Image processing apparatus, image processing method, and program

Abstract

To solve the problem in which: settings of a parameter for inspecting a print are complicated.SOLUTION: An image processing apparatus comprises: reference image acquisition means that acquires a reference image to be a reference of inspection of a print; read image acquisition means that acquires a read image obtained by reading the print; correction means that corrects the color of first areas in the reference image and the read image with a first correction condition, and corrects the color of second areas with a second correction condition; and inspection means that inspects the print on the basis of the color of the first areas corrected with the first correction condition and the color of the second areas corrected with the second correction condition.SELECTED DRAWING: Figure 2

Description

[Technical field]

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

[0002] Printed matter output by a printing device may have defects due to stains caused by color materials such as ink or toner adhering to unintended locations, or defects due to color loss caused by insufficient color materials adhering to locations where images should be formed. As a system for inspecting the presence or absence of such print defects, for example, there is a print inspection system that reads the printed matter output by a printing device with a line sensor of a camera or scanner, and automatically inspects whether printing is performed normally from the read image. In such a print inspection system, the presence or absence of print defects in the print to be inspected can be detected based on the difference between a reference image showing image data of a print without defects and a read image showing image data of the print to be inspected. In the print inspection system, the sensitivity for inspecting defects (for example, the contrast and size threshold value of the defect to be detected) can be adjusted, but since the inspection result varies greatly depending on the adjustment value of the inspection level, it is necessary to appropriately adjust the inspection level in order to obtain the desired inspection result. For example, Patent Document 1 proposes a method of outputting an image with artificially created defects, checking the inspection result, and adjusting the inspection level. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6241121 Summary of the Invention [Problem to be solved by the invention]

[0004] However, with the technique disclosed in Patent Document 1, it is necessary to confirm what type of defects will actually be detected and determine the parameters in accordance with the inspection level. Therefore, the technique of Patent Document 1 has a problem in that the setting of parameters for inspecting the printed matter becomes complicated.

[0005] An object of the present invention is to reduce the need for complicated setting of parameters for inspecting printed matter. [Means for solving the problem]

[0006] In order to solve this problem, for example, an image processing device of the present invention has the following configuration: That is, the image processing device has a reference image acquisition means for acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition means for acquiring a read image obtained by reading the printed matter; a correction unit that corrects a color of a first region in the reference image and the read image under a first correction condition and corrects a color of a second region in the reference image and the read image under a second correction condition; an inspection means for inspecting the printed matter based on the color of the first region corrected under the first correction condition and the color of the second region corrected under the second correction condition; The present invention is characterized by comprising: Effect of the Invention

[0007] According to the present invention, it is possible to reduce the need for complicated setting of parameters for inspecting printed matter. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing the configuration of a print inspection system. [Diagram 2] FIG. 2 is a block diagram showing the functional configuration of the image processing apparatus. [Diagram 3] 1 is a flowchart showing the flow of an image processing method. [Figure 4] 4A to 4C are diagrams showing examples of UIs displayed by a display unit. [Diagram 5] 10 is a flowchart showing the process flow in step S15. [Figure 6] 10 is a flowchart showing the process flow in step S16. [Figure 7] 10 is a flowchart showing the process flow of step S16 in the second embodiment. [Figure 8] 10 is a flowchart showing the flow of an image processing method according to a third embodiment. [Figure 9] 13 is a flowchart showing the process flow of step S368 in the third embodiment. [Figure 10] 13A and 13B are diagrams showing examples of UIs displayed by a display unit in another embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the embodiments will be described in detail with reference to the attached drawings. Note that the following embodiments do not limit the invention according to the claims. Although the embodiments describe a number of features, not all of these features are essential to the invention, and the features may be combined in any manner. Furthermore, in the attached drawings, the same reference numbers are used for the same or similar configurations, and duplicated descriptions are omitted.

[0010] [First embodiment] The image processing device according to the first embodiment divides an inspection image into regions according to brightness values, and judges the presence or absence of defects in the print using an image in which the brightness values ​​have been corrected for each region. When an inspection image includes low brightness regions, defects in the low brightness regions are more difficult to detect than defects in medium brightness regions and high brightness regions (hereinafter referred to as mid-high brightness regions) because the contrast of the defects is lower. Therefore, the image processing device corrects the brightness value for each region in order to detect defects using the same detection parameters in the low brightness regions and the mid-high brightness regions.

[0011] (Print inspection system configuration) 1 is a diagram showing the overall configuration of a print inspection system that outputs and inspects printed matter, including an image processing device 100 according to the first embodiment. The print inspection system according to the first embodiment includes the image processing device 100 and a printing device 190. The print inspection system according to the first embodiment may further include a printing server 180.

[0012] The printing server 180 generates a print job including a document to be printed, and submits the print job to the printing device 190. The printing device 190 is a device that forms an image on roll paper based on the print job submitted from the printing server 180, and the roll paper is stored in a paper feed unit 191. When a print job is submitted, the printing device 190 forms an image while transporting the roll paper stored in the paper feed unit 191 along a transport path 192 with rollers, and transports the paper to the image processing device 100.

