JPH0792103A - Print inspection device - Google Patents

Abstract

(57) [Abstract] [Purpose] To provide a printed matter inspection apparatus that classifies print defects of printed matter so that the state of the defects can be easily understood and outputs appropriate countermeasures to a printing machine. [Structure] A part for inputting image data to be inspected, a part for comparing standard image data with the input image data, and a defect candidate, a degree, a connected pixel component, an area, a directivity, etc. are judged from the comparison result. Part, a part that determines the type of defect from the plurality of elements, a part that determines whether or not to detect a defect candidate as a defect based on the defect type and the area of the print defect, and a type of the printing machine based on the defect type. A printed matter inspection device having means for selecting countermeasure information.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an apparatus for inspecting printed matter, and more particularly to an apparatus for discriminating the type of defects on printing.

[0002]

2. Description of the Related Art As a method of inspecting a printed matter, when the difference between the read image data of the printed matter and a reference value exceeds a set value, it is judged as an error point, and a printing defect is determined based on the number of the error points. A method for determining is known. There is also known a method of detecting a printing defect by determining a difference value between read image data and reference data for each predetermined pixel at a predetermined determination level.

Furthermore, in the method disclosed in Japanese Patent Laid-Open No. 2-20348, the detected signal is compared with the reference signal and white difference is determined if there is a difference of a predetermined value or less, and black loss is determined if there is a difference of a predetermined value or more. It shows how to do it.

[0004]

A defect detection method based on density comparison, which is widely used as a conventional printed matter inspection method, determines whether printing is good or bad based on a physical judgment standard. There is a problem that it is difficult to obtain inspection results that match human judgment such as oil stains and roller scratches.

As described above, various improvements have been made to the inspection method by comparing these concentrations. However, these methods have the following problems. That is, in the method of detecting the printing defect by determining the difference value between the read image data and the reference data at a predetermined determination level for each predetermined pixel,
Although there is a feature that the threshold value for determination can be changed for each pixel, there is no mechanism for determining this value, so it takes time for humans to set the threshold value. That is, the inspection is performed by physical judgment, and a person adjusts the threshold value, that is, the physical quantity by trial and error.

Further, as disclosed in Japanese Patent Application Laid-Open No. 2-20348, the read image signal and the reference signal are compared, and if there is a difference of a predetermined value or less, white loss, and if there is a difference of a predetermined value or more, black loss. In the method of determining, the physical and simple determination criteria are used. Therefore, with such a method, it is not possible to know the detailed state of the printing defect such as the degree, position and meaning of the defect.

As described above, the conventional inspection apparatus for printed matter is performed only by determining a defect based on a simple physical quantity. Regarding the correspondence relationship between the physical quantity and the type of defect and the correspondence relationship between the defect and its print area, It has no means of storing and utilizing information that humans can judge in detail. Further, all of the methods are inventions relating only to print defect inspection, and there is no invention relating to automation of work for taking countermeasures to a printing machine or the like based on the result of the print defect inspection.

[0008]

A printed matter inspection apparatus according to the present invention comprises a portion for reading a printed image of a printed matter using a CCD or the like, a portion for comparing the printed image with a standard printed image of the printed matter, and the comparison. It is provided with a part for extracting a plurality of features of the printing defect from the comparison result obtained by the part and a part for judging the type of the printing defect from the features of the printing defect.

[0009]

The printing defects of the printed matter are classified into types of defects that can be easily understood by humans. Furthermore, depending on the type of defect,
An appropriate countermeasure is output to the printing device.

[0010]

1 is a block diagram showing an example of a printing inspection apparatus according to the present invention. As shown in FIG. 1, the print inspection apparatus according to the present invention includes a sensor 101, an image input unit 102, an image storage unit 103, an alignment unit 105, and a reference image storage unit 1.
04, data comparison unit 106, defect candidate extraction unit 107, difference code extraction unit 108, difference absolute value extraction unit 109, defect connected component extraction unit 110, defect direction feature extraction unit 111, defect area extraction unit 112, defect type determination unit. 113, a defect determination unit 114, a determination result output unit 115, a countermeasure determination unit 118, a printing press countermeasure output unit 116, a display unit 117, a parameter input / output unit 120, an editing unit 119, and a data storage unit 121.

The inspection object P is, for example, a printed matter mainly composed of a line drawing as shown in FIG. 2, and the printed matter passes through a sensor 101 such as a CCD by a transport mechanism (not shown) to collect image data. . Sensor 101
The image output signal of the image input unit 102 includes an A / D converter.
A / D conversion is performed and the digital image data is recorded in the image storage unit 103. In the image storage unit 103, data is recorded in the memory in the form as shown in FIG. 3 or 4. As shown in the figure, the image signal has a size of 1024 pixels in the horizontal direction and 512 pixels in the vertical direction, and each pixel is recorded as image data composed of 256 gradations.

