Image inspection device, image inspection system, and program

Abstract

To provide an image inspection device, an image inspection system, and a program, capable of comparing printing data being data to become a source of a printed image with reading data obtained by reading the printed image, and performing alignment for even an image having a periodic structural feature or an image having no structural feature when inspecting the printed image.SOLUTION: An image inspection device 30 includes a processor. The processor acquires printing data being data to become a source of a printing image, acquires reading data obtained by reading an image printed on a sheet, identifies whether the printing data or the reading data corresponds to either an image having a periodic structural feature or an image having no structural feature, performs alignment using a position correction amount being a correction amount for aligning a position of the image of the printing data and a position of the image of the reading data, which is calculated for the already printed image when the data corresponds to the image having the periodic structural feature or the image having no structural feature, and compares the printing data with the reading data so as to inspect the image.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to an image inspection device, an image inspection system, and a program. [Background technology]

[0002] Conventionally, image inspection devices are used to inspect printed images by comparing print data, which is the source of the image to be printed, with scanned data obtained by scanning the printed image. At this time, alignment marks are added to the image to align the image based on the print data with the image based on the scanned data.

[0003] Patent Document 1 describes an inspection system that performs alignment processing by printing an image pattern with low visual sensitivity on a printed image of an inspection target from which feature points cannot be extracted. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2012-232510 Summary of the Invention [Problem to be solved by the invention]

[0005] However, there are cases where it is not possible to provide marks for alignment depending on the type of paper, etc. In such cases, if you try to align the image based on the image rather than using marks, it can be difficult to align the image with periodic structural features such as a continuous vertical pattern, or with no structural features such as an image that is almost entirely halftone. The present invention aims to provide an image inspection device, an image inspection system, and a program that can align images with periodic structural features or images without structural features when inspecting printed images by comparing print data that is the source of the printed image with read data obtained by reading the printed image. [Means for solving the problem]

[0006] The invention described in claim 1 includes a processor, which acquires print data, which is data that is the source of an image to be printed, acquires read data, which is data obtained by reading the image printed on paper, identifies whether the print data or the read data is an image that corresponds to either an image with periodic structural features or an image without structural features, and if the print data or the read data is an image with periodic structural features or an image without structural features, aligns the image using a position correction amount that is a correction amount for aligning the position of an image based on the print data and an image based on the read data, calculated for an image that has already been printed, compares the print data with the read data, and inspects the image. The case where the structural feature corresponds to an image having a periodic structure or an image having no structural feature is a case where a feature amount is extracted from the print data and / or the read data, and the position correction amount cannot be calculated using the feature amount, and the feature amount is a matching degree when the print data and the read data are moved relatively in parallel. It is an image inspection device. Claim 2 The invention described in claim 2 is characterized in that the processor cannot calculate the position correction amount when the matching degree does not reach a predetermined range within the predetermined range of the amount of translation. 1 2. An image inspection device according to claim 1. Claim 3 The invention described in an image inspection device including a processor, the processor acquiring print data which is data that is the source of an image to be printed, acquiring read data which is data obtained by reading the image printed on paper, identifying whether the print data or the read data is an image that corresponds to either an image with periodic structural features or an image with no structural features, and if the print data or the read data is an image with periodic structural features or an image with no structural features, aligning the image using a position correction amount that is a correction amount for aligning the position of an image based on the print data and an image based on the read data, calculated for an image that has already been printed, comparing the print data with the read data, and inspecting the image, the processor identifying the image with periodic structural features by detecting repetition of pixel values ​​in the print data. is. Claim 4 The invention described in claim 1 is characterized in that the processor determines that the image has periodic structural features when the pixel values ​​are the same for every predetermined number of pixels in the print data in the paper transport direction and / or in a direction intersecting the transport direction. 3 2. An image inspection device according to claim 1. Claim 5 The invention described in an image inspection device including a processor, the processor acquiring print data which is data that is the source of an image to be printed, acquiring read data which is data obtained by reading the image printed on paper, identifying whether the print data or the read data is an image that corresponds to either an image with periodic structural features or an image that does not have structural features, and if the image corresponds to an image with periodic structural features or an image that does not have structural features, aligning the image using a position correction amount that is a correction amount for aligning the position of an image based on the print data and an image based on the read data, calculated for an image that has already been printed, comparing the print data with the read data, and inspecting the image, the processor determining that the image does not have the structural features when pixel values ​​fall within a predetermined range in a predetermined area of ​​the print data. is. Claim 6 The invention described in claim 1 is an image inspection device according to claim 1, wherein the already printed image is an image printed one page before. Claim 7The invention described in the item (1) comprises a printing device that prints an image on paper, a reading device that reads the image printed on paper by the printing device, and an image inspection device that inspects the image read by the reading device, wherein the image inspection device has a processor, and the processor acquires print data that is data that is the source of an image to be printed, acquires read data that is data obtained by reading the image printed on paper, identifies whether the print data or the read data is an image that corresponds to either an image with periodic structural features or an image without structural features, and if the image corresponds to an image with periodic structural features or an image without structural features, aligns the image using a position correction amount that is a correction amount for aligning the position of an image based on the print data and an image based on the read data that is calculated for an image that has already been printed, compares the print data with the read data, and inspects the image. The case where the structural feature corresponds to an image having a periodic structure or an image having no structural feature is a case where a feature amount is extracted from the print data and / or the read data, and the position correction amount cannot be calculated using the feature amount, and the feature amount is a matching degree when the print data and the read data are moved relatively in parallel. It is an image inspection system. Claim 8 The invention described in is a program for causing a computer to realize the following functions: acquiring print data, which is data that is the source of an image to be printed; acquiring read data, which is data obtained by reading the image printed on paper; identifying whether the print data or the read data is an image that corresponds to either an image with periodic structural features or an image without structural features; and, if the print data or the read data corresponds to an image with periodic structural features or an image without structural features, performing position adjustment using a position correction amount that is a correction amount for adjusting the position of an image based on the print data and an image based on the read data, which is calculated for an image that has already been printed; and comparing the print data with the read data and inspecting the image. The case where the structural feature corresponds to an image having a periodic structure or an image having no structural feature is a case where a feature amount is extracted from the print data and / or the read data, and the position correction amount cannot be calculated using the feature amount, and the feature amount is a matching degree when the print data and the read data are moved in parallel relative to each other. is. [Effects of the Invention]

