JP5061543B2 - Printed matter inspection device, printed matter inspection method - Google Patents

Description

  The present invention relates to a printed matter inspection apparatus and printed matter inspection method for detecting defects (stain defects, missing defects, blurring, poor color tone, etc.) of printed matter such as cards.

  Conventionally, a card inspection apparatus acquires a reference image acquired by imaging a non-defective card, acquires an inspection image by imaging a card to be inspected, and compares the entire card between the reference image and the inspection image. The number of relationships is calculated, position correction is performed, and an absolute difference comparison inspection is performed (for example, refer to [Patent Document 1]).

JP 2000-348174 A

  However, the card configured by stacking the printing film has poor accuracy in the bonding position between the offset printed material and the silk printed material, resulting in misalignment of the printed pattern, and the absolute difference is compared between the entire reference image and the entire inspection image. When inspection is performed, there is a problem in that defect detection accuracy deteriorates.

  The present invention has been made in view of the above problems, and an object of the present invention is to provide a printed matter inspection apparatus and a printed matter inspection method capable of quickly inspecting a printed matter and improving defect detection accuracy. To do.

In order to achieve the above-described object, the first invention performs image processing on a reference image acquired by imaging a non-defective printed material and an inspection image acquired by imaging a printed material to be inspected, and the quality of the printed material is determined. And a divided region setting means for setting a divided region for each of the reference image and the inspection image, and the degree of coincidence between the reference image and the reference image is maximum for each divided region. A region extracting unit that extracts the extracted region from the inspection image, a first correcting unit that corrects the position of the divided region of the inspection image at the position of the extraction region for the extraction region that satisfies a predetermined condition, and the extraction region When a part of the inspection image does not satisfy the predetermined condition, based on the position correction amount of at least one of the other divided areas, the divided area of the inspection image corresponding to the extraction area that does not satisfy the predetermined condition A second correction means for correcting the location in the reference image and the inspection image, and the contour extracting means for extracting an outline of the printed material, accumulating the pixel values of the contour and the extracted each axis direction of the x-coordinate and y-coordinate End point position calculating means for calculating both peak positions of the integrated pixel value as the position coordinates of the end points of the printed matter, and end point correction amounts from the position coordinates of the end points in the reference image to the position coordinates of the end points in the inspection image An end point correction amount calculating unit that calculates the position, a third correction unit that corrects the position of the divided region of the inspection image based on the end point correction amount when all of the extraction regions do not satisfy a predetermined condition, and the divided region A printed matter inspection apparatus, comprising: a defect detection unit that performs defect detection by performing comparison processing between the reference image and the inspection image.

The printed matter inspection apparatus sets a divided region for each of the reference image and the inspection image, and extracts, from the inspection image, an extraction region where the degree of coincidence of the image with the reference image is maximized for each divided region. The printed matter inspection apparatus corrects the position of the divided region of the inspection image at the position of the extraction region and holds the position correction amount for the extraction region that satisfies the predetermined condition . When a part of the extraction region does not satisfy the predetermined condition, the printed matter inspection apparatus determines the division region of the inspection image corresponding to the extraction region that does not satisfy the predetermined condition based on the position correction amount of at least one of the other division regions. Correct the position. For example, the printed matter inspection apparatus sets the average value of the position correction amounts of the other divided regions as the position correction amount of the divided region of the inspection image. In addition, the printed matter inspection apparatus extracts the contour of the printed matter in the reference image and the inspection image, integrates the pixel values of the extracted contour in the coordinate axis direction, and calculates the peak position of the accumulated pixel value as the position coordinate of the end point of the printed matter. Then, the end point correction amount from the end point position coordinate in the reference image to the end point position coordinate in the inspection image is calculated. If all of the extraction regions do not satisfy the predetermined condition, the printed matter inspection apparatus corrects the position of the divided region of the inspection image based on the end point correction amount. Then, the printed matter inspection apparatus performs defect detection by performing a comparison process between the reference image and the inspection image for each divided region after the position correction.

