JPH09330410A - Picture inspecting method and its device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a picture inspecting method and a device applying the method, by which a picture inspection can be performed by reliably correcting positional deviation in a short time with respect to wide inspecting conditions and inspecting object. SOLUTION: An intersection pixel is designated to extract two reference pixel data storing concerning two directions to correct. In addition a pixel within a prescribed range corresponding to the intersection pixel is designated to extract plural corresponding inspecting objective pixel data strings on an inspecting objective picture concerning the two direction to correct. The evaluating numerical value of coincidence is calculated concerning them and positional deviation is corrected based on data o the position of the pixel within the prescribed range providing the evaluating numerical value of maximum coincidence and positional data of the intersection pixel to compare a reference picture and the inspecting objective picture.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image inspection method and apparatus for correcting a positional shift between a reference image and an image to be inspected, and comparing and inspecting the images.

[0002]

2. Description of the Related Art Defects in printed matter are caused by defects such as wrinkles, foreign substances, and stains on printing paper, ink stains, hickies, doctor streaks, poor density, poor color tone, etc. that occur during printing. is there. Conventionally, the inspection of the printed matter is mainly a visual inspection performed by a human.For example, in the case of the printed matter discharged from the folding unit of the sheet-fed printing press or the rotary printing press, the operator of the printing press pulls it out at a proper time. Then, a visual inspection was performed. If continuous printed matter is ejected from the printing machine and cannot be extracted, the printed matter is irradiated with strobe light that instantaneously emits light in synchronization with the running speed of the printed matter, and the afterimage of the human eye is used to stop the printed matter. Was being visually inspected.

The visual inspection imposes a very heavy work load on the person to be inspected, and since it is performed by a person, it is unavoidable to overlook defects. Therefore, various techniques have been disclosed by making a proposal for automatically inspecting a printed matter. For example, in Japanese Examined Patent Publication No. 1-47823, the image data read from the pattern of the running print at the time when the normal printed matter is printed is stored in the image memory as reference image data, and the reference image data read from the image memory is stored. There is disclosed a technique relating to a printed matter inspection apparatus of a system in which the quality of printing is determined by comparing, in pixel units, with the inspection target image data read from the pattern of the printed matter of the inspection target being printed.

However, when the reference image data and the image data to be inspected are compared on a pixel-by-pixel basis, if the accuracy of defect detection is increased, even if there is a slight misalignment between the two data when reading the pattern from the printed matter, the position The deviation is erroneously detected as a defect. Therefore, in order to prevent the misregistration of the misregistration as a defect, it is necessary to lower the accuracy of the defect detection. If the displacement between the two data cannot be avoided to some extent, the requirement is satisfied. Insufficient inspection performance was obtained. Therefore, Japanese Patent Publication No. 1-20477
In, the inspection target image data or the reference image data is displaced by one pixel in the left-right direction with respect to the traveling direction of the printed matter, and the inspection target image data and the reference image data are compared.
A technique is disclosed in which, after the positional deviation is corrected based on the positional deviation value between the two data when the two data are most matched, the inspection target image data and the reference image data are compared.

[0005]

However, in the conventional method for correcting the positional deviation of the image in the automatic inspection technique, the inspection target image data and the reference image data are compared.
There is a problem that an enormous amount of processing time is required because the image data having an extremely large amount of data is processed. Further, in view of the problem, Japanese Patent Laid-Open No. 7-249122 by the present inventor discloses a method for correcting an image position shift that shortens the processing time. However, this method has a problem in that sufficient correction accuracy cannot be obtained when large positional deviations occur simultaneously in the horizontal direction and in the case where the content of the design of the printed matter mismatches the correction method. Therefore, an object of the present invention is to perform an image inspection by performing a highly reliable positional deviation correction with a short processing time even when there is a special tendency of positional deviation or a special content of a printed matter. An object of the present invention is to provide a possible image inspection method and an apparatus to which the method is applied. The image inspection method and apparatus of the present invention can be applied to a wide range of inspection conditions and inspection objects.