[0013] The image processing device 100 inspects the inspection target medium for defects on which printing has been performed. The inspection target medium is obtained by forming an image on the printing medium by the printing device 190, and is transported through a transport path 192 inside the printing device 190. The image processing device 100 may have a CPU 101, a RAM 102, and a ROM 103 inside. The image processing device 100 may also have an image reading device 105, a printing device interface (I / F) 106, a general-purpose interface (I / F) 107, a user interface (hereinafter, UI) panel 108, and a main bus 109. The image processing device 100 may also have a print medium transport path 110 connected to the transport path 192 of the printing device 190. The roll paper passes through the printing device and then through the image processing device 100, and is taken up by a take-up unit 193 and stored as printed roll paper.

[0014] The image processing device according to each embodiment described below can be realized by a computer including a processor and a memory. For example, a processor such as a CPU 101 can execute a program stored in a memory such as a RAM 102 or a ROM 103 to realize the functions of each unit. The processor such as the CPU 101 can also control each module in the image processing device 100 as necessary. Note that the image processing device according to one embodiment of the present invention may be composed of a plurality of processing devices connected via a network, for example.

[0015] The CPU 101 is a processor that controls each unit in the image processing device 100. The RAM 102 temporarily holds applications executed by the CPU 101, data used in image processing, etc. The ROM 103 stores a group of programs executed by the CPU 101.

[0016] The image reading device 105 scans and reads the print medium sent from the printing device 190 on the conveying path 110, and acquires the data as image data. The conveying path 110 serves as the background when the image reading device 105 reads the image on the print medium, so the conveying path 110 can be configured to have a color (e.g., black) that is easily distinguishable from the print medium on the image. The printing device I / F 106 is connected to the printing device 190, and the image processing device 100 can communicate with the printing device 190 through the printing device I / F 106. For example, the image processing device 100 and the printing device 190 can be synchronized with each other and notify each other of their operating statuses via the printing device I / F 106.

[0017] The UI panel 108 can output information to the user. The UI panel 108 can be a display device such as a liquid crystal display, and can function as a user interface of the image processing device 100. The UI panel 108 can, for example, inform the user of the current status or settings of the image processing device 100. The UI panel 108 can also include an input device such as a touch panel or buttons, and can thus accept instructions from the user. The main bus 109 is a transmission path that connects the various modules of the image processing device 100.

[0018] While the print medium output from the printer 190 is being transported along the transport path 110, the image processing device 100 performs an inspection process to check for defects in the print medium based on image data of the print medium acquired by the image reading device 105. The results of the inspection process are stored in the RAM 102 or the ROM 103. Note that, in the present embodiment, the configuration of the print inspection system is described assuming roll paper, but a system configuration assuming cut sheets of paper may also be used. In the case of sheet paper, the system may be provided with an output tray for outputting print media that have been determined to pass inspection, and an output tray for outputting print media that have been determined to fail inspection. In this case, the output tray is connected to the CPU 101 via the main bus 109, and the destination of the print medium is set to the output tray according to the inspection result.

[0019] (Functional configuration of image processing device) The function of the image processing device 100 will be described. FIG. 2 is a block diagram showing the functional configuration of the image processing device 100 according to this embodiment. The image processing device 100 has a reference image acquisition unit 201, a read image acquisition unit 202, an inspection information acquisition unit 203, a region determination unit 204, a first color correction unit 205, a second color correction unit 206, an inspection unit 207, a display control unit 208, a noise reduction unit 209, and a judgment unit 210. For example, the image processing device 100 may realize each function of the reference image acquisition unit 201, the read image acquisition unit 202, the inspection information acquisition unit 203, the region determination unit 204, the first color correction unit 205, the second color correction unit 206, the inspection unit 207, the display control unit 208, the noise reduction unit 209, and the judgment unit 210 by the CPU 101 reading a program stored in the ROM 103 and expanding the program in the RAM 102. The first color correction unit 205 and the second color correction unit 206 are an example of a correction means.

[0020] The reference image acquisition unit 201 reads out manuscript data, which is the original data of the printed matter, into the RAM 102, and acquires a reference image by performing a correction process, which will be described later, on the manuscript data. In this embodiment, an image obtained by performing a correction process, which will be described later, on the manuscript data is acquired as the reference image, but an image generated based on a read image of a print medium on which printing is performed by the printing device 190 based on the manuscript data may also be acquired as the reference image. The read image acquisition unit 202 acquires a read image of a print medium on which printing is performed by the printing device 190. The acquired image data is stored in the RAM 102. In this embodiment, the read image acquisition unit 202 acquires image data obtained by the image reading device 105 reading the print medium on the transport path 110.

[0021] The inspection information acquisition unit 203 acquires information on the inspection job and the inspection level related to the inspection information setting based on the user's operation acquired via the UI panel 108. The area determination unit 204 determines the area in which the color information of the images acquired by the reference image acquisition unit 201 and the read image acquisition unit 202 is to be corrected.

[0022] A first color correction unit 205 performs color correction processing on the inspection image using a first color correction condition. A second color correction unit 206 performs color correction processing on the inspection image using a second color correction condition different from the first color correction condition.

[0023] The inspection unit 207 compares the read image with the reference image corrected by the first color correction unit 205 and the second color correction unit 206, and determines the presence or absence of defects based on the compared data. The display control unit 208 displays a UI on the UI panel 108 to notify the user of information and to allow the user to input information necessary for processing.

