Image processing device, control method for image processing device, and program

Abstract

The system will be able to determine the cause of streaks that appear in the area corresponding to the printed material in the scanned image. [Solution] The image processing device 100 for inspecting printed materials includes a reading image acquisition unit 120 that acquires a read image obtained by reading the printed material, a streak acquisition unit 140 that acquires streaks contained within the region corresponding to the printed material in the read image acquired by the reading image acquisition unit 120, and a streak determination unit 150 that determines the cause of streak occurrence based on the characteristic quantities of streaks acquired by the streak acquisition unit 140.

Description

Technical Field

[0001] The present invention relates to an image processing apparatus, a control method for the image processing apparatus, and a program.

Background Art

[0002] Printed matter printed and output by a printing apparatus may have printing defects such as stains caused by color materials such as ink or toner adhering to unintended locations, or color bleeding caused by insufficient color material adhering to locations where an image should be formed. As a printing inspection system for inspecting the presence or absence of these printing defects, for example, there is a printing inspection system that reads a printed matter output from a printing apparatus as an image using a camera or a line sensor of a scanner, and automatically inspects whether printing is being performed normally from the read image. At this time, the read image may include effects caused by reading that do not exist in the actual printed matter. For example, as an effect caused by reading, deposits such as paper dust adhering to the above-described line sensor may appear as streaks in the read image.

[0003] The above-described effects caused by reading in the read image to be inspected are detected as defects during inspection, so the printed matter read as the read image is treated as waste paper. In order not to treat the printed matter as waste paper, it is necessary to distinguish between the above-described effects caused by reading and the defects of the printed matter. For example, Patent Document 1 describes a technique for determining that a pattern that commonly exists in a medium area corresponding to a recording medium and a background area of the recording medium in a read image read by a reading unit is a pattern generated by the reading unit.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, with the technology described in Patent Document 1 above, if streaks appear only in the media area corresponding to the recording medium (printed material) in the read image, it may be impossible to distinguish whether the streaks are due to the effects of the reading process or to defects caused by the printing process.

[0006] This invention has been made in view of these problems, and aims to enable the determination of the cause of streaks when streaks appear in an area corresponding to a printed material in a read image. [Means for solving the problem]

[0007] The present invention relates to an image processing apparatus for inspecting printed materials, comprising: a reading image acquisition means for acquiring a reading image obtained by reading the printed material; a streak acquisition means for acquiring streaks contained within a region corresponding to the printed material in the reading image; and a streak determination means for determining the cause of the streaks based on the characteristic quantities of the streaks. [Effects of the Invention]

[0008] According to the present invention, when streaks appear in the area corresponding to the printed material in the read image, the cause of the streaks can be determined. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows a first example of the schematic configuration of a print inspection system according to the first embodiment. [Figure 2] This figure shows a second example of the schematic configuration of the print inspection system according to the first embodiment. [Figure 3] This figure shows an example of the functional configuration of the image processing apparatus according to the first embodiment. [Figure 4] This figure shows a first embodiment and illustrates an example of how foreign matter adhesion can affect the reading. [Figure 5]This figure shows a first embodiment and illustrates an example of features (feature quantities) related to the shape of streaks caused by printing and streaks caused by reading. [Figure 6] This flowchart shows an example of the processing procedure for inspection in the control method for the image processing apparatus according to the first embodiment. [Figure 7] This flowchart shows an example of the processing procedure for displaying a UI panel on the screen in the control method for the image processing apparatus according to the first embodiment. [Figure 8] This figure shows an example of a display screen that appears on the UI panel in step S204 of Figure 7, illustrating the first embodiment. [Figure 9] This figure shows the first embodiment and is a diagram illustrating another example of a display screen shown on the UI panel. [Figure 10] This figure shows a second embodiment and illustrates an example of the characteristics (feature quantities) related to the density of streaks caused by printing and streaks caused by reading. [Figure 11] This figure shows a third embodiment and illustrates an example of the functional configuration of the streak detection unit. [Modes for carrying out the invention]

[0010] The embodiments for carrying out the present invention will be described below with reference to the drawings. Note that the embodiments described below do not limit the invention as defined in the claims. Furthermore, while the embodiments described below include multiple features, not all of these features are essential to the present invention, and the features may be combined in any way.

[0011] (First embodiment) First, let me describe the first embodiment.

[0012] [Outline configuration of the print inspection system] FIG. 1 is a diagram showing a first example of the schematic configuration of a printing inspection system 10 according to the first embodiment. Hereinafter, the printing inspection system 10 in the first example of the first embodiment shown in FIG. 1 will be described as the "printing inspection system 10-1".

[0013] As shown in FIG. 1, the printing inspection system 10-1 includes an image processing device 100, a printing device 200, and a printing server 300.

[0014] The printing server 300 generates a printing job including the manuscript to be printed and inputs the generated printing job to the printing device 200.

[0015] Based on the printing job input from the printing server 300, the printing device 200 forms an image on printing paper (printing medium) to generate a printed matter. The printing device 200 has a paper feeding unit 201, and the user can supply printing paper to the paper feeding unit 201 in advance. Specifically, when a printing job is input from the printing server 300, the printing device 200 conveys the printing paper supplied to the paper feeding unit 201 along the conveyance path 202 and forms an image on one side or both sides of the printing paper to generate a printed matter. Then, the printing device 200 sends the generated printed matter to the image processing device 100 via the conveyance path 202.

[0016] The image processing device 100 inspects for defects in the printed matter (inspection target medium), which is the printing paper (printing medium) on which printing has been performed. The inspection target medium is obtained as a printed matter by the printing device 200 forming an image on the printing paper and is conveyed through the internal conveyance path 202 of the printing device 200.

[0017] The image processing apparatus 100 includes a CPU 101, a RAM 102, a ROM 103, and an image reading unit 104. The image processing apparatus 100 also includes a network interface (I / F) 105, a printing apparatus interface (I / F) 106, a general-purpose interface (I / F) 107, a user interface (UI) panel 108, and a bus 109. Further, the image processing apparatus 100 includes a conveyance path 111, an output tray 112, and an output tray 113.

[0018] The CPU 101 is a processor that controls each component inside the image processing apparatus 100 to comprehensively control the operation of the image processing apparatus 100 and performs various processes.

[0019] The RAM 102 is a memory that temporarily holds applications executed by the CPU 101, data used for image processing (including various image data), and the like.

[0020] The ROM 103 is a memory that stores a group of programs executed by the CPU 101 and various information (including various data) necessary when the CPU 101 performs various controls and various processes.

