JP2023184321A - Corrugated sheet defect detection method - Google Patents

Abstract

To provide a method for detecting defects of a corrugated board sheet capable of detecting the defects such as stain, tear, and wrinkle with higher accuracy in a shorter processing time in a manufacturing line of the corrugated board sheet.SOLUTION: A back liner surface or a front liner surface of a corrugated board sheet traveling on a manufacturing line is photographed by a camera, and the obtained two-dimensional image (imaging 1 of the corrugated board sheet) is partitioned in a lattice shape to set unit regions 4 each consisting of multiple and the same number of pixels. For each unit area 4, whether or not the corrugated board sheet has the defects is determined on the basis of addition processing for obtaining an addition processing value which is either the total value of gradation values of pixels or an average value obtained by dividing the total value by the number of pixels.SELECTED DRAWING: Figure 3

Description

The present invention relates to a method for detecting defects such as stains, tears, and wrinkles in a corrugated board sheet production line.

Corrugated cardboard sheets are generally manufactured using equipment called a corrugator. In a corrugator, a single facer is manufactured by laminating a corrugated core and a back liner to produce a single-sided corrugated sheet, while a double facer is manufactured by laminating a single-sided corrugated sheet and a front liner, or multiple single-sided corrugated sheets. and a front liner to produce a corrugated board sheet in which one side is a back liner and the other side is a front liner, such as a double-sided corrugated sheet or a double-sided corrugated sheet. The manufactured corrugated board sheet is subjected to creasing and cutting in a slitter scorer parallel to the running direction, and then cut to a predetermined length in a direction perpendicular to the running direction.

When a corrugated board sheet is manufactured through such a process, defects such as stains due to adhesion of machine oil, glue, etc., and tears and wrinkles in the back liner and front liner may occur. Conventionally, as a method for detecting such defects, there has been a method of photographing a corrugated cardboard sheet with a digital camera and analyzing the image.

Specifically, images captured by a digital camera are binarized. In this case, a threshold value is set to detect dark-colored defects that are darker than the base color of the corrugated board sheet, such as stains caused by machine oil or shadows of wrinkles, and dark-colored defects that are lighter than the base color of the corrugated board sheet, such as stains due to adhesion of glue. Two types of binarized images are obtained by separately setting a threshold value for detecting a light-colored defect. For example, as shown in FIG. 5(a), an image 100 including a dark color defect 101 is binarized, and pixels whose gradation value is equal to or greater than a threshold value are converted to "1", and pixels whose tone value is less than the threshold value are converted to "0". As a result, a binarized image 110 in which a black defect image 111 appears as shown in FIG. 5(b) is obtained. Regarding light-colored defects, by converting pixels that are equal to or greater than the threshold value to "0" and pixels less than the threshold value to "1", a binarized image in which the defect appears in black can be similarly obtained.

In the obtained binarized image, if a defective pixel (pixel converted to "0") is isolated, it is considered to be noise, and if defective pixels are clustered within a predetermined range or more, it is considered to be noise. , it is possible to perform processing to determine that the defect is a defect that should be detected. For example, as shown in FIG. 5C, adjacent pixels among the defective pixels are grouped together. Here, for identification purposes, the pixels constituting each of the groups 201 to 204 are numbered 1 to 4, and the non-defective pixel 200 is numbered 0. For images subjected to such processing, the number of pixels constituting each group, the length in the X direction, the length in the Y direction, or the area of each group when two-dimensional coordinates are XY coordinates are determined in advance. By comparing it with a predetermined threshold value, it is possible to determine that the corrugated board sheet has a defect that should be rejected as a defective product. However, in the case of such processing, there is a problem that if the number of pixels determined to be defective or the number of groups to be divided are large, the grouping processing and determination processing take time.

Furthermore, since the image has already been subjected to binarization processing, there is a problem in that defects closer to the ground color than the threshold value (thin defects) cannot be detected at the binarization stage. In FIG. 5B, broken lines schematically indicate that the thin portion of the dark-colored defect 101 in FIG. 5A is missing in the binarized image 110.

