JP7772092B2 - Printed matter inspection device, printed matter inspection method, and program - Google Patents

Description

The present disclosure relates to a printed matter inspection device, a printed matter inspection method, and a computer-readable medium, and in particular to a printed matter inspection device, a printed matter inspection method, and a computer-readable medium for inspecting printed matter having an OVD (Optical Variable Device) attached to a substrate.

Inspection of printed materials is carried out taking into consideration various variables that occur during the printing process of the printed material being inspected and when capturing an image of the printed material. For example, variables include misalignment during printing and changes in brightness values due to the reflection of illumination light when capturing an image. When inspecting printed materials, areas where these variables may occur are masked (set outside the inspection area), making it possible to perform the inspection without affecting inspection accuracy.

OVDs are sometimes affixed to printed materials, such as banknotes, securities, gift certificates, coupons, and cards, to prevent counterfeiting. OVDs come in a variety of shapes, including circular and rectangular, as shown in Figure 1. However, regardless of their shape, OVDs have significant variations in brightness due to the reflection of illumination light during photography due to their optical properties. For this reason, OVDs are masked in print inspection methods related to related technology, as shown in Figure 1. Furthermore, as shown in Figure 2, there is variation in the placement of OVDs. For this reason, print inspection methods related to related technology have masked areas where OVDs may be present, taking into account misalignment of the OVD.

Patent No. 4753181

However, defects may occur in areas of the mask area that are not OVD (hereinafter referred to as dead zone areas). In the print inspection method according to the related art described above, areas where OVD may exist are also masked. As a result, as shown in Figure 3, defects within the dead zone areas are also masked, making it impossible to detect defects within the dead zone areas. While methods for inspecting OVD have been disclosed (for example, Patent Document 1), no inspection method has been disclosed for inspecting dead zone areas within the mask area that are not OVD.

In view of the above-mentioned problems, the object of this disclosure is to provide a print inspection device, a print inspection method, and a computer-readable medium that are capable of inspecting dead zone areas within a mask area that are not OVD during print inspection.

A print inspection device according to one aspect includes:
A print inspection device that inspects a print to which an OVD (Optical Variable Device) is attached,
a matching template creation unit that creates a matching template image for identifying the attachment position of the OVD by template matching;
a defect detection unit that uses the matching template image to identify an OVD attachment position in an inspection object image obtained by photographing the printed matter, masks the identified OVD attachment position, and detects defects in the inspection object image based on a difference image between the inspection object image in which the OVD attachment position has been masked and the inspection template image;
Equipped with.

A print inspection method according to one aspect includes:
A print inspection method performed by a print inspection device that inspects a print to which an OVD (Optical Variable Device) is attached, comprising:
a matching template creation step of creating a matching template image for identifying the attachment position of the OVD by template matching;
a defect detection step of using the matching template image to identify an OVD attachment position in an inspection object image obtained by photographing the printed matter, masking the identified OVD attachment position, and detecting defects in the inspection object image based on a difference image between the inspection object image in which the OVD attachment position has been masked and the inspection template image;
Includes.

According to one aspect, a computer-readable medium includes:
A non-transitory computer-readable medium storing a program to be executed by a print inspection device that inspects a print to which an OVD (Optical Variable Device) is attached,
The program
a matching template creation step of creating a matching template image for identifying the attachment position of the OVD by template matching;
a defect detection step of using the matching template image to identify an OVD attachment position in an inspection object image obtained by photographing the printed matter, masking the identified OVD attachment position, and detecting defects in the inspection object image based on a difference image between the inspection object image in which the OVD attachment position has been masked and the inspection template image;
Includes.

The above-mentioned aspects have the effect of providing a print inspection device, a print inspection method, and a computer-readable medium that are capable of inspecting dead zone areas within a mask area that are not OVD during print inspection.

