JP7643112B2 - Inspection device, inspection method, and program - Google Patents

Description

The present invention relates to an inspection device, an inspection method, and a program.

In recent years, the quality of an object to be inspected has been determined by processing image data obtained by photographing the object.

For example, Patent Document 1 discloses a technique for accurately inspecting defects such as poor density and printing defects even when a printed matter expands or contracts during the manufacturing process. Specifically, a matching image is created by pattern matching between an image of the printed matter to be inspected and a position reference image. The reference position image is an image to which reference coordinates are assigned as a reference position when judging the quality of the printed matter. Then, a level correction image is created by correcting the density of the base material in the matching image to match the reference density that is the reference when judging the quality of the printed matter. Next, an upper threshold image and a lower threshold image are created, which are at least the upper and lower limits of position variation within the acceptable range when judging the quality of the printed matter. Next, the level correction image is compared with the upper and lower threshold images, respectively, and abnormal pixels that exceed the threshold value of the upper or lower threshold image are counted within a judgment area of any size of the level correction image, to judge the quality of the printed matter.

Patent Document 2 discloses the following technology. First, the printed surface of the printed material is optically scanned to extract a density signal, and this density signal is sampled to extract the desired number of density sample data. Next, from this density sample data, an appropriate number of data items are extracted, starting from the highest density, and an appropriate number of data items are extracted, starting from the lowest density. Then, for each of these appropriate numbers of data items, the average value of the highest density data and the average value of the lowest density data are calculated. The difference between these two average values is then found and compared with a predetermined value, and if the result of this comparison is outside a specified range, it is determined that the density is poor.

JP 2014-38425 A Japanese Patent Application Publication No. 05-185574

When image data is used to determine the quality of an object to be inspected, it may not be possible to obtain sufficient resolution, for example when high-speed processing is required. One of the objects of the present invention is to determine the quality of an object to be inspected with high accuracy even in such cases.

According to the present invention, there is provided an image acquisition means for acquiring an image including an inspection object;
a first position determination means for generating first data, which is statistical data of pixel values within a first frame while moving the first frame in a region of the image including the inspection object, and determining a position of the first frame using the first data;
a second position determination means for generating second data, which is statistical data of pixel values within the second frame, while moving a second frame smaller than the first frame within the first frame, and determining a position of the second frame using the second data;
a determination means for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
An inspection apparatus is provided comprising:

According to the present invention, a computer
an image acquisition process for acquiring an image including an object to be inspected;
a first position determination process for generating first data, which is statistical data of pixel values within a first frame, while moving the first frame in a region of the image including the inspection object, and determining a position of the first frame using the first data;
a second position determination process for generating second data, which is statistical data of pixel values within the second frame, while moving a second frame smaller than the first frame within the first frame, and determining a position of the second frame using the second data;
a determination process for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
An inspection method is provided for carrying out the above steps.

According to the present invention, a computer includes:
an image acquisition function for acquiring an image including an object to be inspected;
a first position determination function that generates first data, which is statistical data of pixel values within a first frame while moving the first frame in a region of the image that includes the inspection object, and determines a position of the first frame using the first data;
a second position determination function that generates second data, which is statistical data of pixel values within the second frame, while moving a second frame smaller than the first frame within the first frame, and determines a position of the second frame using the second data;
a determination function for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
A program will be provided to help students develop these skills.

According to the present invention, even when the image resolution is insufficient, the quality of the inspection object can be determined with high accuracy.

FIG. 1 is a diagram for explaining a usage environment of an inspection device according to an embodiment. FIG. 2 illustrates an example of a functional configuration of an inspection apparatus. FIG. 2 is a diagram illustrating an example of an image generated by an imaging device. FIG. 11 is a diagram illustrating an example of an operation of a first position determining unit. FIG. 11 is a diagram illustrating an example of an operation of a second position determining unit. FIG. 2 illustrates an example of a hardware configuration of an inspection device. 10 is a flowchart illustrating an example of a process performed by an inspection device.

The following describes an embodiment of the present invention with reference to the drawings. Note that in all drawings, similar components are given similar reference numerals and descriptions will be omitted where appropriate.

Figure 1 is a diagram for explaining the environment in which an inspection device 10 according to an embodiment is used. The inspection device 10 is used together with an imaging device 20. The imaging device 20 captures an image of an object to be inspected, generates an image, and transmits the image to the inspection device 10. The inspection device 10 processes the image to determine whether the object to be inspected is good or bad.

