Image processing device, image processing method, and program
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-03-27
- Publication Date
- 2026-04-02
AI Technical Summary
Existing methods for inspecting printed matter on transparent paper fail to accurately detect defects in both transparent and opaque parts, leading to decreased detection accuracy when using reflected and transmitted light simultaneously.
An image processing device that acquires and compares diffusely reflected light and specularly transmitted light distributions to inspect printed matter, adjusting the usage ratio of these light types based on transparency to enhance defect detection accuracy.
The method allows for high-precision detection of defects in printed matter on transparent paper by optimizing the use of reflected and transmitted light based on transparency, ensuring accurate identification of both transparent and opaque part defects.
Smart Images
Figure 00000000_0000_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to an image processing technique for inspecting printed matter output by a printing device. [Background technology]
[0002] In the printing industry, prints are inspected for defects to ensure that they are free of defects and of acceptable quality. Prints are inspected using the difference between two types of image data: image data that serves as the standard for quality (hereafter referred to as the reference image), and image data of the print to be inspected obtained by capturing an image of the print with a sensor or the like (hereafter referred to as the inspection image).
[0003] Incidentally, in many cases, the papers used for printing are opaque papers with low light transmittance, such as copy paper, and transparent papers with high light transmittance, such as transparent films for protecting products and transparent labels for packaging. When inspecting printed matter using opaque paper, an imaging method that receives reflected light from the printed matter is used. On the other hand, when inspecting printed matter using transparent paper, an imaging method that receives not only reflected light but also transmitted light is used. This is because, when a printed matter using transparent paper is placed on a black board and imaged, an image obtained based only on reflected light cannot distinguish between light absorption by coloring material and light transmission in the transparent part. Since the light that has transmitted through the transparent part is absorbed by the black board and the proportion of it reflected is low, the transparent part becomes an image as if a "solid" pattern with a high coloring material concentration is printed. Therefore, an imaging method that receives not only reflected light but also transmitted light is used for printed matter using transparent paper. Patent Document 1 discloses a method for inspecting printed matter using transparent paper based on an image obtained by imaging using transmitted light and reflected light. Illumination conditions, such as the ratio of transmitted light intensity to reflected light intensity, are determined according to the inspection content. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] WO 2020 / 158725 Specification Summary of the Invention [Problem to be solved by the invention]
[0005] However, in the method of Patent Document 1, when there are defects in both the transparent and opaque parts of a printed matter printed on transparent paper, if an inspection is performed based on an image obtained by irradiating only one of reflected light and transmitted light and capturing an image, it is not possible to correctly detect either of the defects. On the other hand, if an inspection is performed based on an image obtained by irradiating both reflected light and transmitted light simultaneously and capturing an image, it is possible to detect both defects, but the detection accuracy for both defects decreases.
[0006] SUMMARY OF THE PRESENT DISCLOSURE An object of the present invention is to detect defects in printed matter using transparent paper with high accuracy. [Means for solving the problem]
[0007] The present invention is an image processing device for inspecting the presence or absence of defects in a printed matter printed on transparent paper, comprising a first acquisition means for acquiring a first reference image corresponding to a distribution of diffuse reflected light that serves as a reference for inspecting the printed matter and a second reference image corresponding to a distribution of specularly transmitted light, a second acquisition means for acquiring a first inspection target image obtained by reading the diffuse reflected light from the printed matter and a second inspection target image obtained by reading the specularly transmitted light from the printed matter, and an inspection means for inspecting the presence or absence of defects in the printed matter based on at least one of a first comparison result between the first reference image and the first inspection target image and a second comparison result between the second reference image and the second inspection target image, depending on the transparency of each area of the printed matter. Effect of the Invention
[0008] According to the present invention, defects in printed matter using transparent paper can be detected with high accuracy. [Brief description of the drawings]
[0009] [Figure 1] Conceptual diagram explaining the characteristics of reflected light [Diagram 2] Conceptual diagram explaining the characteristics of transmitted light [Diagram 3] Light receiving characteristics of diffuse reflected light intensity and specular transmitted light intensity on transparent paper [Figure 4] FIG. 1 is a diagram showing the overall configuration of a printing system including an image processing unit according to a first embodiment. [Diagram 5] FIG. 1 is a block diagram showing an example of the arrangement of an image processing unit according to a first embodiment. [Figure 6] FIG. 1 is a diagram showing an example of the configuration of an image reading apparatus according to a first embodiment; [Figure 7] 1 is a main processing flow showing an inspection process including an inspection process executed by an image processing unit in the first embodiment. [Figure 8] Processing flow for generating a reference transmitted light utilization ratio map and a reference reflected light utilization ratio map in the first embodiment [Figure 9] Processing flow for generating an inspection transmitted light utilization ratio map and an inspection reflected light utilization ratio map in the first embodiment [Figure 10] Processing flow for calculating transparency in the first modification of the first embodiment [Figure 11] Processing flow for calculating transparency in the second modification of the first embodiment [Figure 12] FIG. 11 is a block diagram showing an example of the configuration of an image processing unit in a third modified example of the first embodiment. [Figure 13] A main processing flow showing an inspection process including an inspection process executed by an image processing unit in the second embodiment. [Figure 14] Processing flow for generating an inspection image in the second embodiment [Figure 15] FIG. 13 is a block diagram showing an example of the arrangement of an image processing unit in the third embodiment. [Figure 16] A main processing flow showing an inspection process including an inspection process executed by an image processing unit in the third embodiment. [Figure 17] Processing flow for performing alignment with respect to a reference image in the third embodiment [Figure 18]Processing flow for performing alignment on an inspection image in the third embodiment DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The following embodiment does not limit the present invention, and not all of the combinations of features described in the embodiment are necessarily essential to the solution of the present invention. Note that the same components will be described with the same reference numerals.
[0011] [Embodiment 1] In this embodiment, an inspection method will be described in which transparency is calculated from a specular transmitted light intensity image, which is transmitted light information of a transparent paper, and the ratio of use of transmitted light information and reflected light information is changed for each region.
