JP2016075542A - Defect detection apparatus and defect detection method of corrugated cardboard sheet in solid color - Google Patents

Abstract

PROBLEM TO BE SOLVED: To automatically create master image data for defect detection.SOLUTION: A defect detection apparatus 1 of corrugated cardboard sheets in solid color comprises: inspected image data acquisition means 3 for acquiring inspected image data Dt obtained by imaging a surface of a corrugated cardboard sheet S as an inspected portion; inspected image data analysis means 5 for totalizing the number of pixels having the same density value in the whole inspected image data, for each density value and acquiring a density value which becomes the maximum number of pixels therefrom; master image data creation means 6 for creating master image data Dm using the density value which becomes the maximum number of pixels; and inspected image data inspection means 8 for inspecting the presence/absence of a defect of the inspected image data Dt on the basis of the master image data Dm.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a defect detection device and a defect detection method for a plain cardboard sheet.

  The cardboard sheet is manufactured by a corrugating machine and processed into a cardboard box by a box making machine. The corrugating machine forms a belt-like corrugated cardboard sheet by corrugating the base paper, using it as an intermediate layer, and sandwiching both sides of the base paper between straight base papers. The product size corrugated cardboard sheet is manufactured by cutting into a predetermined size. The box making machine is to process each corrugated cardboard sheet produced by the corrugating machine into a corrugated cardboard box by printing and folding. Some box making machines have only printing processes. During these manufacturing processes and processing steps, the adhesive or the oil components such as machine grease may adhere to the base paper or the corrugated cardboard sheet, and the surface of the corrugated cardboard sheet may be soiled.

  As a background technique that can be used to detect such stains, the defect detection method for sheet-like printed matter described in Patent Document 1 is exemplified. In this detection method, a master printed matter that is a criterion for pass / fail judgment is selected by performing a visual inspection in advance, and a master image (see FIG. 10A) obtained by imaging the master printed matter is recorded in the inspection memory of the inspection apparatus. . Then, the printed object image (see FIG. 10B) is acquired by imaging the object to be inspected by the imaging means, the density level of the area image of the printed object image, and the density of the master image corresponding to the area image. The level is compared, and if there is a part where the difference between the density levels of the two images exceeds the allowable value, the part is determined as a defective part.

JP-A-6-201611

However, when the defect detection method of Patent Document 1 is used for defect detection of a plain cardboard sheet, there are the following problems.
(1) In corrugated machines and box making machines, it is difficult to identify a part without a fouling part in a corrugated cardboard sheet that flows continuously at high speed, and after registering that part as a master image Otherwise, the sheet cannot be inspected.
(2) If a defect is missed by visual inspection and a portion including the defect is registered as a master image, a portion without a defect is determined to be defective.
(3) Due to the influence of disturbance such as external light, the color of the captured image of the object to be inspected may be different from the color of the master image, and what should be determined as a non-defective product may be determined as a defective product.
(4) The warp situation in the width direction of the sheet may vary with time, so that the color of the captured image of the object to be inspected differs from the color of the master image and should be judged as a non-defective product. Things may be judged as defective. FIG. 11 shows an example of the influence of the warp in the width direction of the sheet during cardboard sheet imaging. FIG. 11 (I) shows the case where the sheet is not warped, and FIG. In the case of overhanging and warping, (III) represents the case where the central portion in the width direction of the sheet protrudes downward and warps. Moreover, each (a) in FIG. 11 is a cross-sectional view showing a state of warping of the sheet, and each (b) is a view taken in the direction of arrow b in (a).

In order to solve the above-described problem, the plain cardboard sheet defect detection apparatus according to the first aspect of the present invention provides:
Inspected image data acquisition means for acquiring inspected image data obtained by imaging the surface of the cardboard sheet as the inspected site;
Inspected image data storage means for storing the inspected image data;
Inspected to collect the number of pixels having the same density value in the entire inspected image data stored in the inspected image data storage means for each density value, and obtain the density value having the maximum number of pixels among them Image data analysis means;
Master image data creating means for creating master image data using the density value which is the maximum number of pixels;
Master image data storage means for storing the master image data;
Inspected image data inspection means for inspecting the presence or absence of defects in the inspected image data stored in the inspected image data storage means based on the master image data stored in the master image data storage means ing.

