Information processing apparatus, information processing method, and program

Abstract

To inform the possibility of excessive detection of defects and undetected defects in a result of inspection of a print.SOLUTION: An information processing apparatus has: inspection means that performs defect detection processing on an inspection image obtained by reading a print to inspect the presence or absence of a defect in the inspection image; evaluation means that performs evaluation on excessive detection of defects or undetected defects in a result of the detection processing; and display control means that performs control to display an inspection result from the inspection means and an evaluation result from the evaluation means in association with each other.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to the inspection of printed matter. [Background technology]

[0002] One method for inspecting printed matter is to detect defects by using the difference between a reference image and an inspection image obtained by reading the printed matter using a sensor, etc. Patent Document 1 discloses a method for displaying the type of defect, the printing date and time, the inspection level, and the location of the defect together with the inspection results as related information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-169160 Summary of the Invention [Problem to be solved by the invention]

[0004] When detecting defects from inspection images, overdetection, where a defect is mistakenly detected when there is none, and underdetection, where a defect is mistakenly detected when there is none, can occur. In the inspection of printed matter, it is important to prevent overdetection and underdetection. However, the method disclosed in Patent Document 1 does not allow knowledge of the possibility of overdetection or underdetection from the inspection results of printed matter and related information.

[0005] Therefore, an object of the present invention is to notify the user of the possibility of overdetection or underdetection of defects in the inspection results of printed matter. [Means for solving the problem]

[0006] The information processing device according to the present invention is characterized by having an inspection means for performing a defect detection process on an inspection image obtained by reading a printed material and inspecting the presence or absence of defects in the inspection image, an evaluation means for evaluating the results of the detection process regarding overdetection or non-detection of defects, and a display control means for controlling the display of the inspection results by the inspection means and the evaluation results by the evaluation means in association with each other. [Effects of the Invention]

[0007] According to the present invention, it is possible to notify the user of the possibility of overdetection or underdetection of defects in the inspection results of printed matter. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating inspection of a printed matter. [Figure 2] FIG. 1 is a diagram illustrating an example of the overall configuration of a print inspection system. [Figure 3] FIG. 2 illustrates an example of the internal configuration of a cloud server. [Figure 4] FIG. 2 is a diagram illustrating an example of a functional configuration of an image processing apparatus. [Figure 5] 10 is a flowchart showing an image inspection process. [Figure 6] FIG. 10 is a diagram showing an example of an examination result screen. [Figure 7] 10 is a flowchart illustrating an evaluation value calculation process. [Figure 8] 10 is a flowchart illustrating an evaluation value calculation process. [Figure 9] 10 is a flowchart illustrating an evaluation value calculation process. [Figure 10] 10 is a flowchart illustrating an evaluation value calculation process. [Figure 11] 10 is a flowchart illustrating an evaluation value calculation process. [Figure 12] 10 is a flowchart illustrating an evaluation value calculation process. [Figure 13] FIG. 2 is a diagram illustrating an example of a functional configuration of an image processing apparatus. [Figure 14] FIG. 10 is a diagram showing an example of an examination result screen. [Figure 15] FIG. 2 is a diagram illustrating an example of a functional configuration of an image processing apparatus. [Figure 16] FIG. 10 is a diagram showing an example of an examination result screen. [Figure 17] FIG. 2 is a diagram illustrating an example of a functional configuration of an image processing apparatus. [Figure 18] 10 is a flowchart showing an image inspection process. [Figure 19] FIG. 10 is a diagram illustrating an example of a setting screen. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Note that the following embodiments do not limit the present invention, and not all of the combinations of features described in the embodiments are necessarily essential to the solution of the present invention.

[0010] [Embodiment 1] First, overdetection will be explained using Figure 1. Figure 1(a) shows a schematic diagram of a reference image of a print in which a picture 102 is printed on a print medium 101. Figure 1(c) shows the results of reading pixel values ​​near the edge of the picture 102 along a horizontal line 103 in Figure 1(a). The vertical axis of Figure 1(c) represents pixel values ​​(0 to 255), and the horizontal axis represents positions on the horizontal line 103. Pixel value 107 represents the pixel value of the print medium 101. Pixel value 109 represents the pixel value of the picture 102. Pixel position 108 represents the pixel position that is intermediate between pixel value 107 and pixel value 109.

[0011] FIG. 1(b) shows a schematic diagram of an inspection image of a print in which a pattern 105 is printed on a print medium 104. FIG. 1(d) shows the results of reading pixel values ​​near the edge of the pattern 105 along a horizontal line 106 in FIG. 1(b). The vertical axis of FIG. 1(d) represents pixel values ​​(0 to 255), and the horizontal axis represents positions on the horizontal line 106. Pixel value 110 represents the pixel value of the print medium 104. Pixel value 112 represents the pixel value of the pattern 105. Pixel position 111 represents the pixel position that is intermediate between pixel value 110 and pixel value 112.

[0012] Figure 1(e) shows the pixel value profile shown in Figure 1(c) and the pixel value profile shown in Figure 1(d) after alignment. For ease of understanding, assume that pixel position 108 and pixel position 111 are aligned so that they overlap at pixel position 113. Figure 1(f) shows the results of calculating the difference values ​​of corresponding pixels from the aligned profile shown in Figure 1(e). Pixel value difference 114 indicates the change from the pixel position where the gradient of pixel value 107 changes to pixel position 113. Pixel value difference 115 indicates the change from pixel position 113 to the pixel position where the gradient of pixel value 109 stops changing. Even when alignment is correct, differences between the gradients of pixel values ​​in the edge region of the reference image and the edge region of the inspection image can result in larger-than-expected differences. Therefore, pixel value differences due to gradient differences in edge regions can be mistakenly detected as defects. In other words, overdetection is prone to occur in edge regions.