The printed matter is obtained by printing a pattern, characters, etc. on a printing paper or the like. The printed material is, for example, a card configured by stacking print films.
The degree of coincidence of images is an index indicating the similarity between images. As the degree of coincidence of images, for example, a correlation coefficient in pattern matching processing can be used.
The predetermined condition regarding the extraction area is, for example, whether or not the degree of coincidence of images is larger than a predetermined set value, whether or not the extraction area is within the allowable area, and whether or not the extraction area is extracted from the search area. .

Further, the printed matter inspection apparatus may perform a difference process of the inspection image from the reference image for each divided region, binarize with a predetermined threshold value, and detect a part exceeding a predetermined number of pixels as a stain defect.
Also, the printed matter inspection apparatus may perform a difference process from the inspection image to the reference image for each divided region, binarize with a predetermined threshold value, and detect a portion exceeding a predetermined number of pixels as a defect.

  In the first invention, the printed matter inspection apparatus uses the position correction amount and the end point correction amount of other divided regions when the extraction region does not satisfy a predetermined condition (conditions relating to the degree of coincidence of images, a search region, and an allowable region). Since the position of the divided area is corrected and the defect detection process is performed for each of the divided areas subjected to the position correction, the defect detection process can be performed quickly and with high accuracy.

The second invention is a printed matter inspection method in which image processing is performed on a reference image acquired by imaging a non-defective printed matter and an inspection image acquired by imaging a printed matter to be inspected to inspect the quality of the printed matter. A divided region setting step for setting a divided region for each of the reference image and the inspection image, and for each divided region, an extraction region where the degree of coincidence between the reference image and the reference image is maximized from the inspection image. A region extraction step for extraction, a first correction step for correcting the position of the divided region of the inspection image at the position of the extraction region for the extraction region satisfying a predetermined condition, and a part of the extraction region satisfy the predetermined condition If not, the position of the divided area of the inspection image corresponding to the extracted area that does not satisfy the predetermined condition is corrected based on the position correction amount of at least one of the other divided areas. A correction step, in the reference image and the inspection image, and the contour extracting a contour of the printed matter, the pixel values of the contour and the extracted accumulated in the axial direction of the x and y coordinates, the cumulative pixel value An end point position calculating step for calculating both peak positions as the position coordinates of the end points of the printed matter, and an end point correction amount for calculating an end point correction amount from the end point position coordinates in the reference image to the end point position coordinates in the inspection image A calculation step; a third correction step for correcting a position of the divided region of the inspection image based on the end point correction amount when all of the extraction regions do not satisfy a predetermined condition; and the reference image for each of the divided regions. And a defect detection step of performing defect detection by performing a comparison process between the inspection image and the inspection image.

  2nd invention is invention regarding the printed matter inspection method which inspects the quality of a printed matter by performing image processing with respect to the reference image acquired by picking up a good printed matter and the inspection image obtained by picking up the printed matter to be inspected. is there.

  According to the present invention, it is possible to provide a printed matter inspection apparatus and a printed matter inspection method that can quickly inspect a printed matter and improve defect detection accuracy.

  Hereinafter, preferred embodiments of a printed matter inspection apparatus and a printed matter inspection method 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 printed matter inspection apparatus 1)
First, the configuration of the printed matter inspection apparatus 1 according to the embodiment of the present invention will be described with reference to FIG.
FIG. 1 is a configuration diagram of a printed matter inspection apparatus 1.

The printed matter inspection apparatus 1 includes an image processing unit 3, a display unit 5, a line camera 7, an illuminator 9, and a conveyance stage 11.
The printed matter inspection apparatus 1 captures an image of the printed matter 13 with the line camera 7, performs defect detection in the image processing unit 3 based on the acquired image data, and displays the detection result on the display unit 5. When the inspection start trigger 15 is input to the image processing unit 3, the printed matter inspection apparatus 1 starts an inspection process and outputs a discharge signal 17 that is an inspection result.

  The image processing unit 3 performs image processing on the image data of the printed matter 13 to detect defects. The image processing unit 3 can be configured by, for example, a computer and a program that causes the computer to operate as the image processing unit 3. The details of the configuration and operation of the image processing unit 3 will be described later.

  The display unit 5 is a display device that displays a defect detection result. The display device 5 is, for example, a CRT (Cathode Ray Tube) or an LCD (Liquid Crystal Display).