[0012] <Explanation of the terms reflected light and transmitted light> First, the difference between the transmitted light and the reflected light that can be obtained depending on whether the printed matter is printed on transparent paper or opaque paper will be described.
[0013] FIG. 1(a) is a schematic diagram for explaining the reflection characteristics at a certain position on the object surface. It shows a distribution 103 of reflected light when light is irradiated from the direction of a light source 101 toward an incident point 102 on the object surface. This reflected light is a superposition of the diffuse reflected light component shown in FIG. 1(b) and the specular reflected light component shown in FIG. 1(c). The diffuse reflected light component is generated by the incident light being irregularly reflected in the surface layer of the object, and is observed with a uniform intensity at a position equidistant from the incident point. This intensity is called the diffuse reflected light intensity 104. On the other hand, the specular reflected light component is generated by the incident light being reflected in the specular reflection direction on the object surface. The specular reflection direction is a direction within a plane (incident plane) that includes the incident light and the normal to the object surface at the incident point, and is the direction in which the angle between the incident light and the normal at the incident point is equal to the angle between the incident light and the normal at the incident point. The maximum intensity of this specular reflected light component is called the specular reflected light intensity 105. The specular reflected light intensity 105 is large when the object surface is smooth.
[0014] FIG. 2(a) is a schematic diagram for explaining the transmission characteristics at a certain position on the object surface. It shows a distribution 203 of transmitted light when light is irradiated from the direction of a light source 201 toward an incident point 202 on the object surface. The light transmitted through the object surface is a superposition of the diffuse transmitted light component shown in FIG. 2(b) and the specular transmitted light component shown in FIG. 2(c). The diffuse transmitted light component occurs when the incident light is scattered in a spherical shape due to the unevenness inside the object or on the surface when it exits on the opposite side of the object, and is observed with a uniform intensity at positions equidistant from the incident point. This intensity is called the diffuse transmitted light intensity 204. On the other hand, the specular transmitted light component occurs when the incident light travels straight through the object and exits on the opposite side. The transmission intensity in the direction in which the specular transmitted light intensity is maximum is called the specular transmitted light intensity 205.
[0015] In this disclosure, since the subject matter is printed matter that uses general color materials that have non-uniform surface smoothness, rather than special color materials that provide a smooth surface, the reflected light intensity detected when reading the printed matter is considered to be the diffuse reflected light intensity 104. In addition, transparent paper used as a recording medium has a high tendency for incident light to travel in a straight line, making it difficult to detect the diffuse transmitted light intensity 204, so the transmitted light intensity detected when reading the printed matter is considered to be the regular transmitted light intensity 205.
[0016] <Features of interest> Next, the light receiving characteristics of the light receiving element of the diffuse reflected light intensity 104 and the regular transmitted light intensity 205 in transparent paper, which is the focus of this embodiment, will be described with reference to Fig. 3. Fig. 3(a) is a schematic diagram showing a defect 301 caused by mistakenly applying a coloring material to a transparent area surrounding a print, and a defect 302 caused by mistakenly applying a coloring material with a higher reflectance than the surrounding printed area.
[0017] The left diagram in Fig. 3(b) is a schematic diagram showing the profile of the diffuse reflected light intensity of the first line 303, showing the diffuse reflected light intensity 305 of the portion where only the transparent paper has no colorant attached, and the diffuse reflected light intensity 306 of the portion of the defect 301 where the colorant has attached. The right diagram in Fig. 3(b) is a schematic diagram showing the profile of the specular transmitted light intensity of the first line 303, showing the specular transmitted light intensity 307 of the portion where only the transparent paper has no colorant attached, and the specular transmitted light intensity 308 of the portion of the defect 301 where the colorant has attached.
[0018] The left diagram in FIG. 3(c) is a schematic diagram showing the profile of the diffuse reflected light intensity of the second line 304. This diagram shows the diffuse reflected light intensity 309 of the normal printed portion and the diffuse reflected light intensity 310 of the defective portion 302, which is coated with a color material with a higher reflectance than the surrounding normal printed portions. The right diagram in FIG. 3(c) is a schematic diagram showing the profile of the specular transmitted light intensity of the second line 304. This diagram shows the specular transmitted light intensity 311 of the normal printed portion and the specular transmitted light intensity 312 of the defective portion 302, which is coated with a color material with a higher reflectance than the surrounding normal printed portions.
[0019] Although it is easy to visually distinguish defect 301 on the print, the difference between diffuse reflected light intensities 305 and 306 is small, making it difficult to detect defect 301 based on the profile of the diffuse reflected light intensity. On the other hand, the difference between specular transmitted light intensities 307 and 308 is large, making it easy to detect defect 301 based on the profile of the specular transmitted light intensity. As for defect 302, the difference between diffuse reflected light intensities 309 and 310 is large, making it easy to detect defect 302 based on the profile of the diffuse reflected light intensity. On the other hand, the difference between specular transmitted light intensities 311 and 312 is small, making it difficult to detect defect 302 based on the profile of the specular transmitted light intensity.
[0020] In this way, in the inspection of a print using transparent paper based on an image captured using a light receiving element, the illumination method suitable for detecting a defect differs depending on whether or not a coloring material is present around the defect. Therefore, in the technology disclosed herein, taking into account the above characteristics, the utilization ratio of the diffuse reflection light intensity and the regular transmission light intensity is changed for each region of the print based on the transparency that represents the transmittance of regular transmission light, thereby making it possible to improve the detection accuracy of defects on a print using transparent paper.
[0021] <Overall system description> FIG. 4 shows an example of the overall configuration of a printing system that outputs and inspects printed matter, including an inspection device 400 to which the present invention is applied. The printing system of this embodiment includes an inspection device 400, a printing server 480, and a printing device 490. The printing server 480 generates a print job for a document to be printed, and inputs the print job to the printing device 490. The printing device 490 forms an image on paper based on the print job input from the printing server 480. The printing device 490 has a paper feed unit 491, and a user sets printing paper in the paper feed unit in advance. When a print job is input, the printing device 490 transports the printing paper set in the paper feed unit 491 along a transport path 492, forms an image on one or both sides of the paper, and sends it to the inspection device 400.
