Defect analysis method and defect analysis system of printing surface

Abstract

To provide a defect analysis method and a defect analysis system of a printing surface in which more secure, accurate and efficient analysis for causes of a defect can be performed.SOLUTION: A defect analysis method comprises: identifying a defect and a position thereof from image information of a printing surface 10 that is obtained by first imaging means 11; estimating causes of a defect on the basis of a shape and color density of the defect; identifying an inspection area 101 that is composed of dot images which is appropriate to analyze the estimated causes in detail; and analyzing causes of the defect in detail on the basis of the dot image in which the inspection area 101 is imaged by second imaging means 12 to acquire.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a method and system for analyzing defects in printed matter. [Background technology]

[0002] Conventionally, an inspection device has been used to detect defects and their locations in printed workpieces, and either mark the locations or store the information on the locations. After printing of a particular lot is completed, the workpiece is wound up and inspected for defects in the process of being rewound onto another roll. If the defect is determined to be defective, the defect is removed by cutting and pasting (see, for example, Patent Document 1). During this inspection, an operator visually analyzes the defects using a magnifying glass or the like, and, based on the results of the analysis and the operator's experience, the ink density, printing pressure, and other parameters of the printing device are adjusted as necessary.

[0003] However, in the conventional method of analyzing defects during inspection and adjusting the printing equipment, many similar printing defects occur in the same lot and other works between the time the defect occurs and the time the printing equipment is adjusted, which increases the inspection work and inevitably results in many rejected products, making it difficult to improve production efficiency.

[0004] Furthermore, because the inspection equipment is designed to determine the quality of the printed surface, it is performed after the ink has completely set and the printed surface has been completed as a product. Furthermore, because this defect inspection (and analysis) is performed when the workpiece is rewound and then rewound, if the analysis reveals, for example, that the ink is bleeding, it is impossible to accurately determine whether the cause is ink viscosity, printing pressure, the drying process, or the problem worsened during the rewound process. Therefore, adjustments to the printing equipment based on such analysis are heavily dependent on the operator's past experience, making it difficult to adjust the printing equipment quickly and accurately.

[0005] In response to this, the present applicant has already proposed a method for analyzing defects in printed surfaces, which comprises a first imaging means and a second imaging means that is located upstream of the first imaging means and closer to the printing device and that captures images in greater detail with higher resolution than the first imaging means, and which includes the steps of comparing image information of the printed surface obtained by the first imaging means with reference image information to identify the defect and its position, operating the second imaging means based on the defect position information to capture in detail an area corresponding to the position of the defect on the printed surface of a workpiece that was printed after the first printed surface, and storing the detailed image information of the area captured by the second imaging means as information for defect analysis (see Patent Document 2).

[0006] This defect analysis method makes it possible to accurately grasp the details of a defect during printing. However, the image captured by the second imaging means and used for defect analysis is an image of a position corresponding to the position of the defect, and it is not always possible to appropriately and efficiently analyze the cause of the defect based on this image. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-71067 [Patent Document 2] Japanese Patent Application Publication No. 2018-80955 Summary of the Invention [Problem to be solved by the invention]

[0008] In view of the above situation, the present invention aims to solve the problem of providing a method and system for analyzing defects on a printed surface that enable more reliable, accurate, and efficient analysis of the causes of defects. [Means for solving the problem]

[0009] In light of this current situation, the inventors have conducted extensive research and have discovered that by providing a process for inferring the cause of a defect based on an image of the defect, obtaining an image suitable for analyzing the inferred cause, and analyzing the defect based on that image, particularly in the case of halftone image printing, and by referring not only to the location of the defect but also to suitable halftone dot images other than the defect, it becomes possible to determine the cause of the defect, such as whether the defect is due to thick or crushed halftone dots, or whether the ink density is too high or too low, thereby enabling more reliable, accurate, and efficient analysis, and have completed the present invention.

[0010] That is, the present invention includes the following inventions. (1) A method for analyzing defects on printed surfaces, comprising: a first imaging means for imaging the printed surface of a workpiece printed by a printing device; and a second imaging means for imaging the printed surface of a workpiece printed by the same printing device, the second imaging means imaging in greater detail with a higher resolution than the first imaging means; a processing device for comparing image information of the printed surface obtained by the first imaging means with reference image information to identify defects and their positions; a step for inferring the cause of the defect based on the shape and color density of the defect; a step for identifying an inspection area on the printed surface of the workpiece consisting of a halftone image suitable for detailed analysis of the inferred cause; a step for operating the second imaging means to image the identified inspection area in detail; and a step for analyzing the details of the cause of the defect based on the halftone image of the inspection area imaged by the second imaging means.