10A and 10B are diagrams showing examples of OVD attachment positions, mask areas, and dead zone areas on a printed material. FIG. 10 is a diagram showing an example of an image of misalignment of an OVD. 10A and 10B are diagrams showing an example in which defects in a dead zone cannot be detected by a print inspection method according to the related art; 1 is a diagram illustrating an example of the configuration of a print inspection device according to a first embodiment; 5A to 5C are diagrams illustrating an example of a method for creating a matching template image according to the first embodiment. FIG. 1 is a diagram illustrating an example of a print inspection method according to a related art. 10A and 10B are diagrams illustrating an example of a method for creating a detection template image according to the related art. 5A to 5C are diagrams illustrating an example of a method for creating a detection template image according to the first embodiment. 1A and 1B are diagrams illustrating an example of a printed matter inspection method according to a first embodiment. 4 is a flowchart showing an example of the flow of a process for creating a matching template image, a process for creating an inspection template image, and an inspection process in the print inspection device according to the first embodiment. FIG. 10 is a diagram illustrating an example of the configuration of a print inspection device according to a second embodiment. FIG. 10 is a diagram illustrating an example of the hardware configuration of a print inspection device according to a third embodiment.

Embodiments of the present disclosure will be described below with reference to the drawings. Note that the following description and drawings have been omitted and simplified as appropriate for clarity of explanation. In addition, in each of the following drawings, identical elements are given the same reference numerals, and duplicate explanations will be omitted as necessary.

First Embodiment
As shown in Figure 1, the printed matter inspection device 10 of this embodiment 1 is also capable of inspecting dead zone areas that are not OVDs among the mask areas related to related technologies on the printed matter to be inspected.

First, an example configuration of the print inspection device 10 according to the first embodiment will be described with reference to Figure 4. As shown in Figure 4, the print inspection device 10 according to the first embodiment includes a matching template creation device 11, an inspection template creation device 12, a defect detection device 13, an image input device 14, and a storage device 15.

The matching template creation device 11 is connected to the inspection template creation device 12, the defect detection device 13, and the storage device 15, and includes a calculation unit 111 and an image output unit 112. The matching template creation device 11 creates a matching template image for identifying the OVD attachment position through template matching. As shown in FIG. 5, the matching template creation device 11 calculates the luminance value variance of each pixel in multiple learning OVD images, and uses an image of an area (pattern) where pixels with a relatively low luminance value variance compared to other areas as the matching template image. The calculation unit 111 reads multiple learning OVD images previously stored in the storage device 15 and calculates the luminance value variance of each pixel in the multiple learning OVD images. After the calculation unit 111 calculates the luminance value variance of each pixel, the image output unit 112 extracts an area where pixels with a relatively low luminance value variance compared to other areas are collected, and outputs the image of the extracted area as the matching template image. Here, the matching template image has the shape of a cut-out portion of a pattern drawn on the OVD, and cannot be represented in a specific shape, but for simplicity's sake is shown as a star in Fig. 5. The matching template image output from the matching template creation device 11 is input to the inspection template creation device 12 and the defect detection device 13.

The inspection template creation device 12 is connected to the matching template creation device 11, the defect detection device 13, and the storage device 15, and includes an OVD position detection unit 121, a calculation unit 122, and an image output unit 123. The inspection template creation device 12 creates an inspection template image for detecting defects in the inspection target image.

As shown in Figure 6, inspection of printed matter is performed using a difference image between the image to be inspected and the inspection template image. If a defect is present on the printed matter, only the defective portion will appear in the difference image, allowing the defect to be detected. While the OVD within the mask area does not actually appear in the difference image, the mask area and OVD are illustrated in Figure 6, Figure 3 above, and Figure 9 below to show the positional relationship between the mask area, the OVD, and the defect.

The inspection template creation device 12 creates an inspection template image from multiple learning normal paper images previously stored in the storage device 15. The learning normal paper image is a defect-free image that has been previously confirmed to have no defects on the substrate of the printed material except for the OVD and its surroundings. For example, the learning normal paper image may be a defect-free image in which no defects exist on the substrate of the printed material except for a mask area related to related technology.

When inspecting printed matter, in order to take into account the printing process of the printed matter being inspected and the various variations in normal paper that occur when capturing images of the printed matter, the average brightness value of each pixel in multiple learning normal paper images is calculated to create an inspection template image, as shown in Figure 7. In other words, the average value image of the learning normal paper images is used as the inspection template image.