[0007] According to the invention of claim 1, when inspecting a printed image by comparing the print data that is the source of the printed image with the read data obtained by reading the printed image, alignment can be performed even for images with periodic structural features or images with no structural features. Furthermore, according to the invention of claim 1, it becomes easier to determine whether alignment is possible. Claim 2 According to the invention, it becomes easier to determine that the position correction amount cannot be calculated. Claim 3、4 According to the invention, images with periodic structural features can be more easily detected. Claim 5 According to the invention, images without structural features can be more easily detected. Claim 6 According to the invention, a more appropriate value can be set as the amount of position correction. Claim 7 According to the invention, an image inspection system can be provided that compares the print data that is the source of the printed image with the read data obtained by reading the printed image, and when inspecting the printed image, aligns the image even if the image has periodic structural features or no structural features, and inspects the image. Claim 8 According to the invention, when inspecting a printed image, the printing data that is the basis of the printed image is compared with the read data obtained by reading the printed image, and the computer can realize a function that can align images that have periodic structural features or images that have no structural features. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating a configuration example of an image inspection system according to an embodiment. [Figure 2] FIG. 2 illustrates an example of the hardware configuration of a printing apparatus. [Figure 3] 1(a) and 1(b) are diagrams illustrating a reading device. [Figure 4] FIG. 1 is a diagram showing a processing flow performed in an image inspection system. [Figure 5] FIG. 2 is a block diagram showing a signal processing system in the information processing device. [Figure 6] FIG. 1 is a diagram illustrating template matching. [Figure 7] 10(a) and 10(b) are diagrams showing an example in which periodicity exists in an image. [Figure 8] 10 is a first example showing a positioning method according to the present embodiment. [Figure 9] 10 is a second example showing the alignment method according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0010] <Explanation of the overall image inspection system> FIG. 1 is a diagram showing an example of the configuration of an image inspection system 1 according to this embodiment. As shown in the figure, the image inspection system 1 of this embodiment comprises a printing device 10 that prints an image, a reading device 20 that reads the printed image, an image inspection device 30 that inspects the image, and an information processing device 40 that creates printing data and color data for inspection.