The image data of the inspection object P recorded in this way is corrected by the alignment section 105 for each sample. This is executed by moving the print image in parallel and changing the origin 0o to 0n as shown in the conceptual diagram of FIG. The alignment unit 105 is specifically realized by the configuration shown in FIG. The buffer control unit 601 outputs the address signal ADR1 to the image storage unit 103, reads the image data from the image storage unit 103, simultaneously transmits the image data to the binarization processing unit 603, and writes the image data to the image buffer 602. . For the image data as shown in FIG. 4 read from the image storage unit 103, the binarization processing unit 603 sets a threshold value at a constant value THR (for example, 80H = 128) in order to extract a print portion having a small pixel value. Perform processing. As a result, as shown in FIG. 7, the image data is converted into a binary image in which the print portion has a pixel value “1” and the paper / background has “0”. The unit 604 and the horizontal pixel accumulator 605 calculate accumulated data in each direction as indicated by P1 and P2 in FIG. 7, respectively. The start points of the accumulated data P1 and P2 are detected by the start point detection units 606 and 607, respectively, and start point coordinate data X0 and Y0 are obtained. Then, the image data address conversion unit 608 outputs (0, Y0) to (0, Y0) for the address signal ADR2 output from the buffer control unit 601.
0) and a new address signal ADR
3 is output. Specifically, the conversion shown in the following equation is performed using the address ADR2 of the memory storing the data of the coordinate value (xs, ys) to generate ADR3.

ADR3 = ADR2-Y0 × 1024-X0 (1) According to this address signal ADR3, the image buffer 60
The image data read from No. 2 is the image buffer 609.
Written in. For the image in FIG. 4, the alignment unit 1
When the alignment is performed by 05, the image data is stored in the image buffer 609 in the data format shown in FIG.

The image data shown in FIG. 8 whose alignment has been completed in the data comparison unit 106 is the reference image storage unit 1
The reference image data written in 04 is compared with the reference image data shown in FIG. 9 to obtain the difference in each pixel value. The data comparison unit 106 is specifically realized by the configuration shown in FIG. The buffer control unit 1001 outputs the address signal ADR4, and simultaneously reads the input image data from the alignment unit 105 and the reference image data from the reference image storage unit 104 pixel by pixel. The difference between the two read image data is calculated by the difference calculator 1002 for each pixel, and the result is written in the image buffer 1003. When the difference between the input image in FIG. 8 and the reference image data in FIG. 9 is calculated, two-dimensional data having the difference value as a pixel value as shown in FIG. 11 is obtained in the same form as the image data. The data is stored in the image buffer 1003. The differential image data in FIG. 11 is stored in the form of 8 bits per pixel, the absolute value of which is represented by the lower 7 bits and the code is represented by the 8th bit.

With respect to the difference image data calculated in the data comparison unit 106 and stored in the form of FIG. 11, the defect candidate extraction unit 107, the difference code extraction unit 108, the difference absolute value extraction unit 109, and the defect connected component extraction. The six processing units, that is, the unit 110, the defect direction feature extraction unit 111, and the defect area extraction unit 112 extract the feature amount related to the defect.

The defect candidate extraction unit 107 extracts pixels whose value is equal to or more than a constant value THR2 (for example, 5) or less than a constant value THR3 (for example, -5) from the difference data with respect to the reference image, and at the same time, the read pixel is read. The number of extracted pixels in the area is measured by dividing the area into small areas of 5 × 5 pixels. The defect candidate extraction unit 107 is specifically realized by the configuration shown in FIG. As shown in FIG. 12, the defect candidate extraction unit 107 reads out the difference image data stored in the data comparison unit 106 by the address signal ADR5 output from the buffer control unit 1201 and outputs the difference image data to the comparator 120.
2, when the data value is THR2 or more, the comparator 120
In No. 3, when the data value is THR3 or less, "1" is output. The OR operation circuit 1204 uses the two comparators 12
The logical sum of the outputs of 02 and 1203 is calculated. This logical sum data is written in the image buffer 1207 in the form as shown in FIG. Here, in FIG. 13, blanks are numerical values ”
0 ". The logical sum data is simultaneously transmitted to the memory data addition unit 1205. The address conversion unit 1206 outputs the address ADR5 output from the buffer control unit 1201.
To an address corresponding to every 5 pixels in the horizontal and vertical directions, and the memory data adding unit 12
05 and 1208 are controlled. Memory data addition unit 12
05 counts the number of pixels of logical sum “1” in the 5 × 5 small area, and records the counting result in the image buffer 1208. That is, the data shown in FIG. 13 is divided into small areas of every 5 × 5 pixels as shown by the solid line in FIG. 14, and the number of pixels having the value “1” in the small area is represented by an image having a data structure as shown in FIG. It is stored in the buffer 1208.