Although it does not specifically limit as said master image data, The following aspect is illustrated.
(1) The size of the image data is the same as that of the image data to be inspected, and all pixels (in the case of color image data, have independent density values for each of the three primary colors, in the case of grayscale image data) Has a single density value.) Has a density value that is the maximum number of pixels.
(2) A mode in which the size of the image data is formed as one pixel, and the pixel has a density value that is the maximum number of pixels.

  Although it does not specifically limit about the said test | inspection, The following aspect is illustrated. That is, the density values of the corresponding parts of the master image data and the image data to be inspected are compared, and all the parts where the density difference between the two images exceeds the density difference allowable value are extracted. If there is a value exceeding the allowable value, it is determined that there is a defect.

  According to this configuration, the inspection image data is analyzed, and the master image data is generated using the density value having the maximum number of pixels. Even if the influence appears in other density values, the master image data from which it is excluded can be automatically created. Further, since the master image data is created for each image data to be inspected, even if the influence of disturbance such as external light differs for each image data to be inspected, The corresponding master image data can be obtained, and appropriate inspection can be performed.

As a defect detection device for a plain cardboard sheet of the second invention, in the first invention,
The inspected image data and the master image data are color image data in which each pixel is expressed by density values of a plurality of primary color components,
The inspected image data analysis means exemplifies an aspect configured to be performed for each primary color component of each pixel.

  According to this configuration, it is possible to cope with the case where the inspected image data and the master image data are color image data.

As a defect detection device for a plain cardboard sheet of the third invention, in the first invention,
The inspected image data and the master image data are grayscale image data in which each pixel is expressed by a density value of a single color from white to black,
The inspected image data analyzing means exemplifies an aspect configured to perform the density value of the single color.

  According to this configuration, it is possible to cope with the case where the inspection image data and the master image data are grayscale image data.

As a defect detection device for a plain cardboard sheet of the fourth invention, in any one of the first to third inventions,
Inspected image data element that divides the inspected image data stored in the inspected image data storage means into a plurality of the width direction of the corrugated cardboard sheet, and sequentially acquires the divided inspected image data elements An acquisition means,
The inspection image data analysis means, the master image data creation means, and the inspection image data inspection means are configured to act on each of the inspection image data elements acquired by the inspection image data element acquisition means. And
When any one of the image data elements to be inspected is determined to be defective, the aspect configured to determine that the inspected part is defective is illustrated.

Although it does not specifically limit as said master image data in this structure, The following aspect is illustrated.
(1) The size of the image data is the same as that of the image data to be inspected, and all pixels (in the case of color image data, have independent density values for each of the three primary colors, in the case of grayscale image data) Has a single density value.) Has a density value that is the maximum number of pixels.
(2) The size of the image data is the same as the image data element to be inspected, and all pixels (in the case of color image data, have independent density values for each of the three primary colors, and the grayscale image data In the case, it has a single density value.) Has a density value that is the maximum number of pixels.
(3) A mode in which the size of the image data is formed as one pixel, and the pixel has a density value that is the maximum number of pixels.

  According to this configuration, the image data to be inspected is divided into a plurality in the width direction of the cardboard sheet, and the master image data is created and inspected for each of the divided image data elements to be inspected. For example, it corresponds to the case where the color of the captured image differs depending on the position in the width direction of the cardboard sheet, such as when the warping situation in the width direction of the sheet changes with time. can do.

As a defect detection device for a plain cardboard sheet of the fifth invention, in any one of the first to fourth inventions,
When the master image data created with respect to the corrugated cardboard sheet to be inspected is stored in the master image data storage means, the inspection image data analyzing means and the master image data are inspected for the subsequent inspection of another part to be inspected. An example in which the processing by the creation unit is omitted and the image data to be inspected is inspected using the stored master image data will be exemplified.

  According to this configuration, there is a possibility that appropriate inspection cannot be performed when the influence of disturbance such as external light is different for each image data to be inspected, but it is not necessary to create the master image data every time. The processing load can be reduced.

Moreover, the defect detection method of the plain cardboard sheet of the sixth invention is:
Inspected image data acquisition stage for acquiring inspected image data obtained by imaging the surface of the corrugated cardboard sheet as the inspected site;
Inspected image data analysis stage for totalizing the number of pixels having the same density value in the entire image data to be inspected for each density value, and obtaining the density value having the maximum number of pixels among them,
A master image data creation step of creating master image data using the density value which is the maximum number of pixels;
And an image data inspection stage for inspecting the inspection image data for defects based on the master image data.

