JP2007017214A - Inspection device and inspection method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an inspection device or the like capable of improving the inspection accuracy and responding to an inspected object of various printing forms. <P>SOLUTION: A plurality of patterns including reversed patterns are arranged on the inspected object (printed matter or the like). The inspection device 1 specifies a reference region image (a) including the patterns, and extracts similar region images (b) having high correlation to the reference region image (a). The inspection device 1 extracts the sum of differences between the reference region image (a) and similar region images (b) and circumscription difference of a region frame, and produces a mask. The mask section is removed from the reference region image (a), and a reference region image (am) is formed. The inspection device 1 extracts similar region images (bm) having high correlation to the reference region image (am). The inspection device 1 extracts a defect (dirt or chip) from the differences between the reference region image (am) and similar region images (bm). The inspection device 1 precisely inspects the defect of the inspected object having tightly arranged patterns (including rotated patterns). <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an inspection apparatus, an inspection method, and the like for detecting defects (such as chipped defects, stain defects, blurring, and color tone defects) of printed materials. More specifically, the present invention relates to an inspection apparatus, an inspection method, and the like for detecting a defect such as a printed matter in which a plurality of identical patterns are arranged.

  Conventionally, the inspection for determining the quality of a printed material is performed by dividing an inspection object image obtained by inputting an image of a printed material with the same pattern or the same page as the inspection object into multiple regions to generate a plurality of region images. Then, the defect is detected by subtracting the region images having the maximum correlation coefficient in each region image (see, for example, [Patent Document 1]).

JP 2003-123056 A

  However, the printed matter with the same design and the same page in multiple faces has a large number of designs arranged so as not to waste material. The design is reversed and the designs are closely related to each other. There is a print to be placed.

  In the conventional inspection method, since the pattern to be the inspection standard is specified in a rectangular area, other patterns are included in the specified rectangular area, and different patterns are subjected to image processing such as normalized correlation (pattern matching). It is difficult to search, and the difference calculation is performed in a state where the position is shifted, which is a cause of deterioration in detection accuracy.

  For example, in the conventional inspection method, as shown in FIG. 13, the reference area image c73 of the printed material and the similar area images d75-1 to 75-5 to be inspected are arranged so as to be separated by rectangular areas. It was. If another image enters the rectangular area when it is divided into rectangular areas, it is difficult to search for similar area images by increasing the correlation accuracy with the reference image, and the quality of the printed material to be inspected is high. It was difficult to judge. Therefore, the conventional inspection method has a problem that, for example, it is not possible to deal with printed matter arranged in close contact with a mixture of, for example, a 180 ° inverted pattern.

  The present invention has been made in view of the above problems, and aims to provide an inspection apparatus and the like that can improve inspection accuracy and can cope with inspection objects of various printing forms. .

  In order to achieve the above-described object, the first invention is an inspection apparatus that performs image processing on an inspection image obtained by imaging an inspection object in which a plurality of identical arrangement units are arranged, and inspects the quality. A designation means for designating a first reference area image including a reference arrangement unit, and at least one first similar area image satisfying a predetermined standard in the inspection image, the degree of similarity with the first reference area image. A first extracting means for extracting, and a mask creating means for creating a mask area from a difference between the first reference area image and each of the first similar area images, and in the inspection of the area including the arrangement unit, An inspection apparatus is characterized by excluding a mask region from inspection.

The inspection apparatus irradiates the inspection object with light, captures reflected light from the inspection object, acquires an inspection image, performs image processing on the inspection image, and determines whether the inspection object is good or bad.
The inspection object is, for example, a printed material. An inspection object can also be applied to a printing paper with a sticking material (such as a seal), a coating material (such as printing), or a vapor deposition material.
An arrangement unit indicates one unit such as a symbol or a character string. It is assumed that the same arrangement unit (design etc.) is arranged on the inspection object (printed article etc.) according to a predetermined rule. For example, in order to arrange as many arrangement units as possible, arrangement units obtained by reversing or rotating the arrangement units (such as 180 ° rotation) may be mixed and arranged closely.

The first reference area image is an image of an area including a reference arrangement unit (design). The first reference area image is set as a rectangular area, for example.
The similarity is an index indicating the similarity between image regions. For example, a correlation coefficient or the like is used as the similarity.
The similarity satisfying a predetermined standard means that the correlation coefficient satisfies a standard such as a maximum, 60% or more, 80% or more.
The first similar region image is a region where the correlation coefficient with the first reference region image is a predetermined value (correlation coefficient is maximal, 60% or more, 80% or more).