Although not shown, when the imaging device 20 is imaging the object 30, the amount of light incident on the object 30 is constant. As an example, the relative positions of the light source and imaging device 20 with respect to the object 30 during imaging are constant. This is because the inspection device 10 uses pixel values of the image when determining whether the inspection object is good or bad. Note that when the image is a grayscale (monochrome image), the pixel value of each pixel is uniquely determined. On the other hand, when the image is a color image, the inspection device 10 may, for example, calculate pixel values on the grayscale using the pixel values of each color and use these pixel values, or may use the pixel value of a specific color (for example, blue in RGB).

In the example shown in this figure, the inspection target is a part of the object 30. The object 30 is, for example, a printed matter such as a banknote, pamphlet, or poster, and the inspection target is a specific part of this printed matter. The inspection device 10 judges whether the inspection target is good or bad, for example, whether the print density is good or bad. The judgment speed at this time is, for example, 100 milliseconds or less per sheet, or even 20 milliseconds or less. Note that when the object 30 is a banknote, the inspection target is a specific mark. This mark is, for example, at least a part of the euroion.

When the object 30 is a printed matter, the imaging device 20 generates an image immediately after the printed matter is printed and transmits the image to the inspection device 10 in real time. The inspection device 10 judges the quality of the inspection object each time it acquires an image. When the printed matter is printed continuously and all the printed matters are inspected, the inspection device 10 and the imaging device 20 perform imaging and inspection continuously.

Figure 2 is a diagram showing an example of the functional configuration of the inspection device 10. In the example shown in this figure, the inspection device 10 includes an inspection device 10, a first position determination unit 120, a second position determination unit 130, a determination unit 140, and an output unit 150.

The image acquisition unit 110 acquires the image generated by the imaging device 20.

The first position determination unit 120 sets an area in the image acquired by the imaging device 20 where the first frame should be placed. The first frame is preferably large enough to include the inspection target, but is not limited to this size. The size of the first frame is, for example, 0.7 to 1.5 times the size of the inspection target, but is not limited to this size. The first position determination unit 120 moves the first frame in the area of the image including the inspection target and generates statistical data (hereinafter referred to as first data) of pixel values inside the first frame at each position. The first data is, for example, the variance of pixel values, but may be any other statistical value as long as it is an index indicating the magnitude of variation in pixel values. The first position determination unit 120 then uses this first data to determine the position of the first frame.

The second position determination unit 130 moves a second frame, which is smaller than the first frame, within the first frame, and generates statistical data of pixel values within the second frame at each position (hereinafter referred to as second data). The size of the second frame is preferably capable of including the inspection object within it, and is, for example, between 0.5 and 1.5 times the inspection object, but is not limited to this size. The second data is, for example, the variance of pixel values, but may be any other statistical value as long as it is an index indicating the magnitude of variation in pixel values. The second position determination unit 130 then uses the second data to determine the position of the second frame.

Here, we assume that the area surrounding the object to be inspected is plain (but may have a particular color) or has a color with less shading compared to the object to be inspected. One example of such a case is when the object 30 is a printed matter such as a banknote, and the object to be inspected is a mark.

The first frame includes the inspection object and the area surrounding the inspection object. In this case, if the inspection object is located approximately in the center of the first frame, the variation in pixel values within the first frame will be large. Therefore, the first position determination unit 120 determines the position of the first frame so that the variation in pixel values is maximized (for example, so that the variance is maximized). At the position determined by the first position determination unit 120, the first frame includes the inspection object within it. Note that an example of such a case is when the object 30 is a printed matter such as a banknote, and the inspection object is a mark.

The second frame is smaller than the first frame. Therefore, the proportion of the second frame that is taken up by the periphery of the inspection object is smaller than that of the first frame. It is preferable that the size of the second frame is approximately the same as or slightly larger than the inspection object. In this case, when the inspection object is positioned approximately in the center of the second frame, the variation in pixel values within the second frame is small. Therefore, the second position determination unit 130 determines the position of the second frame so that the variation in pixel values is minimized (for example, so that the variance is minimized). At the position determined by the second position determination unit 130, the second frame includes the inspection object inside.

The determination unit 140 determines whether or not there is an abnormality in the test subject using data relating to pixel values within the first frame (hereinafter referred to as third data) and data relating to pixel values within the second frame (hereinafter referred to as fourth data).