[0022] An inspection device 400 to which the present invention is applied performs an inspection process in which a printout, on which an image has been formed on paper by a printing device 490, is acquired via a conveying path 492, the printout is read, and the read image is subjected to image processing to check for the presence or absence of defects. The inspection device 400 has a CPU 401, a RAM 402, a ROM 403, a main memory device 404, an image reading device 405, an interface 406 with the printing device, a general-purpose interface 407, a user interface panel 408, and a main bus 409 inside. It also has a conveying path 410 for printed matter connected to the conveying path 492 of the printing device 490, an output tray 411 for printed matter that has passed inspection, and an output tray 412 for printed matter that has been found to have a defect and has failed inspection.
[0023] The CPU 401 is a processor that controls each unit in the inspection device 400 and performs image processing on image data. The RAM 402 functions as the main memory, work memory, etc. of the CPU 401. The ROM 403 stores a boot program for starting the inspection device 400 executed by the CPU 401. The main storage device 404 stores application programs executed by the CPU 401 and data used for image processing. The image reading device (scanner) 405 can read one side or both sides of a printed matter sent from the printing device 490 on the conveying path 410 and acquire it as image data. The printing device interface 406 is connected to the printing device 490, and can synchronize the processing timing of the printing device 490 and the printed matter and communicate each other's operating status. The general-purpose interface 407 is a serial bus interface such as USB or IEEE1394, and allows the user to acquire data such as logs. The user interface panel 408 is, for example, a liquid crystal display, and functions as a user interface for the inspection device 400, and can display and present the current status and settings to the user, and is equipped with a touch panel or buttons to accept instructions from the user. A main bus 409 connects each part of the inspection device 400.
[0024] In addition, the inspection device 400 and various internal parts of the printing system can be operated by instructions from the CPU 401. For example, it is possible to synchronously move the transport paths, and to switch whether printed matter is sent to the pass output tray 411 or the fail output tray 412 depending on the inspection results.
[0025] Overall, the inspection device 400 carries out the inspection process described below based on the image data of the printed matter read by the image reading device 405 while transporting the printed matter sent from the printing device 490 on the transport path 410. If the printed matter passes the inspection, it is transported to an acceptable output tray 411, and if not, it is transported to a rejected output tray 412. In this way, only those that have been confirmed to have a specified level of quality can be collected in the output tray 411 for delivery.
[0026] <Explanation of the image processing block diagram> 5 shows the system configuration of an image processing unit 500 related to the inspection process of this embodiment. The image processing unit 500 has a raster image generating unit 501, a transmitted light image acquiring unit 502, a reflected light image acquiring unit 503, a reference transmitted light image generating unit 504, a reference reflected light image generating unit 505, a utilization ratio calculating unit 506, a weighting unit 507, and an inspection processing unit 508. In this embodiment, the input of the image processing unit 500 receives a control signal to the image processing unit 500 that is sent from the printing device 490 in synchronization with the output of the printed matter or as necessary. The output of the image processing unit 500 is pass / fail information of the inspection process based on the images acquired by the transmitted light image acquiring unit 502 and the reflected light image acquiring unit 503, and is used as a control signal for the internal operation of the printing system.
[0027] The raster image generating unit 501 acquires PDL data, which is the original data, and generates a raster image RIP(x,y) by performing RIP (Raster Image Processor) processing on the PDL data. A control signal is created for forming the raster image RIP(x,y) on paper by the printing device 490, and printing is performed. x represents any position in the horizontal direction of the two-dimensional data, y represents any position in the vertical direction of the two-dimensional data, and (x,y) represents the value of the position specified by x and y. Note that hereinafter, the notation (x,y) will be omitted for convenience.
[0028] The transmitted light image acquisition unit 502 acquires a printed matter printed by the printing device 490, irradiates the printed matter with light and detects the specular transmitted light from the printed matter to acquire a specular transmitted light intensity distribution, and generates a specular transmitted light intensity image Tr. FIG. 6(a) shows an illumination method used when reading the specular transmitted light intensity image Tr in the image reading device 405. When reading the specular transmitted light intensity image Tr, the image reading device 405 turns on an illumination device arranged on the opposite side of the printed matter to the light receiving element. In this disclosure, the specular transmitted light intensity image Tr that is to be inspected is referred to as an inspection transmitted light image TrT.
[0029] The reflected light image acquisition unit 503 acquires a printed matter printed by the printing device 490, irradiates the printed matter with light and detects diffuse reflected light from the printed matter to acquire a diffuse reflected light intensity distribution, and generates a diffuse reflected light intensity image Dr. FIG. 6(b) shows an illumination method when reading the diffuse reflected light intensity image Dr in the image reading device 405. When reading the diffuse reflected light intensity image Dr, the image reading device 405 turns on a light in which the light receiving element and the light source are arranged on the same side of the printed matter. In this disclosure, the diffuse reflected light intensity image Dr that is to be inspected is referred to as an inspection reflected light image DrT.
[0030] 6 is configured so that lighting is arranged on both sides of the transport path of the printed material, and both the specular transmitted light intensity image Tr and the diffuse reflected light intensity image Dr can be read by one light receiving element, but the configuration is not limited to this. For example, the image reading device 405 may be configured to have two light receiving elements, with one light receiving element and lighting dedicated to reading the specular transmitted light intensity image Tr, and another light receiving element and lighting dedicated to reading the diffuse reflected light intensity image Dr.
[0031] The reference transmitted light image generating unit 504 acquires a plurality of regular transmitted light intensity images Tr from the transmitted light image acquiring unit 502, and synthesizes them to generate a reference transmitted light image TrR that serves as a reference for inspection.
