JP2019067373A - Feature image generation device, inspection equipment, feature image generation method and feature image generation program - Google Patents

Abstract

To provide a feature image generation device capable of appropriately generating, from a reference image, a feature image to be used in matching for alignment of the reference image and a comparison image of high resolution.SOLUTION: When a difference satisfies a prescribed condition, the difference between a first cutout image obtained from an image binarizing, at a first gradation, an edge image in which an edge is extracted from a reference image, and a second cutout image obtained from an image binarizing the edge image at a second gradation, a feature image is obtained by cutting out a same location from an image binarizing the edge image at a gradation between the first gradation and the second gradation.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a technique for aligning a reference image obtained by imaging an object serving as a reference with a comparison image obtained by imaging a comparison object.

  Conventionally, an inspection image obtained by capturing an image of a printed matter with a camera is used as a method of automatically performing an inspection such as goodness of color tone, presence or absence of stain, presence or absence of omission, etc. of printed matter printed by a printing machine. There is a method of comparing reference images that satisfy certain criteria.

  In such an inspection method, when the reference image and the inspection image are compared, accurate alignment needs to be performed. For example, in rotary printing, printing is performed on a continuous sheet such as roll paper, but when imaging the continuous sheet after printing to obtain an image to be inspected, the continuous sheet shrinks in the conveying direction or meanders in the width direction It is necessary to perform alignment before comparison inspection in order to In sheet-fed printing, printing is performed on a cut sheet such as a sheet, but if the cut sheet is imaged after printing to obtain an image to be inspected, the cut sheet is irregular in the vertical direction, horizontal direction, and rotational direction. Alignment is necessary because of misalignment.

  Patent Literatures 1 to 3 disclose a technique for performing alignment (sometimes referred to as position correction) of an image to be inspected so that it can be compared with a reference image. These are techniques for subdividing the inspection image and the reference image into a plurality of blocks, calculating the amount of image shift for each block, and performing overall position correction. In addition, an image including a distinctive pattern (feature portion) is cut out for each block to generate a feature image, matching is performed between the inspection image and the reference image, and position correction is performed depending on how much the feature portion is shifted. It is also known.

Patent No. 3916596 Patent No. 4163199 Patent No. 5061543 gazette

  On the other hand, with technological advances such as cameras, it has become possible to more precisely inspect printed matter using high resolution images. However, the techniques of Patent Documents 1 to 3 are techniques suitable for low-resolution images, and there are cases where sufficient position correction can not be performed for high-resolution images. In addition, also in the method of position correction using a feature, there is a problem that a high resolution image can not select a feature suitable for position correction in a block. This is thought to be caused by the fact that the design becomes relatively large and abstract in the subdivided blocks due to the increase in resolution, and that there are a large number of blocks with no design because the block size becomes small. Be

  The present invention has been made in view of such problems, and one example of the problem is appropriately generating from a reference image a feature image used for matching for aligning a high-resolution reference image and a comparison image. It is an object of the present invention to provide a feature image generating apparatus and the like that can be performed.

  In order to solve the above problems, the invention according to claim 1 is an edge extraction unit for generating an edge image in which an edge is extracted from a reference image, and a first obtained by binarizing the edge image with a first tone. A binarized image, a second binarized image obtained by binarizing the edge image with a second tone lower than the first tone, the edge image with the first tone and the second tone A binarization unit for generating a third binarized image binarized at a third gradation between two gradations, and a horizontal straight line and a vertical straight line in the first binarized image An intersection acquiring unit for acquiring intersection coordinates, and an image including the intersection coordinates cut out from the first binarized image and the second binarized image, and cut out to generate a first cutout image and a second cutout image respectively The image generation unit, and the difference pixel number of the first cut-out image and the second cut-out image is a predetermined condition If the plus, characterized in that it and a feature image generation unit for generating feature images cut out an image including the intersection coordinates from said third binary image.

  The invention according to claim 2 is the feature image generating device according to claim 1, wherein a first horizontal image obtained by extracting a horizontal straight line from the first binarized image, and the first binarized image A first combining unit that combines a first vertical image in which vertical straight lines are extracted from the second to generate a first combined image; a second horizontal image in which a horizontal straight line is extracted from the second binarized image; And a second combining unit that combines a second vertical image obtained by extracting a vertical straight line from the binary image and generates a second combined image, and the intersection acquiring unit further includes the first binarized image. The intersection coordinates are acquired based on the first composite image generated from the image, and the cut-out image generation unit is configured to generate the first composite image and the second binarization generated from the first binarized image. The first cutout image and the second are respectively generated from the second composite image generated from the image. And generating an image Eject and.

  The invention according to claim 3 is the feature image generating apparatus according to claim 2, wherein the first combining unit extracts a horizontal straight line from the first binarized image and enlarges it in the horizontal direction. A vertical straight line is extracted from the first horizontal image and the first binarized image, and the first vertical image enlarged in the vertical direction is synthesized to generate the first synthesized image; The synthesizing unit extracts a horizontal straight line from the second binarized image, extracts a vertical straight line from the second horizontal image expanded in the horizontal direction, and the second binarized image, and extends the vertical straight direction. The enlarged second vertical image may be combined to generate the second combined image.

  The invention according to claim 4 is the feature image generating device according to any one of claims 1 to 3, further comprising: a dividing unit for dividing the reference image into a plurality of blocks, the intersection acquiring unit The intersection point coordinate is acquired for each of the blocks, the cutout image generation unit generates the first cutout image and the second cutout image for each of the blocks, and the feature image generation unit generates the feature for each of the blocks. Generating an image.

  The invention according to claim 5 is the feature image generating apparatus according to claim 4, wherein the reference image is used to capture a part of the continuous sheet while the continuous sheet is being conveyed along the longitudinal direction. In the case of an image, one feature image is generated for one of the blocks.

  The invention according to claim 6 is the feature image generating apparatus according to claim 4, wherein the reference image is an image obtained by photographing a cut sheet obtained by cutting a continuous sheet into single sheet units. Two feature images are generated for the block.

  The invention according to claim 7 is the feature image generating device according to any one of claims 1 to 6, wherein a verification region based on the intersection coordinates in the third binarized image is referred to as: The feature image is compared with the third binarized image while being moved, and the feature image is further provided with a determination unit that determines the feature image as an inappropriate feature image when they match other than the intersection coordinates.

  The invention according to claim 8 performs position correction of the inspection image using the feature image created by the feature image generation device according to any one of claims 1 to 7, and the reference image and the subject An inspection apparatus which performs comparison inspection of inspection images, and specifies a coordinate corresponding to the feature image in the inspection image, and calculates a deviation amount that is a difference from the intersection coordinates acquired by the intersection acquisition unit An amount calculation unit, a position correction unit that performs position correction of the inspection image based on the displacement amount, and a comparison unit that compares the inspection image that has been subjected to the position correction with the reference image It is characterized by

  The invention according to claim 9 is an edge extraction step of generating an edge image in which an edge is extracted from a reference image, a first binarized image obtained by binarizing the edge image with a first gradation, and the edge A second binarized image obtained by binarizing the image with a second tone lower than the first tone, and a second between the first tone and the second tone, the second binarized image being binarized at a second tone lower than the first tone. A binarization step of generating a third binarized image binarized with 3 gradations, and an intersection point acquisition step of acquiring intersection coordinates of a horizontal straight line and a vertical straight line in the first binarized image Cutting out an image including the intersection coordinates from the first binarized image and the second binarized image, and generating a first cutout image and a second cutout image, respectively; When the difference pixel number between the cutout image and the second cutout image satisfies a predetermined condition, And wherein the image generating step from the 3 binary image to generate a feature image cut out an image including the intersection coordinates, characterized in that it comprises a.

