Inspection system, information processing device, inspection method, and program

The inspection system addresses the issue of overlooked defects in manual quality inspection by automating the comparison of captured images with correct images, enhancing accuracy and efficiency.

JP7882097B2Active Publication Date: 2026-06-30RICOH CO LTD

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
RICOH CO LTD
Filing Date
2022-11-30
Publication Date
2026-06-30

Smart Images

  • Figure 0007882097000001
    Figure 0007882097000001
  • Figure 0007882097000002
    Figure 0007882097000002
  • Figure 0007882097000003
    Figure 0007882097000003
Patent Text Reader

Abstract

To reduce the defects that have occurred but have been overlooked in human quality inspection based on visual observation by operators.SOLUTION: Provided is an inspection system that inspects an inspection object to which a prescribed print image is printed, the inspection system comprising: an image acquisition unit that acquires a captured image in which the inspection object placed on a placement surface is captured by an imaging device; a display control unit that displays data related to the print image and the attribute information of the inspection object on the inspection object placement surface by a projection device; an image verification unit that verifies the captured image of the inspection object having been acquired by the image acquisition unit against the data related to the print image; and a defect information notification unit that notifies defect information for identifying a defect when it is determined by the image verification unit that there is a defect.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to an inspection system, an information processing apparatus, an inspection method, and a program.

Background Art

[0002] Conventionally, when printing a desired design on a shirt fabric or the like, an operator visually inspects the printed finished product for printing misalignment and whether the image is correct.

[0003] Patent Document 1 discloses a technique for aligning a shirt on a table with a boundary line displayed for the purpose of embroidering a predetermined position of the shirt or printing a predetermined motif.

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, there has been a problem that defects are overlooked in the conventional manual quality inspection by an operator's visual inspection.

[0005] The present invention has been made in view of the above, and an object thereof is to reduce the overlooking of defects that has occurred in the manual quality inspection by an operator's visual inspection.

Means for Solving the Problems

[0006] To solve the above-mentioned problems and achieve the objective, the present invention provides an inspection system for inspecting an object to be inspected on which a predetermined printed image has been printed, comprising: an image acquisition unit that acquires an image of the object to be inspected placed on a mounting surface by an imaging device; a display control unit that displays data relating to the printed image and attribute information of the object to be inspected on the mounting surface of the object to be inspected by a projection device; an image matching unit that compares the image of the object to be inspected acquired by the image acquisition unit with the data relating to the printed image; and a defect information notification unit that notifies the image matching unit of defect information for identifying the defect when the image matching unit determines that a defect exists based on the image matching. [Effects of the Invention]

[0007] According to the present invention, it is possible to reduce the number of defects that are overlooked during manual quality inspections performed by operators. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 is a block diagram showing the configuration of the inspection system according to the embodiment. [Figure 2-1] Figure 2-1 is a perspective view showing the configuration of the second inspection device. [Figure 2-2] Figure 2-2 is a side view showing the configuration of the second inspection device. [Figure 2-3] Figure 2-3 is a magnified perspective view showing part of the configuration of the second inspection device. [Figure 2-4] Figure 2-4 shows the positional relationship between the imaging device and the projection device of the second inspection apparatus. [Figure 3] Figure 3 is a block diagram showing the electrical system connections of the second inspection device. [Figure 4] Figure 4 is a hardware configuration diagram of the information processing device. [Figure 5] Figure 5 is a functional block diagram showing the functional configuration of the information processing device. [Figure 6] Figure 6 is a flowchart showing the flow of the inspection process using the second inspection device. [Figure 7] Figure 7 shows an example of a table that associates identification information with attribute information and data related to printed images. [Figure 8] Figure 8 is an illustrative diagram showing the projected guide frame. [Figure 9] Figure 9 is an illustrative diagram showing the projected attribute information. [Figure 10] Figure 10 is an illustrative diagram showing a T-shirt placed on a display stand. [Figure 11] Figure 11 is a flowchart showing an example of the processing procedure for the image matching process in step S8. [Figure 12] Figure 12 is a flowchart showing the flow of the difference detection process between the captured image and the ground truth image in step S82. [Figure 13] Figure 13 shows an example of how the OK / NG judgment result and defect information are displayed. [Figure 14] Figure 14 is a block diagram showing a modified configuration of the inspection system according to the embodiment. [Modes for carrying out the invention]

[0009] The embodiments of the inspection system, information processing device, inspection method, and program will be described in detail below with reference to the attached drawings.

[0010] Figure 1 is a block diagram showing the configuration of an inspection system 100 according to an embodiment. The inspection system 100 is a system for inspecting the print quality of a custom T-shirt (object to be inspected) after printing. As shown in Figure 1, the inspection system 100 comprises a first inspection device 10 and a second inspection device 20. The inspection system 100 also includes an information processing device 50-1, which is a server or PC connected to the first inspection device 10, an information processing device 50-2, which is a server or PC connected to the second inspection device 20, a smartphone 30 and a PC (Personal Computer) 40, and a printer 60, all of which are communicated via a network 70.