[0006]

In order to achieve the above object, the present invention is directed to orthogonal (generally not parallel) line segments on a reference image and a line segment including its position and parallel to the line segment. Select a plurality of orthogonal (generally not parallel) line segments on the image to be inspected in which the relationship is maintained and the relative position of the two-dimensional predetermined region is changed, and the reference corresponding to the selected line segments The degree of coincidence between the image data and the inspection image data is evaluated, the positional deviation value is calculated based on the plurality of line segments given the evaluation with a large degree of coincidence, and the positional deviation correction is performed based on the calculated positional deviation value. The inspection is performed on the image.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, the present invention will be described with reference to embodiments. FIG. 1 is a flow chart showing an image inspection process in an image inspection method and apparatus according to the present invention. The process of image inspection will be described with reference to FIG. First, in step S1, intersection pixel designation is performed to designate one of the pixels forming the reference image as an intersection pixel. Next, in step S2, a predetermined range pixel designation is performed to designate, as a predetermined range pixel, a pixel within a predetermined range determined corresponding to the intersection pixel among the pixels forming the inspection target image. In principle, the designation of intersection pixels is arbitrary. However, if there is no change in the pixel data of the pixel row in the vertical direction and the pixel data of the pixel row in the horizontal direction in the predetermined range of pixels specified in relation to the intersection pixel, it is possible to detect the positional deviation. Can not. Therefore, it is preferable to specify the intersection pixels such that those pixel data are rich in variation. The predetermined range pixel is designated as a pixel of 5 rows and 5 columns centering on the intersection pixel, for example.

Next, in step S3, the first reference pixel data row, which is the data of the pixel row including the intersection pixel and in the direction parallel to the first direction in which the positional deviation is to be corrected, and the intersection pixel are set. The first data extraction is performed to extract the second reference pixel data row, which is the data of the pixel row that is parallel to the second direction in which the included positional deviation should be corrected.
Next, in step S4, a second inspection target pixel data row that is data of a pixel row that includes one pixel selected from the predetermined range pixels and is in a direction parallel to the second direction in which positional deviation is to be corrected, and A second data extraction is performed to extract a second inspection target pixel data row that is data of a pixel row that includes the selected one pixel and is in a direction parallel to the second direction in which the positional deviation should be corrected. . The first direction and the second direction are usually the vertical direction (web transfer direction).
And the left-right direction (the direction orthogonal to the web transfer direction), but is not necessarily limited to that direction, and may be any two directions that are not parallel.

Next, in step S5, all of the first reference pixel data sequence and the first inspection target image data, and the second reference pixel data sequence and the second inspection target image data are all used. An evaluation numerical value calculation is performed to obtain an evaluation numerical value of the degree of coincidence based on the image data. Next, in step S6, one pixel selected from the predetermined range pixels is changed, and the second data extraction process and the correlation coefficient calculation process are repeated to correspond to all the predetermined range pixels. The calculation is repeated to obtain the evaluation value. The evaluation value of the degree of coincidence may be any one of a correlation coefficient, a sum of absolute differences, and a sum of squared differences. If the evaluation value is a correlation coefficient, the closer the evaluation value is to “1”, the greater the degree of agreement. If the evaluation value is either the sum of the absolute values of the differences or the sum of the squares of the differences, the evaluation value is “ The closer to 0 ", the greater the degree of coincidence.

The above correlation coefficient is calculated by the following equation 1.

[Equation 1] The sum of the absolute values of the differences described above is calculated by the following equation 2.

[Equation 2] Further, the sum of squared differences described above is calculated by the following expression 3.

(Equation 3)

Next, in step S7, the intersection of the position data of one pixel selected from the pixels in the predetermined range, which gives the evaluation numerical value with the highest degree of coincidence among the evaluation numerical values obtained in the calculation iterative process, and the intersection point. A displacement value calculation is performed to obtain a displacement value from the pixel position data. Finally, in step S8, a positional deviation correction comparison is performed in which the positional deviation is corrected based on the positional deviation value obtained in the positional deviation value calculation process and compared with the reference image to inspect the inspection target image. As described above, according to the present invention, when the positional deviation value is obtained, the evaluation values of the degree of coincidence are not separately obtained for the two directions of the first direction and the second direction, but are combined for the two directions. To obtain the evaluation value of the degree of coincidence. As a result, it is possible to obtain an accurate positional deviation value and perform optimal positional deviation correction.

FIG. 2 is a diagram showing the relationship between the reference image data and the corresponding image data to be inspected when the evaluation value of the degree of coincidence is obtained in the two directions in the present invention.
FIG. 2A shows the intersection pixel P (x, y) on the reference image, the reference pixel data string Lx in the first direction to be corrected, and the reference pixel data string Ly in the second direction to be corrected. It is the figure shown. In addition, FIG. 2B includes a predetermined range pixel A on the inspection target image and an inspection target pixel data string Lx− in the first direction that includes a pixel selected from the predetermined range pixel A and should be corrected for the positional deviation. 2, Lx-1, Lx, Lx + 1, Lx
A diagram showing +2 and the inspection target pixel data sequence Ly-2, Ly-1, Ly, Ly + 1, Ly + 2 in the second direction that includes one pixel selected from the predetermined range of pixels A and should be corrected for positional deviation. Is.