  The line camera 7 is an apparatus that images the printed material 13. The line camera 7 is, for example, a camera (imaging device) including 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 line camera 7 is provided above the conveyance stage 11 and acquires image data of the printed matter 13 by imaging.

  The illumination 9 is a light source that irradiates the printed material 13 with light. The illuminator 9 is, for example, an illuminator in which a plurality of LEDs are arranged in a planar shape. A fluorescent lamp can also be used as the illuminator 9. The illuminator 9 has an opening near the center so as not to obstruct the field of view of the line camera 7.

The conveyance stage 11 is an apparatus that sequentially conveys the printed material 13 below the line camera 7.
The printed matter 13 is obtained by printing a pattern or characters on a printing paper or the like. The printed material 13 is, for example, a card configured by laminating printing films.

(2. Hardware configuration of image processing unit 3)
Next, the hardware configuration of the image processing unit 3 will be described with reference to FIG.
FIG. 2 is a hardware configuration diagram of the image processing unit 3.

  The image processing unit 3 includes a CPU 21 and a memory 22. The image processing unit 3 is connected to the line camera 7 via a network interface or connection line, and is connected to the display unit 5 via a video adapter. 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, etc., and realizes various functions to be described later.

The memory 22 is a storage device such as a RAM or a hard disk. The memory 22 includes a reference image memory 23, an inspection image memory 25, a display memory 27, and the like.
The reference image memory 23 is a memory that holds image data (a reference image or a divided reference image) of a non-defective product that serves as a reference.
The inspection image memory 25 is a memory that holds image data (inspection image or divided inspection image) of a printed matter to be inspected.
The display memory 27 is a memory that holds display data to be displayed on the display unit 5, and holds, for example, image data indicating a defective portion.
The reference image memory 23, the inspection image memory 25, and the display memory 27 may be provided independently from the image processing unit 3, or an area may be appropriately allocated on the RAM.

  When the line camera 7 captures the reference image and the inspection image of the printed matter 13 and inputs them to the image processing unit 3, the reference image and the inspection image are stored in the reference image memory 23 and the inspection image memory 25, respectively. The CPU 21 performs defect detection processing on the printed matter 13 to be inspected based on the reference image and the inspection image, and outputs the detection result to the display memory 27. The contents of the display memory 27 are input to the display unit 5 and displayed.

(3. Operation of image processing unit 3)
Next, the overall operation of the image processing unit 3 will be described with reference to FIG.
FIG. 3 is a flowchart showing the overall operation of the image processing unit 3.

The image processing unit 3 captures the non-defective printed matter 13 to acquire the reference image 31 and holds it in the reference image memory 23 (step 1001). The image processing unit 3 sets a divided area 39 in the reference image 31, creates a divided reference image 41, and stores it in the reference image memory 23 (step 1002).
The image processing unit 3 captures the printed matter 13 to be inspected, acquires the inspection image 33, and holds it in the inspection image memory 25 (step 1003). The image processing unit 3 sets a divided area 43 in the inspection image 33 (step 1004). The image processing unit 3 sets a search area 45 and an allowable area 46 for each divided area 43 in the inspection image 33 (step 1005).

FIG. 6 is a diagram showing the reference image 31 (a) and the inspection image 33 (b).
FIG. 7 is a diagram showing a divided area 39 (a) of the reference image 31 and a divided area 43 (b) of the inspection image 33.
The reference image 31 includes a printed product image 35 that is an image of the non-defective printed product 13. The inspection image 33 includes a printed material image 37 that is an image of the printed material 13 to be inspected.
The divided reference image 41 is an image obtained by dividing the reference image 31 into divided areas 39. Initially, the divided area 43 of the inspection image 33 is set at the same position as the divided area 39 of the reference image 31. The search area 45 is set around the divided area 43. The allowable area 46 is set inside the search area 45.
Hereinafter, the processing for the divided region 43 will be described in the order of (1), (2), and (3) in FIG. 7B in the order from the upper stage to the lower stage, and for each stage from left to right. .