  According to a tenth aspect of the present invention, there is provided an edge extraction unit that generates an edge image in which an edge is extracted from a reference image, a first binarized image in which the edge image is binarized with a first gradation. A second binarized image obtained by binarizing the edge image with a second tone lower than the first tone, and the edge image between the first tone and the second tone A binarization unit for generating a third binarized image binarized with the third gradation of the second gradation, acquiring an intersection point for acquiring an intersection coordinate of a horizontal straight line and a vertical straight line in the first binarized image A cutout image generation unit that cuts out an image including the intersection coordinates from the first binarized image and the second binarized image, and generates a first cutout image and a second cutout image, and the first cutout If the difference pixel number between the image and the second cutout image satisfies a predetermined condition, Feature image generation unit for generating feature images cut out an image including the intersection coordinates from the third binarized image, characterized in that to function as a.

  According to the present invention, an edge image obtained by extracting an edge from a reference image is binarized with a first cut-out image obtained from an image binarized with a first tone and an edge image with a second tone. Since the same position is cut out from the image obtained by binarizing the edge image with the third gradation when the difference between the second cut-out images obtained from the shot images satisfies the predetermined condition, and the feature image is obtained. If the gradation in the edge image of the image to be compared with the reference image is between the first gradation and the second gradation, the reference image and the comparison image can be aligned. That is, a feature image used for matching for aligning the high-resolution reference image and the comparison image can be appropriately generated from the reference image.

It is a figure showing an example of printing machine S in a 1st embodiment. It is a block diagram showing an example of composition of inspection device T in a 1st embodiment. It is a flowchart which shows an example of the template image creation process for continuous sheets by the test | inspection apparatus T in 1st Embodiment. It is a figure which shows an example which divided | segmented the reference | standard image 200 in 1st Embodiment into several blocks. It is an example of A image of R component image. It is an example of A image of G component image. It is an example of A image of B component image. (A) is an example of B image of R component image, (B) is an example of B image of G component image, (C) is an example of B image of B component image, (D) is RGB It is an example of B image of a component image. (A) is an example of a C image of an R component image, (B) is an example of a C image of a G component image, (C) is an example of a C image of a B component image, (D) is an RGB It is an example of C image of a component image. (A) is an example of a C1 image, (B) is an example of a C2 image, and (C) is an example of an image obtained by combining the C1 image and the C2 image. (A) is an example of a B1 image, (B) is an example of a B2 image, and (C) is an example of an image obtained by combining the B1 image and the B2 image. (A) is an example of a C3 image, (B) is an example of a B3 image, (C) is an example of a C 'image, and (D) is an example of a B' image. It is an example of D image. It is a flowchart which shows an example of the continuous sheet test | inspection process by the test | inspection apparatus T in 1st Embodiment. It is a flowchart which shows an example of a continuous sheet and deviation | shift amount calculation process by the test | inspection apparatus T in 1st Embodiment. It is a flowchart which shows an example of the continuous sheet and template presence block process by the test | inspection apparatus T in 1st Embodiment. It is a flowchart which shows an example of the template image creation process for sheets by the test | inspection apparatus T in 2nd Embodiment. It is a flowchart which shows an example of the sheet inspection process by the inspection apparatus T in 2nd Embodiment. It is a flowchart which shows an example of the sheet | seat / deviation | shift amount calculation process by the inspection apparatus T in 2nd Embodiment. It is a flowchart which shows an example of the block process with sheets and a template by the inspection apparatus T in 2nd Embodiment.

[1. First embodiment]
Hereinafter, a first embodiment of the present invention will be described with reference to the drawings. The embodiment described below is an embodiment in which the present invention is applied to an inspection device installed in a rotary offset printing press.

[1.1. Configuration of offset rotary printing press and inspection device]
The configuration of the rotary offset printing press S (hereinafter referred to as "printing press S") and the inspection device T in the present embodiment will be described using Figs. 1 and 2.

[1.1.1. Configuration of Printing Machine S]
First, the configuration of the printing press S will be described with reference to FIG. The printing machine S is a multicolor printing machine, and printing units U1-U4 are provided for each of ink colors (C (cyan), M (magenta), Y (yellow), K (black)). Since the printing machine S is a double-sided printing press, each printing unit U1-U4 is provided with a blanket cylinder (upper cylinder, lower cylinder) so as to sandwich the paper conveyance path, and the printing cylinder (upper cylinder) , Lower cylinder) and an ink supply device (upper cylinder side, lower cylinder side). The printing plate cylinder is formed with a printing plate for one sheet, and the printing blanket cylinder is made to carry two sheets of printing ink. When the printing cylinder is rotated twice, the blanket cylinder rotates one revolution. (The so-called "double-body type blanket cylinder"). That is, during one rotation of the blanket cylinder, a pattern of two cut sheets is printed. In the present embodiment, although the case where the printed material is a band-like roll paper (an example of a "continuous sheet") will be described, the present invention can be applied to continuous sheets other than roll paper. The material of the continuous sheet may be cloth, vinyl or the like as long as it can be printed. Moreover, what cut | disconnected the continuous sheet per sheet (for example, a sheet) is called cut sheet.

  A dryer U5 is provided downstream of the printing units U1-U4. Further, downstream of the dryer U5, there is an inspection target area (image portion and non-image portion constituting a pattern) including a pattern (symbol, figure, photograph, pattern, etc.) printed on roll paper which is a substrate. For example, in order to pick up an image on a page 1 of a newspaper, a front camera 31A and a front illumination 32A, and a rear camera 31B and a rear illumination 32B are provided. The front surface camera 31A and the rear surface camera 31B (hereinafter, sometimes collectively referred to as "camera 31") are line sensor cameras capable of capturing a line image of 4096 pixels every 25 μs, for example. A camera signal obtained by imaging the printed roll paper is output. The front surface illumination 32A and the rear surface illumination 32B (hereinafter sometimes collectively referred to as "the illumination 32") respectively emit light sufficient for the front surface camera 31A and the rear surface camera 31B to capture a high resolution image.

  Further downstream of the portion where the camera 31 and the illumination 32 are installed, a folding machine U6 is provided for folding the roll paper on which the design is printed.

[1.1.2. Configuration of inspection apparatus T]
Next, the configuration of the inspection apparatus T will be described using FIG. The inspection apparatus T includes a system controller 11, pipeline image processing unit 12, parallel image processing unit 13, front camera branch board 14, back camera branch board 15, encoder branch board 16, HUB 17, camera 31, illumination 32, and encoder 33. It is comprised including. Further, the inspection device T is connected to the inspection server 20, the plate making server SV, and the offset printing machine S.

  The system controller 11 is a programmable logic controller (PLC) that receives various signals from the printing machine S and each unit in the inspection apparatus T and controls each unit in the inspection apparatus T.

  The pipeline image processing unit 12 has a total of four image processing boards (two sets for the front and the back) (the front image processing board 121A, the front image processing board 122A, the back image processing board 121B, and the back image A processing board 122B) is mounted. The operation of the front image processing board 121A and the front image processing board 122A is switched alternately (the same applies to the rear image processing board 121B and the rear image processing board 122B). Each image processing board mounts a plurality of parallel processing chips, and for example, performs processing of an image of 10,000,000 × 3 colors every 45 ms. The front image processing board 121A and the front image processing board 122A receive camera signals from the front camera 31A via the front camera branch board 14, and high resolution images of the front surface based on the pulse signals received from the encoder branch board 16 (For a specific generation method, refer to Japanese Patent No. 3811565), and 100% inspection (inspection for all printed matter) is performed using the high resolution image. Similarly, the back image processing board 121B and the back image processing board 122B also receive camera signals from the back camera 31B via the back camera branch board 15, and perform 100% inspection.

  Next, the contents of the exhaustive inspection will be described. The pipeline image processing unit 12 performs an exhaustive inspection based on an image (sometimes referred to as an inspection image) captured after the exhaustion inspection starts, using the high resolution image that the operator has determined in advance to have no problem as a reference image. Specifically, a defect is detected by comparing the difference image obtained by subtracting the reference image from the image to be inspected and the difference image obtained by subtracting the image to be inspected from the reference image with the threshold image.