In FIG. 2, in the intersection pixel P (x, y), (x, y) indicates the address of the intersection pixel P on the image data (on the plane). Therefore, the addresses of the pixels included in the predetermined range pixel A are (x-2, y-2),
(X-2, y-1), (x-2, y), (x-2, y +
1), (x-2, y + 2), (x-1, y-2), (x
-1, y-1), (x-1, y), (x-1, y +)
1), (x-1, y + 2), (x, y-2), (x, y
−1), (x, y), (x, y + 1), (x, y +)
2), (x + 1, y-2), (x + 1, y-1), (x
+1, y), (x + 1, y + 1), (x + 1, y +
2), (x + 2, y-2), (x + 2, y-1), (x
+2, y), (x + 2, y + 1), (x + 2, y + 2)
Becomes In the example shown in FIG. 2, the predetermined range of the predetermined range pixel A is thus 5 × 5 (top and bottom × left and right).

In FIG. 2, Lx and Ly in the reference pixel data string and the inspection object pixel data string indicate the addresses of the pixels belonging to the respective image data strings. Lx is m
Indicates that the pixel address is (x, m) for all y addresses belonging to the data string, and Ly indicates that the pixel address is (n, y) for n for all x addresses belonging to the data string. Is shown. Lx-2, Lx-
1, Lx + 1, Lx + 2, Ly-2, Ly-1, Ly +
The same applies to 1 and Ly + 2.

In the present invention, when the degree of coincidence between the reference pixel data string and the inspection object pixel data string is evaluated, the two directions in which the positional deviation is to be corrected are evaluated simultaneously. The intersection pixel P (x, on the reference image in FIG.
y) reference pixel data string L in the first direction to be corrected
The pixel to be inspected in the first direction to be corrected including the pixels on the predetermined range pixel A of the image to be inspected in FIG. 2B corresponding to x and the reference pixel data row Ly in the second direction to be corrected The degree of coincidence is evaluated for the data row Lx and the inspection-target pixel data row Ly in the second direction to be corrected.

FIG. 3 shows an intersection pixel P (x, y) on the reference image.
7 is an explanatory diagram of a process of sequentially moving pixels on a predetermined range pixel A of the inspection target image corresponding thereto to evaluate the degree of coincidence over the entire predetermined range. In the example shown in FIG. 3, the intersection pixel P (x, y) on the reference image is a pixel on the predetermined range pixel A of the inspection target image, and its address is (x
-2, y + 2), (x-1, y + 2), (x, y +
2), ..., (x, y-2), (x + 1, y-
2), sequentially move to (x + 2, y-2),
The degree of coincidence is evaluated over the entire predetermined range.

In the above description, the intersection pixel P (x, y) on the reference image sequentially moves the pixels on the predetermined range pixel A of the image to be inspected corresponding to the intersection point pixel P (x, y) so that the degree of coincidence is maintained over the entire predetermined range. Although the description is given so that the evaluation is performed, even if the relationship between the reference image and the inspection target image is exchanged, there is no change in the meaning of the positional deviation correction.
Therefore, even if the terms “reference” and “inspection target” are replaced with each other including the claims, the same effect can be obtained. For convenience of description, the description has been limited to the above, but in the present invention, the relationship between the reference image and the inspection target image can be interchanged, and any case is included in the present invention. However, in a strict sense, they are not the same. The reason is that the intersection pixel P on the reference image
Although it is guaranteed that there is a change in the pixel data on the line segment in two directions passing through (x, y) (such an intersection is selected), the intersection pixel P (x, y) on the inspection target image is selected. It is not guaranteed that there is a change in the pixel data on the line segment in two directions passing through () due to the positional deviation. Therefore, at that point, it is better to specify the intersection pixel P (x, y) on the reference image.

[0018]

EXAMPLE FIG. 4 is a schematic diagram showing an outline of the apparatus configuration of the present invention. In FIG. 4, 1 is a printing unit, 2 is a printed matter, 3 is a guide roller, 4 is a light source for illumination, 5 is a camera unit for imaging, 6 is a camera control unit for controlling the camera unit, and 7 is a machine of the printing unit. A rotary encoder for detecting a target position (rotational position of the plate cylinder), and 8 is a main body of a printed matter inspection apparatus for processing image data obtained by imaging by a camera unit. The printing paper passes through the printing unit 1, where printing is performed and becomes printed matter 1,
It is guided by the guide roller 3 and reaches a position illuminated by the light source 4. The guide roller 3 is usually in that position.
Therefore, the position of the printed matter 2 is defined. The printed matter 2 is imaged by the camera unit 5 at that position. In the example of FIG. 4, the camera unit 5 is a linear sensor camera that captures an image by one-dimensional scanning.