[0011] (2) The method for analyzing defects on a printed surface according to (1), wherein the suspected cause of the defect is one or more selected from the group consisting of misregistration, color density deviation, shape defect, and dot gain.

[0012] (3) A method for analyzing defects on a printed surface according to (1) or (2), wherein the specified inspection area is an area consisting of the halftone image of the same ink color as the defective portion.

[0013] (4) A method for analyzing defects on a printed surface according to (3), wherein the inspection area is a color patch consisting of the halftone dot image of the same ink color.

[0014] (5) A method for analyzing defects on a printed surface described in any one of (1) to (4), wherein when the suspected cause is dot gain, the details of the analysis are analysis of the color density level and shape of the halftone dots of the halftone dot image.

[0015] (6) A system for analyzing defects on printed surfaces, comprising: a first imaging means for imaging the printed surface of a workpiece printed by a printing device; a second imaging means for imaging the printed surface of a workpiece printed by the same printing device, the second imaging means imaging in greater detail with a higher resolution than the first imaging means; a defect identification processing unit for comparing image information on the printed surface obtained by the first imaging means with reference image information to identify defects and their positions; a cause estimation processing unit for estimating the cause of the defect based on the shape and color density of the defect; an area identification processing unit for identifying an inspection area on the printed surface of the workpiece consisting of a halftone image suitable for detailed analysis of the estimated cause; an imaging processing unit for operating the second imaging means to image the identified inspection area in detail; and a processing device having a detailed analysis processing unit for analyzing the details of the cause of the defect based on the halftone image of the inspection area imaged by the second imaging means. [Effects of the Invention]

[0016] According to the printing surface defect analysis method and defect analysis system of the present invention, the causes of defects can be analyzed more reliably, accurately, and efficiently. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is an explanatory diagram illustrating a defect analysis system according to a representative embodiment of the present invention. [Figure 2] FIG. 2 is an explanatory diagram showing the configuration of a processing device included in the defect analysis system. [Figure 3] FIG. 4 is an explanatory diagram showing a first imaging means of the defect analysis system. [Figure 4] FIG. 10 is an explanatory diagram showing a second imaging means and a moving means of the defect analysis system. [Figure 5] FIG. 10 is a flowchart showing the processing procedure of the defect analysis system. [Figure 6A] FIG. 10 is an explanatory diagram showing a modified example of the second imaging means. [Figure 6B] FIG. 10 is an explanatory diagram showing another modified example of the second imaging means. DETAILED DESCRIPTION OF THE INVENTION

[0018] Next, an embodiment of the present invention will be described in detail with reference to the accompanying drawings.

[0019] As shown in Figure 1, the printed surface defect analysis system S1 of the present invention comprises a first imaging means 11 that images the printed surface 10 of a workpiece W printed by a printing device 1 (1A to 1D), a second imaging means 12 that also images the printed surface 10 of a workpiece W printed by the printing device 1, the second imaging means 12 capturing images in greater detail and with higher resolution than the first imaging means 11, and a processing device 5.

[0020] The defect analysis system S1 of the present invention is a system that identifies defects and their positions from image information of the printed surface 10 obtained by the first imaging means 11, infers the cause of the defect based on the shape and color density of the defect, identifies an inspection area 101 consisting of a halftone image suitable for detailed analysis of the inferred cause, and analyzes the details of the cause of the defect based on the halftone image acquired by imaging the inspection area 101 with the second imaging means 12. This enables more reliable, accurate, and efficient analysis of defects in printed matter.

[0021] Although the workpiece W is illustrated as an example of a method in which the same type of print is printed on a continuous strip of sheet, the present invention can also be applied to a method in which printing is performed on cut sheets rather than on a continuous sheet. In addition to paper, various sheets such as synthetic resin film and aluminum foil are also included. The printed surface of the printed matter W includes at least a predetermined area consisting of halftone dot printing consisting of a single ink color printed on the sheet and a background.