  In the inspection image 33, the divided area 43 is not set according to the pattern, and therefore, the degree of correlation between the image of the divided area 39 on the reference image 31 side and the image of the divided area 43 on the inspection image 33 side is not sufficient. There is. Accordingly, if the defect detection process is performed by comparing the reference image 31 and the inspection image 33 for each divided region 43 at this stage, there is a possibility that the defect detection accuracy is lowered or a defect is erroneously detected.

Returning to FIG. 3, the image processing unit 3 corrects the position of the divided region 43 of the inspection image 33 (step 1006). Details of the divided region position correction process (step 1006) will be described later. The image processing unit 3 performs defect detection processing for each divided region 43 of the inspection image 33 (step 1007). Details of the processing in step 1006 will be described later.
The image processing unit 3 displays the defect detection result on the display unit 5 (step 1008). The image processing unit 3 repeats the processing from Step 1003 until all the inspections of the printed matter 13 to be inspected are completed (Step 1009).

(4. Division area position correction processing)
Next, the divided region position correction process (step 1006 in FIG. 3) will be described with reference to FIGS.

(4-1. Operation of Image Processing Unit 3 in Division Area Position Correction Process)
4 and 5 are flowcharts showing the operation of the image processing unit 3 in the divided region position correction processing.

  First, the image processing unit 3 starts position correction processing of the divided area 43 in the upper left corner. The image processing unit 3 performs pattern matching processing in the search area 45 to search for and extract an area where the degree of correlation with the division reference image 41 is maximized (step 2001).

FIG. 8 is a diagram illustrating region extraction by pattern matching processing.
FIG. 8A shows a case where the extraction area 47 extracted by the pattern matching process fits within the allowable area 46. FIG. 8B shows a case where the extraction area 49 extracted by the pattern matching process does not fit within the allowable area 46.

When the correlation between the division reference image 41 and the image of the extraction region is equal to or greater than a predetermined setting value (Yes in Step 2002), the image processing unit 3 determines that the extraction region is within the allowable region 46 (Yes in Step 2003: In FIG. 8A, the position of the divided area 43 of the inspection image 33 is corrected at the position of the extraction area 47 and held in the memory 22 (step 2004). Further, the image processing unit 3 holds the position correction amount 48 in the process of step 2004 in the memory 22.
Note that the case where the correlation degree is equal to or greater than a predetermined set value (Yes in step 2002) indicates a case where an area in the search area 45 whose image matching degree is greater than the predetermined set value is extracted.

The image processing unit 3 determines whether the correlation between the division reference image 41 and the image of the extraction area is less than a predetermined setting value (No in step 2002) or when the extraction area 49 does not fit in the allowable area 46 ( No in step 2003: FIG. 8B), end point correction processing (step 2005 to step 2007) is performed.
The case where the degree of correlation is less than a predetermined set value (No in step 2002) indicates a case where an area in the search area 45 where the degree of coincidence of images is larger than the predetermined set value cannot be extracted.

FIG. 9 is a diagram showing the flow of the end point correction process.
When starting the end point correction process, the image processing unit 3 extracts the contour 53 of the printed material image 35 from the reference image 31 and extracts the contour 63 of the printed material image 37 from the inspection image 33 (step 2005). For the extraction of the contour 53 and the contour 63, a contour extraction filter such as a Sobel filter can be used.

  The image processing unit 3 integrates the pixel values of the contour 53 in the Y-axis direction in the reference image 31, calculates the peak position 55 of the integrated pixel value, integrates the pixel values of the contour 53 in the X-axis direction, and integrates the pixels. The peak position 57 of the value is calculated. The image processing unit 3 sets the peak position 55 and the peak position 57 as the X coordinate and the Y coordinate of the end point 59 of the printed image 35, respectively. Similarly, the image processing unit 3 integrates the pixel values of the contour 63 in the Y-axis direction in the inspection image 33, calculates the peak position 65 of the integrated pixel value, and integrates the pixel values of the contour 63 in the X-axis direction. Then, the peak position 67 of the integrated pixel value is calculated. The image processing unit 3 sets the peak position 65 and the peak position 67 as the X coordinate and the Y coordinate of the end point 69 of the printed material image 37, respectively (step 2006).

The image processing unit 3 calculates an end point correction amount 71 from the position coordinates of the end point 59 and the position coordinates of the end point 69 and stores the calculated end point correction amount 71 in the memory 22 (step 2007).
The image processing unit 3 corrects the position of the divided region 43 of the inspection image 33 based on the end point correction amount 71 and stores it in the memory 22 (step 2008).