A rotary encoder 7 is installed in the plate cylinder of the printing unit 1 or in a portion which rotates in synchronization with the plate cylinder, and outputs a pulse signal in synchronization with a printing cycle.
This pulse signal is input to the camera control unit 6, and the camera control unit 6 outputs an imaging start signal to the camera unit 5 every time the printed matter 2 travels a predetermined amount in synchronization with the printing cycle, and the camera unit 5 captures an image. Data, that is, analog data is input, A / D (analog to digital) conversion is performed to convert it into digital data, and the data is transferred to the printed matter inspection apparatus main body 8. In this way, two-dimensional scanning is performed at a timing synchronized with the printing cycle, and digital image data is read into the printed matter inspection apparatus main body 8. Further, since the image is captured in synchronization with the printing cycle in this manner, If there is no disturbance factor or error factor, the imaging data read in each printing cycle will always be the imaging data at the same print pattern position if the imaging data is at the same cycle timing.

The printed matter inspection apparatus main body 8 to which the digital image signal is input stores the digital image data of the printed matter 1 when a non-defective product is printed in the memory as a reference image. Then, it is determined whether or not a defect of the printed material 1 has occurred by using the digital image data input thereafter as the inspection target image data.

FIG. 5 is a block diagram showing the structure of the main body of the printed matter inspection apparatus. In FIG. 5, reference numeral 8 is a printed matter inspection apparatus main body, 5 is a camera unit, 6 is a camera control unit, 9 is a reference image data memory, 10 is an inspection target image data memory, 11 is a reference input command input unit, and 12 is a misregistration detection. Reference numeral 13 is a positional deviation correction comparison unit, and 14 is a parameter input unit. Each of the reference image data memory 9 and the inspection target image data memory 10 has a storage capacity capable of storing at least one unit of printed matter (a printing screen for one cycle performed by the printing unit). Further, the reference input command input unit 11 is a command for taking a reference image to start the image inspection and inputting data to the reference image data memory 9, and then taking an inspection target image to be stored in the inspection target image data memory 10. Switch the command to input.

When the reference image command input unit 11 commands the input of the reference image data, the selector shown in FIG. 5 connects the image data to the reference image data memory 9, and at this time, the positional deviation detecting unit 12, And misregistration correction comparison unit 13
Does not work. On the other hand, when the input of the inspection target image data is commanded by the reference input command input unit 11, the selector makes an input connection of the imaging data to the inspection target image data memory 10. Then, the positional deviation detecting unit 12 detects the positional deviation between the inspection target image and the reference image, and sends the resulting positional deviation correction value to the positional deviation correction comparing unit 13. Then, the misregistration correction comparison unit 13 that has received the misregistration correction value performs a collation comparison inspection of the inspection target image data and the reference image data in consideration of the misregistration correction value. In addition, the parameter input unit 1
Reference numeral 4 is an input for setting parameters used in the positional deviation detecting unit 12 and the positional deviation correction comparing unit 13. As a parameter, for example, a threshold value for performing a pass / fail judgment by comparing the inspection target image data with the reference image data in the positional deviation correction comparing unit 13 is input.

FIG. 6 is a block diagram showing the configuration of the position shift detecting section. In FIG. 6, reference numeral 12 denotes a positional deviation detection unit,
Reference numeral 9 is a reference image data memory, 10 is an inspection target image data memory, 11 is a reference input command input unit, 13 is a positional deviation correction comparison unit, 15 is an intersection pixel designation unit, 16 is a predetermined range pixel designation unit, and 17 is a first A data extracting unit, 18 is a second data extracting unit, 19 is a first image data string memory, 20 is a second image data string memory, 21 is an evaluation numerical value calculating unit, and 22 is a middle value calculating unit.

In FIG. 6, the intersection pixel specifying section 15 refers to the reference image data in the reference image data memory 9 and specifies one intersection pixel position. The first data extraction unit 17 inputs the intersection pixel position, and extracts from the reference image data memory 9 a reference pixel data string of a line segment position including the intersection pixel and intersecting in the horizontal direction in the vertical direction. Further, the predetermined range pixel designation unit 16 inputs the intersection pixel position and designates the pixels in the predetermined range including the intersection pixel from the inspection target image data memory 10. Second
The data extraction unit 18 extracts an inspection target pixel data string at a line segment position that includes a predetermined range of pixels and intersects in the horizontal direction.
This inspection target pixel data string exists in the same number as the number of pixels in the predetermined range.