[0021] The image processing apparatus 100 according to the present embodiment can be realized by a computer including a processor and a memory. For example, by a processor such as the CPU 101 executing a program stored in a memory such as the RAM 102 or the ROM 103, the functions of each component of the image processing apparatus 100 can be realized. At this time, a processor such as the CPU 101 can also control each component of the image processing apparatus 100 as necessary. Note that the image processing apparatus 100 according to the present embodiment may be constituted by, for example, a plurality of processing apparatuses communicably connected via a network.

[0022] The image reading unit 104 scans and reads one or both sides of the printed material that has been transported from the printing device 200 via the transport path 202 and the transport path 111 on the transport path 111, and acquires this as a read image (read image data). At this time, the transport path 111 becomes the background area (the area outside the area corresponding to the printed material) when the image reading unit 104 reads the image of the printed material and acquires the read image. For this reason, it is preferable that the transport path 111 has a color (for example, black) that makes it easy to distinguish from the printed material in the read image.

[0023] Network I / F105 is an interface for connecting to computer networks such as the Internet in a communicative manner.

[0024] The printing device interface 106 is an interface for communicating with the printing device 200. The image processing device 100 can communicate with the printing device 200 via this printing device interface 106. For example, the image processing device 100 and the printing device 200 can be synchronized via this printing device interface 106, and they can send and receive information about each other's operating status.

[0025] The general-purpose interface (I / F) 107 is an interface for enabling communication between the UI panel 108 and the bus 109.

[0026] The UI panel 108 is a component that can output information to the user. The UI panel 108 may be a display device (display means) such as a liquid crystal display, and can function as a user interface for the image processing device 100. For example, the UI panel 108 can inform the user of the current status and settings of the image processing device 100. The UI panel 108 may also be equipped with input devices (input means) such as a touch panel or buttons, and can receive instructions from the user through the functions of these input devices.

[0027] Bus 109 is a transmission path that enables communication between the various components of the image processing device 100.

[0028] The transport path 111 is connected to the transport path 202 of the printing device 200. Printed materials output from the printing device 200 are transported along this transport path 111.

[0029] The CPU 101 of the image processing device 100 performs an inspection process to check for defects in the printed material based on the read image (read image data) of the printed material acquired by the image reading unit 104 while the printed material output from the printing device 200 is passing through the transport path 111. In this embodiment, the output trays 112 and 113 are communicated to the CPU 101 via the bus 109. If the CPU 101 of the image processing device 100 determines that the inspection process is successful (the printed material has no defects), it controls the transport of the successful printed material to the output tray 112. If the CPU 101 of the image processing device 100 determines that the inspection process is unsuccessful (the printed material has defects), it controls the transport of the unsuccessful printed material to the output tray 113. Through this control by the CPU 101, the destination of the printed material, which is the medium to be inspected, is set to either the output tray 112 or the output tray 113. Specifically, in this embodiment, only printed materials determined to be free of defects are output to output tray 112, and only printed materials determined to have defects are output to output tray 113.

[0030] Figure 2 shows a second example of the schematic configuration of the print inspection system 10 according to the first embodiment. Hereinafter, the print inspection system 10 in the second example of the first embodiment shown in Figure 2 will be referred to as "print inspection system 10-2" in the description. In Figure 2, the same reference numerals are used for components that are the same as those shown in Figure 1, and their detailed descriptions are omitted.

[0031] The print inspection system 10-2 shown in Figure 2 has a configuration that adds a cloud server 400 and the internet 500 compared to the print inspection system 10-1 shown in Figure 1. The cloud server 400 in this embodiment is one or more server devices that provide cloud services on the internet 500.

[0032] The cloud server 400 is connected to the image processing device 100 via the internet 500, enabling communication. The cloud server 400 receives the scanned image (scanned image data) of the printed material acquired by the image reading unit 104 of the image processing device 100, performs inspection processing, and transmits the inspection result information to the image processing device 100 as needed. The cloud server 400 has a CPU 401, RAM 402, ROM 403, storage unit 404, network interface (I / F) 405, and bus 406.

[0033] The CPU 401 is a processor that controls each internal component of the cloud server 400 to comprehensively control the operation of the cloud server 400 and perform various processing tasks. The CPU 401 uses the RAM 402 as work memory to execute programs stored in the ROM 403 (or storage unit 404), and controls each component of the cloud server 400 via the bus 406 to comprehensively control the operation of the cloud server 400.

[0034] RAM402 functions as the work memory for CPU401.

[0035] ROM403 is a memory that stores programs executed by CPU401, as well as various information (including various data) necessary for CPU401 to perform various control and processing operations.

[0036] The storage unit 404 is, for example, an HDD or SSD, and stores various types of information (including various types of data) handled by the cloud server 400. The CPU 401 writes information to the storage unit 404 and reads information stored in the storage unit 404 via the bus 406.

[0037] Network I / F 405 is an interface for communicating with the Internet 500. The cloud server 400 uses Network I / F 405 to receive requests from, for example, a web browser and send and receive image data in the image processing device 100.

[0038] Bus 406 is a transmission path that enables communication between the various components of the cloud server 400.

[0039] The cloud server 400 may consist of one server device or multiple server devices. Furthermore, the cloud server 400 may implement the functions of multiple server devices using virtualization software on a single server device. Additionally, the cloud server 400 may communicate not only with the image processing device 100 but also with, for example, the printing device 200 to manage print jobs and inspection results.

[0040] [Functional Configuration of Image Processing Devices] Figure 3 shows an example of the functional configuration of the image processing apparatus 100 according to the first embodiment. As shown in Figure 3, the image processing device 100 has the following functional configurations: a reference image acquisition unit 110, a read image acquisition unit 120, an inspection processing unit 130, a streak acquisition unit 140, and a streak determination unit 150. Each of the functional configurations (110 to 150) of the image processing device 100 is realized, for example, by the CPU 101 executing a program stored in the ROM 103.

[0041] The reference image acquisition unit 110 is a reference image acquisition means that acquires a reference image (reference image data), for example, the original image of a printed material, by reading it from the ROM 103 to the RAM 102.

[0042] The image reading unit 120 controls the image reading by the image reading unit 104 and is an image reading means that reads the printed material output from the printing device 200 and transported along the transport path 111 and acquires the read image (read image data). The image reading unit 120 then stores the acquired read image (read image data) in the RAM 102.