[0011] The printing device 10 is a device that has a printer function for printing an image on paper, which is a recording medium, and outputting the image as a printed document.

[0012] FIG. 2 is a diagram showing an example of the hardware configuration of the printing device 10. As shown in FIG. As shown in the figure, the printing device 10 includes a CPU 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, a storage 14, an operation panel 15, an image forming unit 16, and a communication I / F 17. These components exchange necessary data via a bus B.

[0013] The CPU 11 loads various programs stored in the ROM 13 or the like into the RAM 12 and executes them to realize various functions, which will be described later. The RAM 12 is a memory used as a working memory for the CPU 11, etc. The ROM 13 is a memory that stores various programs executed by the CPU 11. The storage 14 is a hard disk drive (HDD) or a solid state drive (SSD), and stores image information and the like used by the image forming unit 16.

[0014] The operation panel 15 is, for example, a touch panel that displays various types of information and accepts operation inputs from the user. When the operation panel 15 is a touch panel, it has a display unit such as a liquid crystal panel that displays content (information content) as an image in a predetermined area. It also has a function of detecting the position of a contact object, such as a human finger or a stylus pen, when the contact object touches the liquid crystal panel. In this embodiment, the touch panel is not particularly limited, and various types such as a resistive film type or a capacitive type can be used.

[0015] The image forming unit 16 is an example of a printing mechanism that forms an image on paper. Here, the image forming unit 16 can use an electrophotographic method that forms an image by transferring toner attached to a photosensitive member onto paper, or an inkjet method that forms an image by ejecting ink onto paper.

[0016] The communication I / F 17 transmits and receives various information to and from other devices.

[0017] The reading device 20 reads an image printed on paper by the printing device 10. The reading device 20 is a so-called in-line sensor, and reads an image printed on paper while it is being transported. 3(a) and 3(b) are diagrams illustrating the reading device 20. Here, Fig. 3(a) is a diagram of the reading device 20 viewed from the same direction as Fig. 1. Fig. 3(b) is a diagram of the reading device 20 viewed from the direction IIIb in Fig. 3(a). As shown in the figure, the reading device 20 includes a light source 21, an optical system 22, a CCD (Charge Coupled Device) sensor 23, and a housing 24.

[0018] The light source 21 irradiates light onto the paper P on which an image has been formed. The light source 21 is composed of, for example, a pair of tungsten lamps 21a and 21b. The light source 21 irradiates the image formed on the paper P with light, generating reflected light that contains information about the image.

[0019] The optical system 22 guides light reflected from the image formed on the paper P to the CCD sensor 23. In this embodiment, the optical system 22 is made up of a SELFOC lens array (SLA: registered trademark), which is a lens array. This SELFOC lens array collects mainly diffusely reflected light out of the light reflected from the image, and forms an image on the CCD sensor 23.

[0020] The CCD sensor 23 receives light guided by the optical system 22. The CCD sensor 23 has CCDs 23a arranged in a line as pixels that receive light reflected from the image. In this embodiment, CCDs corresponding to the colors R (Red), G (Green), and B (Blue) are arranged in three lines, allowing the image to be measured in each of the RGB colors. In other words, the CCD 23a is a three-line color CCD. The CCDs 23a are arranged in the main scanning direction for each RGB color. This allows the image to be read in the main scanning direction. In addition, the sub-scanning direction allows reading in accordance with the movement of the paper as it is transported. The light received by the CCD 23a is photoelectrically converted into electric charges, and these electric charges are transferred to the read data generation unit 23b.

[0021] The read data generating unit 23b detects the charges transferred from the CCD 23a and generates a detection signal. This detection signal becomes read data obtained by reading the image formed on the paper. Since the CCD 23a is a color CCD for three colors, R, G, and B, the read data generating unit 23b generates an R signal, a G signal, and a B signal as read data corresponding to each color.

[0022] The housing 24 is a case for housing the light source 21, the optical system 22, and the CCD sensor 23.