[0032] The reference reflected light image generating unit 505 acquires a plurality of diffuse reflected light intensity images Dr from the reflected light image acquiring unit 503, and synthesizes them to generate a reference reflected light image DrR that serves as a reference for inspection.
[0033] The reference transmitted light image TrR and the reference reflected light image DrR may be generated in advance and stored in the RAM 402, the main storage device 404, or the like, and then read out for use.
[0034] The utilization ratio calculation unit 506 acquires the reference transmitted light image TrR and the incident light intensity I, and generates a reference reflected light utilization ratio map Rmap_Dr and a reference transmitted light utilization ratio map Rmap_Tr. The utilization ratio calculation unit 506 also acquires the inspection transmitted light image TrT, and generates an inspection reflected light utilization ratio map Tmap_Dr and an inspection transmitted light utilization ratio map Tmap_Tr.
[0035] The weighting unit 507 acquires the reference reflected light image DrR and the reference reflected light utilization ratio map Rmap_Dr, and generates a weighted reference reflected light image DrRW by applying the utilization ratio map. The weighting unit 507 also acquires the reference transmitted light image TrR and the reference transmitted light utilization ratio map Rmap_Tr, and generates a weighted reference transmitted light image TrRW by applying the utilization ratio map. Similarly, the weighting unit 507 acquires the inspection reflected light image DrT and the inspection reflected light utilization ratio map Tmap_Dr, and generates a weighted inspection reflected light image DrTW by applying the utilization ratio map. The weighting unit 507 acquires the inspection transmitted light image TrT and the inspection transmitted light utilization ratio map Tmap_Tr, and generates a weighted inspection transmitted light image TrTW by applying the utilization ratio map.
[0036] The inspection processing unit 508 acquires the weighted reference reflected light image DrRW and weighted reference transmitted light image TrRW, and the weighted inspection reflected light image DrTW and weighted inspection transmitted light image TrTW output from the weighting unit 507. The inspection processing unit 508 then outputs inspection result information indicating whether or not there is a defect in the printed matter, based on the differences between the weighted reference reflected light image DrRW and weighted reference transmitted light image TrRW and the weighted inspection reflected light image DrTW and weighted inspection transmitted light image TrTW.
[0037] <Explanation of the image processing flow> 7 is a flowchart showing the inspection process including the inspection process executed by the image processing unit 500 in this embodiment. The CPU 401 reads out and executes a program following the flowchart shown in FIG.
[0038] In S701, the utilization ratio calculation unit 506 acquires the reference transmitted light image TrR from the reference transmitted light image generation unit 504. In addition, the weighting unit 507 acquires the reference transmitted light image TrR and the reference reflected light image DrR from the reference transmitted light image generation unit 504 and the reference reflected light image generation unit 505.
[0039] In S702, the utilization ratio calculation unit 506 generates a reference reflected light utilization ratio map Rmap_Dr and a reference transmitted light utilization ratio map Rmap_Tr based on the acquired reference transmitted light image TrR. Then, the weighting unit 507 generates a weighted reference reflected light image DrRW by applying the reference reflected light utilization ratio map Rmap_Dr to the reference reflected light image DrR. Similarly, the weighting unit 507 generates a weighted reference transmitted light image TrRW by applying the reference transmitted light utilization ratio map Rmap_Tr to the reference transmitted light image TrR. A detailed flow will be described later. The weighting process may be a combination of known color conversion, thin line correction, local distortion correction processes, and the like.
[0040] In S703, the utilization ratio calculation unit 506 acquires the inspection transmitted light image TrT from the transmitted light image acquisition unit 502. In addition, the weighting unit 507 acquires the inspection transmitted light image TrT and the inspection reflected light image DrT from the transmitted light image acquisition unit 502 and the reflected light image acquisition unit 503.
[0041] In S704, the utilization ratio calculation unit 506 generates an inspection reflected light utilization ratio map Tmap_Dr and an inspection transmitted light utilization ratio map Tmap_Tr based on the acquired inspection transmitted light image TrT. Then, the weighting unit 507 generates a weighted inspection reflected light image DrTW by applying the inspection reflected light utilization ratio map Tmap_Dr to the inspection reflected light image DrT. Similarly, the weighting unit 507 generates a weighted inspection transmitted light image TrTW by applying the inspection transmitted light utilization ratio map Tmap_Tr to the inspection transmitted light image TrT. A detailed flow will be described later. In this embodiment, known color conversion, thin line correction, local distortion correction processing, etc. may be combined.
[0042] In S705, the inspection processing unit 508 acquires the weighted reference reflected light image DrRW and the weighted reference transmitted light image TrRW generated in S702, and the weighted inspection reflected light image DrTW and the weighted inspection transmitted light image TrTW generated in S704. Further, the inspection processing unit 508 adds the weighted reference reflected light image DrRW and the weighted reference transmitted light image TrRW to generate a reference image R. Similarly, the inspection processing unit 508 adds the weighted inspection reflected light image DrTW and the weighted inspection transmitted light image TrTW to generate an inspection image T. Then, the inspection processing unit 508 performs an inspection process to detect defects in the printed matter to be inspected based on the difference between the reference image R and the inspection image T, and notifies inspection result information indicating the presence or absence of defects in the printed matter. In this embodiment, the inspection process for detecting defects shall use a known technique.
[0043] In S706, the CPU 401 determines whether the inspection of the printed matter to be inspected is passed or failed based on the inspection result information output in S705 by the inspection processing unit 508. If the inspection is passed, the process proceeds to S707; if it is failed, the process proceeds to S708.
[0044] In S707, the CPU 401 conveys the printed matter being inspected to the pass tray 411.
[0045] In S708, the CPU 401 ejects the printed matter being inspected onto the fail tray 412.
[0046] In S709, if there is still a printed matter to be inspected, the CPU 401 repeatedly executes the processes from S703 to S708, and if there is no printed matter to be inspected, the inspection process ends.
[0047] <Explanation of the flow of S702> FIG. 8 is a flowchart showing the details of the process of S702 in this embodiment. The CPU 401 reads and executes a program along the flowchart shown in FIG. 8.