  Also with this configuration, the same effect as that of the first invention can be obtained.

As a defect detection method of the plain cardboard sheet of the seventh invention, in the sixth invention,
The inspected image data and the master image data are color image data in which each pixel is expressed by density values of a plurality of primary color components,
The inspected image data analysis step exemplifies an aspect configured to be performed for each primary color component of each pixel.

  Also with this configuration, the same effect as that of the second invention can be obtained.

As a defect detection method of the plain cardboard sheet of the eighth invention, in the sixth invention,
The inspected image data and the master image data are grayscale image data in which each pixel is expressed by a density value of a single color from white to black,
The inspected image data analysis step exemplifies an aspect configured to be performed for the density value of the single color.

  Also with this configuration, it is possible to obtain the same effect as that of the third invention.

As a defect detection method of the plain cardboard sheet of the ninth invention, in any of the sixth to eighth inventions,
The inspection image data is divided into a plurality of the width direction of the corrugated cardboard sheet, and includes an inspection image data element acquisition step of sequentially acquiring the divided inspection image data elements,
Each of the inspected image data elements acquired in the inspected image data element acquisition stage is configured to perform the inspected image data analysis stage, the master image data creation stage, and the inspected image data inspection stage. ,
When any one of the image data elements to be inspected is determined to be defective, the aspect configured to determine that the inspected part is defective is illustrated.

  Also with this configuration, the same effect as that of the fourth invention can be obtained.

As a defect detection method of the plain cardboard sheet of the tenth invention, in any of the sixth to ninth inventions,
When the master image data is generated for the corrugated cardboard sheet to be inspected, the subsequent inspection of another inspection site is performed by omitting the inspection image data analysis step and the master image data generation step, The aspect comprised so that the said to-be-inspected image data may be test | inspected using image data is illustrated.

  Also with this configuration, the same effect as that of the fifth invention can be obtained.

  According to the defect detection device and the defect detection method for the plain cardboard sheet according to the present invention, there is an excellent effect that the master image data for defect detection can be automatically created.

It is a block diagram which shows the structure of the defect detection apparatus of the plain corrugated cardboard sheet | seat which concerns on 1st embodiment which actualized this invention. It is a side view which shows the structure of the to-be-inspected site | part imaging part of the same defect detection apparatus. It is a figure explaining the acquisition method of the to-be-inspected image data in the same defect detection apparatus. It is the histogram (frequency distribution diagram) showing the analysis result by the to-be-inspected image data analysis means of the defect detection apparatus. It is a flowchart showing the flow of the defect detection method which the defect detection apparatus uses. It is a figure showing the mode of defect detection in one example of operation of the same defect detection device. It is a block diagram which shows the structure of the defect detection apparatus of the plain cardboard sheet | seat which concerns on 2nd embodiment which actualized this invention. It is a figure explaining the acquisition method of to-be-inspected image data and to-be-inspected image data element in the same defect detection apparatus. It is a front view which shows the structure of the to-be-inspected site | part imaging part of the defect detection apparatus which concerns on the example of a change. It is a figure explaining the defect detection method which concerns on background art. It is a figure explaining the example of influence of the curvature of the width direction of a sheet at the time of cardboard sheet imaging.

  1 to 6 show a first embodiment embodying the present invention. DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, an embodiment in which the present invention is embodied in a plain cardboard sheet defect detection apparatus 1 will be described with reference to the drawings together with a defect detection method used in the apparatus.

  The defect detection apparatus 1 of this example is installed in-line in a corrugating machine 15 that manufactures a plain corrugated cardboard sheet S, and detects defects on the surface of the corrugated cardboard sheet S conveyed on the sheet conveying surface 15a. As shown in FIG. 1, the inspected part imaging unit 2, the inspected image data acquisition means 3, the inspected image data storage means 4, the inspected image data analysis means 5, the master image data creation means 6, and the master image data storage means 7. An inspection image data inspection unit 8, an inspection result output unit 9, and an output unit 10 are provided. In this example, the inspected image data acquisition means 3, the inspected image data storage means 4, the inspected image data analysis means 5, the master image data creation means 6, the master image data storage means 7, the inspected image data inspection means 8, The inspection result output means 9 is realized by a known computer 11. In this example, the defect detection apparatus 1 is installed on the upstream side of the slitter scorer 15b that cuts the strip-shaped corrugated cardboard sheet S in the width direction, but it can also be installed on the downstream side. Here, the “upstream side” means a side opposite to the conveyance direction of the corrugated cardboard sheet S in the corrugating machine 15, and the “downstream side” means a side in the same direction as the conveyance direction.