  Next, the image processing unit 3 starts position correction processing for the other divided regions 43. The image processing unit 3 performs pattern matching processing in the search area 45 to search for and extract an area where the degree of correlation with the division reference image 41 is maximized (step 3001).

When the correlation between the division reference image 41 and the image of the extraction region is equal to or greater than a predetermined setting value (Yes in Step 3002), the image processing unit 3 determines that the extraction region is within the allowable region 46 (Yes in Step 3003: 8A), the position of the divided area 43 of the inspection image 33 is corrected at the position of the extracted extraction area 47 and held in the memory 22 (step 3004). In addition, the image processing unit 3 holds the position correction amount 48 in the process of step 3004 in the memory 22.
The case where the degree of correlation is equal to or higher than a predetermined set value (Yes in step 3002) indicates a case where an area in the search area 45 where the degree of coincidence of images is larger than the predetermined set value is extracted.

The image processing unit 3 determines whether the correlation between the division reference image 41 and the image of the extraction area is less than a predetermined setting value (No in step 3002), or the extracted extraction area 49 does not fit in the allowable area 46. In the case (No in step 3003: FIG. 8B), based on the position correction amount 48 in the process of step 2004 or step 3004, the position of the divided region 43 of the inspection image 33 is corrected and held in the memory 22 (step 3005). ).
The case where the degree of correlation is less than the predetermined set value (No in step 3002) indicates a case where an area in the search area 45 where the degree of coincidence of images is larger than the predetermined set value cannot be extracted.

  When the position correction process has not been completed for all the divided regions 43 of the inspection image 33 (No in Step 3006), the image processing unit 3 repeats the processes from Step 3001.

(4-2. Specific Example of Division Area Position Correction Process)
FIG. 10 is a diagram illustrating the types of pattern matching processing results performed on the divided region 43 of the inspection image 33.
The type 73 (“◯”) indicates a case where the degree of correlation of the extraction area is greater than or equal to a set value and falls within the allowable area 46. The type 75 (“Δ”) indicates a case where the degree of correlation of the extraction area is equal to or greater than the set value but does not fit within the allowable area 46. The type 75 (“×”) is a case where the correlation degree of the extraction region is less than a predetermined setting value, and the region where the matching degree of the image is larger than the predetermined setting value in the search region 45 cannot be extracted. Show.

(4-2-1. When it is all type 73 (“◯”))
FIG. 11 is a diagram showing an inspection image 33a in which all the divided areas 79-1 to 79-6 are of type 73 (“◯”).
In the inspection image 33a, for all the divided areas 79-1 to 79-6, an extraction area 47 having a correlation degree equal to or higher than a set value and falling within the allowable area 46 is extracted. The image processing unit 3 corrects the positions of the divided areas 79-1 to 79-6 at the position of the extraction area 47.

(4-2-2. When part is type 75 (“Δ”))
FIG. 12 is a diagram illustrating an inspection image 33b in which some of the divided areas 81-2 and 81-6 are of type 75 (“Δ”). FIG. 12A shows before position correction, and FIG. 12B shows after position correction.

  In the inspection image 33b, for the divided area 81-1, and the divided area 81-3 to the divided area 81-5, an extraction area 47 having a correlation degree equal to or higher than a set value and falling within the allowable area 46 is extracted. -2 and the divided area 81-6, the extraction area 49 whose degree of correlation is equal to or higher than the set value but does not fall within the allowable area 46 is extracted.

  The image processing unit 3 corrects the positions of the divided area 81-1 and the divided areas 81-3 to 81-5 at the position of the extraction area 47. Instead of correcting the position of the divided area 81-2 and the divided area 81-6 at the position of the extraction area 49, the image processing unit 3 corrects the position based on the position correction amount 48 (FIG. 8) of the other extraction areas. I do.

  The image processing unit 3 performs position correction on the upper right divided region 81-2 based on the position correction amount 48 of the left divided region 81-1. The image processing unit 3 performs position correction on the lower right divided region 81-6 based on the average of the position correction amounts 48 of the left divided region 81-5 and the upper divided region 81-4.