[0043] The inspection processing unit 130 checks for defects in the read image to be inspected by comparing the difference between the reference image acquired by the reference image acquisition unit 110 and the read image acquired by the read image acquisition unit 120. Specifically, in this embodiment, the inspection processing unit 130 is an inspection processing means that performs an inspection process to detect defect candidates from the read image based on the difference between the reference image acquired by the reference image acquisition unit 110 and the read image acquired by the read image acquisition unit 120. That is, the inspection processing unit 130 detects as defect candidates the portion where a difference is recognized between the reference image acquired by the reference image acquisition unit 110 and the read image acquired by the read image acquisition unit 120.

[0044] The streak acquisition unit 140 is a streak acquisition means that acquires streaks contained within the area corresponding to the printed material in the read image acquired by the read image acquisition unit 120.

[0045] The streak detection unit 150 is a streak detection means that determines the cause of a streak based on the characteristic quantities of streaks on the read image acquired by the streak acquisition unit 140. Specifically, the streak detection unit 150 determines whether the cause of the streak is a printing cause, which occurred when the printed material was printed, or a reading cause, which occurred when the printed material was read as a read image. Alternatively, the streak detection unit 150 may use the characteristic quantities of streaks acquired by the streak acquisition unit 140 and the inspection result information obtained from the inspection processing unit 130 to determine whether the cause of the streak is printing-related or reading-related.

[0046] The inspection result information obtained by the inspection processing unit 130 and the judgment result information determined by the streak determination unit 150 are output to the UI panel 108 (and, if necessary, to the printing device 200).

[0047] Here, we will describe the defect candidates on the read image detected by the inspection processing in the inspection processing unit 130. The inspection processing unit 130 compares the reference image and the read image, and if there is a difference, it includes that difference as a defect candidate in the inspection result information and outputs it. The defect candidates detected as the difference between the reference image and the read image include defects that occur in the image formation process of the printing device 200, and printing defects caused by dirt adhering to the printing paper as it is transported along the transport path (hereinafter referred to as "printing-related defects"). Furthermore, the above-mentioned defect candidates also include reading effects caused by abnormalities in the image reading unit 104 when reading the printed material, or by foreign matter adhering to the sensor of the image reading unit 104 (hereinafter referred to as "reading-related effects"). The inspection processing unit 130 may include both defect candidates determined to be printing-related and defect candidates determined to be reading-related as defect candidates to be included in the inspection result information. Furthermore, the inspection processing unit 130 may include only defect candidates determined to be print-related, excluding those determined to be read-related, as defect candidates to be included in the inspection result information.

[0048] In the case of defects caused by printing, the defect exists not only in the scanned image but also in the actual printed material, so it is necessary to identify it as a defect during the inspection process. In contrast, in the case of defects caused by scanning, the scanned image is affected by scanning, but the actual printed material is not defective, so it is necessary to distinguish it from defects caused by scanning.

[0049] Figure 4 shows a first embodiment and illustrates an example of how foreign matter adhesion can affect reading accuracy.

[0050] Figure 4(a) shows an actual printed document 410 and an example of a read image 420 in which streaks caused by paper dust, as an example of foreign matter, have been read. Specifically, the read image 420 includes a region 421 corresponding to the printed document 410 and a background region 422 (black region) which is the region outside the region 421 corresponding to the printed document 410. The read image 420 includes streaks 4211 that were caused by reading paper dust as an example of foreign matter within the region 421 corresponding to the printed document 410. These streaks 4211 are not present in the printed document 410.

[0051] Next, the phenomenon of the presence of streaks 4211 in the read image 420 will be explained using Figures 4(b) to 4(d).

[0052] Figures 4(b) to 4(d) illustrate an example of the process by which a printed material 410 is scanned by the image reading unit 104 and a read image 420 is acquired when the printed material 410 is transported in the direction indicated by the arrow (from top to bottom in the figure).

[0053] First, in Figure 4(b), foreign matter (paper dust) 430 adhering to the printed material 410 is transported along with the transport of the printed material 410.

[0054] Next, in Figure 4(c), foreign matter (paper dust) 430 adheres to the image reading unit 104, and the printed material 410 is transported with the foreign matter (paper dust) 430 still attached to the image reading unit 104, and image reading continues.

[0055] Subsequently, as shown in Figure 4(d), the foreign matter (paper dust) 430 is removed from the image reading unit 104 along with the transport of the printed material 410.

[0056] As a result of the process shown in Figures 4(b) to 4(d) above, the area 421 corresponding to the printed material 410 will contain streaks 4211 caused by reading the foreign matter (paper dust) 430, as shown in the read image 420 of Figure 4(a). In the example shown in Figure 4, the streaks 4211 caused by reading the foreign matter (paper dust) 430 appear only in a portion of the area 421 corresponding to the printed material 410 in the read image 420, but this embodiment is not limited to this. For example, if the foreign matter (paper dust) 430 attached to the image reading unit 104 continues to adhere during the image reading of the printed material 410, the streaks 4211 may always appear from the middle of the read image 420. Also, if the foreign matter (paper dust) 430 was attached to the image reading unit 104 before the printed material 410 was transported, the streaks 4211 may appear throughout the entire read image 420. Furthermore, the streaks 4211 caused by reading are not limited to the adhesion of paper dust, which is one example of foreign matter 430, but can also be caused by other foreign matter 430 such as dirt. In addition, the streaks 4211 caused by reading can also be caused by other malfunctions of the sensor, such as damage to the sensor element of the image reading unit 104.

[0057] Furthermore, in Figures 4(b) to 4(d), the position of the image reading unit 104 is fixed, and the printed material 410 is transported in the direction of the printed material transport indicated by the arrow. However, the image reading unit 104 may move while the position of the printed material 410 is fixed to perform image reading. In that case, the streaks 4211 that appear in the read image 420 will appear in the direction in which the image reading unit 104 moves.

[0058] Next, we will explain how to determine the effects of defects caused by printing and those caused by reading. While printing-induced defects are defects that occur during the image formation process of the printing apparatus 200, reading-induced effects are effects that occur when the printed material 410 is read. Therefore, even streaks that appear in the read image 420 will have different characteristics (feature quantities) depending on their origin.

[0059] Printing defects include, for example, when forming an image on printing paper using the electrophotographic method in the printing device 200, streaks may appear on the printed material if toner that was formed before the image to be printed unintentionally remains on the drum or intermediate transfer medium. Another printing defect is when forming an image on printing paper using the inkjet method in the printing device 200, streaks may appear on the printed material due to unintended ink ejection. Furthermore, another printing defect is when toner or ink residue unintentionally adhering to the transport path 202 (and even the transport path 111) in the printing device 200 is transferred to the printed material as streaks. Because these printing defects involve physical quantities such as toner and ink, which are read as images, they appear as uneven shapes or other irregularities on the read image.