  As shown in FIG. 2, the inspected part imaging unit 2 generates the inspected image data Dt by imaging the surface of the corrugated cardboard sheet S as the inspected part. An illumination device 2a that illuminates the surface of the site to be inspected on the sheet S and a camera 2b as an imaging means for imaging the site to be inspected are provided. And as shown in FIG. 3, the corrugated cardboard sheet S sent continuously is imaged for every imaging length, and each to-be-inspected image data Dt is acquired. In this example, an LED illumination device is used as the illumination device 2a. However, this is an example and not particularly limited, and a known light source such as a fluorescent lamp, a mercury lamp, or a halogen lamp may be appropriately adopted. Can do. The camera 2b of this example outputs color image data in which each pixel is expressed by the density values of the three primary color components of red (R), green (G), and blue (B). In this example, it is assumed that each of the upper and lower widths of the sheet S is covered by one camera 2b. However, this is an example, and the camera 2b has a size corresponding to the width of the sheet S. The number of units can be changed as appropriate. In this example, in order to detect defects on the upper and lower surfaces of the cardboard sheet S, the illumination device 2a and the camera 2b are arranged on both sides.

  The inspected image data acquisition means 3 is configured to acquire the inspected image data Dt generated thereby from the inspected part imaging unit 2, and is an inspected image data acquisition stage in the defect detection method. ing. Note that the inspected image data acquisition unit 3 may include the configuration of the inspected part imaging unit 2 and may be configured as the inspected image data acquisition unit 3.

  The inspected image data storage unit 4 is configured to store the inspected image data Dt acquired by the inspected image data acquisition unit 3 so as to be appropriately readable.

  The inspected image data analyzing means 5 is configured to aggregate the number of pixels having the same density value in the entire inspected image data for each density value, and acquire the density value having the maximum number of pixels among them. The inspection image data analysis stage in the defect detection method is performed. FIG. 4 is a histogram (frequency distribution diagram) showing an example of the totaling result, and a density value (see reference symbol M in the figure) having the maximum number of pixels for each primary color is acquired. ing. Thus, since the master image data Dm is created by using only the density value having the maximum number of pixels for each primary color, for example, as shown by the symbol N in FIG. Since the data Dt includes a defect candidate area (an area having a color different from the original color of the corrugated cardboard sheet), the master image data Dm is not affected even if it appears in the tabulation result. ing.

  The master image data creation means 6 creates master image data Dm using the density value having the maximum number of pixels acquired by the inspected image data analysis means 5, and creates master image data in the defect detection method. It has become a stage. The master image data Dm in this example is formed such that the size of the image data is the same as that of the image data Dt to be inspected, and all pixels have a density value that is the maximum number of pixels.

  The master image data storage means 7 is configured to store the master image data Dm created by the master image data creation means 6 so as to be appropriately readable.

  The inspected image data inspection means 8 is configured to inspect the presence or absence of defects in the inspected image data Dt based on the master image data Dm, and is in the image data inspection stage in the defect detection method. In this example, the density values of the corresponding pixels in the corresponding parts of the master image data Dm and the inspected image data Dt are compared, and all of the pixels that exceed a predetermined allowable value in the comparison result are continuous (or dense). This area is extracted, and if any area exceeds a predetermined allowable condition, it is determined that there is a defect. This will be described more specifically as follows. First, the comparison of the density values is performed by comparing the density values of the three primary colors for each primary color, and grayscale image data having the density difference of the primary color having the maximum density difference among them as the density value. Generate as Next, binary image data is generated by binarizing the grayscale image data using the predetermined allowable value as a threshold value. In the binary image data, all regions where pixels having a value of 1 are continuous (or densely) are extracted. Next, if any of the regions exceeds an allowable condition (for example, a condition that a rectangular area circumscribing the region is equal to or smaller than a predetermined area), it is determined that there is a defect. Note that, in the above, a certain pixel is dense means that an interval between certain pixels is equal to or less than a predetermined interval, and the predetermined interval can be appropriately determined.