  The pipeline image processing unit 12 aligns the two images so that the comparison can be appropriately performed when the inspection is performed to compare the inspection image and the reference image. Therefore, the pipeline image processing unit 12 divides the image into a plurality of blocks, and performs a shift amount calculation process of calculating the shift amount of both images for each block. In the shift amount calculation process, the pipeline image processing unit 12 divides the reference image and the inspection image into blocks, and uses the template image created for each block based on the reference image to generate the inside of the corresponding block of the inspection image. The matching portion is searched by searching, and the difference between the coincident coordinates and the coordinates of the template image is calculated as the amount of deviation.

  In the first embodiment, in which the substrate to be printed is a continuous sheet, the pipeline image processing unit 12 creates one template image for one block and searches the corresponding block of the inspection image with one template image. Do. The process of creating a template image will be described later using a flowchart.

  The pipeline image processing unit 12 may not be able to create a template image for a block having a small number of feature portions in the process of creating a template image. The pipeline image processing unit 12 calculates the amount of deviation based on the template image for the block for which the template image has been created (“block with template”), while the block for which the template image could not be created (“block without template In the case of “)”, the amount of deviation is determined based on the amount of deviation of upper, lower, left, and right blocks or blocks in the same row / in the same row for which the amount of shift is determined.

  Also, when comparing the template image and the inspection image for each block, the pipeline image processing unit 12 creates a block image for the inspection image by the same method as the template image for each block, and uses the template image Search for a matching location by searching in the corresponding block image. As described above, by comparing the images created by the same method, it is possible to search for a matching point more accurately.

  The pipeline image processing unit 12 performs position correction of the image to be inspected based on the displacement amount calculated for each block, thereby aligning the reference image and the image to be inspected.

  The parallel image processing unit 13 has a total of two image processing boards (a front image processing board 131A and a rear image processing board 131B), one for the front and one for the back, and a pipeline image processing unit Operates in parallel with 12 Each image processing board mounts a plurality of parallel processing chips, and for example, performs processing of an image of 10,000,000 × 3 colors every 45 ms. The front image processing board 131A receives a camera signal from the front camera 31A through the front camera branch board 14, generates a high resolution image of the surface based on the pulse signal received from the encoder branch board 16, and makes the plate making data ( Verification inspection with an image represented by plate making data and inspection between double cylinders are performed. The plate-making data is the original data when generating the plate to be attached to the plate cylinder, and in the matching inspection with the plate-making data, imposition, size, calibration, plate damage, with dust (the plate cylinder and blanket cylinder have dust Do not check for

  On the other hand, an inspection between double cylinders is an inspection that compares high-resolution images (that is, continuous high-resolution images) obtained by imaging two sheets (printed matter) printed when the blanket cylinder rotates once. For example, if the images do not match, a defect in which a part of the blanket cylinder is scratched or dust is detected.

  The front camera branch board 14 simultaneously branches and sends camera signals from the front surface camera 31A to the front image processing board 121A, the front image processing board 122A and the front image processing board 131A.

  The back camera branch board 15 simultaneously branches and sends camera signals from the back camera 31B to the back image processing board 121B, the back image processing board 122B, and the front image processing board 131B.

  The encoder branch board 16 is attached to the plate cylinder in the offset printing press S, and encoder pulse signals (A, B, Z phases) output from the encoder 33 interlocked with the plate cylinder (1: 1 interlocked with the rotation of the plate) , And branches and outputs 0.05 to 0.1 mm encoder pulse signals (A, B, and Z phases) to the pipeline image processing unit 12 and the parallel image processing unit 13.

  The HUB 17 is a HUB for LAN connection with the system controller 11, the pipeline image processing unit 12, the parallel image processing unit 13, the inspection server 20, the plate making server SV, and the printing machine S.

  The inspection server 20 performs functions such as storage of reference images, storage of defective images at the time of defect detection, storage of operation records at the start and stop of inspection, and inspection log data. In addition, the inspection server 20 is used when viewing inspection results via the LAN as needed. The plate making server SV stores plate making data and the like, and when the operator performs setting of the printing machine S to print a new printed matter of pattern, the contents of the setting are acquired, and inspection by the inspection device T is performed. Necessary information (including plate making data) is set in the inspection apparatus T.

[1.2. Operation of Template Image Creation Process for Continuous Sheet]
The continuous sheet template image creation processing by the pipeline image processing unit 12 will be described using FIG. 3. FIG. 3 is a flowchart showing an example of the continuous sheet template image creation process.

  First, the pipeline image processing unit 12 acquires a reference image obtained by imaging a printed material that the operator has determined that there is no problem as a product (step S1). The reference image is an RGB image having RGB (Red, Green, Blue) components for each pixel, and each component is a value indicating a gradation that means a step of density (for example, “0 to 255 in the case of 256 gradations It is shown by "value".

  Next, the pipeline image processing unit 12 acquires, for the reference image, the luminance (white portion luminance) of each pixel corresponding to the white portion for each of RGB (step S2). The blank portion is a portion of the paper to which the ink is not attached.

  Next, the pipeline image processing unit 12 calculates a correction coefficient for the reference image so that the white area brightness becomes the target white area brightness for each of RGB, and corrects each pixel (step S3). The target blank area brightness is, for example, set in advance by an operator or the like.

  Next, the pipeline image processing unit 12 divides the reference image (for example, an image obtained by imaging a printed matter having a size of 1030 mm in the width direction × 625 mm in the conveyance direction) into a plurality of blocks (step S4). The number of blocks to be divided is arbitrarily set by the operator. For example, as shown in FIG. 4, the reference image 200 is divided into 512 blocks of 64 rows and 8 columns. However, it is preferable to change the number of lines according to the size of one paper pitch (one line 80 pixels). Further, the pipeline image processing unit 12 stores the range (X and Y coordinates of the four corners) of each block in a storage unit (not shown) in the pipeline image processing unit 12.

  Next, the pipeline image processing unit 12 performs edge extraction on the reference image for each RGB using a Sobel filter or an edge extraction filter (step S5). Specifically, the reference image (RGB) is divided into an R component image, a G component image, and a B component image, and edge extraction is performed on each image. The reason for performing edge extraction for each RGB is to extract more edges. The image from which the edge has been extracted (edge image) is hereinafter referred to as "A image". FIG. 5 shows an example of the A image of the R component image, FIG. 6 shows an example of the A image of the G component image, and FIG. 7 shows an example of the A image of the B component image. The edge is a portion where the density in the image changes rapidly, and corresponds to, for example, the contour or line of an object in the image.

  Next, the pipelined image processing unit 12 binarizes the A image with gradation a ("90" in the present embodiment) (step S6). Specifically, the A image of the R component image, the A image of the G component image, and the A image of the B component image generated in the process of step S5 are binarized with the gradation a. The image obtained by binarization is hereinafter referred to as "B image". 8A shows an example of the B image of the R component image, FIG. 8B shows an example of the B image of the G component image, and FIG. 8C shows the B image of the B component image. This is an example, and FIG. 8D is a B image of an RGB component obtained by combining these B images.

  Next, the pipelined image processing unit 12 binarizes the A image with the gradation b (“130” in the present embodiment) (step S7). Specifically, the A image of the R component image, the A image of the G component image, and the A image of the B component image generated in the process of step S5 are binarized with the gradation b. The image obtained by binarization is hereinafter referred to as "C image". FIG. 9 (A) is an example of a C image of an R component image, FIG. 9 (B) is an example of a C image of a G component image, and FIG. 9 (C) is a C image of the B component image. This is an example, and FIG. 9D is a C image of an RGB component obtained by combining these C images.