For example, when the object 30 is a printed matter, the inspection object is a part of the printed matter, and the judgment unit 140 judges whether the density of the inspection object is light, an example of the third data is one of the maximum and minimum pixel values. In this case, the fourth data is the other of the maximum and minimum pixel values. For example, when the color of the inspection object is darker than the color of the base (surroundings) of the inspection object (for example, when a mark of a darker color than the base is printed on a white or light-colored base), the third data is the maximum pixel value, and the fourth data is the minimum pixel value. On the other hand, when the color of the inspection object is darker than the color of the base (surroundings) of the inspection object (for example, when a mark of a lighter color than the base is printed on a dark-colored base such as black), the third data is the minimum pixel value, and the fourth data is the maximum pixel value. Then, the judgment unit 140 judges whether or not there is an abnormality using at least one of the ratio and difference between the third data and the fourth data. For example, when the third data is the maximum pixel value and the fourth data is the minimum pixel value, the judgment unit 140 judges that the density of the inspection object is abnormal if the third data/fourth data is equal to or less than the reference value. Furthermore, when the third data is the minimum pixel value and the fourth data is the maximum pixel value, the determination unit 140 determines that the density of the test object is abnormal when the fourth data/third data is equal to or less than the reference value. In either case, the determination unit 140 may determine that the density of the test object is abnormal when the difference between the third data and the fourth data is equal to or less than the reference value.

The determination unit 140 may arrange the pixels in the first frame in ascending (or descending) order of pixel value, calculate the average of a predetermined number of the top pixel values, and use this average as the third data. In this case, the determination unit 140 may arrange the pixels in the second frame in ascending (or descending) order of pixel value, calculate the average of a predetermined number of the top pixel values, and use this average as the fourth data. Furthermore, the determination unit 140 may use the average of the pixel values in the first frame (excluding the second frame) as the third data, and the average of the pixel values in the second frame as the fourth data.

The output unit 150 outputs the determination result of the determination unit 140. This output destination may be a display or a speaker. The output unit 150 may perform a predetermined output only when an object 30 having an abnormality is detected.

Next, specific examples of the processing performed by the first position determination unit 120, the second position determination unit 130, and the determination unit 140 will be described with reference to Figures 3, 4, and 5. In these figures, the target object 30 is a printed matter such as a banknote.

Figure 3 is a diagram showing an example of an image generated by the imaging device 20. In the example shown in this figure, the inspection object 32 is a mark printed on a substrate. In addition, the inspection object 32 is surrounded by a margin area 34, with the substrate being almost completely visible. In addition, a predetermined pattern or the like is printed outside the margin area 34. The image 210 generated by the imaging device 20 includes the inspection object 32 and margin area 34 inside, and also includes the area outside the margin area 34.

Figure 4 is a diagram showing an example of the operation of the first position determination unit 120. The first frame 212 set by the first position determination unit 120 is sized so as to include as little of the area outside the margin area 34 as possible. Therefore, when the position of the first frame 212 is appropriately set (for example, so that the variation in pixel values within the first frame 212 is maximized), the area of the image 210 cut out by the first frame 212 (i.e., the area located inside the first frame 212) is almost entirely occupied by the inspection object 32 and the margin area 34.

Figure 5 is a diagram showing an example of the operation of the second position determination unit 130. The second frame 214 set by the second position determination unit 130 is smaller than the first frame 212, but includes the inspection object 32 inside and is sized to include as little of the margin area 34 as possible. Therefore, when the position of the second frame 214 is appropriately set within the first frame 212 (for example, so that the variation in pixel values within the second frame 214 is minimized), the area of the image 210 cut out by the second frame 214 (i.e., the area located inside the second frame 214) is almost entirely occupied by the inspection object 32. By performing such processing, the second position determination unit 130 can cut out the inspection object 32 from the image with high accuracy even if the image resolution is low. In addition, the inspection object 32 may be deformed due to temperature, humidity, etc. Even in such a case, the inspection object 32 can be cut out from the image with high accuracy.

When the color of the margin area 34 is lighter than the color of the inspection object 32, or when the margin area 34 is white, the maximum pixel value in the first frame 212 indicates the pixel value of the margin area 34. The minimum pixel value in the second frame 214 indicates the pixel value of the inspection object 32. Therefore, the determination unit 140 can determine whether or not there is an abnormality in the density of the inspection object 32 by comparing the maximum pixel value in the first frame 212 with the minimum pixel value in the second frame 214.

On the other hand, if the color of the margin area 34 is darker than the color of the inspection object 32, the minimum pixel value in the first frame 212 indicates the pixel value of the margin area 34. Furthermore, the maximum pixel value in the second frame 214 indicates the pixel value of the inspection object 32. Therefore, the judgment unit 140 can judge whether or not there is an abnormality in the density of the inspection object 32 by comparing the minimum pixel value in the first frame 212 with the maximum pixel value in the second frame 214.