[0013] In this embodiment, a method is described in which an inspection image is inspected by performing defect detection processing on the inspection image and the inspection results are displayed, and the results of an evaluation of the possibility of overdetection of defects in the inspection image are also displayed.

[0014] 2 is a diagram showing the overall configuration of a print inspection system that outputs and inspects printed matter, including an image processing device 200 according to this embodiment. The print inspection system includes the image processing device 200, a printing server 280, and a printing device 290.

[0015] The printing server 280 generates a print job including a document to be printed, and submits the print job to the printing device 290. The printing device 290 forms an image on a print medium based on the print job submitted from the printing server 280. The printing device 290 can use a printing method such as an inkjet method or an electrophotographic method. The printing device 290 has a paper feed unit 291, and a user can supply printing paper to the paper feed unit 291 in advance. When a print job is submitted, the printing device 290 forms an image on one or both sides of the recording medium while transporting the recording medium supplied to the paper feed unit 291 along a transport path 292, and sends the image to the image processing device 200.

[0016] The image processing device 200 inspects a recording medium (printed matter) on which printing has been performed. The image processing device 200 is an example of an information processing device. The printed matter is obtained by printing an image on a recording medium by a printing device 290, and is transported from the printing device 290 to the image processing device 200 via an internal transport path 292.

[0017] The image processing device 200 has a CPU 201, a RAM 202, a ROM 203, an image reading device 204, a network I / F (interface) 205, a printing device I / F 206, a general-purpose I / F 207, a UI panel 208, and a main bus 209. Furthermore, the image processing device 200 may have a recording medium transport path 210 connected to a transport path 292 of the printing device 290.

[0018] The image processing device 200 may also include an output tray 211 to which printed materials that have been determined to pass inspection are output, and an output tray 212 to which printed materials that have been determined to fail inspection are output. The image processing device 200 may also include an output tray 213 for which the user can specify a usage purpose. The three output trays 211, 212, and 213 are connected to the CPU 201 via the main bus 209. The CPU 201 assigns printed materials to one of the three output trays 211, 212, or 213 depending on whether the inspection result of the printed materials is pass or fail, or on conditions specified by the user.

[0019] The image processing device 200 according to each embodiment described below can be realized by a computer including a processor and a memory. A processor such as a CPU 201 executes a program stored in a memory such as a ROM 203 to realize the processing shown in the flowchart of the image inspection processing described below. Note that the image processing device may be configured by a plurality of processing devices connected via a network, for example.

[0020] The CPU 201 controls each unit within the image processing device 200. The CPU 201 also controls the entire print inspection system including the image processing device 200. The RAM 202 functions as the main memory, work area, etc. of the CPU 201. The RAM 202 also temporarily stores data used in the image inspection process. The ROM 203 stores various data used in the image inspection process in addition to the group of programs executed by the CPU 201.

[0021] The image reading device 204 reads one or both sides of the printed material sent from the printing device 290 on the conveying path 210 and acquires the read image data. The acquired read image data may be temporarily stored in a buffer area on the RAM 202. From the read image data acquired by the image reading device 204, an inspection image that is the target of defect detection processing is created.

[0022] The transport path 210 serves as the background when the image reading device 204 reads the image on the recording medium, and therefore may be made of a material of a color (for example, black) that is easily distinguishable from the recording medium in the image. The network I / F 205 is an interface having at least one of wired and wireless communication modes, and communicates with external devices via a communication path corresponding to the communication mode used. The network I / F 205 may also be an interface for connecting to the Internet. The image processing device 200 may transmit and receive various control instructions and image data to and from external devices on the Internet via the network I / F 205.

[0023] The printing device I / F 206 is connected to the printing device 290, and the image processing device 200 can communicate with the printing device 290 through the printing device I / F 206. For example, by synchronizing the printing device 290 and the image processing device 200 via the printing device I / F 206, the printing device 290 and the image processing device 200 can acquire each other's operating status.

[0024] The general-purpose I / F 207 is a serial bus interface such as USB or IEEE 1394. The UI panel 208 is connected to the main bus 209 via the general-purpose I / F 207. The UI panel 208 is, for example, a liquid crystal display, and functions as a user interface for the image processing device 200. The UI panel 208 displays information related to the current status, settings, and inspection results of the print inspection system. The UI panel 208 also displays a reference image used for comparison with the inspection image, an inspection image in which no defects were detected and judged to be pass, and an inspection image in which defects were detected and judged to be fail. The UI panel 208 may also be equipped with an input device such as a touch panel, a mouse, or buttons, and may accept instructions from the user. The main bus 209 is a transmission path that connects the modules of the image processing device 200 .

[0025] While the printed matter output from the printing device 290 is being conveyed along the conveying path 210, the image processing device 200 performs a defect detection process based on image data read by the image reading device 204 to determine whether the printed matter passes or fails. If the printed matter is determined to pass, it is conveyed to the output tray 211. If the printed matter is determined to fail, it is conveyed to the output tray 212. By this operation, only printed matters that are determined to pass (no defects detected) are output onto the output tray 211.

[0026] In the print inspection system according to this embodiment, an example will be described in which the image processing device 200 executes the processing shown in the flowchart described below. As another example, a case will be described in which all or part of the processing shown in the flowchart of the image inspection processing described below is executed by a cloud server 300 connected via the Internet via the network I / F 205 of the image processing device 200. In this case, the cloud server 300 is an example of an information processing device.

[0027] FIG. 3 shows an example of the hardware configuration of the cloud server 300. The cloud server 300 shown in Fig. 3 is one or more server devices that provide cloud services over the Internet. The cloud server 300 receives image data acquired by the image reading device 204 of the image processing device 200, performs image inspection processing, and transmits inspection results obtained by performing defect detection processing and an evaluation value indicating the possibility of overdetection of defects to the image processing device 200 as needed. The cloud server 300 may also control an inspection result screen (described later) to be displayed on a terminal device on the Internet. The cloud server 300 has a CPU 301, a RAM 302, a ROM 303, a storage device 304, and a network I / F 305. The components are connected to each other by a system bus 307.