Furthermore, in a production line for corrugated cardboard sheets, since the traveling corrugated cardboard sheets are sandwiched and held from above and below by rotatable press rolls, linear dents remain on the corrugated cardboard sheets due to the pressure of the press rolls. This press mark is called a "press mark." When a corrugated board sheet with press marks is photographed, an image is obtained in which the shadow of the depression appears as a dark line. Therefore, when an image 100 having a press mark 105 and a dark-colored defect 101 is binarized as shown in FIG. It is included in the binarized image 110 together with the defect image 111. If the threshold value is set so that the image 115 of the press mark is not included in the binarized image 110, a defect with a density similar to that of the press mark or a defect thinner than the press mark cannot be detected.

Therefore, in view of the above-mentioned circumstances, the present invention aims to provide a method for detecting defects in corrugated cardboard sheets that can detect defects such as stains, tears, and wrinkles with higher accuracy and in a shorter processing time in a corrugated sheet manufacturing line. That is.

In order to solve the above problems, the method for detecting defects in corrugated cardboard sheets according to the present invention includes:
``We use a digital camera to photograph the back liner surface or front liner surface of corrugated cardboard sheets running on the production line.
By dividing the obtained two-dimensional image into a grid, unit areas each consisting of a plurality of the same number of pixels are set,
For each of the unit areas, it is determined that the cardboard sheet has a defect based on an addition process that calculates an addition process value that is either the total value of the tone values of pixels or the average value obtained by dividing the total value by the number of pixels. "to determine whether or not the

Conventionally, it was determined whether or not a defect existed in a corrugated board sheet by binarizing the image captured by a digital camera, but with the present invention, it is possible to determine whether a defect exists in a corrugated board sheet without binarizing it. Determine whether or not the

Specifically, a two-dimensional image obtained by a digital camera is divided into a grid pattern. The two-dimensional image may be captured by a two-dimensional camera, or may be a two-dimensional composite of images captured by a one-dimensional camera. A unit area divided into a grid is made to include a plurality of pixels and the same number of pixels. Then, addition processing is performed for each unit area. The addition process is a process of calculating the total value of tone values of pixels included in a unit area, or a process of calculating an average value obtained by dividing the total value by the number of pixels. Whether the addition processing value is to be the total value or the average value is unified for all unit areas.

Since the addition processing value (total value or average value) is different between a normal unit area where no defect exists and a unit area where a defect is present, a defect can be detected based on this difference. In conventional binarization methods, it was inevitable that some of the gradation information (shade information) would be lost due to threshold settings, but in the present invention, all pixel information (gradation values) is lost through addition processing. , it is possible to make more accurate judgments.

Further, in the above-mentioned conventional technology, the unit of processing is a pixel, but in the present invention, the unit of processing is a unit area consisting of a plurality of pixels, so that the time required for processing can be shortened. Furthermore, in the above-mentioned conventional technology, adjacent pixels among defective pixels are grouped together, so if the number of defective pixels or the number of groups to be divided is large, However, the present invention performs addition processing for each unit area with a constant area, so the time required for processing is always constant regardless of the number of defects. can do.

In addition to the above configuration, the method for detecting defects in corrugated cardboard sheets according to the present invention includes:
"The determination is performed by comparing the addition processing value of the unit area to be determined with the addition processing value of the other unit areas."

For unit areas with no defects, the addition processing value in each unit area becomes the same value. On the other hand, if there is a defect in a unit area, the addition processing value for that unit area will be a different value from the addition processing value for a unit area without defects. At the manufacturing site of corrugated cardboard sheets, the actual situation is that normal corrugated cardboard sheets are manufactured without any defects in most cases, and defects rarely occur. Therefore, the addition processing value of the unit area to be determined is compared with the addition processing value of other unit areas. Normally, there is no difference between the two added values, and it can be determined that there is no defect. On the other hand, if there is a difference between the added values, it is determined that one of the unit areas has a defect. If there are a plurality of other unit regions whose addition processing values are compared with the unit region to be determined, the presence or absence of a defect in the unit region to be determined can be determined more accurately.

In addition to the above configuration, the method for detecting defects in corrugated cardboard sheets according to the present invention includes:
"The corrugated cardboard sheet has linear press marks that are press marks made by press rolls, and in the determination, the unit area to be determined and the unit area to be compared are The mark may be set so that the positional relationship with the image is the same.