[0023] The image inspection device 30 inspects the image read by the reading device 20. The image inspection device 30 acquires print data, which is the data that forms the basis of the image to be printed, from the information processing device 40. The image inspection device 30 also acquires read data from the read data generation unit 23b of the reading device 20. The image inspection device 30 then compares the print data with the read data to inspect the image. This will be described in detail later. The information processing device 40 creates print data, which will also be described in detail later.

[0024] The image inspection device 30 and the information processing device 40 are computer devices. The image inspection device 30 and the information processing device 40 perform their respective processes by running various application software under the control of an OS (Operating System). The image inspection device 30 and the information processing device 40 include a CPU (Central Processing Unit) as a computing means, a main memory as a storage means, and storage such as an HDD or SSD. The CPU executes various programs such as the OS and application software. The main memory is a storage area that stores various programs and data used to execute them, and the storage is a storage area that stores input data for various programs and output data from various programs. The image inspection device 30 and the information processing device 40 also include a communication interface for communicating with the outside. The CPU is an example of a processor.

[0025] FIG. 4 is a diagram showing a processing flow performed by the image inspection system 1. As shown in the figure, in the image inspection system 1, an information processing device 40 creates print data to be printed by the printing device 10. This print data is RIP (Raster Image Processor) data, and is color data based on the colors of color materials such as toner used in the printing device 10. In this embodiment, C (cyan), M (magenta), Y (yellow), and K (black) are used as the colors of the color materials.

[0026] The printing device 10 prints on paper based on the print data. The printed paper is then transported, and the printed image is read by the reading device 20. The read data read by the reading device 20 is then sent to the image inspection device 30 as inspection image data.

[0027] In the image inspection device 30, the data acquisition unit 31 acquires print data, which is the original data for the image to be printed and created by the information processing device 40. The data acquisition unit 31 also acquires inspection image data as read data, which is data obtained by reading an image printed on paper and sent from the reading device 20. At this time, the alignment unit 32 aligns the image based on the print data with the image based on the inspection image data. Then, for the inspection image data, the edge extraction unit 33 performs edge extraction and extracts a portion of the image. Then, the difference between the print data and the inspection image data is calculated. The threshold calculation unit 34 also calculates a threshold value based on the print data for determining image defects. This threshold value determines that there is no image defect if the difference between the print data and the inspection image data is equal to or less than the threshold value, and determines that there is an image defect if the difference exceeds the threshold value. The threshold comparison unit 35 then compares the difference between the print data and the inspection image data with the threshold value, and the output unit 36 ​​outputs the image defect extraction result. This makes it possible to detect whether or not there is an image defect in the image printed by the printing device 10. The image defects are, for example, when dust adheres to the paper, or when non-existent dots or streaks appear in the image. That is, the image inspection device 30 compares the print data with the inspection image data and inspects the image.

[0028] At this time, the inspection image data, which is the read data sent from the reading device 20, is RGB data. Also, the print data sent from the information processing device 40 is converted into RGB data by an RGB conversion unit 49 in FIG. 5, which will be described later. Then, the image inspection device 30 compares the print data with the corrected inspection image data in the same color space, RGB color space, and inspects the image. Note that the inspection image data sent from the reading device 20 is converted from RGB data to L color data in the image inspection device 30. * a* b * In this case, the information processing device 40 may convert the L data into RGB data. * a * b * Furthermore, the image inspection device 30 converts the print data into L * a * b * Then, the image inspection device 30 acquires the data in the same color space, L * a * b * The print data is compared with the corrected inspection image data in color space to inspect the image.

[0029] <Description of Information Processing Device 40> Next, the processing performed by the information processing device 40 will be described in detail. FIG. 5 is a block diagram showing a signal processing system in the information processing device 40. As shown in FIG. The information processing device 40 includes an RGB data acquisition unit 41 that acquires RGB data created to output an image on the printing device 10, a PDL generation unit 42 that receives RGB (Red, Green, Blue) data and converts it into a page description language (PDL), a rasterize unit 43 that creates a raster image from the PDL created by the PDL generation unit 42, a color conversion processing unit 44 that converts RGB data into CMYK data, a color adjustment unit 45 that performs color adjustment on the CMYK data, a raster image adjustment unit 46 that adjusts the raster image converted by the color adjustment unit 45, a halftone processing unit 47 that performs halftone processing, a print data output unit 48 that outputs the print data after signal processing to the printing device 10, and an RGB conversion unit 49 that converts CMYK data into RGB data.