  The inspection result output unit 9 is configured to output the inspection result to the output unit 10.

  The output unit 10 is configured to output an output result to the operator, and exemplifies that the output unit 10 is implemented as a display device for displaying or / and a printing device for printing the result.

  With the above configuration, as shown in FIG. 5, the defect detection apparatus 1 of the present example images the inspection site imaging stage (step S21) for imaging the inspection site and the surface of the cardboard sheet S as the inspection site. Inspected image data acquisition stage (step S22) for acquiring the inspected image data Dt, and the number of pixels having the same density value in the entire inspected image data are tabulated for each density value, and the maximum number of pixels among them An inspected image data analysis stage (step S23) for acquiring the obtained density value; a master image data creation stage (step S24) for creating master image data Dm using the density value having the maximum number of pixels; An image data inspection stage (step S25) for inspecting the presence or absence of defects in the inspected image data Dt based on the master image data Dm, and an inspection result in the image data inspection stage Test result output step of force includes a (step S26) and, using the defect detection method to perform these steps for each examination site.

  Next, an operation example of the defect detection apparatus 1 of this example will be described with reference to FIG. In this operation example, it is assumed that the inspection image data Dt is color image data in which one pixel has RGB three primary color density values and is composed of 20 horizontal pixels and 10 vertical pixels. Further, since the operation of the defect detection apparatus 1 with respect to the upper surface and the lower surface of the cardboard sheet S is the same, only the operation with respect to one surface will be described in this example. In this example, the density value of the color image data is expressed as “(R: density value of red, G: density value of green, B: density value of blue)”.

  First, the defect detection apparatus 1 images the inspection image data Dt by the inspection part imaging unit 2, acquires the inspection image data Dt by the inspection image data acquisition unit 3, and stores it in the inspection image data storage unit 4. Remember. Here, it is assumed that the inspection image data Dt includes three defect candidate areas having different states (FIG. 6A).

  Next, the defect detection apparatus 1 uses the inspected image data analysis means 5 to count up the number of pixels having the same density value in the entire inspected image data for each density value, and the density value that is the maximum number of pixels among them. To get. In this example, R (red) is 150, G (green) is 130, and B (blue) is 120 as the density value having the maximum number of pixels.

  Next, the defect detection apparatus 1 uses the acquired density values (R: 150, G: 130, B: 120) to create the master image data Dm by the master image data creation unit 6, and the master image data storage unit. 7 (see FIG. 6B).

  Next, the defect detection apparatus 1 inspects the inspected image data Dt by the inspected image data inspection unit 8 based on the master image data Dm. Specifically, the corresponding pixels of the master image data Dm and the inspected image data Dt are compared for each density value of each of the three primary colors, and the density for the primary color having the maximum density difference among them. Grayscale image data having the difference as a density value is generated as the comparison result (see FIG. 6C). The generation method at this time will be specifically described. For example, the upper left pixel of the inspected image data Dt in FIG. 6A has a density value (R: 150, G: 130, B: 110), and the master Since the corresponding pixels of the image data Dm have density values (R: 150, G: 130, B: 120), the density difference is (R: 0, G: 0, B: 10) for each primary color. Among them, the density difference of the primary color B having the maximum density difference is used as the density value in the gray scale image data of FIG. 6C. Binary image data formed by binarizing the grayscale image data generated in this way using the predetermined allowable value (30 in this example) as a threshold value is generated. At this time, in this example, as shown in FIG. 6D, the upper left defect candidate region in the image data Dt to be inspected disappears. From the binary image data, all regions where pixels having a value of 1 are continuous (or densely packed) are extracted (in this example, two regions). Next, if any of the regions exceeds an allowable condition (in this example, a condition that a rectangular area circumscribing the region is equal to or smaller than a predetermined area (5)), it is determined that there is a defect. In this example, since the defect candidate area on the right side in the inspection image data Dt exceeds the allowable condition, it is determined that there is a defect.

  Next, the defect detection apparatus 1 causes the inspection result output means 9 to output the inspection result to the output unit 10.