  The difference is calculated through difference processing, binarization processing, and the like based on pixel values (density values) of corresponding pixels between image regions. The pixel value (density value) is a value that is set to be larger as it is brighter. For example, in the RGB color system, the pixel value of the darkest place (black, etc.) is set as (0, 0, 0), and the pixel value of the brightest place (white, etc.) is set as (255, 255, 255).

The inspection apparatus performs, for example, a difference calculation for each of the corresponding pixels for each of the R component, the G component, and the B component, and sets the maximum value among the R component, the G component, and the B component of the difference pixel value. A binarization process is performed on the difference value, and a binary difference value as a difference is calculated.
The difference calculation is performed in the saturation mode, and when the difference calculation result is negative (minus), the value is set to “0” (0 clip).
The mask area is an area for excluding an area that does not include an arrangement unit (such as a symbol). By excluding the mask area from the inspection target, it is possible to set a large correlation coefficient when extracting the arrangement unit and improve the extraction accuracy.

  In the inspection apparatus according to the first aspect, when the first reference area image including the reference arrangement unit is designated, at least one first similarity in which the similarity with the first reference area image satisfies a predetermined reference in the inspection image A region image is extracted, and a mask region is created from the difference between the first reference region image and each first similar region image. Further, in the inspection of the area including the arrangement unit, the mask area is excluded from the inspection.

Regarding mask creation, the sum of differences circumscribing the area frame may be used as the mask area.
That is, by removing the difference that does not circumscribe the area frame, it is possible to obtain a highly accurate mask area from which the influence of the defect (such as chipping or dirt) of the inspection object is removed.
In addition, a mask region may be created by performing region expansion processing (expansion processing or the like).
That is, by expanding the mask area, it is possible to absorb a positional deviation or the like when extracting the arrangement unit (symbol or the like) as a similar area image.

Even when a part of another arrangement unit enters a rectangular area including the arrangement unit, the inspection accuracy can be maintained by excluding the mask area from the inspection.
That is, inspection accuracy can be maintained even when a plurality of arrangement units are arranged close to each other by being rotated or inverted in the same direction or at a predetermined angle.
The predetermined angle is, for example, 180 °, 90 °, or the like. By arranging the arrangement angles of a plurality of arrangement units on the inspection object, the arrangement density of the inspection object can be increased.

  A second extraction unit configured to extract at least one second similar region image satisfying a predetermined standard in the inspection image with a second reference region image obtained by removing the mask region from the first reference region image; The quality of the inspection object is determined by comparing the second reference area image and the second similar area image.

  The second reference area image is an area obtained by excluding the mask area from the first reference area image. The inspection apparatus extracts, as the second similar region image, a region in which the similarity with the second reference region image satisfies a predetermined criterion. The predetermined reference can be set larger than when the first reference area image is used (for example, the reference correlation coefficient value is set larger than when the first reference area image is used). Therefore, it is possible to extract the second similar region image with high accuracy.

Regarding the determination of pass / fail of the inspection object, the inspection apparatus performs a difference process from the second reference region image to the second similar region image, binarizes with a predetermined threshold value, and sets a region exceeding a predetermined number of pixels as a contamination defect. judge.
Further, the inspection apparatus performs a difference process of the second reference area image from the second similar area image, binarizes with a predetermined threshold value, and determines an area exceeding a predetermined number of pixels as a defective defect.
In other words, the inspection apparatus compares the pixels of the second similar region image with the pixels of the corresponding second reference region image, and the density value (binarized difference value) is lower (darker) than the second reference region image. Is determined as a stain defect of the inspection object, and a pixel having a density value (binarized difference value) higher (brighter) than the second reference region image is determined as a defect defect of the inspection object.
Note that by binarizing the pixel difference with a predetermined threshold, extra information is filtered to emphasize the features.

  According to the inspection apparatus of the first invention, the mask area is created from the difference between the first reference area image and the first similar area image, and the inspection is performed by excluding the mask area. Even if it is a case where the inspection object is arranged in the same direction or rotated at a predetermined angle or reversed, the quality determination inspection can be performed with high accuracy.

The second invention is an inspection method for inspecting pass / fail by performing image processing on an inspection image acquired by imaging an inspection object in which a plurality of the same arrangement units are arranged, and includes a reference arrangement unit A designation step of designating a first reference region image; and a first extraction step of extracting at least one first similar region image satisfying a predetermined standard in the inspection image with a similarity to the first reference region image; A mask creating step of creating a mask area from the difference between the first reference area image and each first similar area image, and inspecting the mask area from the inspection in the area including the arrangement unit Is the method.
2nd invention is invention regarding the inspection method which the inspection apparatus of 1st invention performs.