[0060] In contrast, in the case of reading-induced effects, when reading foreign matter 430 attached to the image reading unit 104, etc., the same foreign matter 430 is always read. Therefore, the information entering the image reading unit 104 remains constant, and appears as a nearly uniform shape on the read image.

[0061] Therefore, in this embodiment, the streak acquisition unit 140 acquires streaks from the read image acquired by the image reading unit 104. Then, the streak determination unit 150 determines the cause of the streaks based on the streak feature quantities, including the feature quantities related to the shape of the streaks, acquired from the read image by the streak acquisition unit 140.

[0062] Next, we will explain the feature quantities related to the shape of the streaks that the streak detection unit 150 uses to determine the cause of streaking.

[0063] Figure 5 shows a first embodiment and illustrates an example of the characteristics (feature quantities) related to the shape of streaks caused by printing and streaks caused by reading. Specifically, Figures 5(a) and 5(b) show the characteristics (feature quantities) related to the shape of streaks caused by printing, and Figure 5(c) shows the characteristics (feature quantities) related to the shape of streaks caused by reading.

[0064] The groove 510 shown in Figure 5(a) has a bent portion 511 as a characteristic feature (feature quantity) of the groove's shape. Similarly, the groove 520 shown in Figure 5(b) has a discontinuity portion 521 of the groove that exists within a predetermined region as a characteristic feature (feature quantity) of the groove's shape.

[0065] The reason for the characteristic shape of streaks caused by printing, as shown in Figures 5(a) and 5(b), is that in the electrophotographic image formation process, there is a step in which the blade cleans the toner remaining on the drum during the image formation of the image to be printed. Specifically, if not all of the toner is removed during this cleaning step and remains on the drum, it may appear as streaky defects caused by printing. In this case, the way in which toner remains on the drum varies depending on the amount of toner that should have been removed and the movement of the blade. Depending on how the toner remains, phenomena such as the streaks transferred to the printed material becoming bent (resulting in the bent portion 511 in Figure 5(a)) or appearing as partially discontinuous portions (discontinuous portion 521 in Figure 5(b)) may occur.

[0066] Furthermore, the reason why the printing-induced streak shape characteristics shown in Figures 5(a) and 5(b) occur is that in the inkjet image formation process, ink contamination in the transport path can cause streak-like defects to appear on the printed material. In this case, variations occur depending on the degree and amount of ink contamination, and warping of the printed material during transport can cause phenomena such as the streak bending (resulting in the bent portion 511 in Figure 5(a)) or the appearance of partially discontinuous portions (the discontinuous portion 521 in Figure 5(b)).

[0067] In contrast, the streak 530 shown in Figure 5(c) does not include the bent portion 511 in Figure 5(a), nor does it have the discontinuous portion 521 in Figure 5(b). This is because, as explained using Figures 4(b) to 4(d), when the foreign object 430 adheres to the image reading unit 104, the same foreign object 430 is read at the same position when the image reading unit 104 reads the printed material 410. As shown in Figure 4, the streak 4211 caused by reading the read image 420 extends in the same direction as the transport direction of the printed material 410 (printed material transport direction). Furthermore, when the foreign object 430 moves, it moves in the printed material transport direction due to the force when the printed material 410 is transported, causing the foreign object 430 to disappear from the image reading unit 104. Therefore, in the case of the reading-induced streaks 530 shown in Figure 5(c), the possibility of the bent portion 511 in Figure 5(a) or the discontinuity portion 521 in Figure 5(b) occurring is small.

[0068] As described above, there are differences in the characteristics (feature quantities) related to the shape of streaks between streaks caused by printing and streaks caused by reading, and the streak determination unit 150 determines the cause of the streaks based on these feature quantities.

[0069] In this embodiment, when the streak detection unit 150 determines the cause of streak occurrence, streaks acquired by the streak acquisition unit 140 are used from the read image acquired by the read image acquisition unit 120. However, the present invention is not limited to this embodiment. When the streak detection unit 150 determines the cause of streak occurrence, the inspection processing unit 130 may further use defect candidate information, which is the result of an inspection using the reference image acquired by the reference image acquisition unit 110 and the read image acquired by the read image acquisition unit 120. In this case, compared to making a determination using only streak information from the read image, further use of defect candidate information narrows down the candidate streaks, thereby reducing the load on the determination process and reducing false detections.

[0070] Figure 6 is a flowchart showing an example of the processing procedure for inspection in the control method of the image processing apparatus 100 according to the first embodiment. Specifically, Figure 6 is a flowchart showing an example of the processing procedure for inspection when defect candidate information is used to determine the cause of streaks by the streak determination unit 150. It is assumed that, before the start of the flowchart shown in Figure 6, the reference image acquisition unit 110 has acquired a reference image, which is the original image of the printed material.

[0071] First, in step S101 of Figure 6, the reading image acquisition unit 120 acquires a reading image of the printed material obtained by reading the printed material.

[0072] Next, in step S102 of Figure 6, the inspection processing unit 130 performs difference processing between the reference image acquired by the reference image acquisition unit 110 and the read image acquired in step S101 to obtain difference information. Specifically, if the inspection processing unit 130 determines that there is a difference between the reference image acquired by the reference image acquisition unit 110 and the read image acquired in step S101, it obtains difference information including the portion of the read image in which the difference is determined.

[0073] Next, in step S103 of Figure 6, the inspection processing unit 130 performs inspection processing based on the difference information acquired in step S102 and detects defect candidates. Specifically, if the difference information acquired in step S102 includes a portion of the read image in which a difference is recognized, the inspection processing unit 130 detects the portion of the read image in which a difference is recognized as a defect candidate.

[0074] Next, in step S104 of Figure 6, the inspection processing unit 130 determines whether the inspection result is NG or not, depending on whether a defect candidate was detected in step S103. Specifically, if a defect candidate is detected in step S103, the inspection processing unit 130 determines that the inspection result is NG, and if no defect candidate is detected in step S103, it determines that the inspection result is not NG (OK).

[0075] In step S104 of Figure 6, if the inspection processing unit 130 determines that the inspection result is NG (S104 / YES), the process proceeds to step S105. When the process proceeds to step S105 in Figure 6, the streak detection unit 150 determines the cause of the streak based on the characteristic quantities of the streak among the defect candidates detected in step S103.