[0028] The CPU 301 uses the RAM 302 as a work memory, executes programs stored in the ROM 303, etc., and comprehensively controls each component of the cloud server 300 via a system bus 307. The storage device 304 is, for example, an HDD or SSD, and stores various data handled by the cloud server 300. The CPU 301 writes data to the storage device 304 and reads data stored in the storage device 304 via the system bus 307. The network I / F 305 is an interface for connecting to the Internet. The cloud server 300 transmits and receives various control instructions and image data to and from the image processing device 200 via the network I / F 305. The cloud server 300 may also provide an examination result screen (described later) to a terminal device on the Internet via the network I / F 305.

[0029] Cloud server 300 may be configured by a single server device or multiple server devices. Furthermore, the functions of multiple server devices may be realized by a single server device using virtualization software. Cloud server 300 may also be interconnected with printing device 290 in addition to image processing device 200 to manage print jobs and inspection results.

[0030] FIG. 4 shows an example of the functional configuration of an image processing device 200 according to this embodiment. The image processing device 200 functions as a print image creation unit 401, an image reading unit 402, a reference image creation unit 403, an inspection unit 404, an inspection evaluation unit 405, and an inspection result display unit 406 by the CPU 201 executing a program stored in the ROM 203 or the like. The print image creation unit 401 creates RIP data from the original data of the print, and uses the printing device 290 to print an image based on the RIP data to create a print.

[0031] The image reading unit 402 creates an inspection image from image data obtained by reading the printout printed by the print image creation unit 401 with the image reading device 204 . The reference image creation unit 403 creates a reference image using RIP data created from the original data of the printed matter. Alternatively, the reference image creation unit 403 may create a reference image from an inspection image obtained by the image reading unit 402. The method for creating the reference image can be arbitrarily specified by the user. The inspection unit 404 performs defect detection processing based on the difference between the inspection image created by the image reading unit 402 and the reference image created by the reference image creation unit 403, thereby determining whether the inspection image passes or fails, and outputs inspection results including the pass / fail determination result.

[0032] The inspection evaluation unit 405 evaluates the results of the defect detection process performed by the inspection unit 404 and outputs information about the evaluation result. In this embodiment, the information about the evaluation result is expressed as a numerical value. Hereinafter, the numerical value representing the evaluation result will be referred to as an evaluation value. The test result display unit 406 controls the UI panel 208 to display the test results from the test unit 404 in association with the evaluation value from the test evaluation unit 405. The test result display unit 406 is an example of a display control means.

[0033] 5 is a flowchart showing image inspection processing executed by the image processing device 200 according to this embodiment. The processing of this flowchart is realized by the CPU 201 loading a program stored in a memory such as the ROM 203 into the RAM 202 and executing it. In the following description, each process (step) is represented by adding an S to the beginning, and the notation of the process (step) is omitted.

[0034] In S501, the reference image creation unit 403 inputs RIP data created from document data or an inspection image, performs correction processing according to the input data, and creates a reference image. The reference image is then read into the RAM 202 or the like. In this embodiment, the reference image is in RGB 8-bit format. When RIP data is input, correction processing includes color conversion, fine line correction, and local distortion correction processing. When an inspection image is input, correction processing includes alignment processing and noise removal processing. Various parameters required for correction processing may be set based on user operations on the UI panel 208.

[0035] In S502, the image reading unit 402 creates an inspection image from the scanned image data obtained by reading the printout printed by the print image creation unit 401 with the image reading device 204. The inspection image is then read into the RAM 202 or the like. In this embodiment, the inspection image is in an RGB 8-bit format. When creating the inspection image from the printout, brightness correction processing or the like may be performed to increase the similarity with the reference image.

[0036] In S503, the inspection unit 404 performs an inspection process. The inspection unit 404 first aligns the reference image created in S501 with the inspection image created in S502 to generate a difference image showing the differences between the reference image and the inspection image, and then performs a defect detection process based on the difference image. The difference image is generated by comparing the reference image and the inspection image pixel by pixel and obtaining the difference in pixel values ​​(e.g., density values ​​for each RGB value) for each pixel. The inspection unit 404 then compares the pixel values ​​of the difference image with a detection sensitivity threshold and detects areas exceeding the detection sensitivity threshold as defective areas. The results of the defect detection process include the presence or absence of a defect, the detected position of the defect, the amount of misalignment, the type of defect, the difference image, etc. The amount of misalignment represents the misalignment between the reference image and the inspection image during the alignment process. The inspection unit 404 also determines whether the image is pass or fail based on the presence or absence of a defect. It is possible to classify the images into three or more types, rather than just two types (pass and fail). The inspection results include the results of the defect detection process and a pass / fail determination result.

[0037] In S504, the inspection evaluation unit 405 calculates an evaluation value that indicates the possibility of overdetection from the result of the defect detection process obtained in S503. The flow of the evaluation value calculation process will be described in detail later. In S505, the CPU 201 determines whether to end the inspection. If there are any printed materials remaining to be inspected, the CPU 201 returns to S502 to continue the inspection, and if there are no more printed materials remaining to be inspected, the CPU 201 proceeds to S506. In S506, the test result display unit 406 arranges the test results obtained in S503 and the evaluation values ​​obtained in S504 on a test result screen in association with each other, and displays the test result screen on the UI panel 208. Fig. 6 shows an example of the test result screen. After that, the series of processes in this flowchart ends.

