JP2000168261A - Method for detecting incorrect collating - Google Patents

Abstract

PROBLEM TO BE SOLVED: To surely detect incorrect collating even in the case where printing density and paper color are different between a printed matter having an inspection image taken therein and a printed matter having a reference image taken therein. SOLUTION: When incorrect collating is detected on the basis of a reference image A image-inputted from a normal printed matter in advance and an inspection image F image-inputted from printed matter in a gathering process, by producing a reference edge image B having an edge extracted from the reference image A, producing an inspection edge image extracted from an edge from the inspection image F, incorrect collating is detected by making comparison between these reference edge images and inspection edge images, Concretely, an expansion image D and contraction image E are produced from a reference bivalued edge image C, an inspection bivalued edge image I is mask-processed by a reference bivalue edged expansion image D, and a reference bivalued edge contraction image E is mask-processed by the inspection bivalued edge image I.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for detecting a mismatched page, which is suitable for detecting a page mismatch occurring in a collating process in a bookbinding process.

[0002]

2. Description of the Related Art Generally, when performing a bookbinding process with a bookbinding machine,
A bundle of printed materials called signatures, which are individually printed in advance by a printing machine, are sequentially superimposed to form one printed material, and then the bundle is bundled to produce one book.

[0003] In this bookbinding process, it is extremely important to overlap each signature in the correct order.
If the order is out of order, it is necessary to reliably detect and deal with it.

[0004] As a conventional misalignment detection technique, for example, Japanese Patent Publication No. 3-44000 discloses a method in which light is applied to a plurality of measurement points on a reference sheet and an inspection sheet, and reflected light from each measurement point corresponds to each measurement point. The difference between the amount of reflected light from the inspection paper surface and the amount of reflected light from the reference paper surface is obtained for each measurement point, and the arithmetic average of the amount of reflection light from the inspection paper surface for each two adjacent measurement points is obtained. By calculating the arithmetic average of the amount of reflected light on the reference paper, taking the difference between the two arithmetic averages, and comparing the number of differences exceeding a predetermined level among the two types of differences with the total number of the two types of differences. A method for detecting a mis-order is disclosed.

[0005]

However, the technology disclosed in Japanese Patent Publication No. 3-44000 discloses the following.
Since the density change of the printed paper surface is detected, the collation is correct, but the print density or paper color changes, or the pattern at the specified measurement point shifts due to misplaced signatures. As a result, erroneous detection may occur due to a change in the amount of reflected light, or a signature with only a similar pattern or character may not be detected, so that stable detection may not be possible.
For this reason, in actual operation, a method is adopted in which a mischief is considered to have occurred only when a plurality of consecutive mischiefs are detected. There was a problem that it was not possible.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned conventional problems. The present invention is applied to the case where the print density or paper color is different between the reference image and the inspection image, or the printed matter has similar patterns or characters. It is an object of the present invention to provide a method for detecting a facsimile that can reliably detect a facsimile even if the signature is only a facsimile, and consequently can detect a falsification of a small number of copies.

[0007]

According to the present invention, there is provided a method for detecting a mismatched page based on a reference image previously inputted from a normal printed matter and an inspection image inputted from the printed matter in a collating step. A reference edge image in which an edge is extracted from a reference image is created, an inspection edge image in which an edge is extracted from the inspection image is created, and the reference edge image and the inspection edge image are binarized to form a reference binary edge. Creating an image and an inspection binary edge image, expanding the reference binary edge image to create a reference binary edge expanded image, and contracting the edge image to create a reference binary edge contracted image, The inspection binary edge image is masked with the reference binary edge expansion image, and the reference binary edge contraction image is masked with the inspection binary edge image. , By detecting the paging disorder by comparing the inspection edge image with those reference edge image is obtained by solving the above problems.

In the present invention, it is determined whether or not a page is incorrect based on the edge information of the printed picture. That is, each edge image is created from the reference image and the inspection image, and both edge images are binarized to create respective binary images. Then, an expanded image and a contracted image are respectively created from the reference binary edge image, and the inspection binary edge image is masked with the dilated image, and the contracted image is masked with the same inspection binary edge image. Since it was decided from the residual image whether or not the same signature,
Even if the signature with the reference image and the signature with the inspection image have different print densities or different paper colors, etc., it is possible to reliably detect incorrect pages, and as a result, even small numbers of incorrect pages can be detected. Can be detected.