[0024] The noise reduction unit 209 performs noise reduction processing on pixels with a noise amount greater than a noise threshold. The determination unit 210 determines whether the pixel to be corrected should be corrected by the first color correction unit 205 or the second color correction unit 206. The determination unit 210 determines whether correction has been completed for all pixels of the inspection image.

[0025] (Processing performed by the image processing device) The process performed by the image processing device 100 according to this embodiment will be described below.

[0026] In step S11, the display control unit 208 of the image processing device 100 displays a UI screen for receiving instructions from a user so that the user can input information necessary for the inspection on the UI panel 108. The UI screen is a screen for acquiring information related to an inspection job or an inspection level based on an operation from the user, etc. Fig. 4 shows an example of the UI displayed in step S11.

[0027] 4, an inspection job setting button 1101 is a button for setting information on an inspection job that corresponds to a print job that manages image data and paper information used for inspection, and information on the inspection level setting. The user presses 1101 to specify an inspection job that has been created and registered in advance. The specified inspection job is held in RAM 102.

[0028] An inspection level setting section 1102 is a screen for setting the inspection level to be used for inspection. The user selects the inspection level from a pull-down menu, and the selected value is stored in the RAM 102.

[0029] The display window 1103 displays an image used for inspection, and the user can set the inspection level for each area while viewing the displayed image. In this embodiment, three areas can be specified as the inspection area: a focus inspection area, a standard inspection area, and a simple inspection area, and the user can specify each area by operating the mouse or the touch panel. If no area is specified, the inspection is performed at the inspection level specified in the standard inspection area. The inspection level is associated with processing parameters required to detect defects according to the size and contrast of the defects to be detected, and defects are detected according to the inspection level selected by the user. In this embodiment, five inspection levels are held, and the higher the inspection level, the lower the detection of defects with low contrast and small size, and the lower the inspection level, the higher the detection of defects with high contrast and large size. In this embodiment, three types of inspection areas and five inspection levels are held, but other settings may be held and set.

[0030] The execute inspection button 1104 is a button for executing the inspection process, and when the execute inspection button 1104 is pressed, the inspection process is executed based on the information set using the inspection job setting button 1101 through the display window 1103. The type of defect determined by the inspection process, position information of the defect on the roll paper, etc. are stored in the RAM 102.

[0031] The inspection result window 1105 is a window that displays a defect map showing defect information of the inspection image and the judgment result of the number of NG images. Information regarding the type and position of defects detected by the inspection process is displayed in the inspection result window 1105 together with the corresponding image area.

[0032] In step S12, the reference image acquisition unit 201 acquires an image obtained by performing correction processing on the document data as a reference image and stores it in the RAM 102. When an image generated based on a read image is used as the reference image, the reference image acquisition unit 201 acquires a read image obtained by the image reading device 105 reading an image of a roll paper on the conveying path 110 and stores it in the RAM 102. In this embodiment, an image expressed in 8 bits for each of RGB is used as the read image, but an image expressed in 16 bits may also be used. Note that the image reading device 105 generates a read image by reading an image of a roll paper, but the reference image acquisition unit 201 may use an image acquired from another device as the reference image. For example, a read image obtained by a device other than the image reading device 105 may be stored in an auxiliary storage device (not shown). In this case, the read image acquisition unit 202 may acquire a read image from the auxiliary storage device to generate a reference image.

[0033] In addition, when original data is used as a reference image, overdetection occurs due to differences in image characteristics from the read image, so the reference image acquisition unit 201 performs correction processing on the original data with respect to color reproduction characteristics and thin line reproduction characteristics as image characteristics. In the color reproduction correction processing, the reference image acquisition unit 201 creates and stores in advance a lookup table (LUT) in which a correspondence relationship for converting four-channel data of CMYK into three-channel data of RGB, which is the read image data, is described for each printing device characteristic, paper, and output condition, and performs correction by referring to this. In addition, in the thin line correction processing, the reference image acquisition unit 201 outputs and reads a thin line chart in advance, and calculates correction data related to the reproduction of thin lines of the original data and the read image. The reference image acquisition unit 201 calculates a filter coefficient for matching the line width with the read image based on the line profile of the thin line, and a filter coefficient for correcting blurring of edges during scanning. The reference image acquisition unit 201 generates a reference image by applying these two types of correction processing to the original data. Furthermore, the reference image acquisition unit 201 performs a process of converting the resolution of the document data to match the image size and resolution of the read image used during inspection.

[0034] In step S13, the read image acquisition unit 202 acquires the read image obtained by the image reading device 105 reading the image on the roll paper on the conveying path 110, and stores the image in the RAM .

[0035] In step S14, the inspection information acquisition unit 203 acquires, as inspection information, an inspection job set by the user using the inspection job setting button 1101 and an inspection level set in the inspection level setting unit 1102 via the UI panel .

[0036] In step S15, the area determination unit 204 determines an area to which correction by a first color correction unit 205 (described later) and an area to which correction by a second color correction unit 206 (described later) are applied when correcting color information of the reference image and the read image. The details of the process by the area determination unit 204 will be described later.

[0037] In step S16, the image processing device 100 performs color correction on the reference image and the scanned image based on the correction area determined in step S15. The process of the image processing device 100 in step S16 will be described in detail later.