(4-2-3. When all are of type 77 (“×”))
FIG. 13 is a diagram illustrating an inspection image 33c in which all the divided regions 83-1 to 83-6 are type 77 (“×”). FIG. 13A shows before position correction, and FIG. 13B shows after position correction.

  In the inspection image 33c, an extraction region having a degree of correlation less than a set value is extracted for all the divided regions 83-1 to 83-6. That is, it shows a case where an area where the degree of coincidence of images is larger than a predetermined set value in the search area 45 cannot be extracted.

  Instead of correcting the positions of the divided regions 83-1 to 83-6 at the position of the extraction region, the image processing unit 3 performs position based on the end point correction amount 71 (FIG. 9) that is the correction amount of the end point 69. Make corrections.

The image processing unit 3 performs position correction based on the end point correction amount 71 for the divided region 83-1 in the upper left column.
The image processing unit 3 performs position correction on the other upper divided area 83-2 based on the position correction amount of the left divided area 83-1.
The image processing unit 3 performs position correction on the middle and lower divided areas 83-3 to 83-6 based on the position correction amount of the upper divided area.

(4-2-4. When a part is type 77 (“×”))
FIG. 14 is a diagram illustrating an inspection image 33d in which some of the divided areas 85-2 and 85-6 are of type 77 (“×”). FIG. 14A shows before position correction, and FIG. 14B shows after position correction.

  In the inspection image 33d, for the divided area 85-1 and the divided areas 85-3 to 85-5, an extraction area 47 having a correlation degree equal to or higher than a set value and falling within the allowable area 46 is extracted. -2 and the divided region 85-6, the extraction region whose correlation is less than the set value is extracted. That is, for a part of the divided areas 85-2 and 85-6, a case where an area in the search area 45 where the image matching degree is larger than a predetermined set value cannot be extracted is shown.

  The image processing unit 3 corrects the position of the divided area 85-1 and the divided areas 85-3 to 85-5 at the position of the extraction area 47. The image processing unit 3 performs position correction based on the position correction amount 48 (FIG. 8) of the other extraction areas instead of correcting the positions of the division areas 85-2 and 85-6 at the positions of the extraction areas. Do.

  The image processing unit 3 performs position correction on the upper right divided region 85-2 based on the position correction amount 48 of the left divided region 85-1. The image processing unit 3 performs position correction on the lower right divided region 85-6 based on the average of the position correction amounts 48 of the left divided region 85-5 and the upper divided region 85-4.

(5. Defect detection processing)
Next, the defect detection process (step 1007 in FIG. 3) will be described with reference to FIG.
FIG. 15 is a diagram illustrating a flow of operations of the image processing unit 3 in the defect detection process.

  The image processing unit 3 performs defect detection processing for each divided region after position correction. The image processing unit 3 acquires the division reference image 121 and the division inspection image 131. The division reference image 121 corresponds to the division reference image 41 (FIG. 7A). The divided inspection image 131 is an image of the divided region 43 in which position correction (FIGS. 4 and 5) is performed on the inspection image 33. The divided inspection image 131 includes a missing image 115 and a dirt image 117 as defects.

The image processing unit 3 subtracts the divided inspection image 131 from the divided reference image 121 for each RGB component, synthesizes the RGB components, performs the MAX processing, and acquires the stain candidate image 123 (step 4001). 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 image processing unit 3 subtracts the divided reference image 121 from the divided inspection image 131 for each RGB component, combines the RGB components, performs MAX processing, and obtains a missing candidate image 133 (step 5001). 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 image processing unit 3 performs binarization processing on the stain candidate image 123 with a predetermined stain threshold (step 4002), and detects a stain portion exceeding a predetermined number of stain pixels as the detected stain 127 (step 4003). ). The image processing unit 3 displays a stain detection image 125 indicating the detection stain 127 as a detection result on the display unit 5.
The image processing unit 3 performs binarization processing on the missing candidate image 133 with a predetermined missing threshold (step 5002), and detects a missing portion exceeding a predetermined number of missing pixels as a detected missing 137 (step 5003). ). The image processing unit 3 displays the missing detection image 135 indicating the detection missing 137 as a detection result on the display unit 5.
The image processing unit 3 repeats the above process for every divided region.