Further, both expansion and contraction processing are performed only on the binary edge image on the reference image side which can be processed in advance, and such processing is not performed on the inspection image side. As a result, the amount of processing calculation after the input of the inspection image can be reduced, so that the time required for outputting the determination result, that is, the time for the inspection lab can be shortened, and a high-speed collation line can be handled. .

[0010]

Embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 is a block diagram showing a schematic configuration of a misalignment detecting apparatus applied to a misalignment detecting method according to an embodiment of the present invention.

The apparatus for detecting irregularities includes a camera 10 for capturing a two-dimensional image from a signature (not shown), and an image processing unit 12 for performing various image processing on the image captured by the camera 10. The image processing device 12
An image memory 14 having processing functions to be described later, a displacement correction unit 16, an edge extraction unit 18, a binarization processing unit 20, an expansion processing unit 22, a contraction processing unit 24, a mask processing unit 26, and a determination processing unit 28 are provided. ing.

In the present embodiment, the camera 10
When detecting a misalignment based on a reference image previously input from a normal signature (printed matter) and an inspection image input from the same type of signature in the collating process, a reference edge obtained by extracting an edge from the reference image In addition to creating an image, an inspection edge image in which edges are extracted from the inspection image is created, and the generated reference edge image and the inspection edge image are compared to detect occurrence of misalignment.

That is, in the present embodiment, the misjudgment is determined by extracting the edges (contour lines) of the patterns of the reference image and the inspection image and detecting the difference between the two edges. Edge differences include (1) a case where the edge of the inspection image is increased with respect to the edge of the reference image, and (2) a case where the edge of the inspection image is missing from the edge of the reference image. Therefore, detection is performed for each of them. If the latter edge loss is regarded as an increase in the edge of the reference image with respect to the inspection image, it becomes the same as the former processing.

Hereinafter, the method for detecting the incorrect page according to the present embodiment will be described.
This will be specifically described with reference to FIG. FIG. 2 schematically shows an image of an image corresponding to each processing step.

First, a picture of a normal signature is captured as a two-dimensional image on a bookbinding machine (not shown) by the camera 10 and stored in the image memory 14 as a reference image A.
The reference image A is read from the image memory 14 to the edge extraction unit 18, and an edge extraction operator such as Laplacian or Sobel is applied to the reference image A to extract a picture edge included in the reference image A. And reference edge image B
Create

The directions of the edges to be extracted here are desirably all directions, but only horizontal depending on the image quality determined by the input system.
Alternatively, only the vertical edge may be extracted.
Further, as a pre-process of edge extraction, a noise removal process using a smoothing filter, a median filter, or the like may be applied.

Next, the above-mentioned reference edge image B read out from the image memory 14 is subjected to a binarization processing section 20 using a mode method or a discriminant analysis method in order to clarify an edge. The value is converted into a reference binary edge image C, which is stored in the image memory 14. Further, in the expansion processing section 22, an expansion operation is performed on the reference binary edge image C similarly read out to obtain a reference binary edge expansion image (inspection image mask) D. Similarly, a contraction operation is performed on the reference binary edge image C to obtain a reference binary edge contraction image E, which is also stored in the image memory 14. The above operations up to the creation of the contracted image E are performed in advance before inputting the inspection image. Note that the expansion processing performed here corresponds to processing for increasing the number of pixels in the area corresponding to the edge toward the inside and the outside, and the contraction processing corresponds to processing for reducing the number of pixels.

Upon completion of the creation of the reference binary edge expansion image D and the reference binary edge contraction image E, the camera 10 inputs an image from a signature on the bookbinding machine, takes in the inspection image F, and stores it in the image memory 14. I do. Usually, since the reference image A and the inspection image F are misaligned due to the misalignment of the signature, the misregistration correction unit 16 calculates the misalignment amount by a method such as template pattern matching. Then, a position-corrected image G obtained by correcting the position corresponding to the shift amount is stored in the image memory 14 again.

Thereafter, as in the case of the reference image A, the position correction image G is sequentially processed by the edge extraction unit 18 and the binarization processing unit 20, whereby
An inspection edge image F and an inspection binary edge image (reference image mask) I are created, and these are stored in the image memory 14.
Respectively.