[0076] When the process in step S105 in Figure 6 is completed, the process proceeds to step S106. Also, in step S104 in Figure 6, if the inspection processing unit 130 determines that the inspection result is not NG (i.e., OK) (S104 / NO), the process proceeds to step S106. When the process proceeds to step S106 in Figure 6, the inspection processing unit 130 generates and acquires inspection result information based on the results of the processing in steps S103 to S105. For example, if the inspection processing unit 130 made a negative judgment in step S104 (S104 / NO), it generates and acquires inspection result information that includes information indicating that the inspection result is OK. Also, for example, if the inspection processing unit 130 made an affirmative judgment in step S104 (S104 / YES), it generates and acquires inspection result information that includes information indicating that the inspection result is NG and information regarding the determination result of the cause of the streaks in step S105.

[0077] When the process in step S106 of Figure 6 is completed, the process in the flowchart shown in Figure 6 is finished.

[0078] Figure 7 is a flowchart showing an example of the processing procedure for the screen display processing of the UI panel 108 in the control method of the image processing apparatus 100 according to the first embodiment.

[0079] First, in step S201 of Figure 7, the CPU 101 determines whether or not there are any defect candidates in the read image based on the inspection result information acquired in step S106 of Figure 6. If the CPU 101 determines in step S201 of Figure 7 that there are no defect candidates in the read image (S201 / NO), the processing of the flowchart shown in Figure 7 ends. If a negative determination is made in step S201 of Figure 7 (S201 / NO), the UI panel 108 may display a read image that does not contain any defect candidates.

[0080] Furthermore, in step S201 of Figure 7, if the CPU 101 determines that there is a candidate for a defect in the read image (S201 / YES), the process proceeds to step S202. When the process proceeds to step S202 in Figure 7, the CPU 101 determines whether or not there are candidate defects in the read image that are affected by the reading, based on the information of the determination result of the cause of streak occurrence included in the inspection result information acquired in step S106 in Figure 6.

[0081] In step S202 of Figure 7, if the CPU 101 determines that there is a candidate defect in the read image that is affected by the reading process (S202 / YES), the process proceeds to step S203. When the process proceeds to step S203 in Figure 7, the CPU 101 eliminates the defect candidates that were determined to be present in the read image in step S201 and that were determined to be affected by the read process in step S202.

[0082] When the processing in step S203 in Figure 7 is completed, the process proceeds to step S204 in Figure 7. Also, in step S202 in Figure 7, if the CPU 101 determines that there are no candidate defects in the read image that are affected by the reading process (S202 / NO), the process proceeds to step S204. When the process proceeds to step S204 in Figure 7, the UI panel 108 displays a defect map as defect information based on the defect candidates determined to be present in the read image, based on the control of the CPU 101, and presents the defect map to the user.

[0083] For example, if a negative judgment is made in S202 in Figure 7 (S202 / NO), only print-related defect candidates remain. Therefore, in step S204 in Figure 7, the UI panel 108 displays a defect map based on print-related defect candidates. Also, after processing in S203 in Figure 7, defect candidates affected by reading are eliminated, leaving only print-related defect candidates. Therefore, in step S204 in Figure 7, the UI panel 108 displays a defect map based on print-related defect candidates. In other words, in step S204 in Figure 7, the UI panel 108 displays and presents to the user a defect map based only on print-related defect candidates.

[0084] When the process in step S204 in Figure 7 is completed, the process in the flowchart shown in Figure 7 is finished.

[0085] Figure 8 shows a first embodiment and is a diagram illustrating an example of the display screen shown on the UI panel 108 in step S204 of Figure 7.

[0086] The display screen of the UI panel 108 shown in Figure 8 shows the inspection image 810, defect map 820, inspection setting information 830, and inspection result information 840.

[0087] The inspection image 810 is the image used in the inspection processing unit 130. This inspection image 810 is, for example, the image of the region 421 corresponding to the printed material 410, which is obtained by removing the background region 422 (black region) from the reading image 420 shown in Figure 4(a).

[0088] As a result of the processing in step S204 of Figure 7, the defect map 820 displays only the print-related defects 821 based on print-related defect candidates. That is, the defect map 820 of the UI panel 108 shown in Figure 8 displays the print-related defects 821 based on print-related defect candidates, excluding the read-related defect candidates, from among the print-related defect candidates and read-related defect candidates.

[0089] Inspection setting information 830 displays the job name, print number, and inspection level.

[0090] Inspection result information 840 displays the number of defects for each defect type (small dot defects and streak defects) and the number of readable streaks that were eliminated as part of the inspection results.

[0091] The UI panel 108 shown in Figure 8 allows the user (inspector) to check only for defects caused by printing without considering the effects of reading, thereby reducing the user's verification burden.

[0092] Figure 9 shows the first embodiment and is a diagram illustrating another example of the display screen shown on the UI panel 108. In Figure 9, the same reference numerals are used for components that are the same as those shown in Figure 8, and their detailed descriptions are omitted.

[0093] The UI panel 108 shown in Figure 8 illustrates a configuration that displays a defect map 820 with the influence of read-induced defects removed. In contrast, the UI panel 108 shown in Figure 9 displays a defect map 920 with print-induced defects 821 based on print-induced defect candidates and read-induced influences 921 based on read-induced defect candidates, distinguishably color-coded. In this case, the UI panel 108 shown in Figure 9 displays the number of detected read streaks as inspection result information 940, instead of the number of removed read streaks shown in Figure 8.

[0094] In the UI panel 108 shown in Figure 9, print-related defects 821 and read-related influences 921 are displayed in the defect map 920 using distinguishable color coding. However, this embodiment is not limited to this configuration. In this embodiment, it is sufficient that both print-related defects 821 and read-related influences 921 are displayed in a distinguishable manner. For example, print-related defects 821 and read-related influences 921 may be displayed with different brightness values, or additional tags may be displayed on the read-related influences 921 based on detected reading streaks, thereby displaying both in a distinguishable manner on the defect map 920. Alternatively, print-related defects 821 and read-related influences 921 may be displayed as separate defect maps, thereby displaying both in a distinguishable manner.

[0095] Next, we will explain the inspection results and post-processing of printed materials in which the streak detection unit 150 determined that the read image was affected by the reading process. Printed materials that are determined to have no printing-related defects in the scanned image but to have effects caused by scanning are deemed to have passed inspection by the inspection processing unit 130, the inspection is completed, and the printed materials are transported to the output tray 112. However, printed materials that are determined to have effects caused by scanning can be separated from those printed materials that have passed inspection without any effects caused by scanning or those that have been determined to have printing-related defects by being discharged into a different tray. In this configuration, the user (inspector) can perform post-processing such as confirmation or re-inspection based on their own judgment. Furthermore, even if the scanned image is determined to have no printing-related defects but to have effects caused by scanning, a defect map indicating this may be displayed on the UI panel 108.