[0038] FIG. 6 shows an example of an examination result screen according to this embodiment. The inspection result screen 600 includes an inspection result list 620 that displays a list of inspection results and evaluation values ​​for multiple inspection images inspected in the image inspection process. The inspection image name 601 column of the inspection result list 620 displays the image name assigned to each inspection image for identification. The inspection result 602 column of the inspection result list 620 displays the pass / fail result determined by the inspection unit 404. The evaluation result 603 column displays the evaluation value calculated by the inspection evaluation unit 405. If multiple defects are detected in a single inspection image, a representative value (e.g., a statistical value such as the average, maximum, minimum, or median) of the evaluation value for each defect may be displayed. Here, a higher evaluation value indicates a higher possibility of overdetection, and a lower evaluation value indicates a lower possibility of overdetection. Furthermore, if the evaluation value exceeds a reference value, the inspection result display unit 406 may display text data indicating a high possibility of overdetection.

[0039] The inspection result screen 600 also has an inspection image display window 604 for displaying an inspection image. The inspection image display window 604 displays an inspection image 605 selected from the inspection result list 620. FIG. 6 shows an example of a display when a row 608 in which the inspection image name 601 is "Image 3" is selected by the user. Two objects 606 and 607 are displayed corresponding to the respective positions and sizes of two defects in the inspection image 605. The objects 606 and 607 are displayed in shades of color according to a color bar 611. Here, a darker color indicates a higher evaluation value, and a lighter color indicates a lower evaluation value. The object 606 is shown as an example of a defect with a high evaluation value, and the object 607 is shown as an example of a defect with a low evaluation value. The objects displayed corresponding to the positions and sizes of the defects in the inspection image 605 may be displayed in different ways depending on the type of defect.

[0040] The inspection result screen 600 also has a detailed result list 630 that displays a list of evaluation values ​​for multiple defects detected in the inspection image 605 currently being displayed in the inspection image display window 604. The evaluation result 609 column of the detailed result list 630 displays the evaluation value of each defect detected in the currently displayed inspection image 605. The defect ID 610 column of the detailed result list 630 displays an ID for identifying each defect detected in the currently displayed inspection image 605.

[0041] 7 shows a flowchart of the evaluation value calculation process executed in S504 according to this embodiment. For simplicity of explanation, the following will describe a case where only one defect is detected from the inspection image in S503. In S701, the inspection evaluation unit 405 inputs an inspection image, calculates the edge region and texture region of the inspection image, and creates a mask image with region classification. Region classification is performed using a known technique. While the inspection image is used in this embodiment, a reference image or RIP data may also be used.

[0042] In S702, the inspection evaluation unit 405 acquires the coordinates (x, y) of defects detected in the edge region and texture region using the differential image representing the difference between the reference image and the inspection image created in S503 and the mask image obtained in S701. x represents an arbitrary position in the horizontal direction of the two-dimensional data. y represents an arbitrary position in the vertical direction of the two-dimensional data. (x, y) represents the value of the position specified by x and y.

[0043] In S703, the inspection and evaluation unit 405 acquires the pixel value I(x, y) of the defect position from the difference image using the difference image created in S503 and the coordinates (x, y) of the defect acquired in S702. In S704, the inspection and evaluation unit 405 calculates the difference D(x, y) using the detection sensitivity threshold used in S503 and the pixel value I(x, y) at the defect position acquired in S703.

[0044] In S705, the inspection evaluation unit 405 calculates an evaluation value from the output value obtained by inputting the difference D(x, y) output in S704 into the following equation (1). Evaluation value = Max(Normal(D(x,y)))···Equation (1) Here, Normal(X) represents a process for outputting a value of a normal distribution for the random variable X. The possibility of overdetection increases as the difference in pixel values ​​approaches the detection sensitivity threshold. In the above formula (1), the smaller the difference D(x, y), the larger the value output. Max() represents a process for obtaining the maximum value output by Normal(X). Note that, in this embodiment, a method for calculating the evaluation value using the above formula (1) has been described, but the evaluation value may also be calculated using other probability distribution functions, lookup tables, etc. Furthermore, the output value from formula (1) may be used as the evaluation value directly, or a value scored on a scale of 1 to 10 may be used as the evaluation value. The processing of this flowchart then ends.

[0045] According to the evaluation value calculation process shown in FIG. 7 as described above, an evaluation value indicating the possibility of overdetection can be calculated for defects detected in edge regions and texture regions where overdetection is likely to occur.

[0046] 8 shows another example of the evaluation value calculation process executed in S504 according to this embodiment. As shown in the flowchart in FIG. 8, the inspection and evaluation unit 405 may calculate the evaluation value based on the number (size) of pixels in which defects are detected. First, the inspection and evaluation unit 405 executes the same processes as in S701 and S702. In S801, the inspection evaluation unit 405 acquires the coordinates (x, y) of the defect calculated in S702 and the number of pixels N of the coordinates of defects occurring around the defect. Note that the periphery of the coordinates (x, y) of the defect uses 4 or 8 neighbors. In S802, the inspection and evaluation unit 405 calculates an evaluation value from the output value obtained by inputting the number of pixels N acquired in S801 into the following equation (2). Evaluation value = Normal(N) Equation (2) Here, Normal(X) represents the process of outputting a value of the normal distribution for the random variable X. The larger the number of pixels (size) of the defect, the higher the possibility of overdetection. In the above formula (2), the larger the number of pixels N, the larger the value output. After that, the process of this flowchart ends.

[0047] According to the evaluation value calculation process shown in FIG. 8 as described above, an evaluation value indicating the possibility of overdetection can be calculated for defects detected in edge regions and texture regions where overdetection is likely to occur.

[0048] 9 shows another example of the evaluation value calculation process executed in S504 according to this embodiment. In the case of a positional misalignment defect caused by a positional misalignment between the reference image and the inspection image, the inspection evaluation unit 405 may calculate an evaluation value based on the amount of positional misalignment, as shown in the flowchart of FIG. In S901, the inspection and evaluation unit 405 acquires the positional misalignment amount Gap calculated in S503. In S902, the inspection evaluation unit 405 calculates an evaluation value from the output value obtained by inputting the positional misalignment amount Gap into the following formula (3): Then, the processing of this flowchart ends. Evaluation value = Normal(Gap) Equation (3) Here, Normal(X) represents a process of outputting a value of a normal distribution in the random variable X. The larger the amount of positional deviation, the higher the possibility of overdetection. In the above formula (3), the larger the amount of positional deviation Gap, the larger the value output.