By performing this type of processing, the judgment unit 140 can judge with high accuracy whether the inspection object 32 is good or bad, even if the image resolution is low.

Note that multiple inspection targets 32 may be set for one object 30. In this case, the inspection device 10 performs a process of generating third data and fourth data for each of the multiple inspection targets 32. The determination unit 140 then uses these multiple sets of third data and fourth data to determine whether or not the object has an abnormality.

For example, the determination unit 140 may determine whether or not there is an abnormality for each of the multiple inspection targets 32, and use these determination results to determine whether or not there is an abnormality in the object 30. In this case, the determination unit 140 determines that the object 30 is abnormal when a predetermined percentage or more of the inspection targets 32 are determined to be abnormal. Furthermore, when the multiple inspection targets 32 are the same mark printed in different locations (e.g., each is at least a part of a europium), the determination unit 140 may calculate the average value of the third data for each of the multiple inspection targets 32 and the average value of the fourth data for each of the multiple inspection targets 32, and use these two average values instead of the third data and the fourth data.

Figure 6 is a diagram showing an example of the hardware configuration of the inspection device 10. The inspection device 10 has a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input/output interface 1050, and a network interface 1060.

The bus 1010 is a data transmission path for the processor 1020, memory 1030, storage device 1040, input/output interface 1050, and network interface 1060 to transmit and receive data to and from each other. However, the method of connecting the processor 1020 and other components to each other is not limited to a bus connection.

The processor 1020 is a processor realized by a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

Memory 1030 is a main storage device realized by RAM (Random Access Memory) or the like.

The storage device 1040 is an auxiliary storage device realized by a hard disk drive (HDD), a solid state drive (SSD), a memory card, or a read only memory (ROM). The storage device 1040 stores program modules that realize each function of the inspection device 10 (e.g., the image acquisition unit 110, the first position determination unit 120, the second position determination unit 130, the judgment unit 140, and the output unit 150). The processor 1020 loads each of these program modules into the memory 1030 and executes them, thereby realizing each function corresponding to the program module.

The input/output interface 1050 is an interface for connecting the inspection device 10 to various input/output devices. For example, the inspection device 10 may communicate with the imaging device 20 via the input/output interface 1050.

The network interface 1060 is an interface for connecting the inspection device 10 to a network. This network is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network). The method for connecting the network interface 1060 to the network may be a wireless connection or a wired connection. However, the inspection device 10 does not have to have the network interface 1060.

Figure 7 is a flowchart showing an example of processing performed by the inspection device 10. When a new object 30 is present (for example, when a new printed matter is printed as the object 30), the imaging device 20 captures the object 30 and generates an image. The inspection device 10 performs the processing shown in this figure each time the imaging device 20 generates an image. This processing is preferably performed in real time.

The image acquisition unit 110 of the inspection device 10 acquires the image transmitted from the imaging device 20 (step S10). Then, the first position determination unit 120 of the inspection device 10 determines the position of the first frame in this image (step S20). Next, the second position determination unit 130 of the inspection device 10 determines the position of the second frame within the first frame determined in step S20. At this time, when the second position determination unit 130 moves the second frame, it is preferable that the initial position of the second frame includes the center of the first frame (for example, so that the centers overlap) (step S30). Details of the processing performed in steps S20 and S30 are as described using Figures 2 to 5.

Then, the judgment unit 140 of the inspection device 10 judges whether the inspection object is good or bad (step S40). Details of the process performed in step S40 are as explained using Figures 2 to 5. Then, the output unit 150 outputs this judgment result (step S50).

As described above, according to this embodiment, by using the inspection device 10, the quality of the inspection object can be determined with high accuracy even when the resolution of the image generated by the imaging device 20 is low. In particular, when the inspection object is a printed matter and the base material of this printed matter is paper, the shape and size of the inspection object itself changes with temperature and humidity. More specifically, there are cases where the shape and size of the inspection object changes due to temperature and humidity during printing, and cases where the shape and size of the inspection object changes due to temperature and humidity during inspection. Even in such cases, by using the inspection device 10, the quality of the inspection object can be determined with high accuracy.

The above describes the embodiments of the present invention with reference to the drawings, but these are merely examples of the present invention, and various configurations other than those described above can also be adopted.