[0022] The first imaging means 11, like the imaging means used in conventional inspection devices, has multiple imaging cameras 2 arranged in the workpiece width direction, as shown in FIG. 3, to image the area across the entire width of the workpiece. It may also be a line sensor camera with multiple CCD or CMOS imaging elements arranged in a horizontal direction perpendicular to the conveyance direction. The number and arrangement of cameras are not particularly limited as long as they can image the workpiece W. In addition to line sensor cameras, a single or multiple area sensor cameras with multiple CCD or CMOS imaging elements arranged in a vertical and horizontal direction may also be used. For imaging purposes, an illumination means (not shown) is also provided to illuminate the workpiece with a substantially uniform illuminance across the entire horizontal width. A horizontally aligned array of multiple lamps or a horizontally elongated straight tube lamp is also preferred.

[0023] As shown in FIG. 4, the second imaging means 12 is, for example, a single imaging camera 3 that captures an imaging area narrower than that of the first imaging means 11, and further, a traverse mechanism 40(4) is provided as a moving means 4 that moves this imaging camera 3 in a direction intersecting the flow direction of the workpiece W, and that supports the imaging camera 3 and moves it in the intersecting direction, in this example, the workpiece width direction.

[0024] In addition, when the specified inspection area 101 is an area selected from a limited area of ​​the printing surface, the second imaging means 12 may be configured to provide imaging cameras 3 at positions where the selectable area can be imaged, omit the moving means 4, and selectively operate only the imaging cameras 3 corresponding to the specified inspection area 101. Figure 6A shows an example in which the selectable areas are the left and right end areas of the printing surface, and imaging cameras 3 are provided corresponding to the left and right areas, respectively. Furthermore, as shown in Figure 6B, the second imaging means 12 may be configured in the same way as the first imaging means 11, with multiple imaging cameras 3 provided in the work width direction so that the area across the entire width of the work can be imaged in detail, and the moving means 4 may be omitted, and only the imaging cameras 3 corresponding to the specified inspection area 101 may be selectively operated.

[0025] The imaging camera 3 is, for example, a 4K camera with a resolution of 0.006 mm / pixel, and is also provided with an illumination means, similar to the first imaging means 11. In this way, in this example, by providing a moving means 4 that moves a single imaging camera 3 with high resolution, which is relatively expensive, in a direction intersecting the flow direction, the inspection area 101 can be efficiently imaged in detail.

[0026] In FIG. 1, reference numerals 11A, 11B, 11C, and 11D denote printing devices that print inks of different colors. The number of printing devices is not limited. A second imaging means may be provided downstream of each of the printing devices 1A to 1D, i.e., between printing devices 1A and 1B, between 1B and 1C, between 1C and 1D, or downstream of 1D. The printing devices 11A, 11B, 11C, and 11D are, for example, offset printing machines, but may also be applied to various other printing devices, such as flexographic printing machines, gravure printing machines, and digital printing machines.

[0027] The processing device 5 is a computer equipped with a processing unit 7 and a storage unit 8. The processing unit 7 is mainly composed of a CPU such as a microprocessor, and transmits and receives various types of information to and from the first imaging means 11, the second imaging means 12, the moving means 4, and each adjustment mechanism of the printing devices 1A to 1B via an input / output unit and a bus line. The storage unit 8 is composed of storage memories such as RAM and ROM inside and outside the processing unit 7, a hard disk, etc., and stores programs and processing data that define the procedures for various processing operations in the processing unit 7.

[0028] As shown in Figure 2, the memory unit 8 includes at least a master image memory unit 8a that stores image data that serves as a reference when detecting defects, a captured image memory unit 8b that stores image data of the printing surface captured by the first imaging means 11, a defect image memory unit 8c that stores image data of the detected defects, a defect position information memory unit 8d that stores position information of the defects, and a detailed image information memory unit 8e that stores detailed image data of the area 9 captured by the second imaging means 12.

[0029] As shown in Figure 2, the processing unit 7 functionally comprises at least a defect identification processing unit 7a that identifies defects and their positions from image information of the printing surface 10 obtained by the first imaging means 11; a cause estimation processing unit 7b that estimates the cause of the defect based on the shape and color density of the identified defect; an area identification processing unit 7c that identifies an inspection area suitable for detailed analysis of the cause estimated by the cause estimation processing unit 7b; a movement processing unit 7d that operates the moving means 4 to move the second imaging means 12 to a position corresponding to the inspection area 101; an imaging processing unit 7e that operates the second imaging means 12 to image the inspection area 101 in detail; and a detail analysis processing unit 7f that analyzes the details of the cause of the defect based on the halftone image of the inspection area 101 imaged by the second imaging means 12, and these functions are realized by the above-mentioned program.