[0011] Note that it is essential that the information processing apparatus 50-1, the information processing apparatus 50-2, the smartphone 30, the PC 40, and the printer 60 are network-connected, and they do not necessarily have to be in the same location. For example, the information processing apparatuses 50-1 and 50-2 may be placed overseas. Also, the information processing apparatuses 50-1 and 50-2 may be configured to distribute and process functions across multiple servers. Hereinafter, when there is no particular need to distinguish between the information processing apparatuses 50-1 and 50-2, the information processing apparatuses 50-1 and 50-2 shall be referred to as the information processing apparatus 50.

[0012] The smartphone 30 and the PC 40 are used by the requester of the custom T-shirt. The smartphone 30 and the PC 40 are used for ordering a custom T-shirt where the requester of the custom T-shirt specifies the T-shirt information (color, size, etc.) and the desired design.

[0013] The information processing apparatus 50 is managed, for example, at the production factory of the printer of the custom T-shirt. The information processing apparatus 50 receives the T-shirt information (color, size, etc.) and the design information from the requester who placed an order via the smartphone 30 or the PC 40.

[0014] The operator at the production factory checks the T-shirt information (color, size, etc.) and the design from the information processing apparatus 50, sets a predetermined T-shirt on the printer 60, and prints the requested design. After printing, the operator at the production factory performs a quality inspection to detect defects in the printing. In this embodiment, the quality inspection is performed in two stages. The first inspection immediately after printing is performed using the first inspection apparatus 10. The second inspection after drying is completed after printing is performed using the second inspection apparatus 20.

[0015] The first inspection apparatus 10 is provided in proximity to the printer 60. The first inspection apparatus 10 is an inspection apparatus that automatically inspects for defects based on the difference between the captured image obtained by photographing the printed surface immediately after printing by the printer 60 with a camera and the correct image.

[0016] After drying is completed after printing, the second inspection device 20 is an inspection device that automatically inspects "printing misalignment" based on the difference between the captured image of the printed surface of the T-shirt placed on the placement table 22 (see FIG. 2) by the imaging device 23 (see FIG. 2) and the correct image. In addition, the second inspection device 20 inspects "discrepancies with printing job information (orderer, size, delivery address, etc.)".

[0017] Here, the configuration of the second inspection device 20 will be described.

[0018] FIG. 2-1 is a perspective view showing the configuration of the second inspection device 20, FIG. 2-2 is a side view showing the configuration of the second inspection device 20, FIG. 2-3 is a perspective view showing a partially enlarged configuration of the second inspection device 20, and FIG. 2-4 is a view showing the positional relationship between the imaging device 23 and the projection device 24 of the second inspection device 20. As shown in FIG. 2-1 and the like, the second inspection device 20 includes a main body portion 21 formed of a rectangular parallelepiped-shaped metal frame. The second inspection device 20 includes a placement table 22 having a placement surface on which the T-shirt 200 after drying is completed after printing is placed at a substantially central portion of the main body portion 21. The placement table 22 is installed inclined toward the operator side to facilitate visual operation by the operator.

[0019] The placement table 22 has a predetermined marker M (see FIG. 10) that indicates the correct placement position of the T-shirt 200 on the placement table 22 to the operator.

[0020] Note that the placement table 22 is not limited to having a placement surface configured in a trapezoidal shape. For example, it may have a placement surface in a mode of suspending and placing the T-shirt 200 after drying is completed after printing.

[0021] The second inspection device 20 includes, on the upper part of the main body 21, an imaging device 23 for imaging a T-shirt placed on a mounting table 22, a projection device 24 which is a projector for displaying operation information to the operator, and a lighting device 25. The imaging device 23 and the projection device 24 are installed so that the imaging surface of the imaging device 23 and the projection surface of the projection device 24 are perpendicular to the mounting table 22, respectively. The imaging device 23 and the projection device 24 are connected to an information processing device 50 in the production plant via a network 70. As shown in Figure 2-4, the positional relationship between the imaging device 23 and the projection device 24 is such that the projection range of the projection device 24 falls within the imaging range of the imaging device 23.

[0022] Next, we will explain the electrical system connections of the second inspection device 20.

[0023] Figure 3 is a block diagram showing the electrical system connections of the second inspection device 20. As shown in Figure 3, the second inspection device 20 includes an I / O power supply box 107 and a light source power supply box 108. The information processing device 50 is connected to the second inspection device 20 via the I / O power supply box 107.

[0024] The lighting device 25 is connected to the information processing device 50 via the I / O power box 107 and the light source power box 108. The lighting device 25 is controlled by the information processing device 50.

[0025] The imaging device 23 and the projection device 24 are directly connected to and controlled by the information processing device 50. The imaging device 23 is, for example, a digital camera using a CMOS (Complementary Metal Oxide Semiconductor) and outputs a signal corresponding to the projected light. Alternatively, the imaging device 23 may be a digital camera using a CCD (Charge Coupled Device).

[0026] Next, the hardware configuration of the information processing device 50 will be described.

[0027] Figure 4 is a hardware configuration diagram of the information processing device 50.