  ADVANTAGE OF THE INVENTION According to this invention, the test | inspection apparatus etc. which can improve a test | inspection precision and can respond | correspond to the test object of various printing forms can be provided.

  DESCRIPTION OF EMBODIMENTS Hereinafter, preferred embodiments of an inspection apparatus and the like according to embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the accompanying drawings, the same reference numerals are given to components having substantially the same functional configuration, and redundant description will be omitted.

(1. Configuration of the inspection apparatus 1)
First, the configuration of the inspection apparatus 1 according to the embodiment of the present invention will be described with reference to FIG.
FIG. 1 is a schematic configuration diagram of an inspection apparatus 1.

  The inspection apparatus 1 includes a line camera 3, an illuminator 5, an image processing unit 9, a display unit 11, an image storage unit 13, an operation unit 15, and the like. The line camera 3, the illuminator 5, the image processing unit 9, the display unit 11, the image storage unit 13, the operation unit 15, and the like are connected to each other via a connection line such as a bus or a cable.

  The inspection apparatus 1 performs image processing such as comparison processing on the basis of the reference region image 26 and the similar region image 28 (see FIG. 2 and the like), determines pass / fail of the printed matter 7 to be inspected, and displays the inspection result on the display unit 11. To display.

  The reference area image 26 is an area image serving as a reference for a non-defective product among the image data obtained by imaging the printed matter 7 to be inspected. The reference area image 26 may be specified by the operator, or the inspection apparatus 1 may automatically specify the range. The reference area image 26 may be obtained from digital data for printing plate output.

  The similar region image 28 is a region image having a high correlation with the reference region image 26 among the image data obtained by imaging the printed matter 7 to be inspected. Note that “high correlation” is synonymous with “high image similarity”.

  The inspection apparatus 1 can acquire image data of the printed matter 7 by imaging with the line camera 3. The inspection apparatus 1 images the printed matter 7 with the line camera 3 while conveying the printed matter 7 in the direction of movement 17.

  The line camera 3 is a device that images the printed matter 7. The line camera 3 is a camera (imaging device) including, for example, an optical sensor such as a CCD (Charge Coupled Device) in which light receiving elements (pixels) are arranged one-dimensionally, a drive circuit, an imaging optical system, and the like.

  The illuminator 5 is a light source that irradiates the printed material 7 with light. The illuminator 5 is, for example, an illuminator in which a plurality of LEDs are arranged in a planar shape. Further, a fluorescent lamp or the like can be used as the illuminator 5.

The image processing unit 9 performs image processing on the image data of the printed matter 7 and detects defects such as chipping and dirt. The image processing unit 9 can be configured by, for example, a computer and a program that causes the computer to operate as the image processing unit 9 of the inspection apparatus 1.
The configuration and operation of the image processing unit 9 will be described later.

The display unit 11 displays a defect detection result or the like in the image processing unit 9. The display unit 11 is, for example, a CRT (Cathode Ray Tube) or an LCD (Liquid Crystal Display).
The image storage unit 13 is a device that stores image data and the like. The image storage unit 13 is, for example, a hard disk or a storage medium drive.
The operation unit 15 is a device that receives an operation instruction from an operator. The operation unit 15 is a pointing device such as a keyboard and a mouse, for example.

(2. Hardware configuration of image processing unit 9)
Next, the hardware configuration of the image processing unit 9 will be described with reference to FIG.
FIG. 2 is a diagram illustrating a hardware configuration of the image processing unit 9.

The image processing unit 9 shown in FIG. 2 is configured by connecting a CPU 21, a memory 23, and the like to each other via a system bus (not shown).
The image processing unit 9 is connected to the line camera 3 via a network interface (not shown) or the like, and is connected to the display unit 11 via a video adapter (not shown) or the like.
Note that the hardware configuration in FIG. 2 is an example, and various configurations can be adopted depending on the application and purpose.

  A CPU 21 (Central Processing Unit) stores a storage device, a ROM (Read Only Memory), an execution program stored in a recording medium, an OS (operation system) program, an application program, and the like in a work memory on a RAM (Random Access Memory). Called and executed in the area, performs arithmetic processing (four arithmetic operations, comparison operations, etc.), operation control of hardware and software, and implements various functions (see FIG. 3 and the like) described later.

  The memory 23 is a storage device such as a RAM or a ROM. The RAM includes a reference area image memory 25, a similar area image memory 27, a display memory 29, a printed matter imaging memory (not shown) for storing imaging data of the printed matter 7 by the line camera 3, and a work memory for executing a processing program (not shown). No.) etc. are assigned.