[0048] In S801, the utilization ratio calculation unit 506 calculates a reference transparency TrR_rate based on the reference transmitted light image TrR. In this embodiment, the transmitted light image acquisition unit 502 calculates a reference transparency TrR_rate defined by formula (1) based on the incident light intensity I of the illumination when acquiring the specular transmitted light intensity image Tr and the reference transmitted light image TrR.
[0049]
number
[0050] Here, the incident light intensity I is a value ranging from 0 as a minimum value to the maximum value that the reference transmitted light image TrR can take as a maximum value, and may be a value previously set in the utilization ratio calculation unit 506 or a value input by the user via the user interface panel 408. Therefore, the reference transparency TrR_rate takes a value between 0 and 1.
[0051] In S802, the utilization ratio calculation unit 506 generates a reference reflected light utilization ratio map Rmap_Dr and a reference transmitted light utilization ratio map Rmap_Tr using the reference transparency TrR_rate calculated in S801. The reference reflected light utilization ratio map Rmap_Dr is calculated using equation (2), and the reference transmitted light utilization ratio map Rmap_Tr is calculated using equation (3).
[0052]
number
[0053]
number
[0054] Here, A represents the light absorption rate with respect to the incident light intensity I in the transparent paper. In this embodiment, the reference reflected light utilization ratio map Rmap_Dr and the reference transmitted light utilization ratio map Rmap_Tr are generated based on calculation formulas. However, the reference reflected light utilization ratio map Rmap_Dr and the reference transmitted light utilization ratio map Rmap_Tr are not limited to this. For example, a look-up table with the characteristic that the utilization ratio of the reference transmitted light image TrR is high when the transparency is high and the utilization ratio of the reference reflected light image DrR is high when the transparency is low may be used.
[0055] In S803, the weighting unit 507 generates a reference image R based on the reference reflected light image DrR, the reference transmitted light image TrR, the reference reflected light utilization ratio map Rmap_Dr, and the reference transmitted light utilization ratio map Rmap_Tr calculated in S802. In this embodiment, as shown in Equation (4), the reference image R is the sum of the weighted reference reflected light image DrRW and the weighted reference transmitted light image TrRW.
[0056]
Equation
[0057] <Explanation of the flow of S704> FIG. 9 is a flowchart showing the details of the process of S704 in this embodiment. The CPU 401 reads and executes a program along the flowchart shown in FIG. 9.
[0058] In S901, the utilization ratio calculation unit 506 calculates an inspection transparency TrT_rate in the same manner as in S801 based on the inspection transmitted light image Tr. The inspection transparency TrT_rate is defined by replacing the reference transmitted light image TrR in Equation (1) with the inspection transmitted light image TrT.
[0059] In S902, the utilization ratio calculation unit 506 generates an inspection reflected light utilization ratio map Tmap_Dr and an inspection transmitted light utilization ratio map Tmap_Tr using the inspection transparency TrT_rate calculated in S901. The inspection reflected light utilization ratio map Tmap_Dr and the inspection transmitted light utilization ratio map Tmap_Tr are defined by replacing the reference transparency TrR_rate in Equation (2) and Equation (3), respectively, with the TrT_rate calculated in S901.
[0060] In S903, the weighting unit 507 generates an inspection image T based on the inspection reflected light image DrT and the inspection transmitted light image TrT, and the inspection reflected light utilization ratio map Tmap_Dr and the inspection transmitted light utilization ratio map Tmap_Tr. In this embodiment, the inspection image T is the sum of the weighted inspection reflected light image DrTW and the weighted inspection transmitted light image TrTW, as shown in formula (5).
[0061]
number
[0062] Through the above processing, the utilization ratio between the image obtained based on diffuse reflected light and the image obtained based on specular transmitted light is changed for each region based on the transmittance of the print, making it possible to accurately detect defects even when they occur simultaneously in both the transparent and opaque parts of the print.
[0063] <Variation 1> In the above-described embodiment, the reference transparency TrR_rate is calculated based on the reference transmitted light image TrR. However, the reference transparency TrR_rate may be calculated based on the raster image RIP used when printing the printout to be inspected.
[0064] Fig. 10 is a flowchart for calculating transparency from a raster image RIP executed by the image processing unit 500 in this modified example. The CPU 401 reads and executes a program according to the flowchart shown in Fig. 10. Since steps S802 and S803 are the same as those in the first embodiment, their explanations will be omitted here.
[0065] In S1001, a raster image RIP used in printing the print to be inspected is acquired, and a reference transparency TrR'_rate is calculated. The reference transparency TrR'_rate is defined by the following formula (6).
[0066]
number
[0067] In this embodiment, the reference transparency TrR'_rate is calculated based on a formula. Alternatively, a lookup table with characteristics in which the transparency is inversely proportional to the square of the raster image RIP may be used.
[0068] Through the above processing, by using the raster image RIP, it is possible to suppress variations due to highly reproducible defects caused by malfunctions or characteristics of the printing machine, and defects caused by paper characteristics, and to obtain a stable and highly accurate reference transparency TrR'_rate.
[0069] <Variation 2> In the above-described embodiment and modified examples, the reference transparency TrR_rate and the reference transparency TrR'_rate are calculated based on the reference transmitted-light image TrR and the raster image RIP, respectively. In contrast, in modified example 2, the reference transparency TrR''_rate is calculated based on the magnitude relationship between the reference reflected-light image DrR and the reference transmitted-light image TrR.
[0070] Fig. 11 is a flowchart executed by the inspection device 400 in this modified example. The CPU 401 reads and executes a program following the flowchart shown in Fig. 11. S802 and S803 are the same as in the first embodiment, and therefore the description thereof will be omitted here.
[0071] In S1101, a reference reflected light image DrR and a reference transmitted light image TrR are acquired, and a reference transparency TrR″_rate(x, y) is generated. The reference transparency TrR″_rate(x, y) is calculated using equation (7).