[0028] As shown in Figure 4, the information processing device 50 is built by a computer and includes a CPU 501, ROM 502, RAM 503, HD 504, HDD (Hard Disk Drive) controller 505, display 506, external device connection I / F (Interface) 508, network I / F 509, bus line 510, keyboard 511, pointing device 512, DVD-RW (Digital Versatile Disc Rewritable) drive 514, and media I / F 516.

[0029] Of these, the CPU 501 controls the operation of the entire information processing unit 50. The ROM 502 stores programs used to drive the CPU 501, such as IPL. The RAM 503 is used as the work area for the CPU 501. The HD 504 stores various data such as programs. The HDD controller 505 controls the reading or writing of various data to the HD 504 according to the control of the CPU 501. The display 506 displays various information such as cursors, menus, windows, characters, or images. The external device connection I / F 508 is an interface for connecting various external devices. In this case, external devices include, for example, USB (Universal Serial Bus) memory and printers. The network I / F 509 is an interface for data communication using the communication network 70. The bus line 510 is an address bus, data bus, etc., for electrically connecting each component such as the CPU 501 shown in Figure 4.

[0030] The keyboard 511 is a type of input means equipped with multiple keys for inputting characters, numbers, and various instructions. The pointing device 512 is a type of input means for selecting and executing various instructions, selecting processing targets, and moving the cursor. The DVD-RW drive 514 controls the reading or writing of various data to the DVD-RW 513, which is an example of a removable recording medium. Note that it is not limited to DVD-RW, but may also be DVD-R, etc. The media interface 516 controls the reading or writing (storage) of data to the recording medium 515, such as flash memory.

[0031] The program executed by the information processing device 50 of this embodiment is provided as a file in an installable or executable format, recorded on a computer-readable recording medium such as a CD-ROM, flexible disk (FD), CD-R, or DVD (Digital Versatile Disc).

[0032] Furthermore, the program executed by the information processing device 50 of this embodiment may be stored on a computer connected to a network such as the Internet and provided by downloading it via the network. Alternatively, the program executed by the information processing device 50 of this embodiment may be provided or distributed via a network such as the Internet.

[0033] In the following, we will describe the characteristic processing of this embodiment among the various arithmetic processes that the CPU 501 of the information processing device 50 executes by program.

[0034] Here, Figure 5 is a functional block diagram showing the functional configuration of the information processing device 50. As shown in Figure 5, the CPU 501 of the information processing device 50 has an information storage unit 51, an identification information reading unit 52, an information acquisition unit 53, an image acquisition unit 54, a display control unit 55, an image matching unit 56, a defect information notification unit 57, and a startup control unit 58, which are activated by executing a program.

[0035] The information storage unit 51 stores data related to the printed image and attribute information of the custom T-shirt (object under inspection) in association with identification information pre-assigned to the custom T-shirt (object under inspection). Here, Figure 7 is a diagram showing an example of a table in which the attribute information and data related to the printed image are associated with the identification information. As shown in Figure 7, the data related to the printed image is image data of the design to be printed on the T-shirt requested by the user (printed image), and predicted image data of the predicted printing result when the image data of the printed image is printed on the T-shirt (ground truth image). Attribute information is information associated with the T-shirt, such as the type of T-shirt, fabric color, size, orderer, and shipping address.

[0036] Now, let's explain the correct image. When printing an image onto a T-shirt, the resulting color will differ depending on the fabric color of the T-shirt. For example, printing on a white T-shirt will result in a different color than printing on a black T-shirt. The correct image is a predicted image generated by predicting what the image should ideally look like when printed on the T-shirt fabric color.

[0037] The correct image is used to compare the printed image with an image of the T-shirt during quality inspection of the T-shirt with the printed image. Normally, since the information of the printed image and the T-shirt to be printed is known when a request is received from the user, the correct image is prepared in advance and stored as data related to the printed image. However, it is also possible to retrieve the printed image during quality inspection, perform prediction processing, and generate the correct image.

[0038] The identification information reading unit 52 reads the identification information attached to the custom T-shirt (object to be inspected).

[0039] The information acquisition unit 53 acquires, based on the identification information, attribute information associated with the identification information and data related to the printed image associated with the identification information from the information storage unit 51.

[0040] The image acquisition unit 54 acquires an image captured by the imaging device 23 of the custom T-shirt (object to be inspected) placed on the mounting surface of the mounting table 22.

[0041] The display control unit 55 displays the data and attribute information related to the printed image acquired by the information acquisition unit 53 on the mounting surface of the mounting table 22 on which the custom T-shirt (object to be inspected) is placed, using the projection device 24.

[0042] The image matching unit 56 compares the captured image of the custom T-shirt (object under inspection) acquired by the image acquisition unit 54 with the correct image, which is one of the data related to the printed image.

[0043] Furthermore, as described above, if the correct image to be compared is already stored in the information storage unit 51 of the information processing device 50, the stored correct image may be acquired and compared. Alternatively, if it is not already stored, the printed image stored in the information storage unit 51 may be acquired during the comparison process, prediction processing may be performed, and the correct image may be generated.