[0096] The image processing apparatus 100 according to the first embodiment described above is an image processing apparatus for inspecting a printed material 410. The image processing apparatus 100 according to the first embodiment includes a reading image acquisition unit 120 that acquires a reading image 420 obtained by reading the printed material 410, and a streak acquisition unit 140 that acquires streaks 4211 contained within a region 421 corresponding to the printed material 410 in the reading image 420. Furthermore, the image processing apparatus 100 according to the first embodiment includes a streak determination unit 150 that determines the cause of the streaks 4211 based on the characteristic quantities of the streaks 4211 acquired by the streak acquisition unit 140. With this configuration, if streaks appear in the area corresponding to the printed material in the scanned image, the cause of the streaks can be determined.

[0097] Furthermore, in the first embodiment, the feature quantities of the striate 4211 include feature quantities related to the shape of the striate 4211. The streak detection unit 150 determines that the cause of the streak is printing if the streak has a bend 511 as a feature quantity related to the shape of the streak (Figure 5(a)). The streak detection unit 150 also determines that the cause of the streak is reading if the streak does not have a bend 511 as a feature quantity related to the shape of the streak (Figure 5(c)). Furthermore, the streak detection unit 150 determines that the cause of the streak is printing if there is a discontinuity 521 in the streak that exists within a predetermined region as a feature quantity related to the shape of the streak (Figure 5(b)). Also, the streak detection unit 150 determines that the cause of the streak is reading if there is no discontinuity 521 in the streak that exists within a predetermined region as a feature quantity related to the shape of the streak (Figure 5(c)).

[0098] According to the first embodiment, even if the streaks 4211 that appear in the read image 420 are not present in the background area 422 but only in the area 421 corresponding to the printed material 410, the cause of the streaks 4211 can be determined. More specifically, according to the first embodiment, it is possible to determine whether the cause of the streaks 4211 is a printing-related cause that occurred when the printed material 410 was printed, or a reading-related cause that occurred when the printed material 410 was read as a read image 420. Furthermore, by displaying the defect map along with the inspection result information on the UI panel 108, the process of the user (inspector) having to look at the read image 420 to confirm and make a judgment can be reduced, thereby reducing the burden on the user (inspector).

[0099] (Second embodiment) Next, a second embodiment will be described. In the description of the second embodiment below, matters common to the first embodiment described above will be omitted, and matters that differ from the first embodiment described above will be explained.

[0100] The schematic configuration of the print inspection system according to the second embodiment is the same as the schematic configuration of the print inspection system 10 according to the first embodiment shown in Figures 1 and 2. Furthermore, the functional configuration of the image processing device 100 according to the second embodiment is the same as the functional configuration of the image processing device 100 according to the first embodiment shown in Figure 3. Also, the processing procedure for the inspection process in the control method of the image processing device 100 according to the second embodiment is the same as the processing procedure for the inspection process in the control method of the image processing device 100 according to the first embodiment shown in Figure 6. Furthermore, the processing procedure for the screen display process of the UI panel 108 in the control method of the image processing device 100 according to the second embodiment is the same as the processing procedure for the screen display process of the UI panel 108 in the control method of the image processing device 100 according to the first embodiment shown in Figure 7.

[0101] In the first embodiment described above, a feature quantity related to the shape of the streak was used as the streak feature quantity used in the streak detection unit 150 to determine the cause of streak occurrence. In contrast, in the second embodiment, a feature quantity related to the density of the streak is used as the streak feature quantity used in the streak detection unit 150 to determine the cause of streak occurrence, in addition to / or instead of the streak shape feature quantity used in the first embodiment described above.

[0102] Figure 10 shows a second embodiment and illustrates an example of the characteristics (feature quantities) related to the density of streaks caused by printing and streaks caused by reading. Specifically, Figure 10(a) shows the characteristics (feature quantities) related to the density of streaks caused by printing, and Figure 10(b) shows the characteristics (feature quantities) related to the density of streaks caused by reading.

[0103] The streak 1010 in Figure 10(a) shows a streak where the density is lighter in the upper and lower regions (the regions with thin streaks) and darker in the central region (the regions with thick streaks), indicating that the density variation is not within the predetermined range (i.e., the density variation is large). The reason why the density characteristics of the streak 1010 caused by printing shown in Figure 10(a) occur is that variations in streak density occur when the amount of toner or ink adhering to the printed material 410 during the image formation process of the printing device 200 is not constant.

[0104] In contrast, the streak 1020 in Figure 10(b) shows a streak where the density is approximately constant throughout the entire area of ​​the upper end, central part, and lower end, and the variation in density is within the predetermined range (when the variation in density is small). The reason why the density characteristics of the streak 1020 caused by reading shown in Figure 10(b) occur is that the image reading unit 104 reads the foreign matter 430 attached to itself, that is, the information of the same foreign matter 430 is input into the read image, so the density of the streak becomes approximately constant.

[0105] As described above using Figure 10, there are differences in the characteristics (feature quantities) related to the density of streaks 1010 caused by printing and streaks 1020 caused by reading. Therefore, the streak determination unit 150 determines the cause of the streaks based on the feature quantities related to the density of the streaks. Specifically, in this embodiment, the streak determination unit 150 determines that the cause of the streaks is printing if the variation in the density of the streaks is not within a predetermined range as a feature quantity related to the density of the streaks. Also, in this embodiment, the streak determination unit 150 determines that the cause of the streaks is reading if the variation in the density of the streaks is within the predetermined range as a feature quantity related to the density of the streaks.

[0106] According to the second embodiment, similar to the first embodiment, if streaks appear in the area corresponding to the printed material in the read image, the cause of the streaks can be determined. Furthermore, according to the second embodiment, even when the streaks are straight due to less variation in the feature quantities related to the shape of the streaks used in the first embodiment, or when the feature quantities related to the shape of the streaks are small and difficult to determine, the cause of the streaks can be determined. In other words, since the feature quantities related to the density of the streaks used in the second embodiment are due to toner or ink, which have physical quantities, it becomes possible to determine the cause of the streaks by observing differences in the feature quantities related to the density of the streaks.

[0107] (Third embodiment) Next, a third embodiment will be described. In the description of the third embodiment below, matters common to the first and second embodiments described above will be omitted, and matters that differ from the first and second embodiments described above will be explained.