[0030] The defect identification processing unit 7a compares the image captured by the first imaging means 11 with the master image stored in the master image storage unit 8a, and if the difference in density level comparison value exceeds a preset tolerance, detects the portion exceeding the tolerance as a defect. The master image stored in the master image storage unit 8a is a multi-tone area image having 256 or more density levels, just like the captured image. The comparison unit compares the multi-tone area image of the captured image with the multi-tone area image of the master image to determine the density level difference for each portion. The image of the detected defect is then stored in the defect image storage unit 8c.

[0031] In addition, the defect identification processing unit 7a can simultaneously detect the defects by counting parts of marks or patterns provided at regular intervals along the length of the sheet and identifying the longitudinal and widthwise positions (coordinates) of the defects based on these counts. Alternatively, the longitudinal position can be determined by counting the pulse signals output from a pulse generator each time the rolled sheet travels a certain distance. The position information of the identified defects is stored in the defect position information storage unit 8d.

[0032] For example, if the shape of the defect is within the normal range and the color density is darker than normal, the cause estimation processing unit 7b estimates that the cause is ink density or dot crushing (dot gain), if the shape is normal and the color density is lighter than normal, the cause is ink density or dot failure, and if the shape is abnormal, the cause is estimated to be misregistration, a plate defect, or the adhesion of foreign matter, and stores information about these estimated causes in the estimated information storage unit 8e. The content of the estimation is not limited to this example.

[0033] In another preferred example, the cause estimation processing unit 7b has a machine learning mechanism, stores the contents of various defects (contents of abnormalities), their continuity (whether they occur consecutively at the same position and to what extent), and the causes of the defects as training data, and makes estimations by referring to the learning results of the machine learning mechanism. The learning method of the machine learning mechanism can be any method, such as deep learning using a neural network.

[0034] The region identification processing unit 7c identifies an inspection region suitable for detailed analysis of the cause of the defect inferred by the cause estimation processing unit 7b, based on information on the cause of the defect (for example, ink density, dot gain, dot fading, dot size, misregistration, plate defect, etc.). For example, if the cause of the defect is inferred to be ink density, it identifies other regions consisting of the halftone dot image of that ink color or regions of color patches consisting of halftone dot images of that ink color. If the cause of the defect is inferred to be dot gain, dot fading, dot size, etc., it identifies other regions with the same halftone dot ratio (dot size) as the image determined to be defective or regions of color patches of that ink color. If the cause is inferred to be misregistration, it identifies a region consisting of an image including color patches of all colors.

[0035] The other areas to be identified as described above can be identified by storing design data for each ink color in a memory unit in advance, such as a single-color halftone dot area of ​​a specific ink color, a halftone dot area of ​​a mixture of two colors, or an area with a predetermined dot size. When identifying other areas of the same ink color or color patch areas, it is preferable to identify areas of the same ink fountain even within the same ink color. Furthermore, even if it is not possible to identify an area of ​​the same ink fountain, it is preferable to identify an area of ​​an adjacent ink fountain of the same color. This is because the same phenomenon is more likely to occur in ink fountains that are close to each other than those that are farther away.

[0036] The movement processing unit 7d operates the movement means 4 to a position corresponding to the inspection area 101 based on the position information from the area information storage unit 8f. Similarly, the imaging processing unit 7e operates the second imaging means 12 to image an area corresponding to the position of the inspection area 101 based on the position information from the area information storage unit 8f. The image of the inspection area imaged by the second imaging means 12 is then stored in the detailed image information storage unit 8g as information for analyzing the details of the cause of the defect.

[0037] The detailed analysis processing unit 7f can perform detailed inspection in the same manner as conventionally known fixed-position detailed inspections. For example, if the suspected cause of the defect is ink density, the color density of the halftone dot image in the inspection area 101 can be analyzed. If the suspected cause is dot gain or dot blurring, analysis can be performed by acquiring the area ratio and shape of the dots that make up the halftone dots in the halftone dot image in the inspection area 101, the color density distribution for each pixel, and the color density profile for each dot. If the suspected cause is dot size, the shape of the dots in the halftone dot image in the inspection area 101 can be acquired and analyzed.

[0038] Furthermore, if the suspected cause is misregistration, for example, the misalignment of color patches (register marks) of multiple ink colors included in the inspection area 101 can be calculated and analyzed. The detailed analysis processing unit 7f stores the results of these analyses in the analysis result storage unit 8h. The results of such analyses are preferably used as control signals for feedback control of an adjustment mechanism of the printing device (not shown). In this way, the detailed analysis processing unit 7f can use a wide range of known techniques to analyze each suspected cause of a defect.