In the print inspection method according to the related art, the pixels in the area where the OVD may exist (the mask area according to the related art) are not added to the inspection template image, including the dead zone area, taking into account the positional misalignment of the OVD. In contrast, in this embodiment 1, the OVD attachment position can be identified by template matching using a matching template image. Therefore, in this embodiment 1, as shown in Figure 8, the pixels in the dead zone area of the mask area according to the related art can be added to the inspection template image (i.e., the mask area of the inspection template image can be narrowed).

The OVD position detection unit 121 identifies the OVD attachment position for each of the multiple normal learning sheets using a matching template created by the matching template creation device 11. The calculation unit 122 adds each pixel in the area excluding the OVD attachment position identified by the OVD position detection unit 121 to the inspection template image for each of the multiple normal learning sheets. The calculation unit 122 then calculates the average brightness value of each pixel in the area excluding the OVD attachment position on the multiple normal learning sheets. The image output unit 123 outputs an image in which the average brightness value of each pixel calculated by the calculation unit 122 is overwritten on each pixel of the inspection template image as the inspection template image. The inspection template image output from the inspection template creation device 12 is input to the defect detection device 13.

The image input device 14 is connected to the defect detection device 13 and includes an imaging unit 141 and an image output unit 142. The imaging unit 141 captures an image of the printed material to be inspected. The image output unit 142 outputs the image obtained by the imaging unit 141 as the image to be inspected. The image to be inspected output from the image input device 14 is input to the defect detection device 13.

The defect detection device 13 is connected to the matching template creation device 11, the inspection template creation device 12, and the image input device 14, and includes an OVD position detection unit 131, an OVD mask setting unit 132, a defect difference calculation unit 133, and a judgment unit 134. The defect detection device 13 detects defects in the inspection target image. As shown in FIG. 9 , the OVD position detection unit 131 identifies the OVD attachment position in the inspection target image using the matching template image created by the matching template creation device 11. The OVD mask setting unit 132 performs masking processing limited to the OVD based on the position information of the OVD attachment position identified by the OVD position detection unit 131. The defect difference calculation unit 133 calculates a difference image between the inspection template image created by the inspection template creation device 12 and the inspection target image in which the OVD attachment position has been masked by the OVD mask setting unit 132. The determination unit 134 determines whether or not a defect exists in the inspection target image based on the difference image calculated by the defect difference calculation unit 133 .

In the print inspection method according to the related art, the area where the OVD may exist (the mask area according to the related art) is masked, taking into account the misalignment of the OVD. In contrast, in this embodiment 1, the OVD attachment position in the image to be inspected can be identified. Therefore, in this embodiment 1, it is possible to limit the masking to the OVD, eliminating the need for a wide-area mask that takes into account the misalignment of the OVD. As a result, it is also possible to inspect the dead zone area of the mask area according to the related art.

Below, with reference to Figure 10, an example of the flow of the matching template image creation process S10, the inspection template image creation process S11, and the inspection process S12 in the print inspection device 10 of this embodiment 1 is described.

First, in the matching template creation process S10, the matching template creation device 11 inputs multiple training OVD images read from the storage device 15 and expands them in memory (not shown) (S101). As shown in FIG. 5, the training OVD images read here must be cropped to include the OVD and its surrounding area, and the OVD positions must be aligned in advance across the multiple training OVD images. Next, the matching template creation device 11 calculates the luminance value of each pixel in each of the multiple training OVD images input in S101 and adds the calculated luminance values of each pixel to the array in memory corresponding to each pixel in the training OVD image (S102). In other words, the luminance values of pixels at the same position are added across the multiple training OVD images. The process of S102 is performed for the number of training OVD images input, i (i is an integer greater than or equal to 2). The matching template creation device 11 repeats the brightness value addition process for the number of input images, and then calculates the brightness value variance of each pixel based on the brightness values of each pixel stored in the array in memory (S103). Next, the matching template creation device 11 extracts, from the regions on the learning OVD image, regions with relatively low brightness value variance compared to other regions (S104). Next, the matching template creation device 11 outputs the image of the region with low brightness value variance extracted in S104 as a matching template image to the inspection template creation device 12 and the defect detection device 13 (S105).