The reference pixel data string extracted by the first data extracting unit 17 is stored in the first image data string memory 19 (one exists). In addition, the second data extraction unit 18
One of the inspection target pixel data strings extracted by is stored in the second image data string memory 20. The evaluation value calculation unit 21 calculates an evaluation value of the degree of coincidence between the reference pixel data string stored in the first image data string memory 19 and the second image data string memory 20 and the inspection target pixel data string. As described above, the calculation of the evaluation numerical value performed on the inspection target pixel data string having one of the predetermined range pixels as an intersection is repeated a plurality of times for all the predetermined range pixels to obtain a plurality of evaluation numerical values.

The median value calculation unit 22 is an evaluation numerical value calculation unit 21.
Among the plurality of evaluation numerical values calculated in step 1, a threshold value is set and the inspection target pixel data string having a high matching value is extracted except for the inspection target pixel data string having a low matching value. Then, based on the extracted intersection point position of the inspection target pixel data string and the intersection point pixel position designated with reference to the reference image data, the displacement value is calculated. Further, the median value calculation unit 22 obtains the median value from the misalignment value and sets it as the misalignment value in the vertical direction. The positional shift value in the horizontal direction is output to the positional shift correction comparing unit 13.

FIG. 7 and FIG. 8 are flow charts of examples of combinations of the positional deviation correction methods. This is a process of improving the positional deviation correction accuracy by performing the positional deviation correction in the vertical direction and the lateral deviation direction according to the present invention after performing the positional deviation correction separately in the vertical direction and the horizontal direction. In FIG. 7, the reference line segment positions are m (in the case of FIG. 7, m = 1), whereas the inspection target line segment positions are n (FIG. 7).
In the case of n = 3), and is a flow chart of the process of correcting the positional deviation separately in the vertical direction and the horizontal direction. This m-to-n line correction is performed by m line segments that are parallel to each other on the reference image, and n line segments that are adjacent to each other and that are parallel to the line segment and that include the position of the m line segments. Is selected, the degree of coincidence is evaluated in the combination of line segments on each image, the positional deviation value is calculated based on a plurality of line segments that are evaluated to have a large degree of coincidence, and the calculated positional deviation value is calculated. The image is inspected by correcting the displacement based on the above. FIG. 8 is a flow chart of the process of correcting the positional deviation in the horizontal direction of the present invention performed after the process of FIG.

In FIG. 7, after the positional displacement in the vertical direction is corrected, the positional displacement in the horizontal direction is corrected. First, in step S101, one line segment on the reference image in the vertical direction and three adjacent line segments on the inspection target image including the position of the one line segment and parallel to the line segment are selected. Then, the positional deviation value is calculated for the combination of the line segments on each image to calculate the maximum degree of coincidence. Then, the positional deviation value is calculated based on the line segment from which the evaluation value with the highest degree of coincidence among the three is obtained. Next, in step S102, this calculation process (S101) is performed for five different sets of line segments on the reference image to obtain five sets of evaluation numerical values and displacement values. That is, Zy is a vertical displacement value, and R is an evaluation numerical value (Zy1, R1), (Zy2, R2),
(Zy3, R3), (Zy4, R4), (Zy5, R
5) is obtained.

Next, in step S103, three larger values are selected from the five sets of evaluation numerical values. Let the three be [Ri, Rj, Rk]. Next, step S10
4, based on the positional deviation values [Zyi, Zyj, Zyk] corresponding to the three evaluation values, the median value (Me
dian) is selected as the vertical displacement value Zy.

Next, in step S105, a correction arithmetic expression for the horizontal line address of the image to be inspected is set on the basis of the positional deviation value Zy in the vertical direction. That is, when the horizontal line address of the reference image is Ly and the horizontal correction line address of the image to be inspected is Ly ', the correction arithmetic expression is represented by the following Expression 4.

## EQU00004 ## Ly1 '= Ly1 + Zy Ly2' = Ly2 + Zy Ly3 '= Ly3 + Zy

Next, in step S106, one line segment (Ly) on the reference image in the left-right direction and its 1
Line segments on the inspection target image that include the line segment position of the line segment position (Ly ′) whose line segment position has been corrected and are parallel to that line segment are selected, and the line segment on each image is selected. The degree of coincidence is evaluated in the combination of, and the positional deviation value is calculated based on the line segment from which the evaluation value with the highest degree of coincidence among the three is obtained. Next, in step S107, this calculation process is performed by three sets of different line segments (Ly1, Ly2, Ly) on the reference image.
Perform 3) to obtain three sets of displacement values. That is, Zx is used as the positional deviation value in the left-right direction (Zx1, Zx
2, Zx3) is obtained. Next, in step S108, the three displacement values (Zx1, Zx2, Zx3).
Based on the above, the median value (Median) is selected and set as the positional deviation value Zx in the left-right direction.