[0072]
number
[0073] Through the above processing, it is possible to minimize the resources required for processing by using only the data with the highest contribution from the reference reflected light image DrR and the reference transmitted light image TrR.
[0074] In this modified example, a method of reducing the required resources has been described by setting the reference transparency TrR''_rate to a binary value based on the magnitude relationship between the reference reflected light image DrR and the reference transmitted light image TrR. However, for example, a method may be used in which the reference transparency TrR_rate defined by equation (1) is used when the reference transmitted light image TrR is larger than the reference reflected light image DrR, and the reference transparency is set to 0 in other cases.
[0075] <Modification 3> In the above-described embodiment and modifications, the reference reflected light image DrR and the reference transmitted light image TrR are generated by synthesizing the diffuse reflected light intensity image Dr and the specular transmitted light intensity image Tr obtained by reading a printed material. In contrast, in modification 3, the reference reflected light image DrR and the reference transmitted light image TrR are generated based on a raster image RIP using a known technique. Fig. 12 shows the configuration of an image processing unit 500 according to modification 3. The configuration is the same as that of embodiment 1 except for the method of generating the reference reflected light image DrR and the reference transmitted light image TrR.
[0076] [Embodiment 2] In the first embodiment, the weighted reference reflected light image DrRW and the weighted reference transmitted light image TrRW are generated based on the reference reflected light utilization ratio map Rmap_Dr and the reference transmitted light utilization ratio map Rmap_Tr. Then, the weighted inspection reflected light image DrTW and the weighted inspection transmitted light image TrTW are generated based on the inspection reflected light utilization ratio map Tmap_Dr and the inspection transmitted light utilization ratio map Tmap_Tr. In this embodiment, the reference reflected light utilization ratio map Rmap_Dr and the reference transmitted light utilization ratio map Rmap_Tr are also used to generate the weighted inspection reflected light image DrTW and the weighted inspection transmitted light image TrTW.
[0077] The configuration and system configuration of the image processing unit 500 that executes a series of processes described in the second embodiment are the same as those of the first embodiment, except for the weighting process for the inspection transmitted light image TrT and the inspection reflected light image DrT in the weighting unit 507. Therefore, a description will be omitted other than the weighting process for the inspection transmitted light image TrT and the inspection reflected light image DrT in the weighting unit 507. Note that in the second embodiment, the output of the inspection transmitted light image TrT from the transmitted light image acquisition unit 502 to the utilization ratio calculation unit 506, and the generation of the inspection reflected light utilization ratio map Tmap_Dr and the inspection transmitted light utilization ratio map Tmap_Tr by the utilization ratio calculation unit 506 are not required.
[0078] The weighting unit 507 performs weighting based on the reference reflected light utilization ratio map Rmap_DrR when generating the weighted reference reflected light image DrRW and the weighted inspection reflected light image DrTW. Also, the weighting unit 507 performs weighting based on the reference transmitted light utilization ratio map Rmap_Tr when generating the weighted reference transmitted light image TrRW and the weighted inspection transmitted light image TrTW.
[0079] <Main flow> Fig. 13 is a flowchart showing the inspection process including the inspection process executed by the image processing unit 500 in this embodiment. The CPU 401 reads and executes a program according to the flowchart shown in Fig. 13. Note that S701 and S703 to S707 are the same as those in the first embodiment, and therefore the description thereof will be omitted.
[0080] In S1301, the weighting unit 507 acquires an inspection transmitted light image TrT and an inspection reflected light image DrT from the transmitted light image acquisition unit 502 and the reflected light image acquisition unit 503.
[0081] In S1302, the weighting unit 507 acquires the inspection reflected light image DrT, the inspection transmitted light image TrT, the reference reflected light utilization ratio map Rmap_Dr, and the reference transmitted light utilization ratio map Rmap_Tr, and generates an inspection image T for inspection. Fig. 14 is a flowchart showing the details of S1302 in this embodiment. The CPU 401 reads out and executes a program following the flowchart shown in Fig. 14.
[0082] In S1401, the weighting unit 507 acquires the reference reflected light utilization ratio map Rmap_Dr and the reference transmitted light utilization ratio map Rmap_Tr generated in S802.
[0083] In S1402, the weighting unit 507 weights the inspection reflected light image DrT with the reference reflected light utilization ratio map Rmap_Dr, and weights the inspection transmitted light image TrT with the reference transmitted light utilization ratio map Rmap_Tr, as shown in equation (8), and determines the sum of these as the inspection image T.
[0084]
number
[0085] As described above, in this embodiment, by using only the reference reflected light utilization ratio map Rmap_Dr and the reference transmitted light utilization ratio map Rmap_Tr as the utilization ratio maps, it is possible to reduce processing costs.
[0086] [Embodiment 3] In the first embodiment, the positional deviation of the reference reflected light image DrR, the reference transmitted light image TrR, the test reflected light image DrT, and the test transmitted light image TrT was not taken into consideration. In this embodiment, the reference reflected light image DrR and the reference transmitted light image TrR, and the test reflected light image DrT and the test transmitted light image TrT are aligned before the test process is performed. Note that the configuration and system configuration of the image processing unit 500 that executes the series of processes described in the third embodiment are the same as those of the first embodiment except for the alignment unit 1501 as shown in FIG. 15, and therefore the description of the configuration other than the alignment unit 1501 will be omitted.
[0087] <Explanation of a block diagram of an image processing device according to the third embodiment> 15 shows a system configuration of an image processing unit 500 related to the inspection process of embodiment 3. The image processing unit 500 has a registration unit 1501 in addition to the configuration of embodiment 1. In this embodiment, an image used as a reference for registration is referred to as a reference reflected light image DrR.