[0038] In step S17, the inspection unit 207 inspects the presence or absence of defects using the reference image and the read image corrected in step S16. The inspection unit 207 aligns the reference image with the read image, calculates the difference between the two images, and determines a pixel for which the calculated difference is greater than a predetermined inspection threshold as a defective pixel. For example, the inspection unit 207 may hold an inspection threshold for the contrast for the difference for each inspection level, and for the size, the size of a dot and the size of a line, and determine the presence or absence of a dot defect and a line defect from the contrast of the difference and the shape size.

[0039] In step S18, the display control unit 208 displays the results processed in step S17 in the inspection result window 1105. If a defect is detected, an image of the defect map or an enlarged image of the defect map is displayed in the inspection result window 1105. The defect map is a map that indicates the position of the defect when there is a defect. The defect map is an image file with the same vertical and horizontal sizes as the reference image and the read image. If there is a defect, the inspection unit 207 stores, for example, a pixel value of RGB=(255,255,255) in association with the coordinate position of the corresponding defect, and if there is no defect, stores a pixel value of RGB=(0,0,0) in association with the coordinate position of the defect. If there is no defect, the inspection unit 207 stores the pixel value as 0. If there is a point-like defect, the inspection unit 207 stores a pixel value of RGB=(255,0,0) in association with the coordinate position. If there is a line-like defect, the inspection unit 207 stores a pixel value of RGB=(0,255,0) in association with the coordinate position. Note that the inspection unit 207 may store pixel values ​​different from the above-mentioned pixel values ​​in association with the coordinate positions.

[0040] <Operation of region determining unit 204 in step S15> The process of step S15 will now be described in detail with reference to a flowchart of FIG.

[0041] In step S151, the region determining unit 204 obtains an inspection image including the reference image and the read image obtained in steps S12 and S13.

[0042] In step S152, the region determination unit 204 generates histograms based on pixel values ​​of the reference image and the read image. The region determination unit 204 generates a histogram of luminance values ​​to divide the correction region of the image into a low luminance region and a medium to high luminance region other than the low luminance region. The luminance value is an example of a pixel value. A pixel in the low luminance region is an example of a first pixel, and a pixel in the medium to high luminance region is an example of a second pixel. The region determination unit 204 uses the pixel value of the G channel as the histogram of luminance values, but a weighted average of the pixel values ​​of R, G, and B may be used as the histogram. Also, a lookup table (LUT) may hold in advance the correspondence between the scanned image and the luminance measurement value of the print medium. In this case, the region determination unit 204 may generate the histogram of luminance values ​​by referring to the LUT.

[0043] In step S153, the region determination unit 204 calculates a judgment threshold value of the luminance value for dividing the image region into a low luminance region and a medium to high luminance region based on the histogram created in step S152. For example, the region determination unit 204 calculates the average value of the pixel values ​​of the top 1% of the histogram and uses a quarter of the average value as the judgment threshold value. The region determination unit 204 may use another value such as the top 5% of the histogram or a fifth of the average value as the judgment threshold value. The region determination unit 204 may calculate a luminance value at which the accuracy of defect detection decreases as a reference value in advance and set the reference value of the luminance value as the judgment threshold value. Furthermore, the region determination unit 204 sets the judgment threshold value based on the histogram, but may detect the paper white region of the paper without using the histogram and calculate a quarter of the average value of the pixel values ​​of the paper white region as the judgment threshold value. In this case, the region determination unit 204 may omit the process of generating a histogram in step S152. Furthermore, the region determining unit 204 may calculate the determination threshold value using other statistical values ​​such as the median and the mode, in addition to the average value.

[0044] In step S154, the region determination unit 204 divides the image acquired in step S151 into a low brightness region and a medium to high brightness region based on the judgment threshold calculated in step S153. The region determination unit 204 prepares an image file having the same vertical and horizontal sizes as the reference image and the read image. The region determination unit 204 embeds a pixel value of 1 into pixels in the low brightness region whose brightness value is smaller than the judgment threshold or equal to or less than the judgment threshold, and embeds a pixel value of 0 into pixels in the medium to high brightness region other than the pixels in the low brightness region. Note that whether or not the brightness value satisfies the requirement for the judgment threshold is an example of the judgment requirement. In this way, the region determination unit 204 creates a correction region judgment map used to judge the correction region.

[0045] In step S155, the region determining unit 204 obtains the setting value of the inspection level set by the inspection level setting unit 1102, and obtains a noise threshold for judging the amount of noise based on the inspection level. If the image contains noise exceeding a predetermined noise threshold in the luminance value correction process described below, there is a possibility that noise may be over-detected even when there is no defect as a result of correcting the luminance value. For this reason, the region determining unit 204 performs a process of excluding pixels with an amount of noise exceeding a predetermined noise threshold from the correction region. In this embodiment, the higher the inspection level for defects, the more minute the contrast is detected. Therefore, the region determining unit 204 sets the noise threshold for the noise amount lower the higher the inspection level, and sets the noise threshold for the noise amount higher the lower the inspection level.

[0046] In step S156, the region determination unit 204 calculates the amount of noise for each pixel in the correction region determined in step S154. The region determination unit 204 calculates the amount of noise based on a statistical value such as standard deviation or variance that evaluates the variation in pixel values ​​within a predetermined window size centered on each pixel determined to be a low-luminance region in step S154. Note that the region determination unit 204 uses the standard deviation or variance of the pixel values, but may also calculate a PSNR (peak signal-to-noise ratio) for each pixel determined to be a low-luminance region using the reference image and the read image, and use the PSNR as the amount of noise.