[0049] According to the evaluation value calculation process shown in FIG. 9 as described above, an evaluation value indicating the possibility of overdetection can be calculated for a positional displacement defect caused by a positional displacement between the reference image and the inspection image.

[0050] 10 shows another example of the evaluation value calculation process executed in S504 according to this embodiment. As shown in the flowchart in FIG. 10, the inspection and evaluation unit 405 may calculate the evaluation value based on the number of feature points used for alignment. In S1001, the inspection and evaluation unit 405 calculates the number F of feature points to be used in the alignment process from the inspection image. Note that the inspection and evaluation unit 405 may calculate the number F of feature points to be used in the alignment process in advance using a reference image.

[0051] In S1002, the inspection evaluation unit 405 calculates an evaluation value from the output value obtained by inputting the number F of feature points, which is the output of S1001, into the following equation (4). Evaluation value = Normal(F) Equation (4) Here, Normal(X) represents a process that outputs a value of a normal distribution in the random variable X. The fewer the number of feature points used for alignment, the higher the possibility of overdetection. In the above formula (4), the smaller the number F of feature points used for alignment processing, the larger the value output. Then, the process of this flowchart ends.

[0052] According to the evaluation value calculation process shown in FIG. 10 as described above, an evaluation value indicating the possibility of overdetection can be calculated for a positional displacement defect caused by a positional displacement between the reference image and the inspection image.

[0053] 11 shows another example of the evaluation value calculation process executed in S504 according to this embodiment. In the case of a density change defect caused by a difference in density change between the reference image and the inspection image, the inspection evaluation unit 405 may calculate an evaluation result based on the amount of density change, as shown in the flowchart in FIG. In S1101, the inspection and evaluation unit 405 calculates the difference between the printed portion of the reference image and the printed portion of the inspection image, and calculates the density change amount Den(x, y). In S1102, the inspection and evaluation unit 405 calculates an evaluation value from the output value obtained by inputting the density change amount Den(x, y) output in S1101 into the following equation (5). Evaluation value = Max(Normal(Den(x, y)))···Equation (5) Here, Normal(X) represents the process of outputting a value of the normal distribution for the random variable X. The greater the density difference between the reference image and the test image, the higher the possibility of overdetection. In the above formula (5), the greater the density difference Den(x, y), the larger the value output. After that, the process of this flowchart ends.

[0054] According to the evaluation value calculation process shown in FIG. 11 as described above, an evaluation value indicating the possibility of overdetection can be calculated for density change defects caused by the difference in density change between the reference image and the inspection image.

[0055] According to the present embodiment, it is possible to calculate and display the possibility of overdetection of defects in printed matter. This allows the user to know the possibility of overdetection of defects in printed matter. Therefore, by performing reinspection, it is expected that waste paper can be reduced.

[0056] [Variation 1] In the above-described first embodiment, a method for calculating an evaluation value representing the possibility of overdetection was described, but in the modified example 1, a method for calculating an evaluation value representing the possibility of non-detection will be described. In the following, a description of the same configuration as in the first embodiment will be omitted, and the differences from the first embodiment will be mainly described.

[0057] 12 shows a flowchart of the evaluation value calculation process executed in S504 according to this modified example. In the evaluation value calculation process according to this modified example, an evaluation value indicating the possibility of non-detection is calculated. For simplicity of explanation, a case where only one defect is detected from the inspection image in S503 will be described. In S1201, the inspection evaluation unit 405 acquires the coordinates (x, y) of the area where no defect is detected using the difference image representing the difference between the reference image and the inspection image created in S503 and information on the defect detection position. In S1202, the inspection evaluation unit 405 calculates the difference I(x, y) using the pixel value of the difference image corresponding to the coordinates (x, y) acquired in S1201 and the detection sensitivity threshold used in S503.

[0058] In S1203, the inspection evaluation unit 405 calculates an evaluation value from the output value obtained by inputting the difference I(x, y) output in S1202 into the following equation (6). Evaluation value = Max(Normal(D(x,y)))···Eq. (6) Here, Normal(X) represents a process for outputting a value of a normal distribution for the random variable X. The possibility of non-detection increases as the difference in pixel values ​​approaches the detection sensitivity threshold. In the above formula (6), the smaller the difference D(x, y), the larger the value output. Max() represents a process for obtaining the maximum value output by Normal(X). Note that in this modified example, a method for calculating an evaluation value using the above formula (6) has been described, but the evaluation value may also be calculated using other probability distribution functions, lookup tables, etc. After that, the process of this flowchart ends.

[0059] In addition, it may be difficult to distinguish between noise and defects in high-frequency patterns. Therefore, the inspection and evaluation unit 405 may calculate an evaluation value using frequency information of the print area from the inspection image or reference image. For example, if there are many high-frequency components, a large value is output as the evaluation value, and if there are few high-frequency components, a small value is output.

[0060] According to this modified example, it is possible to calculate and display the possibility that defects in printed matter will remain undetected in the detection results. This allows the user to know the possibility that defects in printed matter will remain undetected in the detection results. Therefore, by performing a re-inspection, it is expected that oversights will be reduced.

[0061] The test result display unit 406 may display either the evaluation value representing the possibility of overdetection or the evaluation value representing the possibility of underdetection, or may display both, or may combine the evaluation value representing the possibility of overdetection and the evaluation value representing the possibility of underdetection and display them as a single numerical value. The inspection result display unit 406 may also display an object representing the possibility of undetection in association with the position and size of the defect in the inspection image displayed in the inspection image display window. The color of this object may be varied depending on the magnitude of the evaluation value representing the possibility of undetection.