[0044] The defect information notification unit 57 notifies the image matching unit 56 of defect information to identify the defect when the image matching unit 56 determines that a defect exists.

[0045] The startup control unit 58 starts the imaging device 23, projection device 24, and illumination device 25 installed in the second inspection device 20. The startup control unit 58 also connects the imaging device 23 and projection device 24 to the network 70.

[0046] Next, we will describe a characteristic processing flow among the processes performed by the information processing device 50 according to this embodiment.

[0047] Figure 6 is a flowchart showing the flow of the inspection process using the second inspection device 20.

[0048] As shown in Figure 6, the startup control unit 58 of the information processing device 50 starts the imaging device 23, projection device 24, and illumination device 25 installed in the second inspection device 20 (step S1). The startup control unit 58 of the information processing device 50 also connects the imaging device 23 and projection device 24 to the network 70. This makes it possible for an operator to issue operation instructions to the second inspection device 20 via the information processing device 50.

[0049] Next, the identification information reading unit 52 of the information processing device 50 controls the imaging device 23 to read the identification information attached to the T-shirt, and the information acquisition unit 53 acquires attribute information, etc. (step S2). The identification information is, for example, code symbol information such as a barcode or two-dimensional code attached to the T-shirt, which is commonly used in the apparel industry for managing clothing. Furthermore, the identification information is not limited to barcodes or two-dimensional codes; it may also be a series of numbers (digits) or other manageable information. The code symbol may be printed on the tag of the T-shirt, for example, or formed as a code symbol sticker. The identification image is captured by the imaging device 23 installed in the second inspection device 20.

[0050] In this embodiment, the identification image is captured and read by the imaging device 23 installed in the second inspection device 20, but this is not the only option. A separate code symbol scanner may be provided so that an operator can read the identification image (code symbol).

[0051] The read identification information is transmitted to the information processing device 50. The information storage unit 51 of the information processing device 50 has already associated the identification information with attribute information such as the size, color, and print design (original correct image and reduced image) of the T-shirt and stored it in a storage unit such as the HD504. The information acquisition unit 53 acquires data and attribute information related to the corresponding print image from the storage unit based on the identification information.

[0052] Furthermore, the identification information is not limited to barcodes and may be stored using IC tags or the like. In this case, a separate IC tag reader should be provided. When using IC tags or the like, if the storage capacity is sufficient, the identification information and attribute information may be directly stored within the IC tag. Also, for example, if the inspection order of the custom T-shirts (objects to be inspected) is known in advance, the identification information of the custom T-shirts (objects to be inspected) can be obtained without attaching identification information to the custom T-shirts (objects to be inspected) by sequentially inputting the data of the custom T-shirts (objects to be inspected) into the information processing device 50. Therefore, it is not essential to attach identification information to the custom T-shirts (objects to be inspected).

[0053] Next, the display control unit 55 of the information processing device 50 controls the projection device 24 to project a guide frame G for placing the T-shirt onto the placement table 22 (step S3). The projected guide frame G consists of various guide displays to facilitate inspection operations for the operator.

[0054] Here, Figure 8 is an illustrative diagram showing the projected guide frame G. As shown in Figure 8, the guide frame G projected onto the mounting table 22 is a guide indicator for the operator to place the T-shirt 200 in the correct position on the mounting table 22 of the second inspection device 2. The guide frame G is just an example; any frame that allows the operator to recognize that the T-shirt 200 should be placed in the correct position is acceptable.

[0055] Conventionally, the placement of the T-shirt was difficult to determine, resulting in time-consuming setup and inconsistent inspection speed and accuracy. In contrast, this embodiment projects a guide frame G for T-shirt placement using the projection device 24, stabilizing the shooting (inspection) position and enabling faster and more stable inspection.

[0056] Next, the display control unit 55 of the information processing device 50 controls the projection device 24 to project data and attribute information related to the printed image of the T-shirt onto the periphery of the mounting table 22 (step S4). Specifically, the display control unit 55 of the information processing device 50 displays data and attribute information related to the printed image, which is associated with the identification information read in step S2, onto the periphery of the mounting table 22.

[0057] Here, Figure 9 is an illustrative diagram showing the attribute information that is projected. In the example shown in Figure 9, attribute information A of the type, size, and color of the T-shirt 200 is displayed in the lower left of the mounting table 22. If the information at this stage differs from the correct information to be printed, an "NG" message is displayed. Also in the example shown in Figure 9, data related to the print image (the T-shirt 200 that matches the request and an image based on the design, which may be a reduced image) B is displayed in the lower right of the mounting table 22. It is preferable to display all such attribute information A within the mounting table 22 so that the operator can check it at a glance. Displaying all the information can improve inspection efficiency and prevent oversights.

[0058] The data related to the printed image displayed in the lower right corner of the mounting platform 22 can be either the printed image or the correct image. As mentioned above, the printed image and the correct image have different colors, but the purpose of displaying the data related to the printed image is simply to enable the operator to correctly place the next T-shirt to be inspected.