[0047] In step S157, the region determination unit 204 compares the noise threshold of the noise amount acquired in step S155 with the noise amount calculated in step S156. If the noise amount calculated in step S156 is greater than the noise threshold, the region determination unit 204 proceeds to processing in step S158, and if it is equal to or less than the noise threshold, the region determination unit 204 proceeds to processing in step S159.

[0048] In step S158, the region determination unit 204 excludes pixels for which the amount of noise is determined to be greater than the noise threshold from the correction region. Specifically, the region determination unit 204 refers to the correction region determination map created in step S154, and changes the pixel value of the correction region determination map for the target pixel to a pixel value other than 0 or 1, to exclude the pixel from the correction region.

[0049] In step S159, the region determination unit 204 determines whether the process of generating the correction region determination map has been performed for all pixel values ​​of the reference image and the read image. If the process has been performed for all pixel values, the region determination unit 204 proceeds to step S160, and if not, the process returns to step S156.

[0050] In step S160, the region determining unit 204 stores the correction region determination map in the RAM 102, and the process ends.

[0051] The area determination unit 204 executing step S15 may omit the process of determining the correction area based on the amount of noise in steps S155 to S159, and may store the correction area determination map determined in S154 in the RAM 102, and end the process.

[0052] <Operation of image processing device 100 in step S16> 6 is a flowchart related to the processing of the image processing device 100 in step S16. In step S16, the image processing device 100 performs a strong luminance value correction process for pixels in areas determined to be low luminance areas in step S15, and performs a weak luminance value correction process or no correction process for pixels in areas determined to be medium to high luminance areas. The image processing device 100 designs the detection parameters related to contrast based on the contrast ratio between the paper white reference and the defect. The image processing device 100 corrects the luminance values ​​so that defects can be detected with uniform detection parameters regardless of the pattern (luminance value) of the inspection image by correcting pixels in low luminance areas to the luminance value of the paper white reference.

[0053] In step S161, the region determining unit 204 obtains the reference image and the read image obtained in steps S12 and S13 as inspection images.

[0054] In step S162, the region determining unit 204 generates histograms based on the pixel values ​​of the reference image and the scanned image in the same manner as described in step S152.

[0055] In step S163, the first color correction unit 205 and the second color correction unit 206 each calculate a color correction condition to be used for color correction.

[0056] The first color correction unit 205 calculates a gain value gain(G) of the first color correction condition used for correcting the middle to high luminance region by the following formula (1).

[0057] gain(G) = Gt / G0...Equation (1) The first color correction unit 205 uses the average value of the pixel values in the top 1% of the histogram created in step S162 as G0. Note that the first color correction unit 205 may use other statistical values such as the most frequent value or the median in the top 1% instead of the average value for G0. The first color correction unit 205 uses the target value of the G channel when correcting the luminance value as Gt. The first color correction unit 205 may previously hold the target value of the G channel of the reading image of the paper white used for inspection in the RAM 102 and read this out during processing for use as Gt. When the value of G0 is within 5% above or below the value of Gt, the first color correction unit 205 assumes that the error from the target value is small, sets 1 for the gain value gain(G) in the formula (1) as the first color correction condition, and sets the condition for not performing color correction. When the value of G0 is not within 5% above or below the value of Gt, the first color correction unit 205 assumes that the error from the target value is large, calculates the gain value gain(G) using the formula (1), and holds the calculated value in the RAM 102 as the first color correction condition.

[0058] Also, the second color correction unit 206 calculates the gain value gain_low(G) of the second color correction condition used for correcting the low luminance region by the following formula (2).

[0059] gain_low(G) = Gt / G0_low ··· Formula (2) The second color correction unit 206 uses the average value of the pixel values in the bottom 10% of the histogram created in step S162 as G0_low. Gt is the same as Gt in the formula (1). The second color correction unit 206 may use other statistical values such as the most frequent value or the median instead of the average value in the bottom 10% for G0_low, or may use the value in the bottom 5% instead of the bottom 10%. As can be seen from the formula (1) and the formula (2), gain(G) < gain_low(G), and the correction degree of the low luminance region and the correction degree of the medium and high luminance regions are different.

[0060] In step S164, the determination unit 210 determines which correction region the target pixel of the inspection image belongs to. Specifically, the determination unit 210 acquires the pixel value of one pixel of the inspection image, and refers to the correction region determination map created in step S15 from the RAM 102 to determine whether to perform correction using the first color correction unit 205 or the second color correction unit 206. If the pixel value of the correction region determination map is 0 indicating a medium to high luminance region, the determination unit 210 proceeds to processing in step S165, and if the pixel value of the correction region determination map is 1 indicating a low luminance region, the determination unit 210 proceeds to processing in step S166. Note that if the pixel value of the correction region determination map is not 0 or 1, that is, if the pixel has a large amount of noise and is not a correction target, the determination unit 210 may perform processing in step S167 without performing processing in steps S165 and S166.

[0061] In step S165, first color correction unit 205 corrects the luminance values ​​of pixels in the medium to high luminance region of the inspection image using the first color correction condition calculated in step S163, according to the following formula (3).