(6. Effects, etc.)
Through the above process, the image processing unit 3 performs a pattern matching process on each divided region 43 of the inspection image 33 with the divided reference image 41, and when the extraction region satisfies a predetermined condition, If the position of the divided region 43 is corrected at the position and the extraction region does not satisfy the predetermined condition, the divided region is determined using the position correction amount 48 (FIG. 8) and the end point correction amount 71 (FIG. 9) of the other divided regions 43. 43 position correction is performed. For example, the image processing unit 3 performs position correction using an average value of the position correction amounts 48 of the other divided regions 43. The image processing unit 3 performs a difference process or the like between the divided reference image 121 and the divided inspection image 131 for each divided region 43 for which position correction has been performed, and detects a stain defect or a missing defect.

  As described above, when the extracted region does not satisfy a predetermined condition (conditions regarding the degree of coincidence of the image, the search region, and the allowable region), the printed matter inspection apparatus 1 performs division using the position correction amount and the end point correction amount of the other divided regions. Since the area position correction is performed and the defect detection process is performed for each of the divided areas subjected to the position correction, the defect detection process can be performed quickly and with high accuracy.

In the above-described embodiment, the acquisition of the inspection target image of the printed material has been described as using a line camera. However, the present invention is not limited to this, and a scanner device or the like may be used.
In addition, image data may be acquired by imaging or scanning with a camera or the like, and the present invention is not limited to this. When printing by CTP (Computer To Plate), digital data to be output to a printing plate or the like is image data. You may make it use as.

  The preferred embodiments of the printed matter inspection apparatus and the printed matter inspection method 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.

Configuration diagram of printed matter inspection apparatus 1 Hardware configuration diagram of the image processing unit 3 A flowchart showing the overall operation of the image processing unit 3 The figure which shows the reference | standard image 31 (a) and the test | inspection image 33 (b) The figure which shows the division area 39 (a) of the reference | standard image 31, and the division area 43 (b) of the test | inspection image 33. The flowchart which shows operation | movement of the image process part 3 in a split area position correction process. The flowchart which shows operation | movement of the image process part 3 in a split area position correction process. Diagram showing region extraction by pattern matching processing Diagram showing the flow of endpoint correction processing The figure which shows the classification of the extraction area extracted by pattern matching processing The figure which shows the test | inspection image 33a whose all division areas are the types 73 ("(circle)"). The figure which shows the test | inspection image 33b whose one part division area is classification 75 ("(triangle | delta)"). The figure which shows the test | inspection image 33c in which all the division areas are classification 77 ("x"). The figure which shows the test | inspection image 33d whose one part division area is the classification 77 ("x"). The figure which shows the flow of operation | movement of the image process part 3 in a defect detection process.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ......... Printed material inspection apparatus 3 ......... Image processing part 5 ......... Display part 7 ......... Line camera 9 ......... Illuminator 11 ......... Conveyance stage 13 ......... Printed material 21 ......... CPU
22 ......... Memory 31 ......... Reference image 33, 33a, 33b, 33c, 33d ......... Inspection image 35, 37 ......... Printed image 39, 43 ......... Split area 41 ......... Split reference image 45 ... …… Search area 46 ...... Allowable area 47, 49 ...... Extraction area 48 ............ Position correction amount 53, 63 ...... Contour 59, 69 ...... End point 71 ...... End point correction amount 115 ...... Missing image 117... Dirt image 121... Division reference image 123... Dirt candidate image 125... Dirt detection image 127. ……… Missing detection image 137 ……… Missing detection

Claims (10)