Next, proceeding to FIG. 8, in FIG. 8, positional deviation correction in the horizontal direction according to the present invention is performed. Step S
At 109, a correction calculation formula for the horizontal line address of the image to be inspected is set based on the positional deviation values Zx and Zy in the vertical direction and the horizontal direction. That is, if the vertical line address of the reference image is Lx, the vertical correction line address of the inspection target image is Lx ′, the horizontal line address of the reference image is Ly, and the horizontal correction line address of the inspection image is Ly ′, then The correction calculation formula is expressed by the equation (5).

Lx1 '= Lx1 + Zx Ly1' = Ly1 + Zy Lx2 '= Lx2 + Zx Ly2' = Ly2 + Zy Lx3 '= Lx3 + Zx Ly3' = Zy3 +.

Next, in step S110, three sets of line segment positions (Lx
1 ', Ly1'), (Lx2 ', Ly2'), (Lx
3 ′, Ly3 ′), select a plurality of line segments on the inspection target image that include those line segment positions and maintain a parallel relationship with the line segment and relatively change the position of a predetermined two-dimensional region,
The degree of coincidence between the reference image data and the inspection image data corresponding to the selected line segment is evaluated. Next, step S
In 111, a positional deviation value is calculated from the coordinates of the intersections based on the plurality of line segments that are evaluated with a high degree of coincidence. The positional deviation value for each of the three sets of line segment positions is Zxx
Is a lateral displacement value and Zyy is a vertical displacement value (Zxx1, Zyy1), (Zxx2, Zyy
2), (Zxx3, Zyy3). Next, in step S112, the median value (Me) is separately calculated based on the three positional deviation values in the vertical direction (Zy1, Zy2, Zy3) and the horizontal direction (Zx1, Zx2, Zx3).
dian), and position displacement values Zx and Zy in the horizontal direction.
And

As described above, in this example, after the positional deviation correction in the vertical direction is performed, the positional deviation correction in the horizontal direction is performed,
Further, the position shift in the horizontal direction is corrected. As a result, the positional deviation correction accuracy can be improved, and the processing time required for the high accuracy can be shortened. Further, in the inspection of the printed matter, the behavioral state of the printed matter caused by running may be different from the displacement of the printed matter due to the meandering because the camera unit for photographing the printed matter is installed at a position distant from the printing unit. The vertical displacement is usually larger. Therefore, as in this example, it is possible to perform the positional deviation correction with higher reliability by performing the positional deviation correction in the vertical direction first.

In this example, the number of line segment positions in the vertical direction is five, and the number of line segment positions in the horizontal direction is three. Since the median value of these misalignment correction values or the median value of misalignment correction values selected by the evaluation value is used as the final misalignment correction value, some results may be incorrect. Can also obtain a correct correction value. In this way, by using a plurality of line segment positions, it is possible to improve the reliability of positional deviation correction. The selection of the line segment position and the selection of the intersection pixel position by the intersection pixel designating unit 15 are performed by selecting the vertical line segment from which data changes little when the horizontal position shifts from the reference image data, and the data when the vertical position shift occurs. Select the line segment in the left-right direction that changes less. This line segment selection method is described in Japanese Patent Application Laid-Open No. 7-24 filed by the present inventor.
The method described in No. 9122 can be applied.

FIG. 9 is a block diagram showing the structure of the positional deviation correction comparison unit. In FIG. 9, 13 is a positional deviation correction comparison unit, 6 is a camera control unit, 9 is a reference image data memory,
10 is an image data memory to be inspected, 12 is a displacement detection unit, 23 is an expansion processing circuit, 24 is a degeneration processing circuit, 25 is an upper threshold setting circuit, 26 is a lower threshold setting circuit, 27 is an upper threshold image buffer, and 28 is Lower threshold image buffer, 2
Reference numeral 9 is an image shift circuit, 30 is an upper threshold comparison circuit, and 31 is a lower threshold comparison circuit. In the above configuration, the image shifting circuit 29 shifts the image in the inspection target image data memory 10 according to the positional shift correction value obtained by the positional shift detection unit.

The degeneracy processing circuit 24 performs a process of narrowing an area corresponding to a bright area of the image data written in the reference image data memory 9. vice versa,
The expansion processing circuit 23 performs processing for thickening a bright area. As an example of the actual processing, the degeneration processing circuit 24 is expressed by the following Expression 6, and the expansion processing circuit 23 and the following Expressions 7.

## EQU6 ## f (x, y) = min {f (x-1, y-
1), f (x, y-1), f (x + 1, y-1), f
(X-1, y), f (x, y), f (x + 1, y), f
(X-1, y + 1), f (x, y + 1), f (x + 1,
y + 1)} However, the function min {} indicates that the minimum value of the listed variables is taken.

