials that are successively printed based on multiple source data sets. In this case, the defect inspection device 10 sets a reference image for each source data set.

[0098] In the following, an example will be described in which 100 copies of 10 sets of collated paper, each having different original printing data, are printed. In this case, there are 10 original printing data sets, and a total of 10 reference images corresponding to the respective original printing data sets are set.

[0099] To print 100 copies of 10 collated sheets, you can use stack printing, where 100 sheets are printed on the first sheet, then 100 sheets on the second sheet, ..., 100 sheets on the 100th sheet, or you can use collate printing, where the first sheet of the first copy is printed on the first sheet, the second sheet of the first copy, ..., the 100th sheet of the first copy, the first sheet of the second copy, the second sheet of the second copy, ..., the 100th sheet of the second copy, and so on, until you have 100 copies.

[0100] In the case of stack printing, the defect inspection device 10 inspects the first sheet of the first machine using the data image comparison method, and after setting a reference image, inspects the first 100 sheets of the first machine using the scan image comparison method. Similarly, the defect inspection device 10 inspects the first sheet of the second machine using the data image comparison method, and after setting a reference image, inspects the first 100 sheets of the second machine using the scan image comparison method. By repeating this process up to the 100th machine, it is possible to inspect all printed materials.

[0101] On the other hand, in the case of collated printing, the defect inspection device 10 inspects each of the first through 100th units of the first copy using data image comparison inspection. For example, if a defect is detected only in the second unit of the first copy, the defect inspection device 10 inspects all units other than the second unit using the scan image comparison method in the inspection of the second copy, and performs data image comparison inspection only on the second unit. Furthermore, if the second unit of the second copy is found to be a non-defective product, the defect inspection device 10 inspects all of the first through 100th units of the third copy using scan image comparison inspection. This makes it possible to perform similar inspections.

[0102] In this way, the defect inspection method disclosed herein first performs an inspection using a data image comparison inspection, and then automatically sets the scanned image of the printed material that showed no defects in the data image comparison inspection as the reference image without any user operation, and then performs inspection using the scanned image comparison method.

[0103] This makes it possible to perform a full inspection while compensating for the shortcomings by performing a data image comparison inspection on only the reference image, even if the inspection performance of the data image comparison inspection is lower than that of the scan image comparison method, i.e., even if the defect detection accuracy in the data image comparison inspection is lower than that of the scan image comparison method.

[0104] <Others> The recording medium is not limited to sheets of paper P, but may be continuous paper. The paper P is not limited to paper media, but may be a resin sheet, a metal sheet, or the like. Furthermore, the conveyance of the recording medium is not limited to belt conveyance, but may be a drum conveyance system in which the paper P is conveyed using multiple conveyance drums.

[0105] Furthermore, although printing by a single pass method has been exemplified here, a shuttle scan method (also called a "serial head method") in which printing is performed by moving a short recording head and scanning the head multiple times may also be used. Also, although an inkjet printing system using an inkjet method has been exemplified here, the printing method is not limited to inkjet printing, and printing methods such as offset printing, gravure printing, and letterpress printing may also be used.

[0106] The technical scope of the present invention is not limited to the scope described in the above embodiments. The configurations and the like in each embodiment can be appropriately combined with each other within the scope that does not deviate from the spirit of the present invention.

[0107] DESCRIPTION OF SYMBOLS 10... Defect inspection device 10A... Processor 10B... Memory 10C... Communication interface 12... Reference data acquisition unit 12A... Reference data 14... Scanned image acquisition unit 14A... Scanned image 16... Data comparison inspection unit 16A... Learning model 18... Reference image acquisition unit 18A... Reference image 20... Scanned image comparison inspection unit 22... Output unit 100... Inkjet printing system 110... Conveying unit 112... Upstream pulley 114... Downstream pulley 116... Conveyor belt 120... Printing unit 122C... Inkjet head 122K... Inkjet head 122M... Inkjet head 122Y... Inkjet head 130... Imaging unit 132... Scanner 140... Drying unit 142... Heater 150... Sorting unit 152... Stamper 160... Paper discharge unit 162... Paper discharge tray 170... Input unit 171: Display unit 172: Storage unit 174: General control unit 176: Conveyance control unit 178: Printing control unit 180: Imaging control unit 182: Drying control unit 184: Sorting control unit 186: Paper discharge control unit P: Paper S1 to S7: Steps of defect inspection method

Claims

1. A printed matter defect inspection apparatus for inspecting each of a plurality of continuously printed printed matters at any time by a scan image comparison method of comparing a captured image of a printed matter to be inspected with a reference image of a printed matter that is a correct answer to inspect a defect of the printed matter to be inspected, comprising: one or more processors; one or more memories storing a program to be executed by the one or more processors; wherein the one or more processors execute instructions of the program to inspect a defect of a printed matter by a data comparison method of comparing a captured image of a printed matter to be inspected with reference data generated based on print source data of the printed matter, determine whether the printed matter is good or bad from the result of the inspection by the data comparison method, and set a captured image of a printed matter determined to be good as the reference image.

2. The printed matter defect inspection apparatus according to claim 1, wherein until the reference image is set, the one or more processors perform an inspection by the data comparison method for each of the plurality of continuously printed printed matters, and perform an inspection by the scan image comparison method after the reference image is set.

3. The printed matter defect inspection apparatus according to claim 2, wherein the one or more processors perform an inspection by the scan image comparison method on a printed matter to be the next inspection target after the printed matter of the captured image set as the reference image.

4. The printed matter defect inspection apparatus according to claim 1, wherein the one or more processors set the reference image for each piece of the print source data.

5. The printed matter defect inspection apparatus according to claim 1, wherein the one or more processors perform an inspection by the data comparison method using a learning model.

6. The learning model of the printed matter defect inspection apparatus according to claim 5 is learned using, as learning data, reference data generated based on print source data of a printed matter, a captured image of the printed matter, and a result of inspection of the printed matter.

7. The printed matter defect inspection apparatus according to claim 6, wherein the result of the inspection includes a result of inspection by the scan image comparison method.

8. The printed matter defect inspection apparatus according to claim 6, wherein the result of the inspection includes at least one of presence or absence of a defect, number of defects, position of a defect, and size of a defect.

9. A printing system comprising: a printing device that prints a printed matter based on the printing source data; an imaging device that captures the printed printed matter to obtain the captured image; and a defect inspection device for a printed matter according to any one of claims 1 to 8.

10. In a method for inspecting defects in printed matters, in which each of a plurality of continuously printed printed matters is inspected as needed by a scan image comparison method in which a captured image of a printed matter to be inspected is compared with a reference image of a printed matter that is correct, one or more processors perform inspection of defects in the printed matter by a data comparison method in which a captured image of a printed matter to be inspected is compared with reference data generated based on the printing source data of the printed matter, determine the pass / fail of the printed matter from the result of the inspection by the data comparison method, and set the captured image of the printed matter determined to be a good product as the reference image.

11. A program for causing a computer to execute the method for inspecting defects in printed matters according to claim 10.

12. A non-transitory and computer-readable recording medium on which the program according to claim 11 is recorded.

Images