[0062] [Embodiment 2] This embodiment describes a method for changing the inspection results to be displayed in accordance with conditions set for each defect type. Below, a description of the same configuration as in embodiment 1 will be omitted, and the differences from embodiment 1 will be mainly described. Note that here, as in embodiment 1, a case where the possibility of overdetection is evaluated will be described.

[0063] FIG. 13 shows an example of the functional configuration of an image processing device 200 according to this embodiment. The image processing device 200 has a print image creation unit 401, an image reading unit 402, a reference image creation unit 403, an inspection unit 404, an inspection evaluation unit 405, an inspection result display unit 1302, and an inspection result search unit 1301. It differs from the first embodiment in that it has the inspection result display unit 1302 and the inspection result search unit 1301 instead of the inspection result display unit 406. The test result search unit 1301 searches for test results that correspond to conditions specified by user operations on the UI panel 208, and outputs information on the search results. The test result display unit 1302 controls the display of the test results in association with the evaluation values, based on the search results of the test result search unit 1301. The test result display unit 1302 is an example of a display control means.

[0064] FIG. 14 shows an example of the test result screen according to this embodiment. The inspection result screen 1400 according to this embodiment is a UI that accepts the specification of search conditions for inspection results and displays the search results. The inspection result screen 1400 is provided with an inspection result list 1410 that displays a list of inspection results and their evaluation values ​​for multiple inspection images inspected by image inspection processing. The defect 1401 column in the inspection result list 1410 displays the type name of the defect in each inspection image detected by the inspection unit 404.

[0065] Furthermore, the inspection result screen 1400 displays display options 1420 for specifying the conditions for the inspection results to be displayed in the inspection result list 1410. If the pass check box 1402 in the display options 1420 is checked, the inspection results and their evaluation values ​​for the inspection images that passed are displayed in the inspection result list 1410. If the fail check box 1403 in the display options 1420 is checked, the inspection results and their evaluation values ​​for the inspection images that failed are displayed in the inspection result list 1410. The toggle button 1409 is a button for sorting the data in the corresponding column in ascending or descending order.

[0066] The dot defect check box 1404 in the display options 1420 is enabled when the fail check box 1403 is checked. When the dot defect check box 1404 is checked, the inspection result list 1410 displays the inspection results of the inspection image containing the dot defect (point-like defect) and its evaluation value. The vertical streak defect check box 1405 is enabled when the reject check box 1403 is checked. When the vertical streak defect check box 1405 is checked, the inspection result list 1410 displays the inspection results of the inspection image containing the vertical streak defect (vertical stripe defect) and its evaluation value. The horizontal streak defect check box 1406 is enabled when the reject check box 1403 is checked. When the horizontal streak defect check box 1406 is checked, the inspection result list 1410 displays the inspection results of the inspection image containing the horizontal streak defect (horizontal stripe defect) and its evaluation value. The density change defect check box 1407 is enabled when the fail check box 1403 is checked. When the density change defect check box 1407 is checked, the inspection result list 1410 displays the inspection results of the inspection image containing the density change defect and its evaluation value. The misalignment defect check box 1408 is enabled when the reject check box 1403 is checked. When the misalignment defect check box 1408 is checked, the inspection result list 1410 displays the inspection results of the inspection image containing the misalignment defect and its evaluation value.

[0067] The inspection result screen 1400 may display a UI for changing the detection sensitivity threshold settings for each defect type.

[0068] According to the present embodiment as described above, it is possible to check whether overdetection is likely to occur for each type of detected defect, which allows measures such as changing the defect detection sensitivity depending on the type of defect.

[0069] In the present embodiment, an example has been described in which inspection results and their evaluation values ​​are displayed in a list for each type of defect. However, the inspection results and their evaluation values ​​may be tallied for each type of defect, and the tallied results may be displayed for each type of defect. Alternatively, text data corresponding to the tallied results may be displayed. For example, a message indicating that there is a high possibility of overdetection of small defects or recommending changing the detection sensitivity for small defects may be displayed.

[0070] [Embodiment 3] In this embodiment, a method will be described in which a threshold value is set for the evaluation value, and the pass / fail result of the inspection image is re-determined based on the threshold value and the evaluation value, and the result is displayed. In the following, a description of the same configuration as in embodiment 1 will be omitted, and the differences from embodiment 1 will be mainly described. Note that, as in embodiment 1, a case in which the possibility of overdetection is evaluated will be described.

[0071] FIG. 15 shows an example of the functional configuration of an image processing device 200 according to this embodiment. The image processing device 200 has a print image creation unit 401, an image reading unit 402, a reference image creation unit 403, an inspection unit 404, an inspection evaluation unit 405, an inspection result display unit 1502, and a threshold setting unit 1501. It differs from the first embodiment in that it has the inspection result display unit 1502 and the threshold setting unit 1501 instead of the inspection result display unit 406. A threshold setting unit 1501 sets a threshold for determining whether or not a defect is to be detected in response to a user's operation on the UI panel 208 . The inspection result display unit 1502 performs control so as to display the results of re-determining the pass / fail of the inspection image, excluding defects having evaluation values ​​equal to or greater than the threshold set by the threshold setting unit 1501. The inspection result display unit 1502 is an example of a display control means.

[0072] FIG. 16 shows an example of the test result screen according to this embodiment. The inspection result screen 1600 according to this embodiment is a UI that displays the results of a re-determination of the pass / fail status of the inspection image based on the threshold value and the evaluation value. The inspection result screen 1600 is provided with a check box 1601 and a numerical value input box 1602. When the check box 1601 is checked, it is enabled for the inspection unit 404 to re-determine whether the inspection image passes or fails based on the threshold value and the evaluation value. When the evaluation value of a defect is equal to or greater than the threshold value specified in the numerical value input box 1602, the inspection unit 404 excludes the defect from the detection results and re-determines whether the inspection image passes or fails. When all defects have been excluded and no defects remain, the inspection unit 404 determines that the inspection image passes. Furthermore, when the evaluation value of a defect is less than the threshold value specified in the numerical value input box 1602, the inspection unit 404 determines that the inspection image fails.