Next, in the mask processing section 24,
A mask process equivalent to comparing the reference edge image B and the inspection edge image G is performed. That is, on the reference image A side,
By masking the reference binary edge contracted image E using the inspection binary edge image I, a residual image (missing portion)
On the inspection image F side, the inspection binary edge image H is masked using the reference binary edge dilation image D, thereby obtaining a residual image (increased portion) K. Here, the mask processing corresponds to performing AND processing between corresponding pixels of the inverted image of each mask image D (I) and the binary edge image H (C). Therefore, in the residual image J (K), the pixels become white only when the corresponding pixels in both images are both white, and all other pixels become black.

As described above, the increase in the edge of the inspection image F with respect to the edge of the reference image A is caused by the inspection binary edge image I
On the other hand, it can be detected by performing mask processing using the reference binary edge expansion image D as a mask image, and the decrease (loss) of the edge of the inspection image F with respect to the edge of the reference image A is
It can be detected by masking the reference binary edge contracted image E using the inspection binary edge image I as a mask image.

According to the present embodiment described above, even when there is a missing portion from the reference image A like the residual image J, the judgment processing unit 28 Even if there is an increased portion with respect to the reference image A, any of them can be reliably detected as an incorrect page. By the way,
In the case of a correct page, both residual images J and K are substantially black as a whole.

Further, according to the present embodiment, since the edges of the reference image and the inspection image are compared, it is possible to detect the irregularity without being affected by the change in the print density or the paper color and the pattern. it can.

Also, since the edge dilated image and the edge contracted image can be created in advance on the reference image side, the amount of processing calculation from the input of the inspection image to the determination process is reduced, so that the required inspection time is reduced. It can be shortened and can be used for high-speed collation lines.

Further, in this embodiment, since the positional deviation of the inspection image is corrected with respect to the reference image, even if the pattern to be inspected is misaligned due to misplacement of the signature, etc., the misaligned page is accurately detected. Can be detected.

Although the present invention has been specifically described above, the present invention is not limited to the above-described embodiment, and can be variously modified without departing from the gist thereof.

For example, in the above embodiment, the case where the camera 10 is used as an image input means for inputting a two-dimensional image has been described. However, the present invention is not limited to this, and a contact line sensor or the like may be used.

Also, if the signatures can be placed at substantially the same position, a certain amount of displacement can be dealt with since an image wider than the object to be masked is used as a mask, so that position correction (alignment) is not necessarily performed. It is not necessary to do it.

[0030]

As described above, according to the present invention,
Even if the print density or paper color is different between the printed matter in which the inspection image has been captured and the printed matter in which the reference image has been captured, it is possible to reliably detect incorrect pages. In addition, since the expansion processing and the contraction processing required for the mask processing are performed in advance on the reference image side, the amount of processing calculation after input of the inspection image can be reduced, and the required inspection time can be shortened.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a schematic configuration of a random page detecting device applied to an embodiment according to the present invention;

FIG. 2 is a flowchart showing the operation of the present embodiment.

[Explanation of symbols]

 10 camera 12 image processing device

 ────────────────────────────────────────────────── ─── Continued on the front page (72) Inventor Masanori Kaku 1-1-1, Ichigaya-Kaga-cho, Shinjuku-ku, Tokyo F-term in Dai Nippon Printing Co., Ltd. (reference) 2G051 AA90 AB07 AC21 CA04 EA08 EA11 EA12 EA14 EB01 ED01 ED11

Claims (2)

[Claims] 1. A method for detecting a misalignment based on a reference image previously input from a normal printed matter and an inspection image input from a printed matter in a collating step, wherein the reference extracting an edge from the reference image is performed. An edge image is created, and an inspection edge image is created by extracting an edge from the inspection image. The reference edge image and the inspection edge image are binarized to form a reference binary edge image and an inspection binary edge image. The reference binary edge image is expanded to perform a reference binary edge expansion image, and the edge image is contracted to generate a reference binary edge contraction image. Mask processing with the value edge dilation image and the reference binary edge contraction image
A misalignment detection method characterized by comparing the reference edge image and the inspection edge image to detect a misalignment by performing a mask process using a value edge image. 2. A method according to claim 1, wherein said reference edge image and said inspection edge image are aligned.