  Next, the pipeline image processing unit 12 horizontally differentiates the C image (extracts only the horizontal line of the edge of the pattern by performing horizontal differentiation), and then expands the image in the horizontal direction by two pixels (hereinafter referred to as “C1 image (Step S8). Expansion in the horizontal direction by two pixels means expanding the entire image in the horizontal direction. The expansion in the horizontal direction makes it easier to obtain the intersection point in the process of step S10 described later. FIG. 10A is an example of the C1 image.

  Next, after vertically differentiating the C image, the pipeline image processing unit 12 generates an image (hereinafter referred to as “C2 image”) expanded in the vertical direction by two pixels (step S9). Expansion in the vertical direction by two pixels means expanding the entire image in the vertical direction. The expansion in the vertical direction makes it easier to obtain the intersection point in the process of step S10 described later. FIG. 10B is an example of the C2 image.

  Next, the pipeline image processing unit 12 combines the C1 image and the C2 image to generate a C intermediate image, and is a straight line that is continuous for eight or more pixels both horizontally and vertically, and only a straight line that intersects vertically is left. An image (hereinafter referred to as “C3 image” is generated, and the XY address of the intersection is obtained (step S10). Note that FIG. 10C is an example of an image obtained by combining the C1 image and the C2 image. A) is an example of a C3 image, as shown in FIG.12A, when there are a plurality of intersections, respective XY addresses are acquired.

  Next, the pipeline image processing unit 12 horizontally differentiates the B image, and then generates an image (hereinafter referred to as “B1 image”) expanded in the horizontal direction by two pixels (step S11). FIG. 11A is an example of the B1 image.

  Next, the pipeline image processing unit 12 vertically differentiates the B image, and then generates an image (hereinafter referred to as “B2 image”) expanded in the vertical direction by two pixels (step S12). FIG. 11B is an example of the B2 image.

  Next, the pipeline image processing unit 12 combines the B1 image and the B2 image to generate a B intermediate image, and leaves only straight lines that are straight lines that are continuous for eight or more pixels in both horizontal and vertical directions and that cross vertically An image (hereinafter referred to as "B3 image" is generated (step S13) Note that Fig. 11C is an example of an image obtained by combining the B1 image and the B2 image, and Fig. 12B is an example of the B3 image. It is.

  Next, the pipeline image processing unit 12 generates, from the C3 image (see FIG. 12A), a cutout image (C ′ image) of 32 × 32 pixels centered on the XY address acquired in step S10. (Step S14). The size of the cutout image (C 'image) is arbitrary, and for example, a cutout image (C' image) of 64 pixels x 64 pixels may be generated. FIG. 12C is an example of a C ′ image.

  Next, the pipeline image processing unit 12 generates 32 pixels centered on the same XY address as the XY address that is the center when the cutout image is cut out from the B3 image (see FIG. 12B) in the process of step S13. A cutout image (B ′ image) of × 32 pixels is generated (step S15). Note that it is also possible to generate a cutout image (B ′ image) of 64 pixels × 64 pixels in the same manner as the process of step S13 (however, the same size as the C ′ image). FIG. 12D is an example of the B ′ image.

  Next, if the difference between the C ′ image and the B ′ image is within the range of 1 pixel to 8 pixels, the pipeline image processing unit 12 determines the center address of these images (the XY address acquired in the process of step S10) It is determined that “appropriate of template suitability” (step S16). In addition, when the difference between the C ′ image and the B ′ image is 0 pixel (completely matched), it may be determined as “with template suitability”. On the other hand, if the difference between the C 'image and the B' image is not within the range of 1 pixel to 8 pixels, the pipeline image processing unit 12 determines that the center address of these images is "no template suitability". That is, when the difference between the C ′ image and the B ′ image is, for example, 9 pixels or more as in the present embodiment, the difference is too much, so it is determined that “no template suitability”. In the present embodiment, it is determined that “the template suitability is present” only when the difference is in the range of 1 pixel to 8 pixels, but this is an example, and the threshold may be changed as appropriate.

  When a plurality of XY addresses are acquired in the process of step S10, the processes of steps S14 and S15 are performed by the number of X and Y addresses to generate a C 'image and a B' image. At this time, a C 'image and a B' image cut out from the same XY address are stored as a set. Then, the process of step S16 is performed on each set of C 'and B' images.

  Next, the pipelined image processing unit 12 selects one block divided in the process of step S4 (step S17).

  Next, the pipelined image processing unit 12 searches the block selected in the process of step S17 for an XY address determined to be “with template suitability” (step S18). Specifically, it is searched whether or not there is an XY address determined as “with template suitability” while shifting one pixel at a time in the X direction from the start point (for example, the lower left corner) in the block. If the block end is not found, the pixel is shifted by one pixel in the Y direction, and while shifting the pixel by one pixel in the X direction again, a search is made for an XY address determined to be "template appropriate". The search is ended when one XY address determined to be "appropriate for template" is found.

  Then, the pipeline image processing unit 12 determines whether or not there is an XY address of “with template suitability” in the block (step S19). Specifically, it is determined as "YES" if at least one of the XY addresses "with template suitability" is included in the block.

  If the pipelined image processing unit 12 determines that there is no XY address of “with template suitability” in the block (step S19: NO), the pipeline image processing unit 12 determines that the block is “block without template” (step S20), It transfers to the process of step S26. On the other hand, when the pipeline image processing unit 12 determines that there is an XY address of “with template suitability” in the block (step S19: YES), the pipeline image processing unit 12 determines that the block is “block with template” (step S21). And the process of step S22.

  Next, the pipeline image processing unit 12 performs gradation ((a + b) / 2) ("(90 + 130) / 2 = 110" in this embodiment) of the A image for each RGB as in the process of step S6. The image is binarized, and the same processing as that performed for the B image in the processing of steps S11 to S13 is performed to generate a D image (step S22). FIG. 13 is an example of the D image.

  Next, the pipeline image processing unit 12 cuts out 32 pixels × 32 pixels whose center address is the XY address “with template suitability” from the D image, and a template image (D ′ image) (D ′ image in FIG. 13) 300) is generated (step S23). The size of the D ′ image may also be 64 pixels × 64 pixels.

  Next, the pipeline image processing unit 12 checks the template image (D 'image) (step S24). In this check, the D 'image is shifted by one pixel at a time in the template verification range (a range of ± 64 pixels in the X direction and ± 128 pixels in the Y direction with respect to the center address of the template image (D ′ image)). It is verified that the difference between the D image and the D ′ image at any position (except for the center address) is one pixel or more. That is, it is verified that the template image (D 'image) is unique around it (within the template verification range).

  Then, if the template image (D 'image) is not unique within the template verification range as a result of the check, the pipeline image processing unit 12 rejects the template image (D' image), and returns to step S18. The other "template suitability" XY addresses in the same block are searched, and the processes in steps S19 to S24 are performed on the XY addresses. If the result of the check does not change even if the process of step S18 to step S24 is repeated twice, the process proceeds to step S20. On the other hand, if the template image (D 'image) is unique within the template verification range as a result of the check, the pipeline image processing unit 12 proceeds to the process of step S25.

  Next, the pipeline image processing unit 12 determines identification information (for example, a block ID) of one block selected in the process of the latest step S17, a template image (D 'image), and a center address (template image (D The "image" is registered in the template table (not shown) in association with the XY address) when the "image" is cut out from the D image (step S25), and the process proceeds to step S26.

  After completing the process of step S20 or step S25, the pipelined image processing unit 12 then determines whether all blocks have been selected (step S26). That is, the pipelined image processing unit 12 determines whether all the blocks divided in the process of step S4 have been selected by the process of step S17. At this time, when the pipeline image processing unit 12 determines that all the blocks are not selected (step S26: NO), the process proceeds to step S17, and one block which has not been selected so far Choose On the other hand, when determining that all the blocks have been selected (step S26: YES), the pipeline image processing unit 12 ends the continuous sheet template image creation process.