In addition, in the multiple flow charts used in the above explanation, multiple steps (processing) are described in order, but the order of execution of the steps performed in each embodiment is not limited to the order described. In each embodiment, the order of the steps shown in the figures can be changed to the extent that does not cause any problems in terms of content. In addition, each of the above-mentioned embodiments can be combined to the extent that the content is not contradictory.

A part or all of the above-described embodiments may be described as, but is not limited to, the following supplementary notes.
1. An image acquisition means for acquiring an image including an inspection object;
a first position determination means for generating first data, which is statistical data of pixel values within a first frame while moving the first frame in a region of the image including the inspection object, and determining a position of the first frame using the first data;
a second position determination means for generating second data, which is statistical data of pixel values within the second frame, while moving a second frame smaller than the first frame within the first frame, and determining a position of the second frame using the second data;
a determination means for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
An inspection device comprising:
2. In the inspection device described in 1 above,
An inspection apparatus, wherein the first data and the second data are variances of the pixel values.
3. In the inspection device according to 1 or 2 above,
An inspection device, wherein the inspection object is a part of a printed matter.
4. In the inspection device described in 3 above,
The inspection device, wherein the printed matter is a banknote.
5. In the inspection device according to 3 or 4 above,
the third data relates to one of a maximum value and a minimum value of the pixel values;
The fourth data relates to the other of the maximum and minimum pixel values.
6. In the inspection device described in 5 above,
The determination means determines the presence or absence of the abnormality using at least one of a ratio and a difference between the third data and the fourth data.
7. In the inspection device according to 3 or 4 above,
the third data is an average value of a predetermined number of top pixel values when the plurality of pixel values in the first frame are sorted in ascending or descending order,
The fourth data is an average value of a predetermined number of top pixel values when the multiple pixel values in the second frame are sorted in ascending or descending order.
8. In the inspection device according to any one of 3 to 7 above,
The printed matter has a plurality of the inspection targets,
The determination means determines the presence or absence of the abnormality using the third data and the fourth data for each of the plurality of inspection objects.
9. The computer:
an image acquisition process for acquiring an image including an object to be inspected;
a first position determination process for generating first data, which is statistical data of pixel values within a first frame, while moving the first frame in a region of the image including the inspection object, and determining a position of the first frame using the first data;
a second position determination process for generating second data, which is statistical data of pixel values within the second frame, while moving a second frame smaller than the first frame within the first frame, and determining a position of the second frame using the second data;
a determination process for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
An inspection method.
10. In the inspection method according to the above 9,
An inspection method, wherein the first data and the second data are variances of the pixel values.
11. In the inspection method according to 9 or 10 above,
An inspection method, wherein the inspection object is a part of a printed matter.
12. In the inspection method according to 11 above,
The inspection method, wherein the printed matter is a banknote.
13. In the inspection method according to 11 or 12 above,
the third data relates to one of a maximum value and a minimum value of the pixel values;
An inspection method, wherein the fourth data relates to the other of the maximum and minimum values of the pixel values.
14. In the inspection method according to 13 above,
An inspection method, wherein in the determination process, the computer determines the presence or absence of the abnormality using at least one of a ratio and a difference between the third data and the fourth data.
15. In the inspection method according to 11 or 12 above,
the third data is an average value of a predetermined number of top pixel values when the plurality of pixel values in the first frame are sorted in ascending or descending order,
An inspection method, wherein the fourth data is an average value of a predetermined number of top pixel values when the multiple pixel values in the second frame are sorted in ascending or descending order.
16. In the inspection method according to any one of 11 to 15 above,
The printed matter has a plurality of the inspection targets,
The inspection method, wherein in the judgment process, the computer judges the presence or absence of the abnormality using the third data and the fourth data for each of the plurality of inspection objects.
17. On the computer:
an image acquisition function for acquiring an image including an object to be inspected;
a first position determination function that generates first data, which is statistical data of pixel values within a first frame while moving the first frame in a region of the image that includes the inspection object, and determines a position of the first frame using the first data;
a second position determination function that generates second data, which is statistical data of pixel values within the second frame, while moving a second frame smaller than the first frame within the first frame, and determines a position of the second frame using the second data;
a determination function for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
A program that allows you to have
18. In the program according to 17 above,
The first data and the second data are variances of the pixel values.
19. In the program according to 17 or 18 above,
A program in which the inspection object is a part of a printed matter.
20. In the program according to 19 above,
The program, wherein the printed matter is a banknote.
21. In the program according to 19 or 20 above,
the third data relates to one of a maximum value and a minimum value of the pixel values;
The fourth data relates to the other of the maximum and minimum values of the pixel values.
22. In the program according to 21 above,
The determination function determines the presence or absence of the abnormality using at least one of a ratio and a difference between the third data and the fourth data.
23. In the program according to 19 or 20 above,
the third data is an average value of a predetermined number of top pixel values when the plurality of pixel values in the first frame are sorted in ascending or descending order,
The fourth data is an average value of a predetermined number of top pixel values when the multiple pixel values in the second frame are sorted in ascending or descending order.
24. In the program according to any one of claims 19 to 23,
The printed matter has a plurality of the inspection targets,
The determination function determines the presence or absence of the abnormality using the third data and the fourth data for each of the multiple inspection objects.