## EQU00007 ## f (x, y) = max {f (x-1, y-
1), f (x, y-1), f (x + 1, y-1), f
(X-1, y), f (x, y), f (x + 1, y), f
(X-1, y + 1), f (x, y + 1), f (x + 1,
y + 1)} However, the function max {} indicates that the maximum value among the listed variables is taken.

Expression 6 represents that the darkest brightness value is newly set as the brightness of the target pixel from the brightness of the target pixel and the pixels in the vicinity of the target pixel. Expression 7 represents that the brightest brightness value is newly set as the brightness of the target pixel from the brightness of the target pixel and the pixels in the vicinity of the target pixel. The lower limit threshold value setting circuit 26 has a lower limit value of the brightness variation set in advance by the parameter input unit 14, and the lower limit value is subtracted from the output of the degeneration processing circuit 24.
8 is written. Similarly, the upper threshold setting circuit 25
The upper limit value of the brightness variation is set in advance by the parameter input unit 14, and the upper limit value is added to the output of the expansion processing circuit 23 and written in the upper limit threshold image buffer 27.

In the lower threshold comparison circuit 31, the luminance value of the lower threshold image buffer 28 and the image data memory 10 to be inspected.
Are compared for each corresponding pixel, and when the brightness value of the inspection target image data memory 10 is lower than the brightness value of the lower limit threshold image buffer 28, it is determined that a defect has occurred. Further, the upper limit threshold comparison circuit 30 compares the luminance value of the upper limit threshold image buffer 27 and the luminance value of the inspection target image data memory 10 for each corresponding pixel, and the luminance value of the inspection target image data memory indicates the upper limit threshold image buffer. When the brightness value is higher than 27, it is determined that a defect has occurred.

Since the positional deviation correction process of the present invention is a correction for each pixel, the positional deviation of less than one pixel cannot be corrected even if the correction process is performed. Therefore, in the misregistration correction comparison unit 13, the degeneration processing circuit 24 and the expansion processing circuit 23
With this feature, erroneous detection was allowed in the edge part where the brightness change in the image is drastic. The configuration of the misregistration correction comparing unit 13 of the present invention is not limited to this embodiment, and the brightness of each pixel of the reference image memory and the brightness of each pixel of the image to be inspected can be simply calculated according to the misregistration value. It may be compared to.

[0041]

As described above, according to the present invention, even when there is a special tendency of misregistration or a special content of the pattern of the printed matter, the misregistration correction with a short processing time and high reliability is performed. Provided are an image inspection method and an apparatus to which the method is applied, which can inspect an image. Also,
According to the present invention, when the misalignment value is obtained, the evaluation values of the degree of coincidence are not separately obtained for the two directions of the first direction and the second direction, but the degree of coincidence is comprehensively calculated for the two directions. Get the evaluation value of. As a result, it is possible to obtain an accurate positional deviation value and perform optimal positional deviation correction.

[Brief description of drawings]

FIG. 1 is a flow chart showing an image inspection process in an image inspection method and apparatus according to the present invention.

FIG. 2 is a diagram illustrating a relationship between reference image data and corresponding inspection target image data when an evaluation value of the degree of coincidence is obtained by integrating two directions in the present invention.

FIG. 3 is a process in which an intersection pixel P (x, y) on a reference image sequentially moves corresponding pixels on a predetermined range pixel A of an inspection target image to evaluate the degree of coincidence over the entire predetermined range. FIG.

FIG. 4 is a schematic diagram showing an outline of a device configuration of the present invention.

FIG. 5 is a block diagram illustrating a configuration of a printed matter inspection device main body.

FIG. 6 is a block section showing a configuration of a positional deviation detection section.

FIG. 7 is a standard line segment position for m lines (m = 1 in FIG. 7) and an inspection target line segment position for n lines (n = 3 in FIG. 7).
FIG. 6 is a flow chart of a process of separately correcting the positional deviation in the vertical direction and the horizontal direction.

8 is a flow chart of a process of correcting the positional deviation in the horizontal direction of the present invention performed after the process of FIG.

FIG. 9 is a block diagram showing a configuration of a positional deviation correction comparison unit.