[0059] Conventionally, there was a problem in that the T-shirts 200 to be inspected were sometimes placed incorrectly, resulting in incorrect inspection. In this embodiment, however, information necessary for inspection judgment regarding the attribute information of the T-shirts to be inspected (size, color, design, etc.) is projected and displayed on the left and right sides of the T-shirts 200 on the placement table 22 where the T-shirts are placed using a projection device 24. At this stage, the operator can determine whether the size and color of the T-shirts 200 differ from the request, or whether the wrong design is printed, thus preventing user placement errors and improving inspection efficiency. Furthermore, it is possible to reduce costs (discarding, reinspecting) caused by incorrect placement of the T-shirts to be inspected, resulting in a false negative judgment of a shirt that should have been OK.

[0060] Next, the image acquisition unit 54 of the information processing device 50 determines whether a predetermined time has elapsed since the operator placed the T-shirt 200 on the mounting table 22 so as to conceal the marker M (step S5), and determines whether the operator is inside the second inspection device 2 (step S6).

[0061] Here, Figure 10 is an illustrative diagram showing the state in which a T-shirt is placed on the mounting table 22. As shown in Figure 10, the image acquisition unit 54 of the information processing device 50 takes a photograph or video of the marker M at predetermined intervals using the imaging device 23. The image acquisition unit 54 of the information processing device 50 analyzes the photographed or video recorded images and determines whether a predetermined time (for example, 30 seconds) has elapsed. If the predetermined time has not elapsed since the marker M was hidden (No in step S5), it is determined that the operator is performing the T-shirt 200 placement operation. On the other hand, if the predetermined time has elapsed (Yes in step S5), it is determined that there is a high probability that the operator has finished setting the T-shirt 200 on the mounting table 22.

[0062] Furthermore, even if it is determined in step S5 that the T-shirt has been set on the mounting platform 22 (Yes in step S5), there is still a possibility that a part of the operator's body is inside the second inspection device 2, and the operator may be captured in the image when the T-shirt is photographed. Therefore, the image acquisition unit 54 of the information processing device 50 checks whether the operator is captured by taking photographs or video recordings at predetermined time intervals with the imaging device 23 (step S6). The information processing device 50 performs image / video analysis and determines that no person is captured.

[0063] Conventionally, manual photography had the problem that operators sometimes forgot to take pictures, making inspection impossible. In contrast, in this embodiment, a marker M is provided on the mounting table 22, and the imaging device 23 continuously takes pictures. The presence or absence of the marker M in the image is determined, and if neither the marker M nor the operator is visible, the T-shirt is considered to have been placed and an automatic picture is taken, thereby preventing the inspection (photography) from being forgotten.

[0064] Furthermore, having an operator manually take photos each time a T-shirt is inspected increases the workload and makes it more prone to errors. According to this embodiment, the operator's workload can be reduced because the T-shirts are automatically photographed at predetermined timings. In addition, this embodiment eliminates the operator's presence in the images, allowing for more accurate automatic photography of T-shirts.

[0065] Alternatively, instead of providing the marker M on the mounting base 22, the marker M may be projected from the projection device 24. Furthermore, either the guide frame G or the marker M may be displayed, or both may be displayed in a predetermined order. Alternatively, both the guide frame G and the marker M may be displayed simultaneously.

[0066] If it is determined that the operator is not reflected inside the second inspection device 2 (Yes in step S6), the image acquisition unit 54 of the information processing device 50 takes an image of the T-shirt placed on the mounting table 22 with the imaging device 23 (step S7). In this embodiment, the automatic shooting is triggered by the absence of the operator in the second inspection device 2, but the shooting may also be started by the operator giving an operation instruction (manual or voice).

[0067] Next, the image matching unit 56 of the information processing device 50 compares the captured image with the correct image (step S8). More specifically, when the printed T-shirt image captured by the imaging device 23 is sent to the information processing device 50, the image matching unit 56 of the information processing device 50 performs image comparison with the correct image based on the pre-stored request content and inspects the printed T-shirt image.

[0068] Here, we will explain the image matching algorithm for step S8.

[0069] Figure 11 is a flowchart showing an example of the processing procedure for the image matching process in step S8. As shown in Figure 11, first, the image matching unit 56 of the information processing device 50 acquires the correct image (step S81).

[0070] The image matching unit 56 of the information processing device 50 retrieves the correct image stored in the information storage unit 51 and performs image matching if the correct image is already stored in the information storage unit 51 of the information processing device 50 as data related to the printed image.

[0071] Furthermore, if the correct image is not already stored in the information storage unit 51 of the information processing device 50 as data related to the printed image, the image matching unit 56 of the information processing device 50 generates and acquires the correct image and performs image matching with the generated correct image. More specifically, the image matching unit 56 of the information processing device 50 performs RIP processing on an image of a custom T-shirt created by combining image data of a printed T-shirt requested by the user with the specified T-shirt, and then performs prediction processing on the captured image taken by the imaging device 23 to determine the correct image.

[0072] Next, the image matching unit 56 of the information processing device 50 compares the captured image taken by the imaging device 23 with the correct image and detects the difference (step S82). More specifically, the image matching unit 56 of the information processing device 50 aligns the captured image with the correct image and detects the difference. The image matching unit 56 of the information processing device 50 absorbs slight shrinkage or deformation of the printed surface that does not constitute a defect, and detects only defects that degrade quality as differences.