[0108] The schematic configuration of the print inspection system according to the third embodiment is the same as the schematic configuration of the print inspection system 10 according to the first embodiment shown in Figures 1 and 2. Furthermore, the functional configuration of the image processing device 100 according to the third embodiment is the same as the functional configuration of the image processing device 100 according to the first embodiment shown in Figure 3. Also, the processing procedure for the inspection process in the control method of the image processing device 100 according to the third embodiment is the same as the processing procedure for the inspection process in the control method of the image processing device 100 according to the first embodiment shown in Figure 6. Furthermore, the processing procedure for the screen display process of the UI panel 108 in the control method of the image processing device 100 according to the third embodiment is the same as the processing procedure for the screen display process of the UI panel 108 in the control method of the image processing device 100 according to the first embodiment shown in Figure 7.

[0109] In the third embodiment, the streak detection unit 150 determines the cause of streaks using a pre-trained model that has previously learned the characteristics of streaks. In the third embodiment, when the streak detection unit 150 determines the cause of streaks, it uses a deep learning model that has previously learned the characteristics of streaks caused by printing and the characteristics of streaks caused by reading.

[0110] Figure 11 shows a third embodiment and illustrates an example of the functional configuration of the streak detection unit 150. The streak detection unit 150 has the functional configurations of feature information 151 and a deep learning model (trained model) 152.

[0111] Feature information 151 includes, as feature quantities for print-induced streaks, print-induced streak shape information 1511 and print-induced streak density information 1512. Feature information 151 also includes, as feature quantities for read-induced streaks, read-induced streak shape information 1513 and read-induced streak density information 1514. Here, print-induced streak shape information 1511 is shown, for example, in Figures 5(a) and 5(b), and read-induced streak shape information 1513 is shown, for example, in Figure 5(c). Furthermore, print-induced streak density information 1512 is shown, for example, in Figure 10(a), and read-induced streak density information 1514 is shown, for example, in Figure 10(b).

[0112] The deep learning model (pre-trained model) 152 is a pre-trained model that has been trained in advance using feature information 151. The feature information 151 that the deep learning model (pre-trained model) 152 learns is the aforementioned streak shape information 1511 caused by printing, streak density information 1512 caused by printing, streak shape information 1513 caused by reading, and streak density information 1514 caused by reading. The deep learning model (pre-trained model) 152 determines the cause of the streak from the input streak information 1101, whether it is a defect caused by printing or an effect caused by reading, and outputs the result of that determination as determination result information 1102. Here, the streak information 1101 uses streak information obtained by the streak acquisition unit 140, or streak information obtained by combining the streak information obtained by the streak acquisition unit 140 with defect candidate information obtained by the inspection processing unit 130.

[0113] In this embodiment, as described above with reference to Figure 11, the streak detection unit 150 determines the cause of streaks using a deep learning model (trained model) 152 that has been pre-trained on the characteristic quantities of streaks caused by printing and streaks caused by reading.

[0114] According to the third embodiment, similar to the first embodiment, if streaks appear in the area corresponding to the printed material in the read image, the cause of the streaks can be determined. Furthermore, according to the third embodiment, even in cases where the characteristic quantities of streaks are difficult to discern and determination is difficult in the first and second embodiments described above, the accuracy of determining the cause of streaks can be improved by pre-training streaks with a wide variety of characteristic quantities.

[0115] (Other embodiments) The present invention can also be realized by supplying a program that implements one or more of the functions of the above-described embodiments to a system or device via a network or storage medium, and by having one or more processors in the computer of that system or device read and execute the program. It can also be realized by a circuit (e.g., an ASIC) that implements one or more functions. This program and a computer-readable storage medium storing said program are included in the present invention.

[0116] The embodiments of the present invention described above are merely examples of how the invention can be implemented, and the technical scope of the invention should not be interpreted as being limited by them. In other words, the present invention can be implemented in various forms without departing from its technical concept or its main features.

[0117] This embodiment includes the following configurations, methods, and programs. [Configuration 1] An image processing device for inspecting printed materials, A reading image acquisition means for acquiring a reading image obtained by reading the aforementioned printed material, A means for acquiring streaks contained within the region corresponding to the printed material in the read image, A streak determination means for determining the cause of the streak's occurrence based on the characteristic quantities of the streak, An image processing apparatus characterized by having [Configuration 2] The aforementioned feature quantities of the streak include feature quantities relating to the shape of the streak. The image processing apparatus according to configuration 1, characterized in that... [Configuration 3] The aforementioned streak detection means is The method determines whether the cause of the streaks is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. If the characteristic quantity relating to the shape of the streak indicates that the streak has a bend, it is determined that the cause of the streak's occurrence is the printing process. If the characteristic quantity relating to the shape of the streak indicates that the streak does not have the bent portion, it is determined that the cause of the streak's occurrence is the reading cause. The image processing apparatus according to configuration 2, characterized in that... [Structure 4] The aforementioned streak detection means is The method determines whether the cause of the streaks is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. If, as a characteristic quantity relating to the shape of the streak, there is a discontinuity in the streak that exists within a predetermined region, it is determined that the cause of the streak is the printing process. If, as a characteristic quantity relating to the shape of the streak, there is no discontinuity in the streak that exists within the predetermined region, it is determined that the cause of the streak's occurrence is the reading cause. The image processing apparatus according to configuration 2, characterized in that... [Composition 5] The characteristic quantity of the streak includes a characteristic quantity relating to the concentration of the streak. The image processing apparatus according to configuration 1, characterized in that... [Composition 6] The aforementioned streak detection means is The method determines whether the cause of the streaks is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. If the variation in the density of the streaks is not within a predetermined range as a characteristic quantity related to the density of the streaks, it is determined that the cause of the streaks is the printing process. If the variation in the concentration of the streaks falls within the predetermined range, it is determined that the cause of the streaks is the reading. The image processing apparatus according to configuration 5, characterized by the features described herein. [Composition 7] The direction in which the aforementioned lines extend is the direction in which the printed material is transported. An image processing apparatus according to any one of configurations 1 to 6. [Structure 8] The aforementioned streak detection means is The method determines whether the cause of the streaks is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. The cause of the streaks is determined using a pre-trained model that has been trained in advance on the characteristic quantities of the streaks caused by printing and the characteristic quantities of the streaks caused by reading. An image processing apparatus according to any one of configurations 1 to 7, characterized by the above. [Composition 9] A reference image acquisition means for acquiring a reference image which is the original image of the printed material, An inspection processing means performs an inspection process to detect defect candidates from the read image based on the difference between the reference image and the read image, It further possesses, The streak detection means determines whether the cause of the streak is at least a reading-related cause that occurred when the printed material was read as the read image. The inspection processing means outputs inspection result information in the inspection process based on the defect candidates, excluding the defect candidates that have been determined to be caused by the reading. An image processing apparatus according to any one of configurations 1 to 8. [Configuration 10] The streak detection means determines whether the cause of the streak is at least a reading-related cause that occurred when the printed material was read as the read image. A reference image acquisition means for acquiring a reference image which is the original image of the printed material, An inspection processing means performs an inspection process to detect defect candidates from the read image based on the difference between the reference image and the read image, A display means for displaying defect information based on defect candidates, excluding those defect candidates that have been determined to be caused by the reading process, It further possesses An image processing apparatus according to any one of configurations 1 to 9. [Composition 11] The streak detection means determines whether the cause of the streak is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. A reference image acquisition means for acquiring a reference image which is the original image of the printed material, An inspection processing means performs an inspection process to detect defect candidates from the read image based on the difference between the reference image and the read image, A display means that can distinguish between the defect candidates determined to be caused by printing and the defect candidates determined to be caused by reading, It further possesses An image processing apparatus according to any one of configurations 1 to 8. [Method 1] A control method for an image processing device used to inspect printed materials, A reading image acquisition step involves obtaining a read image obtained by reading the aforementioned printed material, A streak acquisition step involves acquiring streaks included in the region corresponding to the printed material in the read image, A streak determination step in which the cause of the streak is determined based on the characteristic quantities of the streak, A control method for an image processing apparatus, characterized by having the following features. [Program 1] A program for causing a computer to function as one of the means of an image processing apparatus described in any one of configurations 1 to 11. [Explanation of symbols]