[0030] In this embodiment, first, RGB data is received from an external PC by RGB data acquisition unit 41. This RGB data is image data that a user of the PC wants to print using printing device 10. The RGB data is then sent to the PDL generation unit 42, which converts it into code data written in PDL and outputs it.

[0031] The rasterizing unit 43 converts the code data written in the PDL output from the PDL generating unit 42 into raster data for each pixel, thereby creating a raster image.

[0032] The color conversion processing unit 44 converts the raster data input from the rasterization unit 43 into CMYK data, which is the reproduction color (CMYK, which is the color of the toner, which is the color material) of the printing device 10, and outputs the converted data. This CMYK data consists of C color data, M color data, Y color data, and K color data separated for each color.

[0033] The color adjustment unit 45 functions as a color adjustment means for adjusting the colors of the image formed by the printing device 10. The color adjustment unit 45 adjusts the colors of the CMYK data so that they match the target colors that should originally be output by the printing device 10.

[0034] The raster image adjustment unit 46 performs various adjustments on the CMYK data output from the color adjustment unit 45, such as gamma conversion, resolution processing, and halftone processing, to enable the printing device 10 to obtain better image quality.

[0035] The halftone processing unit 47 performs halftone processing on the print data by dither mask processing using a dither mask having a predetermined threshold array in the main scanning direction and the sub-scanning direction, thereby converting the print data, for example, from multi-valued to binary print data.

[0036] The print data output unit 48 outputs the print data created by the halftone processing unit 47 to the printing device 10. This print data is CMYK data.

[0037] The RGB conversion unit 49 reconverts the CMYK data output from the raster image adjustment unit 46 into RGB data, and outputs the print data converted into RGB data to the image inspection device 30.

[0038] <Description of Alignment Unit 32> Next, a method for aligning an image based on print data and an image based on inspection image data in the alignment unit 32 of the image inspection device 30 will be described in detail. The alignment unit 32 determines whether the print data or test image data corresponds to an image with periodic structural features or an image with no structural features. Here, "structural features" are image features determined by the pixel values ​​of the pixels that make up the image. If the image is not one of these, the alignment unit 32 aligns the image using a position correction amount, which is a correction amount for aligning the position of the image based on the print data and the image based on the test image data. On the other hand, if the image is one of these, the alignment unit 32 aligns the image using a position correction amount calculated for an image that has already been printed. An image that has already been printed is, for example, an image printed one page before.

[0039] The alignment of both images is performed by, for example, template matching. FIG. 6 is a diagram illustrating template matching. 6 shows the blocks B that are set for template matching. Here, block B1 is set as block B for the image based on the print data. Block B2 is set at a position corresponding to block B1 for the image based on the inspection image data. In practice, for example, 40 blocks B are set for each image, and template matching is performed for each of them. Then, either block B1 or block B2 is moved, and the pixel values ​​in block B1 and block B2 are compared. Here, for example, the pixel values ​​of each pixel in block B1 are calculated as (L1 * , a1 * , b1 * ) and the pixel value of each pixel in the block B1 at the corresponding position is (L2 * , a2 * , b2 *) Note that the print data is CMYK data and the test image data is RGB data, so * a * b1 * Convert it into data. Then, the positioning unit 32 calculates (L2 * -L1 * ) 2 +(a2 * -a1 * ) 2 +(b2 * -b1 * ) 2 Then, the difference e defined by the following equation (1) is calculated as the sum of the values ​​for all pixels in the blocks B1 and B2.

[0040] e=Σ{(L2 * -L1 * ) 2 +(a2 * -a1 * ) 2 +(b2 * -b1 * ) 2} …(1)

[0041] The positioning unit 32 then translates the block B2 in the left-right and up-down directions within the image to find the point where the difference e is minimum, and sets the minimum value of the difference e as the minimum color difference value.