[0073] The inspection result screen 1600 also has an inspection result list 1670 that displays a list of the inspection results and evaluation values ​​for multiple inspection images inspected in the image inspection process. In the inspection result list 1670, a column of inspection results after re-determination 1603 displays the results of a re-determination of pass / fail for the defect detection results of the inspection image based on the threshold value specified in the numeric value input box 1602.

[0074] According to the present embodiment, even if a printed matter is judged to be unacceptable, it can be judged as acceptable if there is a high possibility of overdetection. This is expected to reduce paper waste.

[0075] [Embodiment 4] In the fourth embodiment, a method for changing the paper discharge destination based on an evaluation value for defects detected from an inspection image will be described. The following description will focus on the differences from the first embodiment, omitting the description of the same configuration as the first embodiment. Note that, as in the first embodiment, the case where the possibility of overdetection is evaluated will be described.

[0076] FIG. 17 shows an example of the functional configuration of an image processing device 200 according to this embodiment. The image processing device 200 has a print image creation unit 401, an image reading unit 402, a reference image creation unit 403, an inspection unit 404, an inspection evaluation unit 405, and a paper discharge destination selection unit 1701. It differs from the first embodiment in that it has the paper discharge destination selection unit 1701 instead of the inspection result display unit 406. The paper discharge destination selection unit 1701 selects an output tray for paper discharge based on the evaluation value of defects detected from the inspection image. The output tray for paper discharge is specified by a user operation on the UI panel 208.

[0077] FIG. 18 is a flowchart showing the image inspection process executed by the image processing device 200 according to this embodiment. In S1801, the discharge destination selection unit 1701 displays a setting screen for setting a discharge destination to be selected based on an evaluation value corresponding to the inspection result on the UI panel 208. After that, the same processes as in S501 to S505 of Figs. 18 are executed, and the series of processes in the flowchart of Fig. 18 is completed.

[0078] FIG. 19 shows an example of a setting screen for setting the paper discharge destination. The pass output tray name 1901 indicates the name of the output tray 211 to which printed materials determined to be pass are output. The fail output tray name 1902 indicates the name of the output tray 212 to which printed materials determined to be fail are output. The intermediate output tray name 1903 is enabled when the check box 1905 is checked, and indicates the name of the output tray 213 to which printed materials whose evaluation value is equal to or greater than the threshold value input in the numerical value input box 1906 are output. If the evaluation value is less than the threshold value, the paper is discharged to the output tray 212. Note that if the intermediate output tray name 1903 is the same as the pass output tray name 1901 or the fail output tray name 1902, printed materials whose evaluation value is equal to or greater than the threshold value may be distinguished from other printed materials by shifting the paper discharge position, inserting paper, or the like. The numerical value input box 1906 can be specified by the user by operating the UI panel 208.

[0079] The above process makes it possible to aggregate printed materials that are likely to be overdetected. This makes it possible to re-inspect only the aggregated printed materials, which is expected to result in efficient re-inspection.

[0080] In another variation, the inspection evaluation unit 405 may calculate an evaluation value representing the possibility of overdetection or non-detection based on an output value obtained by inputting an inspection image into a learning model trained using inspection images that were actually overdetected or non-detected. Furthermore, the inspection evaluation unit 405 may perform additional training on the learning model using inspection images that were overdetected or non-detected by visual re-inspection.

[0081] (Other embodiments) The present invention can also be realized by supplying a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) that realizes one or more functions.

[0082] The disclosure of each of the above-described embodiments includes the following configurations, methods, and programs. (Configuration 1) an inspection means for performing a defect detection process on an inspection image obtained by reading a printed material and inspecting the inspection image for the presence or absence of defects; an evaluation means for evaluating the result of the detection process with respect to overdetection or underdetection of defects; a display control means for controlling the display of the inspection result by the inspection means and the evaluation result by the evaluation means in association with each other; An information processing device comprising: (Configuration 2) 2. The information processing apparatus according to configuration 1, wherein the display control means controls to display an object representing the evaluation result in association with the position of the defect in the inspection image. (Configuration 3) 3. The information processing apparatus according to configuration 1 or 2, wherein the display control means controls the display of the inspection results and the evaluation results for each type of detected defect. (Configuration 4) the evaluation result represents a numerical value indicating the possibility of overdetection or underdetection of a defect; The method further includes setting means for setting a threshold value for the evaluation result, the inspection means re-inspects the inspection image for defects based on the evaluation result and the threshold value; 4. The information processing device according to any one of configurations 1 to 3, wherein the display control means controls the display of the results of the re-inspection by the inspection means. (Configuration 5) 5. The information processing apparatus according to any one of configurations 1 to 4, further comprising a change unit that changes the destination of the printed matter based on the evaluation result. (Configuration 6) 6. The information processing apparatus according to any one of configurations 1 to 5, wherein the inspection means performs the detection process based on a difference image that represents a difference between the inspection image and a reference image. (Configuration 7) 7. The information processing apparatus according to configuration 6, wherein the evaluation means performs evaluation regarding overdetection of a defect based on pixel values ​​of the difference image corresponding to the position of the defect detected by the detection process. (Configuration 8) 7. The information processing apparatus according to configuration 6, wherein the evaluation means performs evaluation regarding non-detection of a defect based on pixel values ​​of the differential image corresponding to positions where no defect was detected by the detection process. (Configuration 9) 7. The information processing apparatus according to configuration 6, wherein the evaluation means performs evaluation regarding overdetection of defects based on the number of pixels corresponding to the positions of defects detected by the detection process. (Configuration 10) the difference image is generated by performing a registration process on the inspection image and the reference image; 7. The information processing apparatus according to configuration 6, wherein the evaluation means performs evaluation regarding overdetection of defects based on the amount of positional deviation in the alignment process between the inspection image and the reference image. (Configuration 11) the difference image is generated by performing a registration process on the inspection image and the reference image; 7. The information processing apparatus according to configuration 6, wherein the evaluation means performs evaluation regarding overdetection of defects based on the number of feature points used in the alignment process between the inspection image and the reference image. (Configuration 12) 7. The information processing apparatus according to configuration 6, wherein the evaluation means performs evaluation regarding overdetection of defects based on the difference in density change between the inspection image and the reference image. (Configuration 13) The information processing device according to any one of configurations 1 to 12, wherein the evaluation means performs evaluation regarding overdetection or underdetection of defects based on output values ​​obtained by inputting the inspection image into a learning model trained using images in which defects have been overdetected or underdetected. (Configuration 14) The information processing device described in any one of configurations 1 to 13, characterized in that the display control means controls to display text data representing the evaluation results by the evaluation means, or text data representing the results of aggregating the evaluation results by defect type, in correspondence with the inspection results by the inspection means, or the aggregated results of the inspection results by defect type. (method) an inspection step of performing a defect detection process on an inspection image obtained by reading the printed matter, and inspecting the inspection image for the presence or absence of defects; an evaluation step of evaluating the result of the detection process regarding overdetection or underdetection of defects; a display control step of controlling the display of the inspection result from the inspection step and the evaluation result from the evaluation step in association with each other; An information processing method comprising: (program) Computer, an inspection means for performing a defect detection process on an inspection image obtained by reading a printed material and inspecting the inspection image for the presence or absence of defects; an evaluation means for evaluating the result of the detection process with respect to overdetection or underdetection of defects; a display control means for controlling the display of the inspection result by the inspection means and the evaluation result by the evaluation means in association with each other; A program characterized by functioning as [Explanation of symbols]