The differential code extraction unit 108 extracts codes of pixel values whose absolute value is a certain value or more, for example, 5 or more, with respect to the differential image data FIG. Specifically, the differential code extraction unit 108 is realized by the configuration shown in FIG. Address signal A output from the buffer control unit 1201 (FIG. 12)
The difference image data is read from the data comparison unit 106 according to DR5, and when the comparator 1601 has a pixel value of THR2 (for example, 5) or more, the comparator 1602 outputs THR3.
When the pixel value is (for example, -5) or less, "1" is output. The logical sum of the outputs of the two comparators 1601 and 1602 is calculated by a logical sum calculator 1603,
It is stored in the image buffer 1604 together with the output of the comparator 1601 as bit 0 and bit 1, respectively. As a result, the extraction result of the differential code extraction unit 108 for the differential image data of the data comparison unit 106 shown in FIG.
18 corresponding to the plus and minus signs shown in FIG.
"3 (binary 11)" or "1 (binary 0
1) ”becomes the data represented by the value.
The image buffer 1604 stores the image data in which the differential code is represented by the value indicated by 8. Note that, in FIG. 18, the blank column represents the pixel value “0”.

The difference absolute value extraction unit 109 obtains the absolute value of each pixel for the difference image data output from the data comparison unit 106 as shown in FIG. The absolute difference value extraction unit 109 is specifically realized by the configuration shown in FIG. The signal read from the data comparison unit 106 according to the address signal ADR5 output from the buffer control unit 1201 (FIG. 12) causes the absolute value calculator 1901 to forcibly set the eighth bit of each data to “0”. As a result, the absolute value is converted and stored in the image buffer 1902. For example, the data shown in FIG.
The data is converted into data such as and stored in the image buffer 1902. In the defect connected component extraction unit 110, the data comparison unit 1
Defects are extracted from the difference image data output from 06 as shown in FIG. 11, and the connected components thereof are detected. The connected component extracting unit 110 is specifically realized by the configuration shown in FIG. In accordance with the address signal ADR5 output from the buffer control unit 1201 (FIG. 12), the signal read from the data comparison unit 106 is the threshold value THR in the comparator 2101.
When (for example, 5) or more, the threshold value TH is set in the comparator 2102.
When R (for example, -5) or less, it is converted to "1". After that, the logical sum data of the outputs of the two comparators 2101 and 2102 is obtained by the logical sum calculator 2103 and stored in the image buffer 2104. Image data is stored in the image buffer 2104 with a data structure as shown in FIG. After the writing to the image buffer 2104 is completed, the CPU 2105 controls the image buffer 2104. The CPU 2105 performs processing according to the flows shown in FIGS. 22 and 23 written in the program memory 2106 to obtain the connected component of the binary image written in the image buffer 2104. As shown in FIG. 22, the binary image written in the image buffer 2104 is expressed as f (i, j) as the input image, and the image buffer 2
The label image output to 108 is represented as l (i, j) (ST1). The term "label" used herein is a number for distinguishing a defective image composed of defective pixels connected to each other, and each pixel forming one connected defective pixel has the same number (label). ) Is attached.
Further, a label table for obtaining correspondence of label values is secured in the work memory 2107 in the form of FIG. 24, and the initial value of f (i, j) is set to 0. For a binary image f (i, j), x =
1, the pixel is checked from y = 1, and if the pixel value is "1", S
Go to T5. In ST5, the label table value T (l (i, j)) is referenced with respect to the label values of the five neighboring pixels shown in FIG. 25, and (1) the number of kinds of values in the label table is n, and (2) is the minimum. The value L1 in the label table and (3) the next smallest value L2 in the label table (there are at most two of these values) are obtained. In the subsequent ST6, depending on the number n of kinds of values in the label table, ST7, S
The process branches to three of T8 and ST9. If n = 0,
This means that a new label is generated at the position (x, y), so the connected component number λ is increased by 1, λ is substituted in the label table T (λ), and the label image l (x, y) is added. ) Is substituted into), and label information is assigned (ST8). Also n =
In the case of 1, since (x, y) is a state in which neighboring components are dotted, the minimum label table value L1 is assigned to the label image l (x, y) and integrated (ST7). When n = 2, FIG.
Since it is shown that there are two components to be integrated within the neighborhood area of 5, the label image l of the position of interest is
The value L1 of the smaller label table is substituted for (x, y), and all other regions that take L2 are replaced with L1 (S
T9). By performing this process on the entire image, labeling is completed when ST13 is completed. Further, the values of T (i) having a missing number are rearranged into a serial number (ST1
4) By replacing the label images with the rearranged values in the label table, the label images in which the connected components are sequentially numbered from 1 are obtained. For example, when the processing shown in FIGS. 22 and 23 is applied to the binary image data recorded in the image buffer 2104 as shown in FIG.
Label image data as shown in 7 is obtained. Here, the blank in FIG. 27 represents the numerical value “0”. The processing result is stored in the image buffer 2108.