[0088] The alignment unit 1501 acquires a reference reflected light image DrR and a reference transmitted light image TrR, performs alignment processing on the reference transmitted light image TrR based on the reference reflected light image DrR, and outputs the parameters used for alignment and the aligned reference transmitted light image TrR_ALI. The alignment unit 1501 further acquires an inspection reflected light image DrT and an inspection transmitted light image TrT, and also performs alignment processing on the inspection reflected light image DrT and the inspection transmitted light image TrT based on the reference transmitted light image TrR. The alignment unit 1501 then outputs the aligned inspection reflected light image DrT_ALI and the aligned inspection transmitted light image TrT_ALI.
[0089] <Main flow> Fig. 16 is a flowchart showing the inspection process including the inspection process executed by the image processing unit 500 in the embodiment 3. The CPU 401 reads and executes a program according to the flowchart shown in Fig. 16. Note that S702 and S704 to S709 are the same as those in the embodiment 1, and therefore the description thereof will be omitted.
[0090] In S1601, the alignment unit 1501 acquires a reference transmitted light image TrR and a reference reflected light image DrR from the reference transmitted light image generation unit 504 and the reference reflected light image generation unit 505.
[0091] In S1602, the alignment unit 1501 performs a first alignment process on the acquired reference transmitted light image TrR based on the reference reflected light image DrR, and updates the reference transmitted light image TrR with the aligned reference transmitted light image TrR_ALI. Outputs the first parameters used for alignment. Although the detailed flow will be described later, the alignment process uses known techniques.
[0092] In S1603, the alignment unit 1501 acquires an inspection reflected light image DrT and an inspection transmitted light image TrT.
[0093] In S1604, the alignment unit 1501 performs a second alignment process on the acquired inspection reflected light image DrT based on the reference reflected light image DrR, and updates the inspection reflected light image DrT with the aligned inspection reflected light image DrT_ALI. Similarly, a second alignment process is performed on the inspection transmitted light image TrT based on the aligned reference transmitted light image TrR_ALI, and the inspection transmitted light image TrT is updated with the aligned inspection transmitted light image TrT_ALI. Although the detailed flow will be described later, the alignment process uses known techniques.
[0094] <Processing flow of S1602> FIG. 17 is a flowchart showing the details of the process of S1602 in the present embodiment. The CPU 401 reads and executes a program along the flowchart shown in FIG. 17.
[0095] In S1701, the alignment unit 1501 obtains first alignment parameters from the reference reflected light image DrR and the reference transmitted light image TrR respectively. The first alignment parameter is a parameter for correcting the deviation between the reference reflected light image DrR and the reference transmitted light image TrR. In the case where the image reading device 405 reads the diffuse reflected light intensity image Dr and the direct transmitted light intensity image Tr with separate light receiving elements, in order to correct the deviation of the light receiving elements, a method of calculating the first alignment parameter in advance during calibration is used.
[0096] In S1702, the alignment unit 1501 performs alignment processing on the reference reflected light image DrR based on the first alignment parameter obtained in S1701, and generates an aligned reference transmitted light image TrR_ALI.
[0097] In S1703, the alignment unit 1501 updates the reference transmitted light image TrR with the aligned reference transmitted light image TrR_ALI generated in S1702.
[0098] <Processing flow of S1604> FIG. 18 is a flowchart showing the details of the process of S1604 in the present embodiment. The CPU 401 reads and executes a program according to the flowchart shown in FIG. 18.
[0099] In S1801, the alignment unit 1501 obtains a second alignment parameter. The second alignment parameter is a parameter for correcting the deviation between the reference image and the inspection image. The second alignment parameter is calculated using the reference transmitted light image TrR and the inspection transmitted light image TrT.
[0100] In S1802, the alignment unit 1501 generates an aligned inspection reflected light image DrT_ALI by the second alignment process based on the reference reflected light image DrR, the inspection reflected light image DrT, and the second alignment parameters. Also, the alignment unit 1501 generates an aligned inspection transmitted light image TrT_ALI' by the second alignment process based on the reference transmitted light image TrR, the inspection transmitted light image TrT, the second alignment parameters, and the second alignment process. Furthermore, the alignment unit 1501 performs a first alignment process on the aligned inspection transmitted light image TrT_ALI' by the second alignment process, and outputs the inspection transmitted light image TrT_ALI.
[0101] In S1803, the alignment unit 1501 updates the inspection reflected light image DrT with the aligned inspection reflected light image DrT_ALI generated in S1802, and updates the inspection transmitted light image TrT with the aligned inspection transmitted light image Tr_ALI.
[0102] By the above processing, in embodiment 3, it is possible to maintain high inspection accuracy even if positional misalignment occurs in the reference reflected light image DrR, the reference transmitted light image TrR, the inspection reflected light image DrT, and the inspection transmitted light image TrT.
[0103] (Other Examples) The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) that implements one or more of the functions.
[0104] The present disclosure includes the following configurations and methods.
[0105] [Configuration 1] 1. An image processing device for inspecting a printed matter printed on a transparent paper for the presence or absence of defects, comprising: a first acquisition means for acquiring a first reference image corresponding to a distribution of diffuse reflected light and a second reference image corresponding to a distribution of regular transmitted light, which serve as a reference in the inspection of the printed matter; a second acquisition means for acquiring a first inspection object image obtained by reading diffuse reflected light from the printed matter and a second inspection object image obtained by reading specularly transmitted light from the printed matter; an inspection means for inspecting the presence or absence of defects in the printed matter based on at least one of a first comparison result between the first reference image and the first inspection target image and a second comparison result between the second reference image and the second inspection target image according to the transparency of each area of the printed matter; An image processing device comprising:
[0106] [Configuration 2] the inspection means inspects the low transparency region based on the first comparison result, and inspects the high transparency region based on the second comparison result; 2. The image processing device according to claim 1,
[0107] [Configuration 3] The method further includes deriving means for deriving a utilization ratio distribution of diffuse reflected light and regular transmitted light based on the transparency of each region of the printed matter, the inspection means weights the first and second comparison results based on the utilization ratio distribution, and inspects based on the weighted ratio of the first and second comparison results; 3. The image processing device according to configuration 1 or 2.