[0062] R' = R × gain(G) G'=G×gain(G)...Equation (3) B' = B × gain(G) (R, G, B) are pixel values ​​of the image before correction, and (R', G', B') are pixel values ​​of the image after correction.

[0063] In step S166, the second color correction unit 206 corrects the luminance values ​​of pixels in the low luminance region of the inspection image using the second color correction condition calculated in step S163, using the following formula (4).

[0064] R' = R × gain_low(G) G' = G × gain_low(G) Equation (4) B' = B × gain_low(G) In step S167, the determination unit 210 determines whether the first color correction or the second color correction has been performed for all pixels of the inspection image. If the determination unit 210 determines that either the first color correction or the second color correction has been performed for all pixels, the process proceeds to step S168. If the determination unit 210 determines that either the first color correction or the second color correction has been performed for all pixels, the process returns to step S164.

[0065] In step S168, the noise reduction unit 209 calculates the amount of noise using statistical values ​​such as the standard deviation or variance of pixel values ​​within a predetermined window size centered on a target pixel of at least one of the reference image and the scanned image. Note that the noise reduction unit 209 may calculate the PSNR of a pair of inspection images before and after correction without using the above-mentioned statistical values, and calculate this as the amount of noise.

[0066] In step S169, the noise reduction unit 209 determines whether the amount of noise calculated in step S168 is greater than a preset noise threshold. If it is greater, the process proceeds to step S170, and if it is equal to or less than the noise threshold, the process proceeds to step S171.

[0067] In step S170, the noise reduction unit 209 performs noise reduction processing on pixels having a noise amount greater than the noise threshold value. For example, the noise reduction processing performed by the noise reduction unit 209 is a smoothing filter processing such as an averaging filter or a Gaussian filter.

[0068] In step S171, the noise reduction unit 209 stores the corrected image in the RAM 102, and the process ends.

[0069] Note that the image processing device 100 in step S16 may omit the noise reduction processing from step S168 to step S170, and may store the image corrected from step S161 to step S167 in the RAM 102, and end the processing.

[0070] In addition, in the present embodiment, the correction of the luminance value by the gain value with the paper white as the target value has been described, but the correction method is not limited to this. For example, a plurality of target values ​​may be set for each gray gradation, not just the paper white, and a correction table may be created that corrects the gradation to the target value, and a first color correction condition and a second color correction condition may be set to correct the gradation of the luminance value of the inspection image.

[0071] As described above, the image processing device 100 of the first embodiment inspects defects by correcting pixel values ​​(luminance values) of at least low luminance regions of the inspection image. This enables the image processing device 100 to reduce cumbersome settings for inspecting defects. For example, the image processing device 100 sets parameters such as an inspection threshold in accordance with the inspection of defects in medium to high luminance regions, and increases the luminance values ​​of pixels in the low luminance region to approach the luminance values ​​of pixels in the medium to high luminance regions, thereby enabling the inspection of defects in both regions with a single inspection threshold.

[0072] The image processing device 100 corrects the luminance values ​​of pixels in the medium to high luminance regions of the inspection image under color correction conditions different from the color correction conditions for correcting pixels in the low luminance regions, thereby enabling the image processing device 100 to inspect defects in the medium to high luminance regions with higher accuracy.

[0073] The image processing device 100 uses different gains, which indicate the degree of correction, for low brightness regions and medium to high brightness regions. This allows the image processing device 100 to perform more appropriate correction for low brightness regions and medium to high brightness regions in order to improve the accuracy of defect inspection.

[0074] The image processing device 100 sets the gain, which is a correction condition for pixel values ​​in low brightness areas and medium to high brightness areas, based on the histogram of pixel values ​​of the inspection image. This allows the image processing device 100 to set appropriate correction conditions for each inspection image.

[0075] Since the image processing device 100 inspects for defects by reducing noise in the corrected inspection image, it is possible to further improve the accuracy of inspection for defects.

[0076] Image processing device 100 corrects the luminance values ​​of pixels in low luminance regions where it is difficult to inspect for defects so as to increase them, and therefore can improve the accuracy of inspecting for defects even in low luminance regions.

[0077] Since the image processing device 100 corrects the luminance values ​​of pixels in low luminance regions to a greater extent than the correction degree of pixels in medium to high luminance regions, the luminance values ​​of the low luminance regions can be brought closer to the luminance values ​​of the medium to high luminance regions. This allows the image processing device 100 to inspect defects with higher accuracy even with a single inspection threshold.

[0078] [Second embodiment] In the first embodiment, a method was described in which an inspection image is divided into two regions, a low brightness region and a medium to high brightness region, a second color correction is performed on the low brightness region, and a first color correction is performed on the medium to high brightness region, and the presence or absence of defects is inspected using the image after color correction. In the second embodiment, in the inspection of a printed matter composed of multiple layers such as a label paper, when the base material on which printing is performed is a transparent material or a thin material, the color of the release paper or backing paper that is the layer below is seen through, and the inspection of the printed matter cannot be performed properly. In such a case, the read image acquired by the reading device may be darker than it appears, and the luminance value or contrast of the image may be insufficient when performing the processing of alignment and defect detection, making it impossible to perform the inspection with the desired accuracy. In addition, in order to reproduce the image quality of the label well, a method of increasing the readability of characters by using, for example, white ink or white toner on the film may be performed. In this case, the luminance value does not decrease in the region covered with white ink or white toner, so if the luminance value is uniformly corrected to match the uncovered region, the gradation of the high luminance region will be crushed and the inspection will not be performed properly. In the second embodiment, to solve this problem, a method is described in which the area to which brightness correction is applied is determined based on whether or not a base layer is formed using, for example, white ink or white toner separate from the printing layer, and the image after color correction is used to inspect for defects.