Although a press mark is not a defect, the addition processing value is different between a unit area where a press mark exists and a unit area where a press mark does not exist, even if both are normal and free of defects. Therefore, it is necessary to make the conditions regarding press marks the same between the unit areas to be compared. A press mark is a press mark made by a press roll, and since the position where the press roll is installed on the corrugated sheet manufacturing line and the position where the image is taken by the camera are known, it is difficult to determine where the image of the press mark will appear in the image taken. It is also possible to set the unit area to be determined and the unit area to be compared so that the positional relationship with the image of the press mark in the two-dimensional image is the same. For example, since press marks are formed in a straight line as the corrugated sheet runs, the unit area to be determined and the unit area to be compared are set to be on the same line in the running direction of the corrugated sheet. Alternatively, a unit area divided into a lattice pattern was considered to be a "column" that continued in the running direction of the corrugated cardboard sheet, and multiple rows were considered to be lined up in the width direction of the corrugated cardboard sheet (direction perpendicular to the running direction). In this case, it is possible to specify which columns include press mark images and which columns do not. In this way, if you want to target a unit area where a press mark exists, compare the addition processing value with a unit area that also belongs to a column where a press mark exists, and then target a unit area where a press mark does not exist. In this case, the defect can be detected without being affected by the presence of the press mark by comparing the addition processing value with the unit area belonging to the column where no press mark is present.

As mentioned above, conventional technology that performs binarization could not detect defects as thick as press marks or defects that are thinner than press marks, whereas the present invention is not affected by press marks. , it is possible to detect defects with higher accuracy than conventional image analysis using binarization.

As described above, according to the present invention, it is possible to provide a method for detecting defects in corrugated cardboard sheets that can detect defects such as stains, tears, and wrinkles with higher accuracy and in a shorter processing time in a corrugated sheet manufacturing line. can.

FIG. 3 is a diagram showing the arrangement of lighting and a camera with respect to a cardboard sheet in a defect detection method according to an embodiment of the present invention. 1 is a configuration diagram of a defect detection device used in a defect detection method that is an embodiment of the present invention. (a) is an explanatory diagram of a process of setting a unit area in a two-dimensional image in a defect detection method that is an embodiment of the present invention, and (b) is an explanatory diagram of an image after addition processing. (a) and (b) are diagrams illustrating the setting of other unit areas to be compared with the unit area to be determined. It is a figure explaining the defect detection method and problem by conventional binarization. FIG. 3 is a diagram illustrating the problem of press marks in a conventional defect detection method using binarization.

DESCRIPTION OF THE PREFERRED EMBODIMENTS A method for detecting defects in corrugated cardboard sheets and a defect detection device 20 used in this method will be described below with reference to FIGS. 1 to 4. FIG.

First, the configuration of the defect detection device 20 will be explained. As shown in FIGS. 1 and 2, the defect detection device 20 includes an illumination 21 that projects light onto a corrugated sheet 30 while it is running on a production line, and a camera 22 that photographs the corrugated sheet 30 onto which the light is projected. , and a computer 40 that determines whether or not the corrugated board sheet has a defect based on images taken by the camera 22.

The corrugated sheets targeted for defect detection are corrugated sheets with a back liner on one side and a front liner on the other, such as double-sided corrugated sheets with one or more single-sided corrugated sheets and a front liner pasted together, or double-sided corrugated sheets. Alternatively, it may be a single-sided corrugated sheet in which a corrugated core and a back liner are bonded together. When the target is a corrugated board sheet having a back liner on one side and a front liner on the other side, the lighting 21 and camera 22 are installed between the double facer and the slitter scorer on the production line. In that case, it is possible to provide both a set of lighting 21 and camera 22 that projects light onto the back liner to take pictures, and a set of lighting 21 and camera 22 that projects light onto the front liner and takes pictures. In the case of a single-sided corrugated cardboard sheet, the illumination 21 and camera 22 are installed between a single facer and a double facer, and project light onto the back liner to take a picture.

The illumination 21 projects light from a direction inclined with respect to a perpendicular to the back liner surface or front liner surface of the corrugated cardboard sheet 30. As a result, if the defect is a tear or wrinkle, its shadow is photographed.