[0108] [Configuration 4] the derivation means calculates the transparency based on a ratio between a pixel value of the second reference image and an intensity of light irradiated when reading the printed matter; 4. The image processing device according to configuration 3.
[0109] [Configuration 5] the derivation means calculates, as the transparency, a first transparency based on a ratio between a pixel value of the second reference image and an intensity of light irradiated when reading the printed matter, and a second transparency based on a ratio between a pixel value of the second inspection target image and an intensity of light irradiated when reading the printed matter, deriving a weighting utilization ratio distribution for the first and second reference images based on the first transparency, and deriving a weighting utilization ratio distribution for the first and second inspection target images based on the second transparency. 5. The image processing device according to configuration 3 or 4.
[0110] [Configuration 6] The derivation means determines a utilization rate of regular transmitted light in the utilization ratio distribution based on the transparency. 6. The image processing device according to any one of configurations 3 to 5.
[0111] [Configuration 7] the derivation means determines a utilization rate of diffuse reflected light in the utilization ratio distribution based on the transparency and a light absorptance of the transparent paper; 7. The image processing device according to any one of configurations 3 to 6,
[0112] [Configuration 8] The utilization rate of the specularly transmitted light and the utilization rate of the diffusely reflected light are determined so that the sum of the utilization rate of the specularly transmitted light and the utilization rate of the diffusely reflected light is constant. 8. The image processing device according to configuration 7.
[0113] [Configuration 9] the inspection means performs a registration process on the first and second reference images and the first and second inspection target images; 9. The image processing device according to any one of configurations 1 to 8.
[0114] [Configuration 10] the first reference image and the second reference image are images generated by synthesizing a plurality of images obtained by reading the printed matter; 10. The image processing device according to any one of configurations 1 to 9.
[0115] [Configuration 11] the first reference image and the second reference image are images generated based on print data for printing the printed matter; 10. The image processing device according to any one of configurations 1 to 9.
[0116] [Configuration 12] 1. An image processing method for inspecting a printed matter printed on a transparent paper for the presence or absence of defects, comprising: acquiring a first reference image corresponding to a distribution of diffuse reflected light and a second reference image corresponding to a distribution of specular transmitted light, which serve as a reference for inspection of the printed matter; acquiring a first inspection object image obtained by reading diffuse reflected light from the printed matter and a second inspection object image obtained by reading specularly transmitted light from the printed matter; inspecting the printed matter for defects based on at least one of a first comparison result between the first reference image and the first inspection target image and a second comparison result between the second reference image and the second inspection target image according to the transparency of each region of the printed matter; An image processing method comprising:
[0117] [Configuration 13] A program for causing a computer to function as the image processing device according to any one of configurations 1 to 11. [Explanation of symbols]
[0118] 500 Image Processing Unit 502 Transmitted light image acquisition unit 503 Reflected light image acquisition unit 504 Reference transmitted light image generating unit 505 Reference reflected light image generating unit 506 Usage ratio calculation section 507 Weighting section 508 Inspection Processing Unit
Claims
1. A first acquisition means for acquiring a first inspection target image obtained by receiving reflected light from a printed material and a second inspection target image obtained by receiving transmitted light from the printed material, A second acquisition means for acquiring a first reference image corresponding to the first image to be inspected and a second reference image corresponding to the second image to be inspected, An inspection means that performs, for each region in the printed material, at least one of a first inspection using the first reference image and the first image to be inspected, and a second inspection using the second reference image and the second image to be inspected, An image processing apparatus characterized by comprising:
2. The image processing apparatus according to claim 1, characterized in that the inspection means performs at least one of the first inspection and the second inspection based on the transparency of each area in the printed material.
3. The inspection means performs the first inspection on areas with low transparency and the second inspection on areas with high transparency. The image processing apparatus according to claim 2.
4. The invention further comprises a derivation means for deriving the utilization ratio distribution of reflected light and transmitted light based on the transparency of each region of the printed material. The inspection means weights the results of the first inspection and the results of the second inspection based on the utilization ratio distribution. The image processing apparatus according to feature 1.
5. The derivation means calculates the transparency based on the ratio of the pixel values of the second reference image to the light intensity irradiated when reading the printed material. The image processing apparatus according to feature 4.
6. The derivation means calculates a first transparency based on the ratio of the pixel value of the second reference image to the light intensity irradiated when reading the printed material, and a second transparency based on the ratio of the pixel value of the second inspection target image to the light intensity irradiated when reading the printed material. The weighting ratio distribution for the first and second reference images is derived based on the first transparency, and the weighting ratio distribution for the first and second inspection target images is derived based on the second transparency. The image processing apparatus according to feature 4.
7. The derivation means determines the utilization rate of transmitted light in the utilization ratio distribution based on the transparency. The image processing apparatus according to feature 4.
8. The derivation means determines the utilization rate of reflected light in the utilization ratio distribution based on the transparency and the light absorption rate of the transparent paper. The image processing apparatus according to feature 4.
9. The utilization rate of transmitted light and the utilization rate of reflected light are determined such that the sum of the utilization rate of transmitted light and the utilization rate of reflected light is constant. The image processing apparatus according to feature 8.
10. The inspection means performs alignment processing on the first and second reference images and the first and second images to be inspected. The image processing apparatus according to feature 1.
11. The first reference image and the second reference image are images generated by combining multiple images obtained by reading the printed material. The image processing apparatus according to feature 1.
12. The first reference image and the second reference image are images generated based on print data for printing the printed material. The image processing apparatus according to feature 1.
13. The steps include obtaining a first inspection target image obtained by receiving reflected light from a printed material and a second inspection target image obtained by receiving transmitted light from the printed material, The steps include obtaining a first reference image corresponding to the first image to be inspected and a second reference image corresponding to the second image to be inspected, For each region in the printed material, the steps include performing at least one of a first inspection using the first reference image and the first image to be inspected, and a second inspection using the second reference image and the second image to be inspected. An image processing method characterized by comprising:
14. A program for causing a computer to function as an image processing device according to any one of claims 1 to 12.