Next, in the inspection template creation process S11, the inspection template creation device 12 first inputs multiple learning normal paper images read from the storage device 15 and stores them in memory (not shown) (S111). The learning normal paper images read here must be images that have been confirmed in advance to be free of defects on the substrate of the printed material, excluding the OVD and its surrounding area. Next, the inspection template creation device 12 reads the matching template image created by the matching template creation device 11 (S112). Next, for each of the multiple learning normal paper images input in S111, the inspection template creation device 12 uses the matching template image read in S112 to identify the OVD attachment position on the learning normal paper image by template matching (S113). Next, the test template creation device 12 calculates the luminance value of each pixel in the area of the learning normal paper image, excluding the OVD attachment position identified in S113, and adds the calculated luminance value of each pixel to the array in memory corresponding to each pixel in the learning normal paper image (S114). That is, the luminance values of pixels at the same position are added across multiple learning normal paper images. The processes of S113 and S114 are performed for the number of input learning normal paper images, j (j is an integer greater than or equal to 2). After repeating the process of identifying the OVD attachment position and the process of adding luminance values for the number of input learning normal paper images, the test template creation device 12 calculates the average luminance value of each pixel by dividing the luminance value of each pixel stored in the array in memory by the number of input learning normal paper images (S115). However, typically, the number of learning normal paper images (input number) to be added varies for each pixel. Therefore, it should be noted that the divisor also varies for each pixel. Thereafter, the inspection template creation device 12 overwrites each pixel of the inspection template image with the average brightness value of each pixel stored in the array on the memory (S116), and outputs the inspection template image to the defect detection device 13 (S117).

Next, in the inspection process S12, the defect detection device 13 first expands the inspection target image input from the image input device 14 in memory (S121). Next, the defect detection device 13 reads the matching template image created by the matching template creation device 11 (S122). Next, the defect detection device 13 uses the matching template image read in S122 to identify the attachment position of the OVD attached to the inspection target image by template matching (S123).

Here, if the matching score for template matching is less than 95% of the matching score for a preset reference image, the defect detection device 13 will not perform further processing. Possible reasons for a low matching score include the OVD not being affixed to the printed material, a portion of the affixed OVD being missing, or the OVD being misaligned beyond the amount of misalignment that would normally occur, all of which are caused by defects in the OVD itself. Inspection target images with defects in the OVD itself are not subject to inspection in this embodiment 1. It should be noted that the above matching score of 95% is an example and is not limited to this value.

Next, the defect detection device 13 places a mask over the OVD attachment position identified in S123 and sets the area where the mask is placed as an area not to be inspected (S124). Next, the defect detection device 13 reads the inspection template image created by the inspection template creation device 12 (S125) and calculates a difference image between the inspection target image on which the mask is placed in S124 and the inspection template image (S126). If a defect exists in the inspection target image, only the defect will appear in the difference image. Therefore, the defect detection device 13 inspects the difference image, including the dead zone area (S127). If an area in the difference image is detected where a difference exceeding a predetermined shape or size is detected, that area becomes a defect candidate.

As described above, according to the first embodiment, the matching template creation device 11 creates a matching template image for identifying the OVD attachment position through template matching. The defect detection device 13 uses the matching template image to identify the OVD attachment position in the inspection target image, masks the identified OVD attachment position, and detects defects in the inspection target image based on a difference image between the inspection target image in which the OVD attachment position has been masked and the inspection template image.

In this way, in this embodiment 1, the defect detection device 13 can identify the OVD attachment position in the inspection target image using a matching template image. Therefore, it is possible to limit the masking to the OVD, eliminating the need for a wide-area mask that takes into account OVD misalignment. As a result, it is possible to inspect even the dead zone areas of the mask areas used in related technologies.

The matching template creation device 11 calculates the brightness value variance of each pixel in multiple learning OVD images, and creates an image of an area with a relatively small brightness value variance compared to other areas as a matching template image.

In addition, in this embodiment 1, the inspection template creation device 12 uses a matching template image to identify the OVD attachment position for each of the multiple learning normal paper images, calculates the average brightness value of each pixel in areas other than the OVD attachment position in the multiple learning normal paper images, and creates an inspection template image by overwriting each pixel in the inspection template image with the calculated average brightness value of each pixel.