[0042] The alignment unit 32 also calculates the amount of movement when the difference e is minimum. The amount of parallel movement when the difference e is minimum can be considered to be the amount of misalignment between the print data and the test image data at that point. This amount of misalignment can also be considered to be the amount of position correction, which is a value for correcting the position. The amount of movement in the left-right direction (main scanning direction) of the image is Δx, and the amount of parallel movement in the up-down direction (sub-scanning direction) of the image is Δy. If the pixel located at (x, y) in block B1 corresponds to the pixel located at (u, v) in block B2, these can be expressed as Δx = xu and Δy = yv. Note that although block B2 is translated here, block B1 may also be translated.

[0043] As described above, in this embodiment, the alignment unit 32 extracts feature values ​​from the print data and / or test image data and performs alignment using these feature values. In this case, the feature value is the degree of matching when the print data and test image data are moved relatively in parallel. The "degree of matching" is a parameter that indicates the degree of identity of the images, such as the difference e. The feature value can also be said to be the pixel value or chromaticity of the image.

[0044] However, if the image based on the print data or the image based on the inspection image data is an image with periodic structural features, the alignment unit 32 may not be able to calculate the amount of position correction. 7(a) and 7(b) are diagrams showing a case where an image based on print data or an image based on inspection image data is an image with periodic structural features. Of these, Figure 7(a) shows an image based on print data, and Figure 7(b) shows an image based on test image data. These images have a vertical stripe pattern with successive vertical patterns, and are periodic in the horizontal direction in the figure. This means that the images based on print data and the images based on test image data are periodic images. When attempting to calculate the amount of position correction to align these images, the alignment unit 32 is unable to determine which location to align because the images have periodic structural features. For example, even if block B2 set in the image based on the inspection image data is moved vertically in the figure, the difference e when compared with the pixel values ​​in block B1 hardly changes, and it is impossible to determine the location where the difference e is smallest. As a result, the alignment unit 32 is unable to determine which location to align in the vertical direction, and alignment is not possible. Furthermore, even when moving horizontally in the figure, the same striped pattern is repeated, so the location where the difference e is smallest is repeated multiple times. As a result, the alignment unit 32 is unable to determine which location to align in the horizontal direction, and alignment is not possible.

[0045] In the above example, an image with periodic structural features has been described, but the present invention is not limited to this. For example, the position correction amount may not be calculated for an image without structural features. Examples of images without structural features include an entirely halftone image and an entirely white image.

[0046] Therefore, in this embodiment, this problem is solved by the following method. FIG. 8 shows a first example of the alignment method according to this embodiment. In FIG. 8, when the position correction amount is calculated, if the position correction amount exceeds a predetermined value and overflows, the image is considered to have periodic structural features or no structural features. First, the alignment unit 32 acquires the print data and the test image data from the data acquisition unit 31 (step 101). Next, the alignment unit 32 performs template matching (step 102). As a result, the alignment unit 32 determines whether the position correction amount has exceeded a predetermined value and overflowed (step 103). The alignment unit 32 predetermines the range for shifting block B1 or block B2 in the left-right direction (main scanning direction) and up-down direction (sub-scanning direction) of the image. This range is, for example, the range in which image misalignment can occur during normal printing. If the position correction amount falls outside this range, it is deemed that the position correction amount has overflowed. In other words, the point where the difference e is minimum cannot be determined, and the position correction amount cannot be calculated within the predetermined range. In this case, the position correction amount exceeds the predetermined range, resulting in an overflow. In other words, the alignment unit 32 predetermines that the position correction amount cannot be calculated if the matching degree (e.g., the difference e) does not reach a predetermined range within the predetermined range of the translation amount.

[0047] If there is no overflow (No in step 103), the position correction amount is determined, and alignment is performed using the determined position correction amount (step 104). On the other hand, if there is an overflow (Yes in step 103), the image is considered to have periodic structural features or no structural features, and the position adjustment is performed using the position correction amount when the previous page was printed (step 105). In other words, it is rare for the position misalignment to be large from page to page, and normally there is not much change from the previous page when it was printed. Therefore, if the position correction amount cannot be obtained, there is no problem even if the position correction amount when the previous page was printed is used.