In this embodiment, a line sensor camera is used as the camera 22, and a one-dimensional image is acquired in the width direction of the corrugated sheet, that is, in a direction perpendicular to the running direction (Y direction in the drawing) of the corrugated sheet. A one-dimensional image acquired as the cardboard sheet travels is transmitted to the computer 40. The scanning period of a line sensor camera (time to store one line's worth of signals) is generally much shorter than the scanning period of a two-dimensional camera (area camera). A two-dimensional image can be formed at high speed by continuously acquiring one-dimensional images as the corrugated sheet runs at high speed and arranging the acquired one-dimensional images. Furthermore, even if the width and length of the camera 22 is changed due to a change in the type of the corrugated sheet 30, the light receiving element is arranged with a length sufficient to capture a one-dimensional image over the entire width of the corrugated sheet 30. Use what you have.

The computer 40 includes, as a hardware configuration, a storage device including a main storage device and an auxiliary storage device, and a central processing unit (CPU) that performs processing according to a program stored in the storage device.

The storage device includes an image processing program that causes the computer 40 to function as an image processing means 41 that forms a two-dimensional image from a one-dimensional image acquired by the camera 22, and a program that allows the computer 40 to function as an image processing means 41 to form a two-dimensional image from a one-dimensional image acquired by the camera 22, and a program that detects defects in the cardboard sheet based on the formed two-dimensional image. A determination processing program is stored that causes the computer 40 to function as a determination means 42 for determining whether or not the computer 40 has the same.

Note that the storage device stores one-dimensional image data sent from the camera 22, two-dimensional image data after image processing, information on unit areas set on the two-dimensional image, and reference values such as thresholds used for determination. , information regarding defects detected as a result of the determination, etc. can be stored.

The defect inspection device 20 also includes an output device 25 such as a monitor or printer that displays the process and results of processing by the computer 40, and a keyboard or pointing device that inputs various commands and reference values such as thresholds to the computer 40. It further includes an input device 24 such as the like. In addition, the defect inspection device 20 includes an alarm device 26 that notifies the occurrence of an abnormality based on a determination that a defect exists in the corrugated cardboard sheet 30.

The computer 40 of this embodiment is connected to the production control device 27 of the manufacturing line and the office computer 28 of the manufacturer for wired or wireless communication. Information about the cardboard sheet, such as the width and length, can be input from the office computer 28 to the computer 40, and the processing steps and results of the processing by the computer 40 can be transmitted from the computer 40 to the office computer 28. Alternatively, the information on the corrugated sheet and the reference value for determination may be transmitted from the office computer 28 to the production control device 27, stored in the production control device 27, and transmitted from the production control device 27 to the computer 40. You can also do it.

In the mechanical configuration of the production line, an encoder 23 is attached to a location that rotates in synchronization with a mechanism that drives the movement of the corrugated cardboard sheet. The electrical signal from the encoder 23 is sent to the computer 40, and the coordinates in the two-dimensional image are associated with the actual position on the cardboard sheet 30 based on the positional relationship between the location photographed by the camera 22 and the encoder 23.

Next, a method for detecting defects in corrugated cardboard sheets using the defect detection device 20 having the above configuration will be described. The method for detecting defects in a corrugated sheet according to the present embodiment involves projecting light from a lighting 21 onto a corrugated sheet 30 running on a production line, and converting a one-dimensional image taken by a camera 22 into a two-dimensional image through image processing, as shown in FIG. An image 1 of a corrugated board sheet as shown in (a) is acquired, and it is determined whether or not the corrugated sheet has a defect through processing based on a determination processing program. The image 1 of the cardboard sheet can be, for example, an 8-bit (256 grayscale) image.

Here, FIG. 3(a) shows an image of a light-colored defect 2 that is lighter in color than the ground color of the corrugated board sheet and an image of a dark-colored defect 3 that is darker than the ground color of the corrugated board sheet in the image 1 of the corrugated board sheet. , and a case where an image of a press mark 5 which is a press mark by a press roll is included is schematically shown.