[0083] 200: Image processing device, 290: Printing device, 208: UI panel

Claims

1. an inspection means for performing a defect detection process on an inspection image obtained by reading a printed material and inspecting the inspection image for the presence or absence of defects; an evaluation means for evaluating the result of the detection process with respect to overdetection or underdetection of defects; a display control means for controlling the display of the inspection result by the inspection means and the evaluation result by the evaluation means in association with each other; An information processing device comprising:

2. 2. The information processing apparatus according to claim 1, wherein the display control means controls the display of an object representing the evaluation result in association with the position of the defect in the inspection image.

3. 2. The information processing apparatus according to claim 1, wherein the display control means controls the display of the inspection results and the evaluation results for each type of detected defect.

4. the evaluation result represents a numerical value indicating the possibility of overdetection or underdetection of a defect; The method further includes setting means for setting a threshold value for the evaluation result, the inspection means re-inspects the inspection image for defects based on the evaluation result and the threshold value; 2. The information processing apparatus according to claim 1, wherein the display control means controls the display of the results of the reinspection by the inspection means.

5. 2. The information processing apparatus according to claim 1, further comprising a change unit for changing a destination of the printed matter based on the evaluation result.

6. 2. The information processing apparatus according to claim 1, wherein the inspection means performs the detection process based on a difference image that represents a difference between the inspection image and a reference image.

7. 7. The information processing apparatus according to claim 6, wherein the evaluation means performs evaluation regarding overdetection of a defect based on pixel values ​​of the difference image corresponding to the position of the defect detected by the detection process.

8. 7. The information processing apparatus according to claim 6, wherein the evaluation means performs evaluation regarding non-detection of a defect based on pixel values ​​of the differential image corresponding to positions where no defect was detected by the detection process.

9. 7. The information processing apparatus according to claim 6, wherein the evaluation means performs evaluation regarding overdetection of defects based on the number of pixels corresponding to the positions of defects detected by the detection process.

10. the difference image is generated by performing a registration process on the inspection image and the reference image; 7. The information processing apparatus according to claim 6, wherein the evaluation means performs evaluation regarding overdetection of defects based on the amount of positional deviation in the positioning process between the inspection image and the reference image.

11. the difference image is generated by performing a registration process on the inspection image and the reference image; 7. The information processing apparatus according to claim 6, wherein the evaluation means performs evaluation regarding overdetection of defects based on the number of feature points used in the registration process between the inspection image and the reference image.

12. 7. The information processing apparatus according to claim 6, wherein the evaluation means performs evaluation regarding overdetection of defects based on a difference in density change between the inspection image and the reference image.

13. 2. The information processing apparatus according to claim 1, wherein the evaluation means performs evaluation regarding overdetection or underdetection of defects based on an output value obtained by inputting the inspection image into a learning model that has been trained using images in which defects have been overdetected or underdetected.

14. 2. The information processing apparatus according to claim 1, wherein the display control means controls to display text data representing the evaluation results by the evaluation means or text data representing the results of aggregating the evaluation results by defect type, in association with the inspection results by the inspection means or the aggregated results of the inspection results by defect type.

15. an inspection step of performing a defect detection process on an inspection image obtained by reading the printed matter, and inspecting the inspection image for the presence or absence of defects; an evaluation step of evaluating the result of the detection process regarding overdetection or underdetection of defects; a display control step of controlling the display of the inspection result from the inspection step and the evaluation result from the evaluation step in association with each other; An information processing method comprising:

16. Computer, an inspection means for performing a defect detection process on an inspection image obtained by reading a printed material and inspecting the inspection image for the presence or absence of defects; an evaluation means for evaluating the result of the detection process with respect to overdetection or underdetection of defects; a display control means for controlling the display of the inspection result by the inspection means and the evaluation result by the evaluation means in association with each other; A program characterized by functioning as

Images