REFERENCE SIGNS LIST 10 Inspection device 20 Imaging device 30 Object 32 Inspection object 34 Blank area 110 Image acquisition section 120 First position determination section 130 Second position determination section 140 Determination section 150 Output section 210 Image 212 First pattern 214 Second pattern

Claims (8)

An image acquisition means for acquiring an image including an inspection object;
a first position determination means for generating first data, which is statistical data of pixel values within a first frame while moving the first frame in a region of the image including the inspection object, and determining a position of the first frame using the first data;
a second position determination means for generating second data which is statistical data of pixel values within the second frame while moving a second frame smaller than the first frame within the first frame whose position has been determined by the first position determination means, and determining a position of the second frame using the second data;
a determination means for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
Equipped with
The inspection target is a part of a printed matter, that is, a mark printed on a base,
A margin area is present around the inspection target,
When the inspection object is darker than the background, the third data relates to a maximum value of the pixel value, and the fourth data relates to a minimum value of the pixel value.
When the object to be inspected is thinner than the base, the third data relates to a minimum value of the pixel value, and the fourth data relates to a maximum value of the pixel value . 2. The inspection device according to claim 1,
An inspection apparatus, wherein the first data and the second data are variances of the pixel values. 3. The inspection device according to claim 1 ,
The inspection device, wherein the printed matter is a banknote. In the inspection device according to any one of claims 1 to 3 ,
The determination means determines the presence or absence of the abnormality using at least one of a ratio and a difference between the third data and the fourth data. 3. The inspection device according to claim 1 ,
the third data is an average value of a predetermined number of top pixel values when the plurality of pixel values in the first frame are sorted in ascending or descending order,
The fourth data is an average value of a predetermined number of top pixel values when the multiple pixel values in the second frame are sorted in ascending or descending order. In the inspection device according to any one of claims 1 to 5 ,
The printed matter has a plurality of the inspection targets,
The determination means determines the presence or absence of the abnormality using the third data and the fourth data for each of the plurality of inspection objects. The computer
an image acquisition process for acquiring an image including an object to be inspected;
a first position determination process for generating first data, which is statistical data of pixel values within a first frame, while moving the first frame in a region of the image including the inspection object, and determining a position of the first frame using the first data;
a second position determination process for generating second data, which is statistical data of pixel values within the second frame, while moving a second frame smaller than the first frame within the first frame whose position has been determined by the first position determination process, and determining a position of the second frame using the second data;
a determination process for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
Do the following:
The inspection target is a part of a printed matter, that is, a mark printed on a base,
A margin area is present around the inspection target,
When the inspection object is darker than the background, the third data relates to a maximum value of the pixel value, and the fourth data relates to a minimum value of the pixel value.
When the object to be inspected is thinner than the base, the third data relates to a minimum value of the pixel value, and the fourth data relates to a maximum value of the pixel value . On the computer,
an image acquisition function for acquiring an image including an object to be inspected;
a first position determination function that generates first data, which is statistical data of pixel values within a first frame while moving the first frame in a region of the image that includes the inspection object, and determines a position of the first frame using the first data;
a second position determination function that generates second data, which is statistical data of pixel values within the second frame, while moving a second frame smaller than the first frame within the first frame whose position has been determined by the first position determination function, and determines the position of the second frame using the second data;
a determination function for determining the presence or absence of an abnormality in the inspection object by using third data on the pixel values in the first frame and fourth data on the pixel values in the second frame;
Let them have
The inspection target is a part of a printed matter, that is, a mark printed on a base,
A margin area is present around the inspection target,
When the inspection object is darker than the background, the third data relates to a maximum value of the pixel value, and the fourth data relates to a minimum value of the pixel value.
When the object to be inspected is thinner than the base, the third data relates to a minimum value of the pixel value, and the fourth data relates to a maximum value of the pixel value .

Images