The defect direction feature extraction unit 111 extracts the directionality of the defect from the differential image data as shown in FIG. 11 output from the data comparison unit 106. The defect direction feature extraction unit 111 is specifically realized by the configuration shown in FIG. According to the address signal ADR5 output from the buffer control unit 1201 (FIG. 12), the difference image data read from the data comparison unit 106 is equal to or greater than the threshold value THR2 (for example, 5) in the comparator 2701, and the threshold value in the comparator 2702. When THR3 (for example, -5) or less, it is converted to "1". After that, the two comparators 2701
And OR 2702 outputs OR data and outputs the OR data 27
03, and stores it in the image buffer 2704. The image buffer 2704 is stored with a data structure as shown in FIG. After the writing to the image buffer 2704 is completed, the CPU 2705 causes the image buffer 2704 to
To control. The CPU 2705 has a program memory 27.
The processing is performed according to the processing flow shown in FIGS. 29 and 30 written in 06, and the characteristic of the direction component of the binary image written in the image buffer 2704 is obtained. Figure 2
As shown in FIG. 9, initially, the binary image data written in the image buffer 2704 is f (i, j), and the image data output to the image buffer 2708 having a pixel value as a pixel value is d (i, j). Define and start processing (ST2
1). Then, for each pixel of the image,
The product-sum calculation values with the weights of the four types of neighboring pixels shown in FIGS. 33 and 34 are obtained (ST25 to ST30). The four parameters of FIG. 31, FIG. 32, FIG. 33, and FIG. 34 are for detecting the vertical direction component, the horizontal direction component, the leftward diagonal direction, and the left downward diagonal direction component, respectively. The sum of products of these four types of parameters and pixels is obtained as m1, m2, m3, and m4, and it is determined in ST31, ST33, ST34, and ST35 whether or not each takes a threshold value THR4 (for example, 3) or more. If you do, 1 (vertical) 2 (horizontal), 3
The values of (upper left diagonal) and 4 (lower left diagonal) are d (x,
y) (ST39). By performing this processing on the entire image, the binary image as shown in FIG. 13 stored in the image buffer 270 is converted into the image data as shown in FIG. 36 showing the directional characteristics as shown in FIG. To be done. Here, in FIG. 36, the blank represents the numerical value “0”.

The defect area extraction unit 112 is a data comparison unit 1
The area of each of the connected components is calculated for the difference image data as shown in FIG. The defect area extraction unit 112 is specifically realized by the configuration shown in FIG. According to the address signal ADR5 output from the buffer control unit 1201 (FIG. 12), the data comparison unit 106
The signal read out from the
When R2 (for example, 5) or more, the comparator 3602 converts it to "1" when it is less than or equal to the threshold value THR3 (for example, -5). After that, the logical sum data of the outputs of the two comparators 3601 and 3602 is obtained by the logical sum calculator 3603 and stored in the image buffer 3604. Image buffer 3604
In FIG. 13, image data is stored with a data structure as shown in FIG. After the writing to the image buffer 3604 is completed, the CPU 3605 controls the image buffer 3604. The CPU 3605 has a program memory 3606.
38, 39, 40, and 41 written in FIG. 38, the connected components of the binary image written in the image buffer 3604 are obtained, and the area of each connected component is obtained. As shown in FIGS. 22 and 23, S
The labeling process from T44 to ST63 is the same as that of the defective connected component extracting unit 111. On the other hand, the number of pixels of each label is measured up to the maximum label value LM obtained in ST57 (ST64 to ST72). At the same time, the image data is converted into image data as shown in FIG. 42 in which area values are assigned to the respective connected components (ST73 to ST79). As a result, the binary image data recorded in the image buffer 3604 is converted into the image data having the pixel value of the area of the connected component as shown in FIG. 42 and the corresponding data of the label area shown in FIG. It is written in the buffer 3608 and the data buffer 3609. Here, in FIG. 42, the blank represents the numerical value “0”.

In this way, six types of feature extraction processing are performed on the difference image data output from the data comparison section 106, and the results are transferred to the defect processing determination section 113.