  According to the plain cardboard sheet defect detection apparatus 1 and the defect detection method of the present example described in detail above, the image data Dt to be inspected is analyzed, and the master image data Dm is used using the density value having the maximum number of pixels. Therefore, even if the inspected image data Dt includes a contaminated part and its influence appears in other density values, the master image data Dm from which it is excluded is automatically generated. Can be created. Further, since the master image data Dm is created for each image data Dt to be inspected, the image data Dt to be inspected even when the influence of disturbance such as external light is different for each image data Dt to be inspected. The master image data Dm corresponding to can be obtained, and appropriate inspection can be performed.

  The inspected image data Dt and the master image data Dm are color image data in which each pixel is expressed by the density values of the components of the three primary colors (RGB), and the inspected image data analyzing means 5 Since it is configured to be performed for each component, according to this configuration, it is possible to cope with the case where the inspected image data Dt and the master image data Dm are color image data.

  7 to 8 show a second embodiment in which the present invention is embodied. The plain cardboard sheet defect detection device 51 of this example and the defect detection method used in the device are mainly different from the first embodiment in the following points. Accordingly, portions common to the embodiment are given the same reference numerals, and redundant description is omitted.

In the defect detection apparatus 51 of the present example, as shown in FIG. 7, the inspected image data Dt stored in the inspected image data storage unit 4 is divided into a plurality of parts in the width direction of the cardboard sheet S. Inspected image data element acquisition means 52 for sequentially acquiring the inspected image data elements Dtd. The inspected image data element acquisition means 52 is in the inspected image data element acquisition stage in the defect detection method. Then, as shown in FIG. 8, the corrugated cardboard sheet S that is continuously sent is imaged for each imaging length, and each image data Dt to be inspected is acquired, and the image data elements to be inspected from the image data Dt to be inspected. Dtd is acquired.
Then, the inspected image data analysis means 5, the master image data creation means 6, and the inspected image data inspection means 8 are made to act on each of the inspected image data elements Dtd acquired by the inspected image data element acquisition means 52. If any of the inspected image data elements Dtd is determined to be defective, it is determined that there is a defect in the inspected part, and the inspection result output means 9 outputs the inspection result to the output unit 10. Is configured to do.

  According to the plain cardboard sheet defect detection device 51 and the defect detection method of this example, in addition to the same effects as those of the first embodiment, the following effects can be obtained. That is, the inspected image data Dt is divided into a plurality of parts in the width direction of the cardboard sheet S, and the master image data Dm is created and inspected for each of the divided inspected image data elements Dtd. Therefore, for example, the case where the color of the captured image differs depending on the position in the width direction of the cardboard sheet S, such as the case where the warp situation in the width direction of the sheet changes with the passage of time, is handled. Can do.

In addition, this invention is not limited to the said embodiment, For example, it can also be suitably changed and embodied as follows, for example in the range which does not deviate from the meaning of invention.
(1) It is configured to detect defects on only the front or back surface of the cardboard sheet S.
(2) The number of cameras 2b is changed as appropriate in accordance with the width size of the sheet S. For example, as shown in FIG. 9, it may be configured to cover the entire upper and lower widths of the sheet S with two cameras 2b.
(3) The inspected image data Dt and the master image data Dm are grayscale image data in which each pixel is expressed by a density value of a single color from white to black. It is set as the aspect comprised so that it may carry out about the density value of one color.
(4) As the master image data Dm, the size of the image data is formed as one pixel, and the pixel has a density value with the maximum number of pixels. And it is configured to inspect all the pixels of the inspected image data Dt based on this one pixel. (5) When the master image data Dm created with respect to the corrugated cardboard sheet S to be inspected is stored in the master image data storage means 7, the inspection image data analyzing means 5 and the inspection of another part to be inspected thereafter The plain cardboard sheet defect detection device 1 or 51 is configured to inspect the inspected image data Dt using the stored master image data Dm without processing by the master image data creation means 6. To change.
(6) When the master image data Dm is created for the corrugated cardboard sheet S to be inspected, the inspection image data analysis stage and the master image data creation stage have been omitted for the subsequent inspection of another part to be inspected. The defect detection method for a plain corrugated cardboard sheet is changed to an aspect configured to inspect the inspected image data Dt using the master image data Dm.
(7) A plain cardboard sheet defect detection apparatus according to the present invention is installed in-line with respect to a box making machine that processes the cardboard sheet S into a cardboard box.