First, as a determination process, the image 1 of the corrugated cardboard sheet is arranged in a grid pattern using a plurality of lines parallel to the traveling direction Y of the corrugated sheet and a plurality of lines perpendicular to this, as shown by the dashed line in FIG. 3(a). compartmentalize. Each unit area 4 divided into a grid includes a plurality of identical pixels.

Next, addition processing is performed to obtain an addition processing value for each of the unit areas 4 partitioned into a grid. The addition processing value is the total value of the gradation values of the pixels included in each unit area 4, or the average value obtained by dividing this total value by the number of pixels forming the unit area. When using the total value as the addition processing value, the total value is calculated for all unit areas, and when using the average value as the addition processing value, the average value is calculated for all the unit areas. By determining the addition processing value in this way, the image 1 of the corrugated board sheet is converted into the image 10 after the addition processing as shown in FIG. 3(b).

In the image 10 after the addition processing, the addition processing value of the unit area 4 without defects and the addition processing value of the unit area 4 with defects are different, but even in the unit area 4 without defects, the image of the press mark 5 is The addition processing value is different between the unit area 4 that includes the image of the press mark 5 and the unit area 4 that does not include the image of the press mark 5. Considering that a plurality of "columns" in which the unit areas 4 are continuous in the running direction Y of the corrugated cardboard sheet 30 are lined up in a plurality of rows in the width direction of the corrugated cardboard sheet 30, the image 10 after the addition process shown in FIG. 3(b) is In this case, since the unit areas 4 belonging to the columns L1, L3, and L5 include the image of the press mark 5, the addition processing value is small.

Further, the unit area 12 (4) including the image of the light color defect 2 has a larger addition processing value than the unit area 4 without defects, and the unit area 13a (4) and the unit area 13b including the image of the dark color defect 3. In (4), the addition processing value is smaller than that of unit area 4 without defects.

Determination as to whether a defect exists in a certain unit area can be made by comparing the addition processing values between the unit area to be determined and other unit areas. In this case, the other unit area to be compared can be a unit area adjacent to the unit area to be determined. For example, when unit area 4a (4) is the determination target as shown in FIG. . These three unit areas have the same positional relationship with the image of the press mark 5, so if there is no defect, the addition processing values are the same. Therefore, the difference between the addition processing value of the unit area 4a (4) and the addition processing value of the unit area 4b (4), the difference between the addition processing value of the unit area 4a (4) and the addition processing value of the unit area 4c (4), When each absolute value is smaller than a predetermined threshold value, it can be determined that no defect exists in the unit area 4a (4).

On the other hand, when the unit area in which a defect exists, such as unit area 12(4), is the target of determination, if the addition processing value is compared with each of the unit areas 4d(4) and 4e(4) on both sides belonging to the same column L2, , it can be determined that a defect exists in the unit area 12(4) when the absolute value of the difference is equal to or greater than a predetermined threshold value.

Note that depending on the setting of the size of the unit area, the eight unit areas surrounding the unit area to be determined may be the same in terms of whether or not they include the image of the press mark 5. In such a case, find the difference between the addition processing value of the unit area to be judged and the addition processing value of each of the eight surrounding unit areas, and calculate the number of cases where the absolute value is greater than or equal to a predetermined threshold (the number to be judged) If the number of combinations of the unit area and surrounding unit areas) is smaller than a predetermined number, it is determined that there is no defect in the unit area to be determined, and if it is greater than or equal to the predetermined number, there is no defect in the unit area to be determined. It can be determined that a defect exists. In this way, by increasing the number of unit areas of the other party to be compared, there is no defect in the unit area to be judged, but because there is a defect in the unit area of the other party to be compared, there is a difference in the addition processing value between the two. It is possible to prevent the occurrence of this from affecting the determination result.

Furthermore, depending on the relationship between the size of a unit area and the size of a defect, if a defect exists in a unit area to be determined, there is a high probability that a defect also exists in an adjacent unit area. In such a case, a unit area that is the same in terms of whether it includes the image of the press mark 5 and is distant from the unit area to be determined is set as a comparison partner based on a certain rule. . An example of a rule in this case is "unit areas belonging to the same column and separated by N units". For example, in FIG. 4B, when the unit area 13b(4) having a defect is the determination target, instead of using the adjacent unit area 13a(4) as the comparison partner, the unit area 13b(4) belonging to the same column L4 and The unit area 4f(4) which is far away is compared with the addition processing value. By doing so, even if there is a high possibility that the defect spans multiple unit areas, the defect can be detected accurately.