  In the present embodiment, the pipeline image processing unit 12 extracts an image (B ′ image) from each of a B image obtained by binarizing the A image with gradation a and a C image obtained by binarizing the A image with gradation b. And C 'images) and if the difference is within a certain range (1 pixel to 8 pixels), it is determined that the XY address at the time of cutting out the B' image and the C 'image is the suitability of the template . This makes it possible to find feature points in a certain gradation range (a range of gradations a to b). Also, the pipeline image processing unit 12 generates a template image (D ′ image) from the D image obtained by binarizing the A image with gradation (a + b) / 2, based on the XY address determined as having the template suitability. Do. Thereby, even if the gradation of the image to be inspected changes in the range of gradation a to b, matching with the template image (D 'image) can be appropriately performed.

[1.3. Operation of continuous sheet inspection process]
Next, continuous sheet inspection processing by the pipeline image processing unit 12 will be described using FIG. FIG. 14 is a flowchart showing an example of the continuous sheet inspection process. The continuous sheet inspection process is an exhaustive inspection that compares the reference image and the inspection image.

  First, the pipeline image processing unit 12 performs a continuous sheet shift amount calculation process (step S31). Note that the continuous sheet displacement amount calculation process will be described later.

  Next, the pipeline image processing unit 12 corrects the position of the image to be inspected based on the displacement amount calculated for each block by the continuous sheet displacement amount calculation process (step S32).

  Next, the pipeline image processing unit 12 performs an inspection for comparing the position-corrected inspection image with the reference image (step S33).

  Next, the pipeline image processing unit 12 outputs the result of the comparison inspection performed in the processing of step S33 (step S34), and ends the continuous sheet inspection processing. In the process of step S34, for example, the pipeline image processing unit 12 creates result data indicating the result of the comparison inspection and transmits it to the inspection server 20 (a defective image at the time of defect detection, at the start or stop of the inspection). The inspection result may be displayed on a display device (e.g., a display device connected to the inspection server 20, etc.).

[1.4. Operation of continuous sheet / displacement amount calculation processing]
Next, the continuous sheet / displacement amount calculation process by the pipeline image processing unit 12 will be described with reference to FIG.

  First, the pipeline image processing unit 12 acquires an inspection image obtained by imaging a printed matter to be an object of exhaustive inspection (step S51). An inspection image is an RGB image, and each component is indicated by a value indicating a gradation of “0 to 255”.

  Next, the pipeline image processing unit 12 obtains the luminance (white portion brightness) of each pixel corresponding to the white portion for each of RGB in the inspection image (step S52).

  Next, the pipeline image processing unit 12 calculates a correction coefficient for each white color of the inspection image so that the white area brightness becomes the target white area brightness for each RGB, and corrects each pixel (step S53). The target blank area brightness is assumed to be set in advance by the operator or the like in the same value as in step S3 of the continuous sheet template image creation process.

  Next, the pipeline image processing unit 12 divides the inspection image into a plurality of blocks in the same manner as the reference image (step S54).

  Next, the pipeline image processing unit 12 performs edge extraction with the Sobel filter for each of the R, G, and B images with respect to the inspection image as in the reference image (step S55). In addition, the image which edge-extracted also in a continuous sheet test | inspection process is called "A image."

  Next, as in step S22 of the continuous sheet template image creation process, the pipeline image processing unit 12 applies the gradation ((a + b) / 2) ((90 + 130) / 2 in the present embodiment) to the A image. The same processing as that performed for the B image in the processing of steps S11 to S13 of the continuous sheet template image creation processing is performed on the image binarized at = 110 ′ ′) to generate a D image (step S56). As a and b, the same values as in the continuous sheet template image creation process are used.

  Next, the pipeline image processing unit 12 performs block processing with continuous sheet / template (step S57). The continuous sheet / template with block process will be described later. The continuous sheet / template / block process is a process of determining the amount of deviation for the template / block.

  Next, the pipelined image processing unit 12 determines whether there is a block for which the shift amount has not been determined (step S58). In the continuous sheet / template present block processing, since the shift amount is determined for the template present block, the block for which the shift amount is not determined here corresponds to the template absent block. If the pipeline image processing unit 12 determines that there is no block for which the amount of deviation has not been determined (step S58: NO), the continuous sheet / amount of deviation calculation process ends. On the other hand, when the pipeline image processing unit 12 determines that there is a block for which the amount of shift has not been determined (step S58: YES), one non-template block is selected (step S59), and the amount of shift is determined. The amount of deviation is determined based on the amount of deviation of upper, lower, left, and right blocks or blocks in the same row / in the same row (step S60), and the process proceeds to step S58. Then, the pipeline image processing unit 12 repeats the processing of steps S58 to S60 until all “blocks without template” are selected (until the amount of deviation is determined for all blocks without template).

[1.5. Operation of block processing with continuous sheet / template]
Next, block processing with continuous sheets and templates by the pipeline image processing unit 12 will be described with reference to FIG.

  First, the pipelined image processing unit 12 selects one block that has been determined as the “template present block” in the process of step S21 of the continuous sheet template image creation process (step S101).

  Next, the pipeline image processing unit 12 determines from the template table (see step S25 of the continuous sheet template image creating process) the template image (D 'image) and the center address included in the block selected in step S101. Are acquired (step S102).

  Next, the pipelined image processing unit 12 sets a preset range (for example, a range of ± 64 pixels in the X direction and a range of ± 128 pixels in the Y direction) based on the center address acquired in the process of step S102. The D ′ image is shifted by one pixel with respect to the D image generated in the process of step S56, and the difference between the D image and the D ′ image is calculated (step S103).

  Next, the pipeline image processing unit 12 specifies the position at which the difference is the smallest (step S104). Note that if there are a plurality of positions with the smallest difference and the same value, one position closest to the center address is identified.

  Next, the pipelined image processing unit 12 determines the difference between the position identified in the process of step S104 and the center address acquired in the process of step S102 as the deviation amount (dx, dy) (step S105). The determined amount of deviation is stored in association with identification information (for example, a block ID) of a block including the center address.

  Next, the pipelined image processing unit 12 determines whether or not all the "template present blocks" have been selected (step S106). At this time, when the pipeline image processing unit 12 determines that not all “blocks with template” have been selected (step S106: NO), the process proceeds to step S101, and selection has been made by that time. Select one non-template block. Then, the processing of steps S101 to S106 is repeated until all the "template present blocks" are selected. On the other hand, if the pipeline image processing unit 12 determines that all "blocks with template" have been selected (step S106: YES), the continuous sheet / template with block processing is ended, and the continuous sheet / displacement amount is calculated. Return to processing.

[2. Second embodiment]
Next, a second embodiment of the present invention will be described with reference to the drawings. The second embodiment is an embodiment in which the present invention is applied to an inspection apparatus installed in an offset sheet-fed printing press. In the second embodiment, there are many parts in common with the first embodiment, and therefore, the differences will be mainly described here.

[2.1. Configuration of offset sheet-fed printing press and inspection apparatus]
The configuration of the offset sheet-fed printing press according to the second embodiment is not directly related to the present invention, and thus the description thereof is omitted.

  Next, the configuration of the inspection apparatus T in the second embodiment will be described. The inspection apparatus T in the second embodiment basically has the same configuration as the inspection apparatus T in the first embodiment.

  The pipeline image processing unit 12 has a total of four image processing boards (two sets for the front and the back) (the front image processing board 121A, the front image processing board 122A, the back image processing board 121B, and the back image A processing board 122B) is mounted. The operation of the front image processing board 121A and the front image processing board 122A is switched alternately (the same applies to the rear image processing board 121B and the rear image processing board 122B). Each image processing board carries a plurality of parallel processing chips, and for example, performs processing of an image of 10,000,000 × 3 colors every 180 msec. The front image processing board 121A and the front image processing board 122A receive camera signals from the front camera 31A via the front camera branch board 14, and high resolution images of the front surface based on the pulse signals received from the encoder branch board 16 (For a specific generation method, refer to Japanese Patent No. 3811565), and 100% inspection (inspection for all printed matter) is performed using the high resolution image. Similarly, the back image processing board 121B and the back image processing board 122B also receive camera signals from the back camera 31B via the back camera branch board 15, and perform 100% inspection.