  Note that the reference area image memory 25 and the similar area image memory 27 may be combined to be considered as a printed matter imaging memory, and first, the imaging data of the printed matter 7 by the line camera 3 may be stored in a predetermined area of the printed matter imaging memory. . In accordance with the processing steps of the inspection apparatus 1 according to the present embodiment, the reference area image 26 serving as a reference for non-defective products among the image data obtained by imaging the printed matter 7 to be inspected is stored in the reference area image memory 25. A similar area image 28 having a high correlation with the reference area image 26 may be stored in the similar area image memory 27.

The display memory 29 is a memory that holds display data to be displayed on the display unit 11, and holds, for example, image data indicating inspection results and defective portions.
The reference area image memory 25, the similar area image memory 27, the display memory 29, the printed matter imaging memory, and the like may be provided independently in the image processing unit 9, or areas may be appropriately allocated on the RAM. Also good.

When the image data of the printed material 7 acquired by the line camera 3 is input to the image processing unit 9, the image processing unit 9 stores the image data in the memory 23 (printed material imaging memory or the like).
The CPU 21 extracts the reference area image 26 and the similar area image 28 from the imaging data, determines pass / fail in the printed matter 7 to be inspected based on the reference area image 26 and the similar area image 28, and displays the inspection result in the display memory 29. Output to.
The contents of the display memory 29 are input to the display unit 11 and displayed.

(3. Processing steps of the inspection apparatus 1 of the present embodiment)
Next, a processing procedure of the inspection apparatus 1 according to the present embodiment will be described with reference to FIGS.
FIG. 3 is a flowchart showing an inspection processing procedure of the inspection apparatus 1 according to the present embodiment.
This inspection process is executed by the CPU 21 of the image processing unit 9 by calling a predetermined program or the like stored in the ROM or the like of the memory 23 to the work memory area on the RAM. By executing this processing, the CPU 21 functions as a (reference region image) designation unit, first and second (similar region image) extraction unit, mask generation unit, defect determination unit, and the like of the present invention.

(3-1. Mask creation process)
With reference to FIG. 3 (Step 1001 to Step 1007) and FIGS. 4 to 9, the mask creation process executed by the inspection apparatus 1 will be described.
FIG. 4 is a diagram illustrating extraction of the similar region image b35.
FIG. 5 is a diagram showing the extraction of the similar region image b35 inverted by 180 °.
FIG. 6 is a diagram showing the reference area image a33 and the extracted similar area image b35.
FIG. 7 is a diagram illustrating a difference between the reference area image a33 and the similar area image b35.

  First, it is assumed that the operator images the printed matter 7 with the line camera 3, and the imaging data is sent to the image processing unit 9 of the inspection apparatus 1 and stored in the memory 23. The imaging data is stored as, for example, printed material image data 31 shown in FIG.

  In the printed matter 7 (printed matter image data 31), not only the basic symbols have the same orientation, but also the symbols reversed by 180 ° are mixed, and the symbols are arranged closely. Therefore, in this embodiment, the operator extracts a reference area image a33 (FIG. 4) and a reference area image am55 (FIG. 10), which will be described later, in two directions of 0 ° and 180 ° (upside down direction) when extracting similar images. Set in advance to use.

  Printed image data 31 shown in FIG. 4 is displayed on the display unit 11, and the operator designates a rectangular reference area image a33 as a reference area image (step 1001). Alternatively, the CPU 21 may automatically specify the reference area image a33. According to the present embodiment, since the patterns are closely arranged, a part of the adjacent pattern is included in the upper right of the reference area image a33 shown in FIG. The inspection process in the case of can not be performed as it is. If the inspection process of the conventional example is performed, there is a possibility that the inspection accuracy is significantly lowered.

  Next, the inspection apparatus 1 extracts a similar image having a high correlation with the reference region image a33 from the printed material image data 31 as a similar region image b35. Since the inspection apparatus 1 includes a part of an adjacent symbol in the upper right of the reference area image a33, the similar area image b35 is extracted with, for example, a loose correlation with a correlation coefficient of about 60%, for example, FIG. Similar region images b35-1 to 35-5 are obtained as shown in FIG.

  Note that in the method for extracting an image with high correlation, the CPU 21 calculates a correlation coefficient with the reference area image a33 by moving the position of a predetermined area pixel by pixel, and obtains the area obtained as the maximum value of the correlation coefficient. Extracted as a similar region image b35. The similar area images b35 are extracted so that the areas do not overlap each other.

  Next, the inspection apparatus 1 inverts the reference region image a33 by 180 ° in accordance with the preset setting, and extracts a similar image from the printed image data 31 again. For example, as shown in FIG. 5, the similar region image b35-6 is extracted. To 35-8 are obtained (step 1002).