As mentioned above, the judgment process by comparing the addition processing value of the unit area to be judged with the addition processing value of other unit areas is performed normally without any defects in most cases at the manufacturing site of corrugated cardboard sheets. Based on the fact that corrugated cardboard sheets are manufactured and defects rarely occur, that is, the number of unit areas without defects is overwhelmingly greater than the number of unit areas with defects. There is. If this situation is not assumed, defects can also be detected by comparing the addition processing value itself of the unit area to be determined with a predetermined threshold value without comparing it with other unit areas. Can be done. In this case, the threshold values can be an upper limit threshold value and a lower limit threshold value that are obtained by adding or subtracting an allowable numerical range to the addition processing value of a normal unit area in which no defects exist. In addition, threshold values are determined separately for a normal unit area that includes the image of the press mark 5 and for a normal unit area that does not include the image of the press mark 5. A corresponding threshold value is used depending on whether the position includes the image of mark 5 or not.

In this way, by comparing the addition processing value itself of the unit area to be determined with the threshold value, it is possible to accurately detect defects, even when defects exist over a fairly wide range.

In addition, when comparing the addition processing value itself of the unit area to be judged with the threshold value, if the addition processing value is an average value rather than a total value, the same threshold value will be set regardless of the size setting of the unit area. can be used.

When a unit area in which a defect exists is detected, the number of unit areas in which a defect exists is counted within a certain range preset for the corrugated cardboard sheet. If the number exceeds a predetermined threshold, it is determined that the area on the cardboard sheet is a defective product containing unacceptable defects, and a defect determination signal is sent from the computer 40 to the alarm device 26. Upon receiving the signal, the alarm device 26 issues a notification by lighting or flashing a warning light or by emitting an alarm sound. At the same time, the range of the corrugated cardboard sheet 30 that has been determined to be defective is specified based on the signal from the encoder 23 and output from the output device 25.

As described above, according to the method for detecting defects in corrugated paperboard sheets according to the present embodiment, defects such as stains, tears, and wrinkles can be detected with higher accuracy and in a shorter processing time in a production line of corrugated paperboard sheets.

Although the present invention has been described above with reference to preferred embodiments, the present invention is not limited to the above embodiments, and various improvements can be made without departing from the gist of the present invention, as shown below. and design changes are possible.

For example, although the shape of the unit area set by dividing the two-dimensional image into a lattice pattern is shown as a square, the shape is not limited to this and may be a rectangle. Determine the time when the length in the Y direction of the two-dimensional image formed from the one-dimensional image taken by the line sensor camera as the cardboard sheet travels is equal to the length in the Y direction of the unit area, and the entire width of the cardboard sheet. The size and shape of the unit area can be set in consideration of the balance with the time required for processing.

1 Imaging of cardboard sheet 2 Light color defect 3 Dark color defect 4 Unit area 5 Press mark 10 Image after addition processing 21 Lighting 22 Camera 30 Cardboard sheet

Claims (3)

A digital camera is used to photograph the back liner surface or front liner surface of the corrugated cardboard sheet running on the production line.
By dividing the obtained two-dimensional image into a grid, unit areas each consisting of a plurality of the same number of pixels are set,
For each of the unit areas, it is determined that the cardboard sheet has a defect based on an addition process that calculates an addition process value that is either the total value of the tone values of pixels or the average value obtained by dividing the total value by the number of pixels. 1. A method for detecting defects in a corrugated cardboard sheet, the method comprising: determining whether or not the defect has occurred. The corrugated cardboard sheet according to claim 1, wherein the determination is performed by comparing the addition processing value of the unit area to be determined with the addition processing value of the other unit areas. Defect detection method. The corrugated cardboard sheet has a linear press mark that is a press mark made by a press roll, and in the determination, the unit area to be determined and the unit area to be compared are the press marks in the imaging. 3. The corrugated board sheet defect detection method according to claim 2, wherein the positional relationship with the image is set to be the same.

Images