  As in the first embodiment, the pipeline image processing unit 12 aligns both images so that the comparison can be appropriately performed when performing an inspection for comparing the inspection image and the reference image in the exhaustive inspection. Therefore, the pipeline image processing unit 12 divides the image into a plurality of blocks, and performs a shift amount calculation process of calculating the shift amount of both images for each block.

  In the second embodiment in which the printed material is a sheet as an example of a cut sheet, when the printed sheets are photographed one after another by the camera 31, the individual sheets have irregular directions (longitudinal direction Because the image is captured with a shift in the lateral direction or the rotational direction, the direction of the continuous inspection image also becomes irregular. Two template images are created for one block, and two template images search the corresponding block of the inspection image. The process of creating a template image will be described later using a flowchart. On the other hand, in the first embodiment, in which the orientation (shift) of consecutive inspection images is related and the printing speed is high and the speed is also required for 100% inspection, as described above, one template for one block is used. Align with the image.

  The pipeline image processing unit 12 may not be able to create two template images for a block having a small number of feature portions in the template image creation processing. The pipeline image processing unit 12 calculates the amount of deviation based on the two template images for the block in which two sheets of template images can be created ("block with template") (calculates the amount of deviation for two coincident points) And the average is taken as the shift amount of that block). On the other hand, for the block where the template image can not be created (“block without template”), the block of the top, bottom, left and right or the same row The amount of deviation is determined based on the amount of deviation of

  Also, when comparing the template image and the inspection image for each block, the pipeline image processing unit 12 creates a block image for the inspection image by the same method as the template image for each block, and uses the template image Search for a matching location by searching in the corresponding block image. As described above, by comparing the images created by the same method, it is possible to search for a matching point more accurately.

  The pipeline image processing unit 12 performs position correction of the image to be inspected based on the displacement amount calculated for each block, thereby aligning the reference image and the image to be inspected.

[2.2. Operation of Template Image Creation Processing for Sheet Sheets]
The sheet template image creation processing by the pipeline image processing unit 12 will be described using FIG. 17. FIG. 17 is a flowchart showing an example of the sheet template image creation processing.

  The process at the beginning of the sheet template image creation process is the same as steps S1 to S16 of the continuous sheet template image creation process (see FIG. 3).

  After completing the process of step S16, the pipelined image processing unit 12 next selects one block divided in the process of step S4 (step S201).

  Next, the pipelined image processing unit 12 searches the block selected in the process of step S17 for an XY address determined to be “with template suitability” (step S202). Specifically, it is searched whether or not there is an XY address determined as “with template suitability” while shifting one pixel at a time in the X direction from the start point (for example, the lower left corner) in the block. If the block end is not found, the pixel is shifted by one pixel in the Y direction, and while shifting the pixel by one pixel in the X direction again, a search is made for an XY address determined to be "template appropriate". The search is ended when two XY addresses determined to be "appropriate for template" are found.

  Then, the pipeline image processing unit 12 determines whether or not there are two XY addresses of “with template suitability” in the block (step S203). If the pipeline image processing unit 12 determines that two XY addresses “with template suitability” are not present (step S203: NO), the pipeline image processing unit 12 determines that the block is “block without template” (step S204). It transfers to the process of S210. On the other hand, when the pipeline image processing unit 12 determines that there are two XY addresses of “template appropriate” (step S203: YES), the pipeline image processing unit 12 determines that the block is a “template present block” (step S205). Then, the process proceeds to step S206.

  Next, as in step S22 of the continuous sheet template image creation process, the pipeline image processing unit 12 applies the gradation ((a + b) / 2) ((90 + 130) / 2 in the present embodiment) to the A image. The same processing as that performed for the B image in the processing of steps S11 to S13 of the continuous sheet template image creation processing is performed on the image binarized at = 110 ′ ′) to generate a D image (step S206).

  Next, the pipeline image processing unit 12 cuts out 32 pixels × 32 pixels centered on the XY address of “with template suitability” from the D image, and generates a template image (D ′ image) (step S207). In the second embodiment, since there are two XY addresses “with template suitability” for one block, the pipeline image processing unit 12 performs the process of step S207 for each of the two template images (D ′ Generate an image).

  Next, the pipeline image processing unit 12 checks the template image (D 'image) (step S208). In this check, the D 'image is shifted by one pixel at a time in the template verification range (a range of ± 64 pixels in the X direction and ± 128 pixels in the Y direction with respect to the center address of the template image (D ′ image)). It is verified that at any position (except for the center address), the difference between the D image and the D 'image is at least one pixel. That is, it is verified that the template image (D 'image) is unique around it (within the template verification range). In the second embodiment, since there are two D 'images per block, the pipeline image processing unit 12 verifies each D' image in the process of step S208.

  Then, as a result of the check, when the template image (D ′ image) is not unique within the template verification range, the pipeline image processing unit 12 rejects the template image (D ′ image) and determines that the template image (D ′ image) is rejected. In order to replace, the process returns to step S202, another "template suitability" XY address in the same block is searched, and the process of step S203 to step S208 is performed on the XY address. If the two template images (D 'images) do not pass even if the processes in steps S202 to S208 are repeated twice, the process proceeds to step S204. On the other hand, the pipeline image processing unit 12 passes if the template image (D ′ image) is unique within the template verification range as a result of the check. When the two template images (D 'images) pass, the pipeline image processing unit 12 proceeds to the process of step S209.

  Next, the pipeline image processing unit 12 identifies the identification information (for example, block ID) of one block selected in the process of the most recent step S201, two template images (D 'images), and each template image ( The center address of the D ′ image), the average coordinates thereof, and the center address of the block are associated with each other and registered in a template table (not shown) (step S 209), and the process proceeds to step S 210.

  After completing the process of step S204 or step S209, the pipelined image processing unit 12 then determines whether all blocks have been selected (step S210). That is, the pipelined image processing unit 12 determines whether all the blocks divided in the process of step S4 have been selected by the process of step S201. At this time, when the pipeline image processing unit 12 determines that all the blocks have not been selected (step S210: NO), the process proceeds to step S201, and one block which has not been selected so far Choose And the process of step S201-step S210 is repeated until all the blocks are selected. On the other hand, when determining that all the blocks have been selected (step S210: YES), the pipeline image processing unit 12 ends the sheet template image creation processing.

  In the second embodiment, the pipelined image processing unit 12 extracts an image (B ′ from the B image obtained by binarizing the A image with gradation a and the C image obtained by binarizing the A image with gradation b (B ′ Compare the image and the C 'image, and if the difference is within a certain range (1 pixel to 8 pixels), determine the XY address at the time of cutting out the B' image and the C 'image as the suitability of the template Do. This makes it possible to find feature points in a certain gradation range (a range of gradations a to b). The pipeline image processing unit 12 also generates a template image (D 'image) 2 based on the XY address determined to be template suitability from the D image obtained by binarizing the A image with gradation (a + b) / 2. Generate a sheet. Thereby, even if the gradation of the inspection image changes in the range of gradations a to b, matching with the template image (D 'image) can be appropriately performed, and two template images per block can be used. Since the displacement amount is calculated and the position correction is performed, the position correction can be performed with higher accuracy than in the first embodiment.

[2.3. Operation of sheet inspection process]
Next, a sheet inspection process by the pipeline image processing unit 12 will be described with reference to FIG. FIG. 18 is a flowchart showing an example of the sheet inspection process. The sheet inspection process is a 100% inspection that compares the reference image and the inspection image.