[0048] FIG. 9 shows a second example of the alignment method according to this embodiment. In FIG. 9, before template matching, an image is identified as having periodic structural features or no structural features. First, the alignment unit 32 acquires the print data and the test image data from the data acquisition unit 31 (step 201). Next, the alignment unit 32 determines whether the image has periodic structural features from the print data (step 202). This determination can be made by determining whether the pixel values ​​are identical for every predetermined number of pixels in the print data. That is, the alignment unit 32 detects whether the same pixel values ​​are repeated in both the vertical and horizontal directions of the print data. The predetermined number of pixels is selected from, for example, two, four, or eight pixels. In this case, the alignment unit 32 determines the image has periodic structural features by detecting the repetition of pixel values ​​in the print data. More specifically, the alignment unit 32 determines that the image has periodic structural features when the pixel values ​​are identical for every predetermined number of pixels in the transport direction (sub-scanning direction) of the paper P and / or in the direction intersecting the transport direction (main scanning direction). Note that "same" here includes not only cases where the pixel values ​​are identical, but also cases where the pixel values ​​are approximately the same.

[0049] As a result, if the image does not have periodic structural features (No in step 202), the print data is used to determine whether the image has no structural features (step 203). To determine this, it is determined whether the pixel values ​​in a predetermined area of ​​the print data fall within a predetermined range. If this is the case, the alignment unit 32 determines that the image has no structural features. In other words, this means that similar pixel values ​​continue, which is the case for halftone images and all-white images. If the image does not have structural features (No in step 203), that is, if the image has structural features, the alignment unit 32 performs template matching (step 204).Then, the alignment unit 32 performs alignment using the calculated position correction amount (step 205). On the other hand, if the image has periodic structural features (Yes in step 202), or if the image has no structural features (Yes in step 203), the position correction amount used when printing the previous page is used for alignment (step 206).

[0050] In reality, as described above, template matching is performed for each block B, and the processes shown in Fig. 8 and Fig. 9 are performed for each block. In other words, there are cases where the position correction amount calculated within the image of one page is used, and cases where the position correction amount calculated for the previous page is used. When the position correction amount calculated for the previous page is used, the position correction amount for block B at the same position in the image of the previous page is used. In addition, the processes shown in FIG. 8 and FIG. 9 may be performed either alone or in combination. 8 and 9, when an image has periodic structural features or no structural features, the position correction amount used for the previous page is used, but this is not limited to this. For example, the average of the position correction amounts for the most recent pages of images that have already been printed may be used. In this case, a weighted average may be used, in which the weight is increased for the most recent page, rather than a simple arithmetic average.

[0051] According to the above-described embodiment, when inspecting a printed image by comparing the print data that is the basis of the printed image with the read data obtained by reading the printed image, alignment can be performed even for images with periodic structural features or images without structural features. This makes image alignment more accurate. As a result, false detections are less likely to occur when inspecting the image.

[0052] <Program Description> The processing performed by the image inspection device 30 in this embodiment described above is realized by the cooperation of software and hardware resources. That is, the CPU in the control computer provided in the information processing device 40 executes a program that realizes each function of the image inspection device 30, thereby realizing each function.

[0053] Therefore, in this embodiment, the processing performed by the image inspection device 30 can also be considered as a program that causes a computer to realize the following functions: acquire print data, which is the data that forms the basis of the image to be printed; acquire test image data, which is read data obtained by reading the image printed on paper P; identify whether the print data or test image data is an image that has periodic structural features or an image that has no structural features; if the print data or test image data is an image that has periodic structural features or an image that has no structural features, align the image using a position correction amount, which is a correction amount calculated for an already printed image to align the position of the image based on the print data with the image based on the test image data; and compare the print data with the read data and inspect the image.

[0054] The program for realizing this embodiment can be provided not only by communication means but also by being stored on a recording medium such as a CD-ROM.