[0118] 10: Print inspection system, 100: Image processing device, 101: CPU, 102: RAM, 103: ROM, 104: Image reading unit, 105: Network interface (I / F), 106: Printing device interface (I / F), 107: General-purpose interface (I / F), 108: User interface (UI) panel, 109: Bus, 110: Reference image acquisition unit, 111: Transport path, 112: Output tray, 113: Output tray, 120: Read image acquisition unit, 130: Inspection processing unit, 140: Streak acquisition unit, 150: Streak detection unit, 200: Printing device, 201: Paper feeding unit, 202: Transport path, 300: Printing server, 400: Cloud server, 401: CPU, 402: RAM, 403: ROM, 404: Storage unit, 405: Network interface (I / F), 406: Bus, 500: Internet

Claims

1. An image processing device for inspecting printed materials, A reading image acquisition means for acquiring a reading image obtained by reading the aforementioned printed material, A means for acquiring streaks contained within the region corresponding to the printed material in the read image, A streak determination means for determining the cause of the streak's occurrence based on the characteristic quantities of the streak, An image processing apparatus characterized by having

2. The aforementioned feature quantities of the streak include feature quantities relating to the shape of the streak. The image processing apparatus according to feature 1.

3. The aforementioned streak detection means is The method determines whether the cause of the streaks is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. If the characteristic quantity relating to the shape of the streak indicates that the streak has a bend, it is determined that the cause of the streak's occurrence is the printing process. If the characteristic quantity relating to the shape of the streak indicates that the streak does not have the bent portion, it is determined that the cause of the streak's occurrence is the reading cause. The image processing apparatus according to claim 2.

4. The aforementioned streak detection means is The method determines whether the cause of the streaks is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. If, as a characteristic quantity relating to the shape of the streak, there is a discontinuity in the streak that exists within a predetermined region, it is determined that the cause of the streak is the printing process. If, as a characteristic quantity relating to the shape of the streak, there is no discontinuity in the streak that exists within the predetermined region, it is determined that the cause of the streak's occurrence is the reading cause. The image processing apparatus according to claim 2.

5. The characteristic quantity of the streak includes a characteristic quantity relating to the concentration of the streak. The image processing apparatus according to feature 1.

6. The aforementioned streak detection means is The method determines whether the cause of the streaks is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. If the variation in the density of the streaks is not within a predetermined range as a characteristic quantity related to the density of the streaks, it is determined that the cause of the streaks is the printing process. If the variation in the concentration of the streaks falls within the predetermined range, it is determined that the cause of the streaks is the reading. The image processing apparatus according to feature 5.

7. The direction in which the aforementioned lines extend is the direction in which the printed material is transported. The image processing apparatus according to feature 1.

8. The aforementioned streak detection means is The method determines whether the cause of the streaks is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. The cause of the streaks is determined using a pre-trained model that has been trained in advance on the characteristic quantities of the streaks caused by printing and the characteristic quantities of the streaks caused by reading. The image processing apparatus according to feature 1.

9. A reference image acquisition means for acquiring a reference image which is the original image of the printed material, An inspection processing means performs an inspection process to detect defect candidates from the read image based on the difference between the reference image and the read image, It further possesses, The streak detection means determines whether the cause of the streak is at least a reading-related cause that occurred when the printed material was read as the read image. The inspection processing means outputs inspection result information in the inspection process based on the defect candidates, excluding the defect candidates that have been determined to be caused by the reading. The image processing apparatus according to feature 1.

10. The streak detection means determines whether the cause of the streak is at least a reading-related cause that occurred when the printed material was read as the read image. A reference image acquisition means for acquiring a reference image which is the original image of the printed material, An inspection processing means performs an inspection process to detect defect candidates from the read image based on the difference between the reference image and the read image, A display means for displaying defect information based on defect candidates, excluding those defect candidates that have been determined to be caused by the reading process, It further possesses The image processing apparatus according to feature 1.

11. The streak detection means determines whether the cause of the streak is a printing-related cause that occurred when the printed material was printed, or a reading-related cause that occurred when the printed material was read as the read image. A reference image acquisition means for acquiring a reference image which is the original image of the printed material, An inspection processing means performs an inspection process to detect defect candidates from the read image based on the difference between the reference image and the read image, A display means that can distinguish between the defect candidates determined to be caused by printing and the defect candidates determined to be caused by reading, It further possesses The image processing apparatus according to feature 1.

12. A control method for an image processing device used to inspect printed materials, A reading image acquisition step involves obtaining a read image obtained by reading the aforementioned printed material, A streak acquisition step involves acquiring streaks included in the region corresponding to the printed material in the read image, A streak determination step in which the cause of the streak is determined based on the characteristic quantities of the streak, A control method for an image processing apparatus, characterized by having the following features.

13. A program for causing a computer to function as one of the means of an image processing apparatus according to any one of claims 1 to 11.

Images