[0079] <Operation of the image processing device 100 in step S26> In the second embodiment, the process of step S16, which is different from the first embodiment, will be described with reference to Fig. 7, and the other processes are similar to those in the first embodiment, so the description will be omitted. Fig. 7 is a flowchart of the process of step S16 in the image processing device 100 in the second embodiment.

[0080] In step S261, the region determining unit 204 obtains a reference image and a read image as inspection images, similar to the process in step S161.

[0081] In step S262, the region determining unit 204 creates a histogram in the same manner as in the process of step S162.

[0082] In step S263, the first color correction unit 205 and the second color correction unit 206 calculate the first and second color correction conditions in the same manner as in the process of step S163.

[0083] In step S264, the examination information acquisition unit 203 acquires paper information to be used as examination information.

[0084] In step S265, the determination unit 210 determines whether or not the image to be inspected has undergone undercoating, such as undercoating or overcoating, and if so, proceeds to step S266, otherwise proceeds to step S267. The determination unit 210 determines whether or not undercoating has been performed by checking whether or not data other than the print color is included in the manuscript data of the inspection image. For example, the determination unit 210 determines that undercoating is performed when data representing output using white ink is included in the image layer of the manuscript data other than CMYK representing the print color, and determines that undercoating is not performed when such data is not included. Therefore, in the case of an area where white ink is output by referring to the manuscript data, the determination unit 210 proceeds to step S266, and in the case of an area where white ink is not output, proceeds to step S267. In this embodiment, white ink or white toner is given as an example of undercoating, but the above-mentioned determination method can also be applied when a printing device is equipped with special toner or ink such as clear, gold, or silver, and a printed matter is formed in a multi-layer structure. For example, special toners or inks such as gold, silver, or clear can be used in a topcoat layer above the printed layer to give the label a luxurious or metallic look, and the judgment unit 210 may decide whether or not to correct the brightness value based on the area in which they are printed.

[0085] In step S266, the first color correction unit 205 corrects the inspection image using the first color correction. For example, the first color correction unit 205 assumes that the pixels in the region where the base processing has been performed will not experience a decrease in luminance value, sets a correction coefficient of 1, and outputs the image without performing the first color correction.

[0086] In step S267, the second color correction unit 206 corrects the inspection image using the second color correction. The process in step S267 is similar to the process in step S166. The second color correction unit 206 obtains a target value corresponding to the paper information obtained in step S264, and corrects the luminance value so that the luminance value of the inspection image becomes the target value.

[0087] In step S268, determination unit 210 determines whether correction has been performed for all pixels of the inspection image. If correction has been performed for all pixels, determination unit 210 proceeds to processing in step S269, and if correction has not been performed, determination unit 210 returns to processing in step S265 and continues processing.

[0088] If it is determined in step S269 that correction has been performed for all pixels of the inspection image, the determination unit 210 stores the corrected image in the RAM 102 and ends the process.

[0089] As described above, according to the method of the second embodiment, by performing color correction for each area depending on whether or not a base treatment is performed, defects in printed matter can be detected with high accuracy without the need for complicated adjustment work such as setting the inspection area and inspection level according to the image content. When a transparent material substrate is used in label printing, the color reproduction characteristics differ between areas covered with white ink or white toner as base treatment and areas not covered, so it is necessary to manually adjust the area designation and inspection level settings according to the covered area. By using the method of the second embodiment, manual adjustment according to the covered area is no longer necessary, and defects in printed matter can be automatically detected with high accuracy.

[0090] [Third embodiment] In the first and second embodiments, a method for dividing an inspection image into regions and performing color correction for each region has been described. In the third embodiment, a method for performing a first color correction and a second color correction for all pixels of an inspection image, inspecting each of the corrected inspection images, and determining the presence or absence of a defect based on both the inspection results using the first color-corrected image and the inspection results using the second color-corrected image will be described.

[0091] <Operation of the image processing device 100 in the third embodiment> FIG. 8 is a flowchart showing the flow of the image processing method performed by the image processing device 100.

[0092] In step S361, the region determining unit 204 obtains a reference image and a read image as inspection images.

[0093] In step S362, the region determining unit 204 creates a histogram in the same manner as in the process of step S162.

[0094] In step S363, the first color correction unit 205 and the second color correction unit 206 calculate the first color correction condition and the second color correction condition in the same manner as in the process of step S163.

[0095] In step S364, the first color correction unit 205 corrects the reference image and the read image using the first color correction condition calculated in step S363.

[0096] In step S365, the second color correction unit 206 corrects the reference image and the read image using the second color correction condition calculated in step S363.

[0097] In step S366, the inspection unit 207 performs an inspection process using the inspection image corrected in step S364 to generate a first inspection result. The inspection process is similar to the process in step S17.

[0098] In step S367, the inspection unit 207 performs an inspection process using the inspection image corrected in step S365 to generate a second inspection result. The inspection process is similar to the process in step S17.