[0055] Although the present embodiment has been described above, the technical scope of the present invention is not limited to the scope described in the above embodiment. It is clear from the claims that various modifications and improvements to the above embodiment are also included in the technical scope of the present invention. [Explanation of symbols]

[0056] REFERENCE SIGNS LIST 1... image inspection system, 10... printing device, 20... reading device, 30... image inspection device, 32... alignment unit, 40... information processing device

Claims

1. a processor; The processor: Obtain print data, which is the data that is the source of the image to be printed; acquiring read data obtained by reading the image printed on paper; Identifying whether the print data or the read data is an image that has periodic structural features or an image that has no structural features; If the image corresponds to an image in which the structural features are periodic or an image in which the structural features are not present, alignment is performed using a position correction amount, which is a correction amount for aligning the positions of the image based on the print data and the image based on the read data, calculated for an image that has already been printed; comparing the print data with the read data and inspecting the image; The case where the structural feature corresponds to an image having a periodic structure or an image having no structural feature is a case where a feature amount cannot be extracted from the print data and / or the read data and the position correction amount cannot be calculated using the feature amount, The feature amount is the degree of matching when the print data and the read data are moved relatively in parallel.

2. The image inspection device according to claim 1 , wherein the processor determines that the position correction amount cannot be calculated if the matching degree does not reach a predetermined range within a predetermined range of the amount of translation.

3. A processor is provided, The processor: Obtain print data, which is the data that is the source of the image to be printed; acquiring read data obtained by reading the image printed on paper; Identifying whether the print data or the read data is an image that has periodic structural features or an image that has no structural features; If the image corresponds to an image in which the structural features are periodic or an image in which the structural features are not present, alignment is performed using a position correction amount, which is a correction amount for aligning the positions of the image based on the print data and the image based on the read data, calculated for an image that has already been printed; comparing the print data with the read data and inspecting the image; The processor is an image inspection device that identifies images in which the structural features are periodic by detecting repetition of pixel values ​​in the print data.

4. The image inspection device of claim 3, wherein the processor determines that the image has periodic structural features when the pixel values ​​are the same for a predetermined number of pixels in the print data in the paper transport direction and / or a direction intersecting the transport direction.

5. A processor is provided, The processor: Obtain print data, which is the data that is the source of the image to be printed; acquiring read data obtained by reading the image printed on paper; Identifying whether the print data or the read data is an image that has periodic structural features or an image that has no structural features; If the image corresponds to an image in which the structural features are periodic or an image in which the structural features are not present, alignment is performed using a position correction amount, which is a correction amount for aligning the positions of the image based on the print data and the image based on the read data, calculated for an image that has already been printed; comparing the print data with the read data and inspecting the image; The image inspection device wherein the processor determines that the image is free of structural features when pixel values ​​in a predetermined area of ​​the print data fall within a predetermined range.

6. The image inspection device according to claim 1 , wherein the already printed image is an image printed one page before.

7. a printing device for printing an image on paper; a reading device that reads the image printed on paper by the printing device; an image inspection device that inspects the image read by the reading device; Equipped with The image inspection device includes a processor; The processor: Obtain print data, which is the data that is the source of the image to be printed; acquiring read data obtained by reading the image printed on paper; Identifying whether the print data or the read data is an image that has periodic structural features or an image that has no structural features; If the image corresponds to an image in which the structural features are periodic or an image without the structural features, alignment is performed using a position correction amount, which is a correction amount for aligning the positions of the image based on the print data and the image based on the read data, calculated for an image that has already been printed; comparing the print data with the read data and inspecting the image; The case where the structural feature corresponds to an image having a periodic structure or an image having no structural feature is a case where a feature amount cannot be extracted from the print data and / or the read data and the position correction amount cannot be calculated using the feature amount, An image inspection system, wherein the feature amount is the degree of matching when the print data and the read data are moved relatively in parallel.

8. On the computer, A function to acquire print data, which is the data that will be used to create the image to be printed; a function of acquiring read data obtained by reading the image printed on paper; a function of identifying whether the print data or the read data is an image that has periodic structural features or an image that has no structural features; When the image corresponds to an image having periodic structural features or an image having no structural features, a function of performing position adjustment using a position adjustment amount, which is a correction amount for adjusting the position of an image based on the print data and an image based on the read data, calculated for an image that has already been printed; a function of comparing the print data with the read data and inspecting the image; A program for realizing the above, The case where the structural feature corresponds to an image having a periodic structure or an image having no structural feature is a case where a feature amount cannot be extracted from the print data and / or the read data and the position correction amount cannot be calculated using the feature amount, The feature amount is a degree of matching when the print data and the read data are moved relatively in parallel.

Images