In this way, in this embodiment 1, the inspection template creation device 12 can identify the OVD attachment position in each of multiple learning normal paper images using the matching template image. Therefore, pixels in the dead zone area of the mask area related to the related technology can be added to the inspection template image. This makes it possible to create an inspection template image that can be used for inspection by the defect detection device 13.

<Second Embodiment>
Next, a configuration example of a print inspection device 20 according to a second embodiment will be described with reference to Fig. 11. The second embodiment corresponds to an embodiment that is a higher-level concept of the first embodiment described above.

As shown in Figure 11, the print inspection device 20 according to the second embodiment includes a matching template creation unit 21 and a defect detection unit 22. The print inspection device 20 according to the second embodiment is a device that inspects prints to which an OVD is attached.

The matching template creating unit 21 creates a matching template image for identifying the OVD attachment position by template matching.
The defect detection unit 22 uses a matching template image to identify the OVD attachment position in the inspection target image obtained by photographing the printed matter to be inspected, masks the identified OVD attachment position, and detects defects in the inspection target image based on the difference image between the inspection target image in which the OVD attachment position has been masked and the inspection template image.

This allows the defect detection unit 22 to identify the OVD attachment position in the inspection target image using a matching template image. Therefore, masking can be limited to the OVD, eliminating the need for a wide-area mask that takes into account OVD misalignment. As a result, it becomes possible to inspect even the dead zone areas of the masked areas used in related technologies.

The matching template creation unit 21 may calculate the brightness value of each pixel in each of the multiple training OVD images, calculate the brightness value variance of each pixel based on the brightness value of each pixel in each of the multiple training OVD images, extract an area with a relatively small brightness value variance compared to other areas, and create an image of the extracted area as a matching template image. Furthermore, each of the multiple training OVD images may be an image in which an area including the OVD and its surroundings has been cut out, and the position of the OVD may be aligned between the multiple training OVD images.

The print inspection device 20 according to the second embodiment may further include an inspection template creation unit that creates an inspection template image. The inspection template creation unit may use a matching template image to identify the OVD attachment position in each of the multiple learning normal paper images, calculate the luminance value of each pixel in the area other than the identified OVD attachment position, calculate the average luminance value of each pixel based on the luminance value of each pixel in the area other than the OVD attachment position in each of the multiple learning normal paper images, and create the inspection template image by overwriting each pixel in the inspection template image with the calculated average luminance value of each pixel.

This allows the inspection template creation unit to identify the OVD attachment position in each of the multiple learning normal paper images using the matching template image. Therefore, pixels in the dead zone area of the mask area according to the related art can be added to the inspection template image. This makes it possible to create an inspection template image that can be used for inspection by the defect detection unit 22.
Each of the plurality of learning normal paper images may be an image that has been confirmed to have no defects in areas other than the OVD and its surroundings.

<Third Embodiment>
Next, an example of the hardware configuration of the print inspection device 30 according to the third embodiment will be described with reference to FIG.
As shown in FIG. 12 , a print inspection device 30 according to the third embodiment includes a processor 31 and a memory 32 .

Processor 31 may be, for example, a microprocessor, an MPU (Micro Processing Unit), or a CPU (Central Processing Unit). Processor 31 may include multiple processors.

Memory 32 is composed of a combination of volatile memory and non-volatile memory. Memory 32 may also include storage located remotely from processor 31. In this case, processor 31 may access memory 32 via an I (Input)/O (Output) interface (not shown).

The printed matter inspection devices 10, 20 according to the first and second embodiments described above may have the hardware configuration shown in FIG. 12. A program is stored in the memory 32. This program includes a set of instructions (or software code) that, when loaded into a computer, causes the computer to perform one or more of the functions described in the first and second embodiments described above. The components of the printed matter inspection devices 10, 20 described above may be realized by the processor 31 reading and executing the program stored in the memory 32. Furthermore, the storage functions of the components of the printed matter inspection devices 10, 20 described above may be realized by the memory 32.