[0073] Here, Figure 12 is a flowchart showing the flow of the difference detection process between the captured image and the ground truth image in step S82. As shown in Figure 12, the image matching unit 56 of the information processing device 50 determines whether the image region of the captured image corresponding to the "background region" of the ground truth image is flat or not, based on the analysis results of the captured image (step S821). At this time, the image matching unit 56 of the information processing device 50 refers to the analysis results of the captured image from the received analysis results and determines whether the reference value (a value representing the flatness that represents the change in pixel values ​​obtained by analyzing the captured image) is greater than or equal to a pre-set threshold.

[0074] The image matching unit 56 of the information processing device 50 assumes that there are no defects in the corresponding image region of the captured image if the reference value is less than a threshold (step S821: Yes), and detects the difference (difference between pixels) between the correct image and the captured image (step S822).

[0075] Next, the image matching unit 56 of the information processing device 50 determines whether the detected difference is greater than or equal to the inspection threshold B1 (step S823). The inspection threshold B1 is a value determined as the second inspection threshold (defect judgment criterion), which is greater than the value that would be used if a defect were assumed to exist when the reference value was less than the threshold.

[0076] As a result, the image matching unit 56 of the information processing device 50 detects an abnormality (defect) that occurred in the corresponding image region of the captured image if the difference is greater than or equal to the threshold B1 (step S823: Yes).

[0077] On the other hand, if the reference value is greater than or equal to a threshold (step S821: No), the image matching unit 56 of the information processing device 50 assumes that a defect exists in the corresponding image region of the captured image and detects the difference between the correct image and the captured image (average difference per pixel within the rectangular region) (step S824).

[0078] Next, the image matching unit 56 of the information processing device 50 determines whether the detected difference is greater than or equal to the inspection threshold B2 (step S825). The inspection threshold B2 is a value determined as the first inspection threshold (defect judgment criterion), which is a value that can detect minute changes in pixel values ​​when the reference value is greater than or equal to the threshold.

[0079] As a result, the image matching unit 56 of the information processing device 50 detects an abnormality (defect) that occurred in the corresponding image region of the captured image if the difference is greater than or equal to the threshold B2 (step S825: Yes).

[0080] Returning to Figure 11, the image matching unit 56 of the information processing device 50 then corrects the difference between the captured image detected in step S82 and the correct image (step S83). More specifically, the information processing device 50 improves productivity, yield rate, and inspection accuracy by classifying defects that are easily noticed or difficult for humans to notice based on human visual characteristics and optimizing the judgment criteria.

[0081] Returning to Figure 6, the defect information notification unit 57 of the information processing device 50 makes an OK / NG determination based on the image matching in step S8 and displays the OK / NG determination result and defect information (step S9). More specifically, the defect information notification unit 57 of the information processing device 50 controls the projection device 24 to display the OK / NG determination result and defect information on the mounting base 22. By projecting the location, type, and size of the detected defect as defect information using the projection device 24, the location of the detected defect becomes easier for the user to recognize.

[0082] Here, Figure 13 shows an example of the display of OK / NG judgment results and defect information. As shown in Figure 13, the defect information C projected from the projection device 24 displays, for example, the location, type, and size of the defect, overlaid on the predicted location on the actual T-shirt 200 so that the operator can easily recognize it. This allows the operator to reduce inspection time by focusing on and checking the notified defect. In addition, since even small defects are detected as candidates, the operator's chances of missing defects are reduced. Furthermore, when multiple operators are performing inspections, there is a possibility of inspection variability due to visual inspection and inspection ability, but this can be greatly reduced.

[0083] Furthermore, this approach allows for user judgment if the detected defect is near the threshold. Even for defects that are difficult for the user to recognize, indicating the location of the defect makes it easier for the user to determine whether it is OK or NG.

[0084] In this embodiment, the defect information notification unit 57 of the information processing device 50 displays the OK / NG judgment result and defect information on the mounting base 22 by controlling the projection device 24, but it is not limited to this. For example, the defect information notification unit 57 of the information processing device 50 may display the OK / NG judgment result and defect information on the display 506 of the information processing device 50, or on the display unit of an external mobile terminal or PC (not shown).

[0085] In addition to displaying the OK / NG judgment result and defect information, the system may also announce to the operator via voice that a defect has occurred, or install a warning light on the second inspection device 20 to notify the operator of the occurrence of a defect.

[0086] As described above, according to this embodiment, when an operator places a T-shirt (object to be inspected) on the mounting table 22 of the second inspection device 20, the projection device 24 displays information useful for quality inspection operation and information useful for error judgment. In addition, the imaging device 23 automatically photographs the T-shirt (object to be inspected) and determines whether the printed design is printed in the correct position and content by comparing it with a correct image. This reduces the chance of missing defects that occurred with manual quality inspection by operators. It also reduces variability in quality inspection among multiple operators. Furthermore, it reduces the inspection workload for operators and improves production efficiency.