  First, the pipeline image processing unit 12 performs sheet / sheet shift amount calculation processing (step S231). The sheet / sheet shift amount calculation process will be described later.

  Next, the pipeline image processing unit 12 performs the same process as steps S32 to S34 of the continuous sheet inspection process (see FIG. 14), and ends the sheet inspection process.

[2.4. Operation of sheet / sheet and shift amount calculation processing]
Next, sheet / sheet shift amount calculation processing by the pipeline image processing unit 12 will be described using FIG.

  The process at the beginning of the sheet / sheet shift amount calculation process is the same as steps S51 to S56 of the continuous sheet / displacement amount calculation process (see FIG. 15).

  Next, the pipeline image processing unit 12 performs block processing with a sheet / template (step S251). The sheet / template / block processing will be described later.

  Next, the pipeline image processing unit 12 performs the same process as step S58 to step S60 of the continuous sheet / displacement amount calculation process (see FIG. 15), and ends the sheet / displacement amount calculation process.

[2.5. Operation of block processing with sheet and template]
Next, block processing with a sheet / template with the pipeline image processing unit 12 will be described with reference to FIG.

  First, the pipeline image processing unit 12 selects one block determined as a “template present block” in the process of step S205 of the sheet template image creation process (step S301).

  Next, the pipeline image processing unit 12 acquires two sets of a template image (D ′ image) and a center address included in the block selected in the process of step S301 from the template table (step S302).

  Next, the pipelined image processing unit 12 sets a preset range (a range of ± 64 pixels in the X direction, a range of ± 128 pixels in the Y direction) based on the first set of center addresses acquired in the process of step S302. The first set of D 'images is shifted by one pixel with respect to the D image, and the difference between the D and D' images is calculated (step S303).

  Next, the pipeline image processing unit 12 specifies the position at which the difference is the smallest (step S304). Note that if there are a plurality of positions with the smallest difference and the same value, one position closest to the center address is identified.

  Next, the pipelined image processing unit 12 sets a preset range (a range of ± 64 pixels in the X direction, a range of ± 128 pixels in the Y direction) based on the second set of center addresses acquired in the process of step S302. The second set of D 'images is shifted by one pixel with respect to the D image, and the difference between the D and D' images is calculated (step S305).

  Next, the pipeline image processing unit 12 specifies the position at which the difference is the smallest (step S306). Note that if there are a plurality of positions with the smallest difference and the same value, one position closest to the center address is identified.

  Next, the pipeline image processing unit 12 calculates the amount of deviation for each of the two template images (D 'images) (step S307). Specifically, the difference between the position specified in the process of step S304 and the first set of center addresses acquired in the process of step S302 is calculated as the first shift amount (dx1, dy1), and the process of step S306 is performed. The difference between the position identified in step S2 and the second set of center addresses acquired in the process of step S302 is calculated as a second deviation amount (dx2, dy2).

  Next, the pipelined image processing unit 12 determines the average value of the two shift amounts calculated in the process of step S307 as the shift amount (dx, dy) of the block (step S308). The determined amount of displacement is stored in association with identification information (for example, block ID) of the block.

  Next, the pipelined image processing unit 12 determines whether or not all “blocks with template” have been selected (step S309). At this time, if the pipeline image processing unit 12 determines that not all “blocks with template” have been selected (step S309: NO), the process proceeds to step S301, and the process has been selected so far. Select one non-template block. Then, the processing of steps S301 to S309 is repeated until all “template present blocks” are selected. On the other hand, if the pipeline image processing unit 12 determines that all the "blocks with template" have been selected (step S309: YES), the block processing with sheet and template ends, and the sheet and slippage are shifted. It returns to quantity calculation processing.

  As described above, the inspection apparatus T (an example of the “feature image generation apparatus”) according to the first and second embodiments includes the pipeline image processing unit 12 (“edge extraction unit”, “binarization unit”) , An example of an edge image extracted from the reference image by the “first combining unit”, the “intersection obtaining unit”, the “second combining unit”, the “cut-out image generating unit”, and the “feature image generating unit”; C image (an example of “first binarized image”) obtained by generating “an edge image” and binarizing the A image with gradation b (an example of “first gradation”), and an edge image Of a B image (an example of a “second binarized image”) binarized with a gradation a (an example of a “second gradation”) lower than the gradation b C1 image (“first water” generated by generating a D image (an example of “third binarized image”) binarized with an intermediate gradation of tone b and extracting a horizontal straight line from the C image Image) and a C2 image (an example of a "first vertical image") obtained by extracting a vertical straight line from the C image, to generate a C3 image (an example of a "first composite image"), and a C3 image B1 image (an example of "second horizontal image") obtained by acquiring the XY addresses (an example of "intersection coordinates") of the horizontal straight line and the vertical straight line in the image B and the horizontal straight line extracted from the B image The B2 image (an example of the "second vertical image") from which the straight line is extracted is synthesized, the B3 image (an example of the "second synthesized image") is generated, and the image including the XY address is cut out from the C3 image and the B3 image To generate the C 'image (an example of the "first cutout image") and the B' image (an example of the "second cutout image"), and the difference pixel number between the C 'image and the B' image is 1 pixel to 8 In the case of being within the range of pixels (in the case of satisfying a predetermined condition) To generate a template image cut out an image including an XY address from D images (D 'image. An example of the "feature image").

  Therefore, according to the inspection apparatus T, the image A obtained by extracting the edge from the reference image, the image C ′ obtained from the image obtained by binarizing with the tone b, and the image obtained by binarizing the edge image with the tone a The same position from the D image obtained by binarizing the A image at a middle gradation between the gradation a and the gradation b when the number of difference pixels of the B ′ image obtained from is within the range of 1 pixel to 8 pixels. Of the edge image of the comparison image to be compared with the reference image if the gradation is between the gradation b and the gradation a, the positions of the reference image and the inspection image It can be done. That is, a template image (D 'image) used for matching for aligning the high-resolution reference image and the inspection image can be appropriately generated from the reference image.

  As described above, since the template image (D ′ image) is generated based on the edge detected in both the image (B image and C image) binarized with the gradation a and the gradation b, the inspection image Even if there is a change such as a decrease in the entire gradation in the printing process, the edge on which the template image is generated is detected when the gradation changes within the range of gradation a to b. Position correction can be performed because this becomes possible. That is, it is ensured that the alignment is properly performed even if there is a tone change of the edge portion within the range of the tones a to b. If a template image is generated based on an edge detected in an image binarized with one gradation, it is unclear in which gradation range the relevant edge can be detected, and the printing process does not If the gray level changes to an undetectable gray level, alignment can not be performed suddenly and the inspection must be stopped.

  The pipeline image processing unit 12 of the inspection apparatus T generates an A image in which the edge is extracted from the reference image, and the C image obtained by binarizing the A image with gradation b and the edge image more than gradation b A B image binarized with low gradation a and a D image binarized with gradation between gradation a and gradation b are generated, and the horizontal straight line and vertical in the C image are generated. Acquire the XY address (an example of “intersection coordinates”) of a straight line, cut out an image including the XY address from the C image and the B image, and respectively obtain a C ′ image (an example of “first cut image”) and a B ′ image An example of the “second cut-out image” is generated, and the difference pixel number between the C ′ image and the B ′ image is in the range of 1 pixel to 8 pixels (an example of “when the predetermined condition is satisfied”) Template image (D 'image) which cut out the image containing XY address from D image. It may be generated an example) of a feature image. "

  Further, in the inspection apparatus T according to the first and second embodiments, the pipeline image processing unit 12 (an example of the “division unit”) divides the reference image into a plurality of blocks, and the template image (D ′ image) Generate). As a result, the shift amount can be calculated for each block for the reference image and the inspection image, and alignment can be performed for each block.