The defect type discriminating unit 113 estimates the type of defect from the characteristic amount and its degree using the plurality of characteristic amounts thus extracted as input data and outputs it. The defect type determining unit 113 is realized by the configuration shown in FIG. The data from the six extractors, which is the input data, is transmitted via the transceivers 4101 to 4108. This is because the CPU 4109 uses the transceiver 4
It is realized by reading out necessary data from the image buffers or the data buffers of the six extraction units via 101 to 4108. CPU 4109 is a program memory 41
The process is performed according to the procedure shown in FIGS. As shown in FIGS. 45 and 46, with respect to the two-dimensional data as shown in FIG. 14 or FIG. 15 in which the number of defect extraction pixels in the small area stored in the defect candidate extraction unit 107 is used as the data, the value is If it is not 0, five pieces of information are checked for the small area and information regarding the type of defect is obtained.

As shown in FIG. 45, in ST103, the first
As the second detection amount, the feature amount data (FIG. 18) stored in the differential code extraction unit 108 is read out via the transceiver 4103, and the plus or minus of the one having the larger number of pixels in the small region of 5 × 5 pixels is read. Select either code. Feature quantity / defect type correspondence table 4112 (FIGS. 47 and 48) in which correspondence data of defect feature quantities and their values are described.
And the feature amount are collated with each other to obtain a defect type candidate D1 (ST104).

As the second detection amount, in ST105, the absolute difference value extraction unit 1 is operated via the transceiver 4104.
The feature amount data (FIG. 20) stored in 09 is read, and the largest absolute value is detected in the 5 × 5 small area. Feature quantity / defect type correspondence table 4112 (FIGS. 47 and 48) in which correspondence data of defect feature quantities and their values are described.
And the feature amount are collated with each other to obtain a defect type candidate D2 (ST106).

As the third detected amount, in ST107, the feature amount data (FIG. 27) stored in the defective connected component extraction unit 110 is read out via the transceiver 4105, and it is different in a 5 × 5 small area. Detect the number of connected components. A feature amount / defect type correspondence table 4112 (FIGS. 47 and 4) in which correspondence data of defect feature amounts and their values are described.
8) and the feature amount are collated to obtain a defect type candidate D3 (ST108).

As the fourth detection amount, in ST109, the data (FIG. 35) stored in the defect direction feature extraction unit 111 is read out via the transceiver 4106, and the direction feature having the largest number in the small area is vertically extracted. Sideways, rising to the left,
Select either diagonally to the lower left. The feature quantity / defect type correspondence table 4112 (FIGS. 47 and 48) in which the correspondence data of the feature quantity of the defect and its value are described is collated with the feature quantity to obtain the defect kind candidate D4. (ST110).

As the fifth detection amount, in ST111, the defect area extraction unit 11 is transmitted via the transceiver 4107.
The data (FIG. 42) stored in No. 2 is read out, and the largest area value among them is detected. The feature quantity / defect type correspondence table 4112 (FIGS. 47 and 48) in which the correspondence data of the feature quantity of the defect and its value are described is collated with the feature quantity to obtain the defect type candidate D5 (ST112). . The logical sum of the obtained five defect type candidates D1, D2, D3, D4, D5 is set as the defect type of the small area (S
T113). Here, the feature amount /
The defect type correspondence table 4112 describes the name and degree of the defect, but the logical OR is simply taken for the defect name.
If there is no information about the degree, do not use it as a logical sum. For example, two logical sums of fading (degree: dark) and fading (degree: unspecified) result in fading (degree: dark).
If the pixel value of the small area data recorded in the defect candidate extraction unit 107 is 0, the detection process is bypassed and "no defect" is set (ST102). If this processing is performed on all the small area data, the two-dimensional array data having a print defect as shown in FIG. 49 can be obtained as a result. An example of another defect type determination unit 113 will be described. This is realized by the configuration shown in FIG. 44 as in the first example. In the feature quantity / defect type correspondence table 4112, a range of feature quantities corresponding to defect types as shown in FIG. 59 is designated.
The type of defect is output for each obtained feature amount.