  For example, the similar area image b35-3 shown in FIGS. 4 and 5 will be described as having a smudge image 37 and the similar area image b35-4 having a missing image 39.

  In step 1002, the inspection apparatus 1 creates a reference area image a <b> 33 and similar area images b <b> 35-1 to 35-8 shown in FIG. 6 and stores them in the memory 23. In the inspection apparatus 1, for example, the reference area image a33 is stored in the reference area image memory 25, and the similar area images b35-1 to 35-8 are stored in the similar area image memory 27 (see FIG. 2).

  Next, the inspection apparatus 1 performs a difference calculation between the reference area image a33 and the similar area images b35-1 to 35-8 (step 1003). That is, a difference result obtained by subtracting the similar area image b35 from the reference area image a33 and a difference result obtained by subtracting the reference area image a33 from the similar area image b35 are calculated. Therefore, in the present embodiment, a total of 16 difference calculations are performed, 8 ways + 8 ways.

Next, the inspection apparatus 1 binarizes the difference calculation value in Step 1003 using a predetermined threshold, filters excess information, and emphasizes features (Step 1004). The size of the threshold used for the binarization process is set to a predetermined value in consideration of various conditions such as the characteristics of the inspection target.
In the present embodiment, the inspection apparatus 1 sets the binarized difference value of a pixel having a difference calculation result (difference value) larger than the threshold value to “255” (white in gray scale), and the difference calculation result (difference value) than the threshold value. A difference 41 is created by setting the binarized difference value of a pixel having a small value to “0” (black in gray scale) (see FIG. 7).

Specifically, the difference calculation is performed for each of the R component, the G component, and the B component for all corresponding pixels of the reference region image a33 and the similar region image b35, and the R component, the G component, and the B component of the difference pixel value are performed. The maximum value among the components is set as a difference value of each pixel, and a binarized difference value is calculated for each pixel through binarization processing.
The difference calculation is performed in the saturation mode, and when the difference calculation result is negative (minus), the value is set to “0” (0 clip).

  For example, the pixel value of a pixel in the reference region image a33 is (R component, G component, B component) = (20, 100, 155), and the pixel value of the corresponding pixel in the similar region image b35 is (R Component, G component, B component) = (60, 20, 100). The difference pixel value of (reference area image a33) − (similar area image b35) in the pixel is (−40, 80, 55). Further, the difference value in the pixel is “80”, which is the maximum value in each component of the difference pixel value. When the threshold value of the binarization process is “50” and binarization is performed to “0” or “255”, the binarization difference value in the pixel is “255”.

  FIG. 7 shows differences 41-1 to 41-5 output as differences after binarizing the difference calculation results of the reference area image a33 and the similar area images b35-1 to 35-8. In FIG. 7, an area where the binarized difference value is “255” (an area where the difference is large) is indicated by “white (blank portion)”, and an area where the binarized difference value is “0” (an area where the difference is small). Is indicated by “black (hatched portion)”.

  The difference 41-1 indicates that the binarized difference values of all the pixels are “0”. Since the difference calculation is performed in the saturation mode, when the difference value (the maximum value of the RGB components of the difference pixel value) is negative, the difference value and the binarized difference value are “0”.

Difference 41-1 is
(Reference area image a33)-(similar area image b35-1),
(Reference area image a33)-(similar area image b35-2),
(Similar area image b35-1)-(reference area image a33),
(Similar area image b35-2)-(reference area image a33),
(Similar area image b35-6)-(reference area image a33),
(Similar area image b35-7)-(reference area image a33),
(Similar area image b35-8)-(reference area image a33),
Is extracted as the difference calculation result.

The difference 41-2 is
(Reference area image a33)-(similar area image b35-4),
(Reference area image a33)-(similar area image b35-5),
(Reference area image a33)-(similar area image b35-6),
(Reference area image a33)-(similar area image b35-7),
(Reference area image a33)-(similar area image b35-8),
Is extracted as the difference calculation result.

The difference 41-3 is extracted as a difference calculation result of (reference area image a33) − (similar area image b35-3).
The difference 41-4 is
(Similar area image b35-3)-(reference area image a33),
(Similar area image b35-5)-(reference area image a33),
Is extracted as the difference calculation result.
The difference 41-5 is extracted as a difference calculation result of (similar area image b35-4)-(reference area image a33).

FIG. 8 is a diagram showing a process of creating the mask area 51 from the difference 41. As shown in FIG.
Next, the inspection apparatus 1 performs an OR process on the difference 41 calculated in Step 1003 and Step 1004 (Step 1005). The inspection apparatus 1 calculates the sum of the differences 41-1 to 41-5, and obtains a composite difference 43 shown in FIG. The composite difference 43 shown in FIG. 8 has circumscribed differences 47-1 and 47-2 and non- circumscribed differences 44-1 and 44-2. The circumscribing difference is an area circumscribing the rectangular area frame.