[Explanation of symbols]

 1 printing unit 2 printed matter 3 guide roller 4 light source 5 camera unit 6 camera control unit 7 rotary encoder 8 printed matter inspection apparatus main body 9 reference image data memory 10 inspection target image data memory 11 reference input command input unit 12 position shift detection unit 13 position shift Correction comparison unit 14 Parameter input unit 15 Intersection pixel designation unit 16 Predetermined range pixel designation unit 17 First data extraction unit 18 Second data extraction unit 19 First image data string memory 20 Second image data string memory 21 Evaluation numerical value calculation unit 22 Mid-value calculator 23 Expansion processing circuit 24 Degeneration processing circuit 25 Upper threshold setting circuit 26 Lower threshold setting circuit 27 Upper threshold image buffer 28 Lower threshold image buffer 29 Image shifting circuit 30 Upper threshold comparison circuit 31 Lower threshold comparison circuit

Claims (6)

[Claims] 1. An image inspection method for inspecting an inspection target image by comparing it with a reference image, wherein an intersection pixel designating process of designating one of the pixels forming the reference image as an intersection pixel, and a pixel forming the inspection target image. A predetermined range pixel designating process of designating a predetermined range of pixels, which is determined corresponding to the intersection pixel, as a predetermined range pixel, and a first direction parallel to the first direction including the intersection pixel and having a positional deviation to be corrected. And a second reference pixel data row which is data of a pixel row which is parallel to a second direction including the intersection pixel and in which positional deviation is to be corrected. A first data extraction step of extracting, and a first inspection target which is data of a pixel row including one pixel selected from the predetermined range pixels and in a direction parallel to the first direction in which the positional deviation is to be corrected. Pixel data A second row for extracting a data row and a second row of pixel data to be inspected, which is data of a row of pixels including the selected one pixel and in a direction parallel to the second direction in which positional deviation is to be corrected. A data extraction process, from the first reference pixel data sequence and the first inspection target image data, and the second reference pixel data sequence and the second inspection target image data to all image data An evaluation numerical value calculation step of obtaining an evaluation numerical value of the degree of coincidence based on the pixel, changing one pixel selected from the predetermined range pixels, repeating the second data extraction step and the correlation coefficient calculation step, A calculation iterative process that obtains evaluation numerical values corresponding to all pixels in a predetermined range, and one of the predetermined range pixels that gives the evaluation numerical value with the highest degree of coincidence among the evaluation numerical values obtained in the calculation repeated process. One pixel position data And a positional deviation value calculation process for obtaining a positional deviation value from the position data of the intersection pixel, and the positional deviation is corrected based on the positional deviation value obtained in the positional deviation value calculation step and compared with the reference image for inspection. An image inspection method comprising: a positional deviation correction comparison process for inspecting a target image; 2. An image inspection apparatus for inspecting an inspection target image by comparing with a reference image, an intersection pixel designating unit for designating one of the pixels forming the reference image as an intersection pixel, and a pixel forming the inspection target image. A predetermined range pixel designating means for designating a predetermined range of pixels, which is determined corresponding to the intersection pixel, as a predetermined range pixel; and a first direction including the intersection pixel and having a position deviation to be corrected, and a parallel direction. And a second reference pixel data row which is data of a pixel row which is parallel to a second direction including the intersection pixel and in which positional deviation is to be corrected. , A first data extraction unit for extracting, and a first inspection that is data of a pixel row that includes one pixel selected from the predetermined range pixels and is in a direction parallel to the first direction in which the positional deviation is to be corrected. Target pixel A second column for extracting a data column and a second pixel data column to be inspected, which is data of a pixel column that includes the selected one pixel and is in a direction parallel to the second direction in which the positional deviation is to be corrected. All the image data from the data extracting means, the first reference pixel data sequence and the first inspection target image data, and the second reference pixel data sequence and the second inspection target image data An evaluation numerical value calculating means for obtaining an evaluation numerical value of the degree of coincidence based on the predetermined range, one pixel selected from the predetermined range of pixels is changed, and the second data extracting means and the evaluation numerical value calculating means are repeated, A calculation repeating means for obtaining evaluation numerical values corresponding to all pixels in a predetermined range, and one selected from the predetermined range pixels giving the evaluation numerical value with the highest degree of coincidence among the evaluation numerical values obtained by the calculation repeating means. The position of one pixel A positional shift value calculating means for obtaining a positional shift value from the data and the position data of the intersection pixel, and correcting the positional shift based on the positional shift value obtained in the positional shift value calculation process and comparing it with a reference image. An image inspection apparatus comprising: a positional deviation correction comparing unit that inspects an image to be inspected. 3. The first direction, which is a direction in which positional deviation should be corrected.
3. The image inspection apparatus according to claim 2, wherein the direction of and the second direction are orthogonal to each other. 4. The image inspection apparatus according to claim 2, wherein the evaluation numerical value is a correlation coefficient. 5. The image inspection apparatus according to claim 2, wherein the evaluation numerical value is a sum of absolute values of differences. 6. The image inspection apparatus according to claim 2, wherein the evaluation value is a sum of squared differences.