Subsequently, the defect determining section 114 determines the presence or absence of a two-dimensional array data defect as shown in FIG. 49 in which data indicating the type of defect is described for each 5 × 5 small area. The defect determination unit 114 is realized by the configuration shown in FIG. The output data of the defect type determination unit 113 is the transceiver 4701.
It is input by the CPU 4703 via. CPU4703
51 stored in the program memory 4704.
Processing is performed according to the procedure shown in. The coordinate / area correspondence database 4702 is for the inspection object as shown in FIG. 2 and for each partial print area preset as shown in FIG. 52, the range of each x coordinate and y coordinate and the print area. The relationship between the name and the area number is described as shown in FIG. Also, in the print defect database 4706, as shown in FIG. 54, the reference information for determining a print defect is the defect type obtained by the defect type determining unit for each print region, and the small region of the defect candidate included in the print region. It is described in terms of numbers. As shown in FIG. 54, the allowable lower limit value of each defect type is different between the various regions in the upper left corner and the central region. As shown in FIG. 51, with respect to the two-dimensional data (FIG. 49) in which the defect type is described for each small area output from the defect type determination unit, for each characteristic print as shown in FIG. Processing is performed on each of the divided areas. ST
At 122, the type of defect and the number of the small areas are obtained for the small areas included in each print area, as indicated by the broken line in FIG. 55, using the information in the coordinate / area correspondence database 4702 (FIG. 53). Then, in ST123,
Printing defect database 47 based on the result of ST122
It is determined whether the defect is a defect to be detected using the reference information 06 (FIG. 54). This process is performed for each print area shown in FIG. 50, and the determination result is output to the output circuit 4708 and the data buffer 4709.

Finally, the countermeasure determining section 118 determines the defect type determining section 1 for the print defect determined by the defect determining section 114.
Based on the information of 13, the measure information for the printing machine is determined. The countermeasure determination unit 118 is realized by the configuration shown in FIG. The transceiver 5301 obtains defect information from the defect type determining unit 113, and the transceiver 5302 obtains defect information from the defect determining unit 114. The CPU 5303 determines the correspondence information of the printing machine according to the processing procedure of FIG. 57 written in the program memory 5304. Here, in the printing press countermeasure information database 5306, defect types and countermeasure information for the printing press are described for each area as shown in FIG. As shown in FIG. 57, the defect determination unit 114
The presence / absence of a defect is determined for each small area using the defect determination data (FIG. 54) output from (ST132), and the information should be output to the printing press using the information in the printing press countermeasure information database 5306 (FIG. 58). Information is selected (ST133).
This processing is performed for each print area shown in FIG. 52, and the determination result is output from the output circuit 5307.

The determination result output from the defect determination section 114 is output from the determination result output section 115 as a system selection signal and, at the same time, is output to the display section 117. The printing press countermeasure information that is also output from the countermeasure determination unit 118 is output from the printing press countermeasure output unit 116 to the display unit 117 to alert the operator, and the cause of automatic adjustment is the printing adjustment output to the printing press. Output.

Defect determination section 113, defect determination section 11
4. The parameters of the countermeasure determining unit 118 are controlled via the parameter input / output unit 120, and the parameters are adjusted while reading data from the data storage unit 121 and displaying the image as shown in FIG. 2 by the editing unit 119. can do.

Further, in the above-mentioned invention, the defect type is discriminated in small area units as shown in FIG. 14, but the defect type discrimination can be conducted in different units. FIG. 60 shows a second embodiment of the present invention in which a defect is determined for each connected component of pixels. According to FIG. 60, the present invention relates to a sensor 101, an image input unit 10
2, image storage unit 103, alignment unit 105, reference image storage unit 104, data comparison unit 106, defect candidate extraction unit 1
07, difference code extraction unit 108, difference absolute value extraction unit 10
9, defect direction feature extraction unit 111, defect area extraction unit 11
2. Defect type determination unit 113, defect determination unit 114, determination result output unit 115, countermeasure determination unit 118, printing machine countermeasure output unit 116, display unit 117, parameter input / output unit 120, editing unit 119, and data storage unit 121. Composed of. The defect candidate extraction unit 107 has the same configuration as the defect connected component extraction unit 110 in FIG. 1 that extracts connected components. afterwards,
For each connected component, the difference code extraction unit 108 shows the difference code, the difference absolute value extraction unit 109 shows the difference absolute value, the defect direction feature extraction unit 111 shows the defect direction, and the defect area extraction unit 112 shows the area. The defect type determination unit 113 extracts the extracted components for each connected component, and the defect determination unit 114 determines each connected component based on the position. Each of these processing units has the same configuration as that of the first embodiment described above. Here, since the degree of the defect is discriminated and comprehensively discriminated for each connected component, the feature amount / defect type correspondence table in the defect type discriminating unit 113 is slightly different from FIG. 42, FIG. 48, or FIG. Further, the print defect database in the defect determination unit 114 shown in FIG.
The printing press countermeasure determination database in the countermeasure determining unit 118 shown in FIG. 58 is also slightly different from that in the first embodiment.
In any correspondence table and database, the editing unit 119
Will be corrected to the optimum data each time.

Further, the gist of the invention does not change even if other related feature amounts are used among the feature amounts. For example, in combination with the area indicating the spread of the defect, the vertical length and the horizontal length of the defect are obtained by projection by, for example, a binary image and used for the determination, or the feature in which the same defect is scattered exists within a certain distance, for example. It is also possible to obtain the number and use it for the determination.