  Next, the inspection apparatus 1 creates a mask by extracting only the circumscribed difference of the rectangular area frame (step 1006). The non- circumscribed differences 44-1 and 44-2 are extracted as the difference between the dirty image 37 and the missing image 39. Therefore, the non- circumscribed differences 44-1 and 44-2 are excluded and updated as the composite difference 45. (See FIG. 8).

  Since the inspection apparatus 1 extracts the similar area image b35 by loosening the correlation coefficient with the reference area image a33 in step 1002, there may be a positional shift of the extracted similar area image b35. Therefore, the inspection apparatus 1 expands the portion that becomes the mask area of the composite difference 45 by performing the expansion process, and absorbs the positional deviation of the similar area image b35 (step 1007). In FIG. 8, the inspection apparatus 1 extends the mask areas 47-1 and 47-2 of the composite difference 45 to the mask areas 51-1 and 51-2 and updates the composite difference 49.

FIG. 9 is a view showing the mask 53.
Further, the inspection apparatus 1 performs black and white reversal processing, creates a mask 53 from the composite difference 49, and stores it in the memory 23. When the mask 53 is applied to a predetermined area (AND processing), the mask area located at the upper left and right corners of the area frame of the mask 53 is excluded.

(3-2. Defect detection processing and determination processing)
With reference to FIG. 3 (Step 1008 to Step 1014) and FIGS. 10 to 12, the defect detection processing and determination processing executed by the inspection apparatus 1 will be described.
FIG. 10 is a diagram illustrating extraction of the reference area image am55 and the similar area image bm57 excluding the mask area.
FIG. 11 is a diagram illustrating an operation flow of the inspection apparatus 1 in the defect detection process and the determination process.
In FIG. 11, it is assumed that the similar region image 28 includes a dirt image 37 and a missing image 39 as defects.

  The inspection apparatus 1 puts the mask 53 on the reference area image a33 (AND processing), creates a reference area image am55 (see FIG. 10), which is an image obtained by removing the mask portion, and stores it in the reference area image memory 25 (step). 1008).

  The inspection apparatus 1 extracts the reference area image am55 and a similar image having a high correlation as the similar area image bm57 from the printed material image data 31 again. The inspection apparatus 1 extracts the similar region image bm57 with a correlation coefficient (for example, a correlation coefficient of 90%) higher than the correlation coefficient of 60% when the previous reference area image a33 is used (step 1009).

  Note that in the image extraction method with high correlation, the CPU 21 calculates the correlation coefficient with the reference area image am55 by moving the position in a predetermined area pixel by pixel, and determines the area obtained as the maximum value of the correlation coefficient. Extracted as a similar region image bm57. The similar area images bm57 are extracted so that the areas do not overlap each other.

  The inspection apparatus 1 inverts the reference area image am55 by 180 ° in accordance with the preset setting, and again extracts a similar image from the printed image data 31, and displays the similar area image shown in FIG. 10 together with the extracted image in step 1009. bm57-1 to 57-8 are obtained (step 1010).

  The inspection apparatus 1 stores the similar area images bm57-1 to 57-8 in the similar area image memory 27 of the memory 23 (see FIG. 2).

The inspection apparatus 1 calculates a difference between the reference area image am55 and the similar area images bm57-1 to 57-8 and extracts defect candidates (step 1011 in FIG. 3, step 2001 and step 3001 in FIG. 11). The difference calculation is performed in the saturation mode, and if the difference result is negative (minus), 0 clip is performed.
As a result of subtracting the similar region image bm57 from the reference region image am55, a stain candidate is extracted. For all the corresponding pixels of the reference area image am55 and the similar area image bm57, the similar area image bm57 is subjected to differential processing from the reference area image am55, the RGB components are combined, and MAX processing is performed to extract the stain candidate image 59 (FIG. 11 step 2001).
On the other hand, a missing candidate is extracted based on a difference result obtained by subtracting the reference area image am55 from the similar area image bm57. For all the corresponding pixels of the reference area image am55 and the similar area image bm57, the reference area image am55 is subjected to differential processing from the similar area image bm57, and the RGB components are combined and MAX processing is performed to extract the missing candidate image 61 (FIG. 11 step 3001).