A printed material inspection apparatus that performs image processing on a reference image acquired by imaging a non-defective printed material and an inspection image acquired by imaging a printed material to be inspected, and inspects the quality of the printed material,
Divided region setting means for setting a divided region for each of the reference image and the inspection image;
For each of the divided regions, a region extracting means for extracting from the inspection image an extraction region where the degree of coincidence of the image with the reference image is maximized;
A first correction unit that corrects the position of the divided area of the inspection image at the position of the extraction area for the extraction area that satisfies a predetermined condition;
When a part of the extraction region does not satisfy the predetermined condition, the position of the divided region of the inspection image corresponding to the extraction region that does not satisfy the predetermined condition is determined based on the position correction amount of at least one other divided region. Second correcting means for correcting;
In the reference image and the inspection image, contour extracting means for extracting the contour of the printed matter;
An end point position calculating unit that integrates the pixel values of the extracted contour in the x-coordinate and y-axis directions, and calculates both peak positions of the integrated pixel values as position coordinates of the end points of the printed matter;
Endpoint correction amount calculation means for calculating an endpoint correction amount from the position coordinates of the endpoint in the reference image to the position coordinates of the endpoint in the inspection image;
Third correction means for correcting the position of the divided area of the inspection image based on the end point correction amount when all of the extraction areas do not satisfy a predetermined condition;
Defect detection means for performing defect detection by performing a comparison process between the reference image and the inspection image for each divided region;
A printed matter inspection apparatus comprising:   The predetermined condition is whether or not the degree of coincidence of images is greater than a predetermined set value, whether or not the extraction area is within an allowable area, or whether or not the extraction area is extracted from a search area, The printed matter inspection apparatus according to claim 1, further comprising:   The printed matter inspection apparatus according to claim 1, wherein the second correction unit corrects the position of the divided region of the inspection image based on an average value of the position correction amounts. .   The defect detection means performs difference processing of the inspection image from the reference image for each of the divided regions, binarizes with a predetermined threshold value, and detects a portion exceeding a predetermined number of pixels as a contamination defect. The printed matter inspection apparatus according to any one of claims 1 to 3.   The defect detection means performs a difference process of the reference image from the inspection image for each of the divided regions, binarizes with a predetermined threshold value, and detects a portion exceeding a predetermined number of pixels as a defect. The printed matter inspection apparatus according to any one of claims 1 to 4. A printed matter inspection method for inspecting the quality of the printed matter by performing image processing on a reference image obtained by photographing a non-defective printed matter and an inspection image obtained by photographing the printed matter to be inspected,
A divided region setting step for setting a divided region in each of the reference image and the inspection image;
An area extraction step for extracting from the inspection image an extraction area where the degree of coincidence of the image with the reference image is maximized for each of the divided areas;
A first correction step of correcting the position of the divided area of the inspection image at the position of the extraction area for the extraction area satisfying a predetermined condition;
When a part of the extraction region does not satisfy the predetermined condition, the position of the divided region of the inspection image corresponding to the extraction region that does not satisfy the predetermined condition is determined based on the position correction amount of at least one other divided region. A second correction step to correct;
In the reference image and the inspection image, a contour extracting step for extracting a contour of the printed matter;
An end point position calculating step of integrating the extracted pixel values of the contour in the respective axis directions of the x coordinate and the y coordinate, and calculating both peak positions of the integrated pixel values as position coordinates of the end points of the printed matter;
An end point correction amount calculating step for calculating an end point correction amount from a position coordinate of the end point in the reference image to a position coordinate of the end point in the inspection image;
A third correction step of correcting the position of the divided region of the inspection image based on the end point correction amount when all of the extraction regions do not satisfy a predetermined condition;
For each of the divided regions, a defect detection step for performing defect detection by performing a comparison process between the reference image and the inspection image;
A printed matter inspection method comprising:   The predetermined condition is whether or not the degree of coincidence of images is greater than a predetermined set value, whether or not the extraction area is within an allowable area, or whether or not the extraction area is extracted from a search area, The printed matter inspection method according to claim 6, further comprising:   The printed matter inspection method according to claim 6, wherein the second correction step corrects the position of the divided region of the inspection image based on an average value of the position correction amounts. .   In the defect detection step, for each of the divided regions, the inspection image is subjected to difference processing from the reference image, binarized with a predetermined threshold value, and a part exceeding a predetermined number of pixels is detected as a contamination defect. The printed matter inspection method according to any one of claims 6 to 8.   In the defect detection step, the difference processing of the reference image from the inspection image is performed for each of the divided regions, and binarization is performed with a predetermined threshold value, and a portion exceeding a predetermined number of pixels is detected as a defect. The printed matter inspection method according to any one of claims 6 to 9.

Images