[0039] The processing procedure of the defect analysis system S1 will be described with reference to FIG.

[0040] The defect identification processing unit 7a sequentially stores image information of the printing surface obtained by the first imaging means 11 in the captured image storage unit 8b (S101), and compares it with the reference image information in the master image storage unit 8a (S102). If a defect is detected as a result of the comparison (S103), the defect identification processing unit 7a acquires position information of the defect (S104), and the image and position information of the defect are stored in the defect image storage unit 8c and the defect position information storage unit 8d, respectively (S105).

[0041] Next, the cause estimation processing unit 7b estimates the cause of the defect based on the shape and color density of the defect (S106). Next, the area identification processing unit 7c identifies an inspection area consisting of a halftone image suitable for detailed analysis of the estimated cause on the printed surface of the workpiece (S107). Next, based on the position information of this inspection area, the movement processing unit 7d operates the movement means 4 to move the second imaging means 12 to a coordinate position in the workpiece width direction that corresponds to the position information of the inspection area (S108).

[0042] Next, the imaging processing unit 7e operates the second imaging means 12 based on the position information of the inspection area, and synchronizes the timing to capture a detailed image of the area corresponding to the position of the inspection area 101 (S109). Then, the detail analysis processing unit 7f analyzes the details of the cause of the defect based on the halftone image of the inspection area captured by the second imaging means (S110).

[0043] Although the embodiments of the present invention have been described above, the present invention is not limited to these examples, and it goes without saying that the present invention can be embodied in various forms without departing from the spirit of the present invention. [Explanation of symbols]

[0044] 1,1A-1D Printing device 2 Imaging camera 3. Imaging camera 4. Means of transportation 5 Processing device 7 Processing section 7a Defect identification processing section 7b Cause estimation processing section 7c Area identification processing unit 7d Movement processing unit 7e Imaging processing section 7f Detailed analysis processing section 8 Memory unit 8a Master image memory unit 8b Captured image storage unit 8c Defect image storage unit 8d Defect position information storage unit 8e Estimated information storage unit 8f Area information storage section 8g Detailed image information storage section 8h Analysis result storage section 10 Printed surface 11 First imaging means 12 Second imaging means 40 Traverse mechanism 101 Area S1 Defect Analysis System W Work

Claims

1. a first imaging means for imaging a printing surface of a workpiece printed by a printing device; a second imaging means for imaging the printing surface of the workpiece printed by the printing device, the second imaging means being configured to image the printing surface in greater detail with a higher resolution than the first imaging means; The processing device a step of comparing image information of the printing surface obtained by the first imaging means with reference image information to identify defects and their positions; a step of inferring the cause of the defect based on the shape and color density of the defect; A procedure for specifying an inspection area consisting of a halftone dot image suitable for detailed analysis of the suspected cause on the printing surface of the work; a step of operating the second imaging means to capture a detailed image of the specified inspection area; and a step of analyzing the details of the cause of the defect based on the halftone image of the inspection area captured by the second imaging means.

2. 2. The method for analyzing defects on a printed surface according to claim 1, wherein the suspected cause of the defect is one or more selected from the group consisting of misregistration, color density deviation, shape defect, and dot gain.

3. 2. The method for analyzing defects on a printed surface according to claim 1, wherein the specified inspection area is an area consisting of the halftone image in the same ink color as the defective portion.

4. 4. The method for analyzing defects on a printed surface according to claim 3, wherein the inspection area is a color patch formed by the halftone dot image of the same ink color.

5. When the suspected cause is dot gain, the details of the analysis include analyzing the color density level and shape of the halftone dots of the halftone dot image. The method for analyzing defects on a printing surface according to claim 1.

6. a first imaging means for imaging a printing surface of a workpiece printed by a printing device; a second imaging means for imaging the printing surface of the workpiece printed by the printing device, the second imaging means imaging the printing surface in more detail with a higher resolution than the first imaging means; A printing surface defect analysis system characterized by comprising a processing device having a defect identification processing unit that compares image information of the printing surface obtained by the first imaging means with reference image information and identifies defects and their positions; a cause estimation processing unit that estimates the cause of the defect based on the shape and color density of the defect; an area identification processing unit that identifies an inspection area consisting of a halftone image suitable for detailed analysis of the estimated cause on the printing surface of the work; an imaging processing unit that operates the second imaging means and images the identified inspection area in detail; and a detailed analysis processing unit that analyzes the details of the cause of the defect based on the halftone image of the inspection area imaged by the second imaging means.

Images