  Furthermore, in the inspection apparatus T according to the first embodiment, the pipeline image processing unit 12 is an image obtained by capturing a part of the continuous sheet while the reference image transports the continuous sheet in the longitudinal direction. Then, one template image (D 'image) is generated for one block.

  Furthermore, in the inspection apparatus T according to the second embodiment, when the pipeline image processing unit 12 is an image obtained by capturing a sheet of paper (an example of a “cut sheet”), one block is processed for one block. Generate two template images (D 'images). When imaging a sheet after printing, the sheet is irregularly displaced in the longitudinal direction, the lateral direction, and the rotational direction, but according to the inspection apparatus T of the second embodiment, two template images per block are used. Since the shift amount is calculated, alignment can be performed with high accuracy.

  Furthermore, in the inspection apparatus T according to the first embodiment and the second embodiment, the pipeline image processing unit 12 (an example of the “determination unit”) generates a template verification range (“verification area” based on the XY address in the D image. The template image (D 'image) is inappropriate if the template image (D' image) is compared with the D image while moving the template image (D 'image) and matches at a position other than the XY address 'Image'. Thereby, an image without a pattern (feature) similar to its surroundings (within the template verification range) can be adopted as a template image (D 'image).

  In addition, when performing image comparison processing for various purposes as well as image comparison processing performed for inspection of printed matter, comparison is appropriately performed because one of the images is distorted, stretched, shrunk, or the like. When it is not possible, the shift amount calculation process of the present invention can be used to align the two images.

  In the first embodiment and the second embodiment, a template image (D ′ image) is generated based on an image (D image) binarized by the middle gradation ((a + b) / 2) of the gradation a and the gradation b in the first embodiment and the second embodiment. However, the template image may not necessarily be generated based on the image binarized at the middle gradation. The image from which the template image is cut out (D image) may be an image binarized with gradations shifted to a higher or lower than the middle gradation, and it is assumed that the gradation of the image to be inspected is lowered in the printing process As long as it is possible, it may be an image binarized with a higher tone than the middle.

T inspection apparatus 11 system controller 12 pipeline image processing unit 13 parallel image processing unit 14 front camera branch board 15 back camera branch board 16 encoder branch board 17 HUB
31A front camera 31B back camera 32A front lighting 32B back lighting 33 encoder S web offset printing press U1-U4 printing unit U5 dryer U6 folding machine

Claims (10)

An edge extraction unit that generates an edge image in which an edge is extracted from a reference image;
A first binarized image obtained by binarizing the edge image with a first tone, and a second binarized image obtained by binarizing the edge image with a second tone lower than the first tone A binarization unit configured to generate an image and a third binarized image obtained by binarizing the edge image at a third gradation between the first gradation and the second gradation;
An intersection acquiring unit that acquires intersection coordinates of a horizontal straight line and a vertical straight line in the first binarized image;
A cutout image generation unit that cuts out an image including the intersection coordinates from the first binarized image and the second binarized image, and generates a first cutout image and a second cutout image, respectively.
A feature image generation unit that generates a feature image obtained by cutting out an image including the intersection coordinates from the third binarized image, when the difference pixel number between the first cutout image and the second cutout image satisfies a predetermined condition; ,
A feature image generating apparatus comprising: The feature image generation apparatus according to claim 1, wherein
A first horizontal image in which a horizontal straight line is extracted from the first binarized image and a first vertical image in which a vertical straight line is extracted from the first binarized image to generate a first combined image; 1 synthesis unit,
A second horizontal image obtained by extracting a horizontal straight line from the second binarized image and a second vertical image obtained by extracting a vertical straight line from the second binarized image to generate a second composite image 2 synthesis unit,
And further
The intersection acquisition unit
Acquiring the intersection coordinates based on the first composite image generated from the first binarized image;
The cutout image generation unit
Generating the first clipped image and the second clipped image from the first composite image generated from the first binarized image and the second composite image generated from the second binarized image A feature image generating apparatus characterized in that. The feature image generation apparatus according to claim 2,
The first combining unit extracts a horizontal straight line from the first binarized image, and extracts a vertical straight line from the first horizontal image expanded in the horizontal direction and the first binarized image. Combining the first vertically magnified image in the vertical direction to generate the first combined image;
The second combining unit extracts a horizontal straight line from the second binarized image, and extracts a vertical straight line from the second horizontal image expanded in the horizontal direction and the second binarized image. A feature image generating apparatus, comprising: synthesizing the second vertical image enlarged in the vertical direction; and generating the second combined image. The feature image generation apparatus according to any one of claims 1 to 3, wherein
The image processing apparatus further comprises a division unit that divides the reference image into a plurality of blocks,
The intersection acquisition unit acquires intersection coordinates for each of the blocks.
The cutout image generation unit generates the first cutout image and the second cutout image for each of the blocks,
The feature image generating device is characterized in that the feature image is generated for each of the blocks. The feature image generation apparatus according to claim 4, wherein
When the reference image is an image obtained by capturing a part of the continuous sheet while conveying the continuous sheet along the longitudinal direction, one feature image is generated for one block. Feature image generation device to be. The feature image generation apparatus according to claim 4, wherein
A feature image generating apparatus characterized by generating two feature images for one of the blocks when the reference image is an image obtained by photographing a cut sheet obtained by cutting a continuous sheet into individual sheets. The feature image generation apparatus according to any one of claims 1 to 6, wherein
The inside of the verification area on the basis of the intersection coordinates in the third binarized image is compared with the third binarized image while moving the feature image, and in the case where they match other than the intersection coordinates, the characteristic image A feature image generation apparatus, further comprising a determination unit that determines that the image is an inappropriate feature image. The inspection apparatus which performs position correction of a to-be-inspected image using the said characteristic image which the characteristic image generation apparatus as described in any one of Claims 1 thru | or 7 produced, and compares and checks the said reference image and the said to-be-tested image And
A shift amount calculation unit that specifies coordinates corresponding to the feature image in the inspection image, and calculates a shift amount that is a difference from the intersection coordinates acquired by the intersection acquisition unit;
A position correction unit that corrects the position of the inspection image based on the displacement amount;
A comparison unit that compares the inspection image subjected to the position correction with the reference image;
An inspection apparatus comprising: An edge extraction step of generating an edge image obtained by extracting an edge from a reference image;
A first binarized image obtained by binarizing the edge image with a first tone, and a second binarized image obtained by binarizing the edge image with a second tone lower than the first tone A binarization step of generating an image and a third binarized image in which the edge image is binarized at a third gradation between the first gradation and the second gradation;
An intersection point acquiring step of acquiring an intersection coordinate of a horizontal straight line and a vertical straight line in the first binarized image;
A cutout image generating step of cutting out an image including the intersection coordinates from the first binarized image and the second binarized image, and generating a first cutout image and a second cutout image, respectively;
A feature image generating step of generating a feature image obtained by cutting out an image including the intersection coordinates from the third binarized image, when the number of difference pixels of the first cutout image and the second cutout image satisfies a predetermined condition; ,
A method of generating a feature image comprising: Computer,
An edge extraction unit that generates an edge image obtained by extracting an edge from a reference image;
A first binarized image obtained by binarizing the edge image with a first tone, and a second binarized image obtained by binarizing the edge image with a second tone lower than the first tone A binarization unit for generating an image and a third binarized image in which the edge image is binarized at a third gradation between the first gradation and the second gradation,
An intersection acquiring unit for acquiring intersection coordinates of a horizontal straight line and a vertical straight line in the first binarized image;
A cutout image generation unit that cuts out an image including the intersection coordinates from the first binary image and the second binary image, and generates a first cutout image and a second cutout image, respectively.
A feature image generation unit that generates a feature image in which an image including the intersection coordinates is cut out from the third binarized image, when the difference pixel number between the first cut-out image and the second cut-out image satisfies a predetermined condition;
A feature image generation program characterized by functioning as