The inspection apparatus 1 binarizes the dirt candidate image 59 and the missing candidate image 61 with a predetermined threshold and extracts defective pixels (step 1012 in FIG. 3, step 2002 and step 3002 in FIG. 11). The inspection apparatus 1 performs a binarization process on the stain candidate image 59 using a predetermined stain threshold value, and extracts a stain failure pixel (step 2002 in FIG. 11). The inspection apparatus 1 performs binarization processing on the missing candidate image 61 using a predetermined missing threshold value, and extracts missing defective pixels (step 3002 in FIG. 11).
By performing binarization processing with a predetermined threshold, all pixel values are set to either the maximum density (density value “255”: white) or the minimum density (density value “0”: black). . Since the binarization process removes excess information, the difference feature (defect) can be emphasized.

The inspection apparatus 1 detects a difference exceeding the predetermined number of defective pixels as a defect (step 1013 in FIG. 3, step 2003 and step 3003 in FIG. 11).
The inspection apparatus 1 detects an area where the number of dirty defective pixels extracted in the process of step 2002 exceeds a predetermined number of dirty pixels as a dirty defect. The inspection apparatus 1 creates a dirt detection image 63 and displays the detected dirt defect as the detection dirt 67 (step 2003).
The inspection apparatus 1 detects an area where the number of defective pixels extracted in the process of step 3002 exceeds a predetermined number of defective pixels as a defective defect. The inspection apparatus 1 creates a chipped detection image 65 and displays the detected chipping defect as a detected chipping 69 (step 3003).
Since an area exceeding the predetermined number of pixels is detected as a stain defect or a chip defect, defect detection accuracy can be adjusted by designating the number of detected pixels.

FIG. 12 is a diagram showing a defect determination display.
The inspection apparatus 1 displays the result on the display unit 11 and ends the process (step 1014 in FIG. 3).
In FIG. 12, the inspection apparatus 1 displays, in the result display image 71, for example, the detected stain 67 detected as a defective stain in “red” and the detected defect 69 detected as a defective defect in “blue”. To do.

(3-3. Overview of operation of inspection apparatus 1)
Through the above process, the inspection apparatus 1 designates a reference region image including a reference pattern or the like from repeated patterns and the like, extracts a similar region image similar to the reference region image, and extracts the reference region image and each of the reference region images. A mask area is created from the difference from the similar area image, the mask area is excluded from the inspection, and an area including each pattern is inspected.
Note that the inspection apparatus 1 regards the mask area as an area that is not to be inspected and does not participate in the calculation of the similarity, extracts a similar area image again, compares the reference area image with the similar area image, Judge the quality. As for mask creation, a mask region is created by performing expansion processing on the sum of differences circumscribing the region frame.

(4. Effect)
As described above, in the embodiment of the present invention, even if the printed matter to be inspected is a printing form in which, for example, the reverse of the orientation of the pattern is mixed and closely arranged, printing failure Can be detected with high accuracy.

As described above, according to the present invention, by specifying a rectangular image as an inspection reference, there is a defect with respect to a printed matter in which the design is reversed (in the shape of a box) or the designs are closely arranged. It becomes possible to detect a defect only in the part to be performed.
Even in a printed matter in which repeated patterns and the like are closely arranged, a defect can be detected with high accuracy, so that yield, printing efficiency, printing cost, and the like can be improved.

  In addition, when setting the reference area image, the operator does not need to specify the area along the outline of the pattern regardless of the pattern, and the area can be specified by a rectangle. There is an effect to reduce the burden.

  Further, by re-creating the optimum reference area image using the mask, the extraction accuracy of the similar area image can be improved.

(5. Other)
In the above-described embodiment, a case has been described in which the quality of a printed matter in which a pattern having a direction of 0 ° and 180 ° is mixed is determined. However, a pattern arranged at another angle (for example, 90 °) is mixed. The present invention can also cope with printed matter. That is, an angle (for example, 90 °) for rotating the reference area image a33 is set in advance, and the reference area image a33 is rotated by a predetermined angle (for example, 90 °) for setting, and arranged on the printed matter. The design can be extracted and the quality can be determined.

In addition, the acquisition of the similar region image or the like has been described as using a line camera, but is not limited thereto, and a scanner device or the like may be used.
Further, the printed image data 31 may be acquired by imaging or scanning with a camera or the like, and is not limited thereto, and when the printing is performed by CTP (Computer To Plate), the reference region image a33 is printed on a printing plate or the like. Digital data for output may be used as image data of the reference area image a33.

  The preferred embodiments of the inspection apparatus and the like according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to such examples. It will be apparent to those skilled in the art that various changes or modifications can be conceived within the scope of the technical idea disclosed in the present application, and these are naturally within the technical scope of the present invention. Understood.