The present invention is not limited to the above-described embodiments, and it goes without saying that various modifications can be made without departing from the spirit of the invention.

[0035]

As described above, the print inspection apparatus according to the present invention aligns an input image to be inspected, detects a plurality of characteristics from data obtained by comparing standard data with the input image, and It is possible to extract the type and degree of the printing defect from the characteristic amount, determine the printing defect to be dealt with from the extracted type and degree of the printing defect, and output the printing press countermeasure information from these information.

[Brief description of drawings]

FIG. 1 is a block diagram showing the configuration of a print inspection apparatus according to an embodiment of the present invention.

FIG. 2 is a diagram showing an example of a printed matter to be inspected according to an embodiment of the present invention.

FIG. 3 is a diagram showing a form of image data stored in an image storage unit according to an embodiment of the present invention.

FIG. 4 is another diagram showing a form of image data stored in an image storage unit according to an embodiment of the present invention.

FIG. 5 is a conceptual diagram showing an origin for aligning positions by the alignment unit according to the embodiment of the present invention.

FIG. 6 is a block diagram showing a configuration of an alignment unit according to an embodiment of the present invention.

FIG. 7 is a diagram showing an example of data accumulated by the alignment unit according to the embodiment of the present invention.

FIG. 8 is a diagram showing an example of an image that is aligned by the alignment unit according to the embodiment of the present invention.

FIG. 9 is a diagram showing an example of reference image data stored in a reference image storage unit according to an embodiment of the present invention.

FIG. 10 is a diagram showing a configuration of a data comparison unit according to an embodiment of the present invention.

FIG. 11 is a diagram showing an example of a processing result of a data comparison unit according to an embodiment of the present invention.

FIG. 12 is a diagram showing a configuration of a defect candidate extraction unit according to an embodiment of the present invention.

FIG. 13 is a diagram showing an example of pixels extracted by a defect candidate extraction unit according to an embodiment of the present invention.

FIG. 14 is a diagram showing an example of a small area determined by a defect candidate extraction unit according to an embodiment of the present invention and the number of extracted pixels.

FIG. 15 is a diagram showing an example of a processing result of a defect candidate extraction unit according to an embodiment of the present invention.

FIG. 16 is a diagram showing a configuration of a differential code extraction unit according to an embodiment of the present invention.

FIG. 17 is a diagram showing an example of code data extracted by a differential code extraction unit according to an embodiment of the present invention.

FIG. 18 is a diagram showing an example of a processing result of a differential code extraction unit according to an embodiment of the present invention.

FIG. 19 is a diagram showing an example of a difference absolute value extraction unit according to an embodiment of the present invention.

FIG. 20 is a diagram showing an example of a processing result of a difference absolute value extraction unit according to an embodiment of the present invention.

FIG. 21 is a diagram showing a configuration of a defect connected component extracting unit according to an embodiment of the present invention.

FIG. 22 is a diagram showing a processing procedure performed by a defect connected component extraction unit according to an embodiment of the present invention.

FIG. 23 is a diagram showing a processing procedure performed by a defect connected component extraction unit according to an embodiment of the present invention.

FIG. 24 is a diagram showing an example of a label table performed by the defect connected component extraction unit according to an embodiment of the present invention.

FIG. 25 is a diagram showing a neighborhood area of an input image of interest in the defect connected component extraction unit according to an embodiment of the present invention.

FIG. 26 is a diagram showing a neighborhood area of a label image of interest in a defect connected component extraction unit according to an embodiment of the present invention.

FIG. 27 is a diagram showing an example of the processing result of the defect connected component extraction unit according to an embodiment of the present invention.

FIG. 28 is a diagram showing a configuration of a defect direction feature extraction unit according to an embodiment of the present invention.

FIG. 29 is a diagram showing a processing procedure performed by a defect direction feature extraction unit according to an embodiment of the present invention.

FIG. 30 is a diagram showing a processing procedure performed by a defect direction feature extraction unit according to an embodiment of the present invention.

FIG. 31 is a diagram showing parameters for detecting a vertical defect according to an embodiment of the present invention.

FIG. 32 is a diagram showing parameters for detecting a lateral defect according to an embodiment of the present invention.

FIG. 33 is a diagram showing parameters for detecting a defect in a diagonally upward left direction according to an embodiment of the present invention.

FIG. 34 is a diagram showing parameters for detecting a defect in a diagonally downward left direction according to an embodiment of the present invention.

FIG. 35 is a diagram showing an example of direction data detected by a defect direction feature extraction unit according to an embodiment of the present invention.

FIG. 36 is a diagram showing an example of the processing result of the defect direction feature extraction unit according to an embodiment of the present invention.