[0087] In this embodiment, a T-shirt was used as the object to be inspected, but it is not limited to this, and can also be applied to custom-ordered printed clothing (dress shirts, casual shirts, sweatshirts, etc.). Furthermore, the object to be inspected is not limited to clothing, but can also be applied to non-rigid objects including fabric products such as bags, masks, and hats.

[0088] Furthermore, although the information processing device 50 and the second inspection device 20 have been described as separate components in this embodiment, the invention is not limited to this configuration. The information processing device 50 may be installed within the second inspection device 20 to form a single inspection device.

[0089] Figure 14 is a block diagram showing a modified configuration of the inspection system according to the embodiment. As shown in Figure 14, the inspection system 100 may have a system configuration in which a first inspection device 10, a second inspection device 20, a smartphone 30 and a PC (Personal Computer) 40, an information processing device 50 which is a server or PC, and a printer 60 are connected to each other via a network 70.

[0090] Each of the functions of the embodiments described above can be realized by one or more processing circuits. Hereinafter, "processing circuit" as used herein includes processors programmed to execute each function by software, such as processors implemented by electronic circuits, as well as devices such as ASICs (Application Specific Integrated Circuits), DSPs (Digital Signal Processors), FPGAs (Field Programmable Gate Arrays), and conventional circuit modules designed to execute each of the functions described above.

[0091] The apparatus described in the examples represents only one of several computing environments for carrying out the embodiments disclosed herein. In one embodiment, the information processing apparatus 50 includes multiple computing devices, such as a server cluster. The multiple computing devices are configured to communicate with each other via any type of communication link, including a network or shared memory, and perform the processing disclosed herein. Similarly, the information processing apparatus 50 may include multiple computing devices configured to communicate with each other.

[0092] Examples of the present invention are as follows: <1> An inspection system for inspecting an object to be inspected on which a predetermined printed image has been printed, An image acquisition unit that acquires an image of the object to be inspected placed on the mounting surface, captured by an imaging device, A display control unit that displays data relating to the printed image and attribute information of the object to be inspected on the surface on which the object to be inspected is placed using a projection device, An image matching unit that compares the captured image of the object to be inspected acquired by the image acquisition unit with data relating to the printed image, If the image matching unit determines that there is a defect based on the image matching, the defect information notification unit notifies the user of defect information to identify the defect. An inspection system characterized by comprising the following features. <2> The data relating to the printed image is the correct image with the printed image printed on the object to be inspected. The display control unit displays the correct image and attribute information on the peripheral portion of the display surface described above. Characterized by <1> The inspection system described above. <3> The mounting surface includes a marker indicating the mounting position of the object to be inspected. The image acquisition unit controls the imaging device to take an image of the object to be inspected if it becomes impossible to detect the marker from the captured image within a predetermined time. Characterized by <1> or <2> The inspection system described above. <4> The mounting surface includes a marker indicating the mounting position of the object to be inspected. The image acquisition unit, when it is unable to detect the marker from the captured image within a predetermined time, and when it determines that the captured image does not contain a person's image, controls the imaging device to capture an image of the object to be inspected. Characterized by <1> or <2> The inspection system described above. <5> The defect information notification unit notifies the OK / NG judgment result and defect information from the image matching unit. Characterized by <1> or <4> The inspection system described in any one of the following. <6> The defect information notification unit projects the OK / NG judgment result and defect information from the image matching unit to the location on the object being inspected, which is placed on the aforementioned surface, where a defect is predicted to have occurred. Characterized by <5> The inspection system described above. <7> The aforementioned defect information notification unit notifies that a defect has occurred. It is characterized by <1> or <6> The inspection system described in any one of the following. <8> An information storage unit stores data relating to the printed image and attribute information of the object to be inspected, in association with identification information previously attached to the object to be inspected. An identification information reading unit reads the identification information attached to the object to be inspected, An information acquisition unit acquires data and attribute information relating to the corresponding printed image from the information storage unit based on the identification information, It is characterized by having <1> or <7> The inspection system described in any one of the following. <9> An information processing device connected to an inspection device that inspects an object to be inspected on which a predetermined printed image has been printed, An image acquisition unit that acquires an image of the object to be inspected placed on the mounting surface, captured by an imaging device, A display control unit that displays data relating to the printed image and attribute information of the object to be inspected on the surface on which the object to be inspected is placed using a projection device, An image matching unit that compares the captured image of the object to be inspected acquired by the image acquisition unit with data relating to the printed image, If the image matching unit determines that there is a defect based on the image matching, the defect information notification unit notifies the user of defect information to identify the defect. An information processing device characterized by comprising: <10> An inspection method for inspecting an object to be inspected on which a predetermined printed image has been printed, An image acquisition step involves acquiring an image of the object to be inspected, which is placed on the mounting surface, by an imaging device, and acquiring the image of that object. A display control step in which data relating to the printed image and attribute information of the object to be inspected are displayed on the surface on which the object to be inspected is placed by a projection device, An image matching step is performed to compare the captured image of the object to be inspected obtained by the image acquisition step with data relating to the printed image, If the image matching process determines that there is a defect, a defect information notification process is performed to notify the system of defect information for identifying the defect. A testing method characterized by including [a certain component]. <11> A computer that controls an information processing device connected to an inspection device that inspects an object to be inspected on which a predetermined printed image has been printed, An image acquisition unit that acquires an image of the object to be inspected placed on the mounting surface, captured by an imaging device, A display control unit that displays data relating to the printed image and attribute information of the object to be inspected on the surface on which the object to be inspected is placed using a projection device, An image matching unit that compares the captured image of the object to be inspected acquired by the image acquisition unit with data relating to the printed image, If the image matching unit determines that there is a defect based on the image matching, the defect information notification unit notifies the user of defect information to identify the defect. A program designed to function as such. [Explanation of Symbols]