Schematic configuration diagram of the inspection apparatus 1 The figure which shows the hardware constitutions of the image process part 9. Flow chart showing processing steps of inspection device 1 The figure which shows extraction of the similar area image b35 The figure which shows extraction of the similar area image b35 reversed 180 degrees The figure which shows the reference | standard area | region image a33 and the extracted similar area | region image b35. The figure which shows the difference 41 of the reference | standard area | region image a33 and the similar area | region image b35. The figure which shows the creation process of the mask area | region 51 from the difference 41 The figure which shows the mask 53 The figure which shows extraction of the reference | standard area | region image am55 and the similar area | region image bm57 which excluded the mask area | region. The figure which shows the flow of operation | movement of the test | inspection apparatus 1 in a defect detection process and determination process. Diagram showing defect judgment display The figure explaining the conventional reference | standard area | region image c and the similar area | region image d

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... …… Inspection apparatus 3 ......... Line camera 5 ......... Illuminator 7 ......... Printed material 9 ......... Image processing part 11 ......... Display part 13 ......... Image memory | storage part 15 ......... Operation part 17 ……… Moving direction 21 ……… CPU
23 ......... Memory 25 ......... Reference area image memory 26 ......... Reference area image 27 ......... Similar area image memory 28 ......... Similar area image 29 ......... Display memory 31 ......... Printed image data 33 ... ...... Reference area image a
35-1 to 35-8... Similar region image b
37... Dirt image 39... Missing image 41-1 to 41-5... Difference 43, 45, 49... Composite difference 44-1, 44-2. 47-2, 51-1, 51-2... Mask area (circumscribed difference)
53 .... Mask 55 .... Reference area image am
57-1 to 57-8 ..... Similar area image bm
59 .... Dirt candidate image 61 .... Deficient candidate image 63 .... Dust detected image 65 .... Deficient detected image 67 .... Detected stain 69 .... Detected missing 71 .... Result display image.

Claims (12)

An inspection apparatus that performs image processing on an inspection image acquired by imaging an inspection object in which a plurality of identical arrangement units are arranged, and inspects the quality.
Designating means for designating a first reference area image including a reference arrangement unit;
A first extraction unit that extracts at least one first similar region image that satisfies a predetermined criterion in the inspection image and a similarity with the first reference region image;
Mask creating means for creating a mask area from the difference between the first reference area image and each first similar area image;
Comprising
An inspection apparatus that excludes the mask area from inspection in inspection of an area including the arrangement unit.   The inspection apparatus according to claim 1, wherein the mask creating unit sets the sum of the differences circumscribing an area frame as the mask area.   The inspection apparatus according to claim 1, wherein the mask creating unit creates the mask region by performing region expansion processing.   4. The inspection apparatus according to claim 1, wherein the plurality of arrangement units are arranged on the inspection object by being rotated in the same direction or at a predetermined angle, respectively. Second extraction means for extracting at least one second similar region image satisfying a predetermined criterion in the inspection image with a second reference region image obtained by removing the mask region from the first reference region image; ,
A determination means for comparing the second reference area image and the second similar area image to determine the quality of the inspection object;
The inspection apparatus according to any one of claims 1 to 4, further comprising:   The determination means performs a difference process of the second similar area image from the second reference area image, binarizes with a predetermined threshold value, and determines an area exceeding a predetermined number of pixels as a stain defect. The inspection apparatus according to claim 5.   The determination means performs a difference process on the second reference area image from the second similar area image, binarizes with a predetermined threshold value, and determines an area exceeding a predetermined number of pixels as a defective defect. The inspection apparatus according to claim 5 or 6. An inspection method for inspecting pass / fail by performing image processing on an inspection image acquired by imaging an inspection object in which a plurality of identical arrangement units are arranged,
A designation step for designating a first reference area image including a reference arrangement unit;
A first extraction step of extracting at least one first similar region image whose similarity with the first reference region image satisfies a predetermined criterion in the inspection image;
A mask creating step for creating a mask area from the difference between the first reference area image and each first similar area image;
Comprising
In the inspection of the area including the arrangement unit, the mask area is excluded from the inspection.   The inspection method according to claim 8, wherein the mask creating step uses the sum of the differences circumscribing a region frame as the mask region.   10. The inspection method according to claim 8, wherein in the mask creation step, the mask area is created by performing an area expansion process. 11.   The inspection method according to claim 8, wherein the plurality of arrangement units are arranged on the inspection object by being rotated in the same direction or a predetermined angle. A second extraction step of extracting at least one second similar region image satisfying a predetermined criterion in the inspection image with a second reference region image in which the mask region is excluded from the first reference region image; ,
A determination step of determining the quality of the inspection object by comparing the second reference area image and the second similar area image;
The inspection method according to any one of claims 8 to 11, further comprising:

Images