FIG. 37 is a diagram showing a configuration of a defect area extraction unit according to an embodiment of the present invention.

FIG. 38 is a diagram showing a processing procedure performed by the defect area extraction unit according to the embodiment of the present invention.

FIG. 39 is a diagram showing a processing procedure performed by a defect area extraction unit according to an embodiment of the present invention.

FIG. 40 is a diagram showing a processing procedure performed by a defect area extracting unit according to an embodiment of the present invention.

FIG. 41 is a diagram showing a processing procedure performed by the defect area extraction unit according to the embodiment of the present invention.

FIG. 42 is a diagram showing an example of the processing result of the defect area extracting unit according to an embodiment of the present invention.

FIG. 43 is a diagram showing another example of the processing result of the defect area extracting unit according to the embodiment of the present invention.

FIG. 44 is a diagram showing the configuration of a defect type determination unit according to an embodiment of the present invention.

FIG. 45 is a diagram showing a processing procedure of a defect type determination unit according to an embodiment of the present invention.

FIG. 46 is a diagram showing a processing procedure of a defect type determination unit according to an embodiment of the present invention.

FIG. 47 is a diagram showing an example of a feature quantity / defect type correspondence table according to an embodiment of the present invention.

FIG. 48 is a diagram showing an example of a feature quantity / defect type correspondence table according to an embodiment of the present invention.

FIG. 49 is a diagram showing an example of a processing result of the defect type determination unit according to the embodiment of the present invention.

FIG. 50 is a diagram showing a configuration of a defect determination unit according to an embodiment of the present invention.

FIG. 52 is a diagram showing a processing procedure of a defect determining section according to an embodiment of the present invention.

FIG. 52 is a diagram showing an example of a print area used by a defect determination unit according to an embodiment of the present invention.

FIG. 53 is a diagram showing an example of a coordinate / region correspondence database of a defect determination unit according to an embodiment of the present invention.

FIG. 54 is a diagram showing an example of a printing press correspondence information database of a defect determination unit according to an embodiment of the present invention.

FIG. 55 is a diagram showing the correspondence between the print area and the small area of the defect determination unit according to the embodiment of the present invention.

FIG. 56 is a diagram showing a configuration of a countermeasure determining unit according to an embodiment of the present invention.

FIG. 57 is a diagram showing a processing procedure of a countermeasure determining unit according to an embodiment of the present invention.

FIG. 58 is a diagram showing an example of a print defect database of a countermeasure determining unit according to an embodiment of the present invention.

FIG. 59 is a diagram showing an example of a feature amount / defect type correspondence table according to an embodiment of the present invention.

FIG. 60 is a block diagram showing the arrangement of a print inspection apparatus according to another embodiment of this embodiment.

[Explanation of symbols]

P ... Printed matter, 101 ... Sensor, 102 ... Image input section, 1
03 ... image storage unit, 104 ... reference image storage unit, 105 ...
Alignment unit, 106 ... Data comparison unit, 107 to 112
... feature extraction unit, 113 ... defect type determination unit, 114 ... defect determination unit, 115 ... determination result output unit, 116 ... printing press countermeasure output unit, 117 ... display unit, 118 ... countermeasure determination unit.

Claims (4)

[Claims] 1. A printed matter inspection apparatus for inspecting a printed matter for printing defects, comprising means for reading a printed image of the printed matter, and means for comparing image data output from the reading means with standard image data of the printed matter. At least one feature extraction unit that extracts the feature of the print defect from the comparison result obtained from the comparison unit; and a unit that determines the type of the print defect from the feature of the print defect output from the feature extraction unit. A printed matter inspection apparatus comprising: 2. A unit that divides the print image into a plurality of areas and sets different judgment criteria for each of the divided areas; and the judgment criteria set in the divided areas including the print defect. Based on the evaluation of the type of printing defects,
The printed matter inspection apparatus according to claim 1, further comprising: a unit that determines whether or not the defect is a defect to be dealt with. 3. A means for generating countermeasure information for a printing press to deal with the printing defect based on an evaluation result output from the evaluation means, further comprising: The printed matter inspection device described. 4. A printed matter inspection apparatus for inspecting a printed matter for printed matter, a means for reading a printed image of the printed matter, a means for converting a signal output from the reading means into digital image data, and a standard for the printed image. First storage means for storing image data; means for comparing the standard image data in the first storage means with image data output from the conversion means; and data from the comparison means. Means for extracting feature amount data for determining a print defect; second storage means for storing a plurality of reference feature amount data indicating the print defect for each type of print defect; By comparing the feature amount data with the plurality of reference feature amount data stored in the second storage unit, the print defect of the printing unit read by the reading unit is detected. Printed matter inspection apparatus characterized by comprising a means for determining.