[0093] 20 Inspection equipment 23 Imaging device 24 Projection device 50 Information Processing Devices 51 Information storage section 52 Identification Information Reading Unit 53 Information Acquisition Department 54 Image acquisition unit 55 Display Control Unit 56 Image matching unit 57. Defect Information Notification Department 100 Inspection Systems [Prior art documents] [Patent Documents]

[0094] [Patent Document 1] U.S. Patent No. 10,675,860

Claims

1. An inspection system for inspecting an object to be inspected on which a predetermined printed image has been printed, An image acquisition unit that acquires an image of the object to be inspected placed on the mounting surface, captured by an imaging device, A display control unit that displays data relating to the printed image and attribute information of the object to be inspected on the surface on which the object to be inspected is placed using a projection device, An image matching unit that compares the captured image of the object to be inspected acquired by the image acquisition unit with data relating to the printed image, If the image matching unit determines that there is a defect based on the image matching, the defect information notification unit notifies the user of defect information to identify the defect. An inspection system characterized by comprising the following features.

2. The data relating to the printed image is the correct image with the printed image printed on the object to be inspected. The display control unit displays the correct image and attribute information on the peripheral portion of the display surface described above. The inspection system according to feature 1.

3. The mounting surface includes a marker indicating the mounting position of the object to be inspected. The image acquisition unit controls the imaging device to take an image of the object to be inspected if it becomes impossible to detect the marker from the captured image within a predetermined time. The inspection system according to feature 1.

4. The mounting surface includes a marker indicating the mounting position of the object to be inspected. The image acquisition unit, when it is unable to detect the marker from the captured image within a predetermined time, and when it determines that the captured image does not contain a person's image, controls the imaging device to capture an image of the object to be inspected. The inspection system according to feature 1.

5. The defect information notification unit notifies the OK / NG judgment result and defect information from the image matching unit. The inspection system according to feature 1.

6. The defect information notification unit projects the OK / NG judgment result and defect information from the image matching unit to the location on the object being inspected, which is placed on the aforementioned surface, where the defect is predicted to have occurred. The inspection system according to feature 5.

7. The aforementioned defect information notification unit notifies that a defect has occurred. The inspection system according to claim 1, characterized in that...

8. An information storage unit stores data relating to the printed image and attribute information of the object to be inspected, in association with identification information previously attached to the object to be inspected. An identification information reading unit reads the identification information attached to the object to be inspected, An information acquisition unit acquires data and attribute information relating to the corresponding printed image from the information storage unit based on the identification information, An inspection system according to any one of claims 1 to 7, characterized by comprising the following:

9. An information processing device connected to an inspection device that inspects an object to be inspected on which a predetermined printed image has been printed, An image acquisition unit that acquires an image of the object to be inspected placed on the mounting surface, captured by an imaging device, A display control unit that displays data relating to the printed image and attribute information of the object to be inspected on the surface on which the object to be inspected is placed using a projection device, An image matching unit that compares the captured image of the object to be inspected acquired by the image acquisition unit with data relating to the printed image, If the image matching unit determines that there is a defect based on the image matching, the defect information notification unit notifies the user of defect information to identify the defect. An information processing device characterized by comprising:

10. An inspection method for inspecting an object to be inspected on which a predetermined printed image has been printed, An image acquisition step involves acquiring an image of the object to be inspected, which is placed on the mounting surface, by an imaging device, and acquiring the image of that object. A display control step in which data relating to the printed image and attribute information of the object to be inspected are displayed on the surface on which the object to be inspected is placed by a projection device, An image matching step is performed to compare the captured image of the object to be inspected obtained by the image acquisition step with data relating to the printed image, If the image matching process determines that there is a defect, a defect information notification process is performed to notify the system of defect information for identifying the defect. A testing method characterized by including [a certain component].

11. A computer that controls an information processing device connected to an inspection device that inspects an object to be inspected on which a predetermined printed image has been printed, An image acquisition unit that acquires an image of the object to be inspected placed on the mounting surface, captured by an imaging device, A display control unit that displays data relating to the printed image and attribute information of the object to be inspected on the surface on which the object to be inspected is placed using a projection device, An image matching unit that compares the captured image of the object to be inspected acquired by the image acquisition unit with data relating to the printed image, If the image matching unit determines that there is a defect based on the image matching, the defect information notification unit notifies the user of defect information to identify the defect. A program designed to function as such.