DESCRIPTION OF SYMBOLS 1 Defect detection apparatus 2 Inspected part imaging part 2a Illuminating device 2b Camera 3 Inspected image data acquisition means 4 Inspected image data storage means 5 Inspected image data analysis means 6 Master image data creation means 7 Master image data storage means 8 Subject Inspection image data inspection means 9 Inspection result output means 10 Output section 11 Computer 15 Corrugating machine 15a Sheet conveying surface 15b Slitter scorer 51 Defect detection device 52 Inspected image data element acquisition means Dm Master image data Dt Inspected image data Dtd Inspected image Data element S Cardboard sheet

Claims (10)

Inspected image data acquisition means for acquiring inspected image data obtained by imaging the surface of the cardboard sheet as the inspected site;
Inspected image data storage means for storing the inspected image data;
Inspected to collect the number of pixels having the same density value in the entire inspected image data stored in the inspected image data storage means for each density value, and obtain the density value having the maximum number of pixels among them Image data analysis means;
Master image data creating means for creating master image data using the density value which is the maximum number of pixels;
Master image data storage means for storing the master image data;
Inspected image data inspection means for inspecting the presence or absence of defects in the inspected image data stored in the inspected image data storage means based on the master image data stored in the master image data storage means A defect detection device for plain cardboard sheets. The inspected image data and the master image data are color image data in which each pixel is expressed by density values of a plurality of primary color components,
2. The plain cardboard sheet defect detection device according to claim 1, wherein the inspected image data analysis means is configured to be performed for each primary color component of each pixel. The inspected image data and the master image data are grayscale image data in which each pixel is expressed by a density value of a single color from white to black,
2. The plain cardboard sheet defect detection device according to claim 1, wherein the inspected image data analysis means is configured to perform the density value of the single color. Inspected image data element that divides the inspected image data stored in the inspected image data storage means into a plurality of the width direction of the corrugated cardboard sheet, and sequentially acquires the divided inspected image data elements An acquisition means,
The inspection image data analysis means, the master image data creation means, and the inspection image data inspection means are configured to act on each of the inspection image data elements acquired by the inspection image data element acquisition means. And
The plain cardboard according to any one of claims 1 to 3, wherein when any of the image data elements to be inspected is determined to be defective, the inspection site is determined to be defective. Sheet defect detection device. When the master image data created with respect to the corrugated cardboard sheet to be inspected is stored in the master image data storage means, the inspection image data analyzing means and the master image data are inspected for the subsequent inspection of another part to be inspected. The plain corrugated cardboard sheet according to any one of claims 1 to 4, which is configured to inspect the image data to be inspected by using the stored master image data without processing by the creating unit. Defect detection device. Inspected image data acquisition stage for acquiring inspected image data obtained by imaging the surface of the corrugated cardboard sheet as the inspected site;
Inspected image data analysis stage for totalizing the number of pixels having the same density value in the entire image data to be inspected for each density value, and obtaining the density value having the maximum number of pixels among them,
A master image data creation step of creating master image data using the density value which is the maximum number of pixels;
A plain cardboard sheet defect detection method comprising: an image data inspection step of inspecting the presence or absence of defects in the image data to be inspected based on the master image data. The inspected image data and the master image data are color image data in which each pixel is expressed by density values of a plurality of primary color components,
The plain cardboard sheet defect detection method according to claim 6, wherein the inspection image data analysis step is performed for each primary color component of each pixel. The inspected image data and the master image data are grayscale image data in which each pixel is expressed by a density value of a single color from white to black,
The plain cardboard sheet defect detection method according to claim 6, wherein the inspection image data analysis step is configured to be performed for the density value of the single color. The inspection image data is divided into a plurality of the width direction of the corrugated cardboard sheet, and includes an inspection image data element acquisition step of sequentially acquiring the divided inspection image data elements,
Each of the inspected image data elements acquired in the inspected image data element acquisition stage is configured to perform the inspected image data analysis stage, the master image data creation stage, and the inspected image data inspection stage. ,
The plain cardboard according to any one of claims 6 to 8, wherein when any of the image data elements to be inspected is determined to be defective, the inspection site is determined to be defective. Sheet defect detection method. When the master image data is generated for the corrugated cardboard sheet to be inspected, the subsequent inspection of another inspection site is performed by omitting the inspection image data analysis step and the master image data generation step, The method for detecting a defect in a plain corrugated cardboard sheet according to any one of claims 6 to 9, wherein the image data to be inspected is inspected using image data.