The above-described programs may also be stored on non-transitory computer-readable media or tangible storage media. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The programs may also be transmitted on transitory computer-readable media or communication media. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

The present disclosure has been described above with reference to the embodiments, but the present disclosure is not limited to the above-described embodiments. Various modifications that would be understood by a person skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure.

REFERENCE SIGNS LIST 10 Printed matter inspection device 11 Matching template creation device 111 Calculation unit 112 Image output unit 12 Inspection template creation device 121 OVD position detection unit 122 Calculation unit 123 Image output unit 13 Defect detection device 131 OVD position detection unit 132 OVD mask setting unit 133 Defect difference calculation unit 134 Determination unit 14 Image input device 141 Imaging unit 142 Image output unit 15 Storage device 20 Printed matter inspection device 21 Matching template creation unit 22 Defect detection unit 30 Printed matter inspection device 31 Processor 32 Memory

Claims (6)

A print inspection device that inspects a print to which an OVD (Optical Variable Device) is attached,
a matching template creation unit that creates a matching template image for identifying the attachment position of the OVD by template matching;
a defect detection unit that uses the matching template image to identify an OVD attachment position in an inspection object image obtained by photographing the printed matter, masks the identified OVD attachment position, and detects defects in the inspection object image based on a difference image between the inspection object image in which the OVD attachment position has been masked and the inspection template image;
Equipped with
The matching template creation unit
For each of the plurality of learning OVD images, a luminance value of each common pixel in the learning OVD image is calculated;
calculating a variance of brightness values of each pixel based on brightness values of the pixels common to each of the plurality of learning OVD images;
Extracting areas with relatively small variance of brightness values compared to other areas,
creating an image of the extracted region as the matching template image;
Print inspection equipment. Each of the plurality of training OVD images is an image obtained by cutting out an area including the OVD and its surroundings, and the positions of the OVDs are aligned among the plurality of training OVD images.
The print inspection device according to claim 1 . an inspection template creation unit that creates the inspection template image,
The inspection template creation unit
For each of a plurality of learning normal paper images, the matching template image is used to identify an OVD attachment position in the learning normal paper image, and a luminance value of each pixel in an area other than the identified OVD attachment position is calculated;
calculating an average brightness value of each pixel based on the brightness value of each pixel in an area other than the OVD attachment position in each of the plurality of learning normal paper images;
creating the inspection template image by overwriting each pixel in the inspection template image with the calculated average luminance value of each pixel;
The print inspection device according to claim 1 or 2 . Each of the plurality of learning normal paper images is an image that has been confirmed to have no defects in areas other than the OVD and its surroundings.
The print inspection device according to claim 3 . A print inspection method performed by a print inspection device that inspects a print to which an OVD (Optical Variable Device) is attached, comprising:
a matching template creation step of creating a matching template image for identifying the attachment position of the OVD by template matching;
a defect detection step of using the matching template image to identify an OVD attachment position in an inspection object image obtained by photographing the printed matter, masking the identified OVD attachment position, and detecting defects in the inspection object image based on a difference image between the inspection object image in which the OVD attachment position has been masked and the inspection template image;
Including,
In the matching template creation step,
For each of the plurality of learning OVD images, a luminance value of each common pixel in the learning OVD image is calculated;
calculating a variance of brightness values of each pixel based on brightness values of the pixels common to each of the plurality of learning OVD images;
Extracting areas with relatively small variance of brightness values compared to other areas,
creating an image of the extracted region as the matching template image;
Print inspection methods. A program to be executed by a print inspection device that inspects a print to which an OVD (Optical Variable Device) is attached,
a matching template creation step of creating a matching template image for identifying the attachment position of the OVD by template matching;
a defect detection step of using the matching template image to identify an OVD attachment position in an inspection object image obtained by photographing the printed matter, masking the identified OVD attachment position, and detecting defects in the inspection object image based on a difference image between the inspection object image in which the OVD attachment position has been masked and the inspection template image;
Including,
In the matching template creation step,
For each of the plurality of learning OVD images, a luminance value of each common pixel in the learning OVD image is calculated;
calculating a variance of brightness values of each pixel based on brightness values of the pixels common to each of the plurality of learning OVD images;
Extracting areas with relatively small variance of brightness values compared to other areas,
creating an image of the extracted region as the matching template image;
program.