[0099] In step S368, the inspection unit 207 determines whether or not there is a defect based on the inspection results in steps S366 and S367. Details of the process in step S368 will be described later.

[0100] In step S369, the display control unit 208 stores the inspection result image in the RAM 102, and ends the process.

[0101] <Operation of the image processing device 100 in step S368> In step S368, the inspection unit 207 refers to the luminance value of the image before correction and integrates the inspection results of steps S366 and S367 to judge the presence or absence of defects. The inspection result of the inspection image corrected under the first color correction condition in step S366 has a low degree of correction of the luminance value, and the reliability of the inspection result of the dark area is low. Therefore, the inspection unit 207 refers to the luminance value of the inspection image before correction and adopts defects in an area (medium-high luminance area) that is equal to or higher than a predetermined judgment threshold. The inspection result of the inspection image corrected under the second color correction condition in step S367 has a high degree of correction of the luminance value, and the reliability of the inspection result of the bright area is low. Therefore, the inspection unit 207 refers to the luminance value of the original image before correction and performs a process of adopting defects in an area (low luminance area) that is less than a predetermined judgment threshold. FIG. 9 is a flowchart showing the flow of the process of step S368 performed by the inspection unit 207.

[0102] In step S3681, inspection unit 207 acquires the first inspection result in step S366.

[0103] In step S3682, inspection unit 207 acquires one pixel from among the pixels determined to be defective from the inspection result image acquired in step S3681, and refers to the luminance value of the inspection image before correction corresponding to the coordinates of that pixel. If the referenced luminance value is equal to or greater than a predetermined judgment threshold, inspection unit 207 proceeds to processing of step S3683, and if it is less than the predetermined judgment threshold, it proceeds to processing of step S3684.

[0104] In step S3683, inspection unit 207 stores a defect flag in the image for pixels determined in step S3682 to be equal to or greater than the predetermined determination threshold, similar to the defect map described in step S18, and saves the inspection result image in RAM 102.

[0105] In step S3684, the inspection unit 207 determines whether or not processing has been performed on all pixels representing defects acquired in step S3681. If processing has been performed, the inspection unit 207 proceeds to processing in step S3685; if processing has not been performed, the inspection unit 207 returns to processing in step S3681 and continues processing.

[0106] In step S3685, inspection unit 207 acquires the second inspection result of step S367.

[0107] In step S3686, inspection unit 207 acquires one pixel from among the pixels determined to be defective from the inspection result image acquired in step S3685, and refers to the luminance value of the original image before correction corresponding to the coordinates of the pixel. If the referenced luminance value is less than a predetermined judgment threshold, inspection unit 207 proceeds to processing of step S3687, and if it is equal to or greater than the predetermined judgment threshold, it proceeds to processing of step S3688.

[0108] In step S3687, inspection unit 207 saves in RAM 102 an inspection result image in which defect flags are stored for pixels determined in step S3686 to have a luminance value less than the predetermined value, similar to the defect map described in step S18.

[0109] In step S3688, the inspection unit 207 determines whether or not processing has been performed on all pixels representing defects obtained in step S3681. If processing has been performed, the processing ends; if processing has not been performed, the inspection unit 207 returns to the processing of step S3685 and continues processing.

[0110] As described above, the image processing device 100 of the third embodiment performs correction on the inspection image based on different color correction conditions, and judges defects based on both inspection results obtained by using the different corrected images. This allows the image processing device 100 to accurately detect defects in printed matter without making corrections for each region. By not making corrections for each region, the image processing device 100 is able to judge defects with a small amount of calculations, which has the effect of speeding up processing time and reducing the hardware cost of the inspection system. In addition, in the image processing device 100, depending on the pattern, there is a problem in whether the boundary values ​​of the regions can be accurately divided when processing by region, but according to the method of the third embodiment, inspection can be performed without depending on the processing accuracy of region judgment, so defects in printed matter can be accurately detected.

[0111] [Other embodiments: Color correction processing] In the first to third embodiments, a method of correcting the luminance value based on the luminance value of the image as the color correction process has been described, but chromaticity correction may be performed based on the chromaticity value of the inspection image. Since the detection parameters for defects are often set based on the paper standard, in cases where the inspection image is partially colored or the content includes high saturation colors, the saturation value of the inspection image is high and processing may not be possible with uniform parameters. For this reason, a saturation histogram of the inspection image may be created, the inspection image may be divided into a low saturation region, a medium saturation region, and a high saturation region (hereinafter, referred to as a medium-high saturation region), and the saturation value of the pixels of the inspection image in the medium-high saturation region may be reduced, or a chromaticity correction may be performed so that the chromaticity value of the white balance becomes the paper white reference value, before the defect inspection. As described in the first embodiment, noise during correction may also be reduced by calculating color noise as the noise amount and comparing it with a predetermined noise threshold value.

[0112] [Other embodiments: Display unit] In the first embodiment, the display control unit 208 displays the inspection result in the inspection result window 1105. However, the inspection result may be displayed in such a way that the user can distinguish whether it is the result of correction by the first color correction unit or the result of correction by the second color correction unit. For example, a caption indicating whether it is the result of correction by the first color correction unit or the result of correction by the second color correction unit may be placed next to the detected defect. In addition, the pixel of the defect target may be displayed so that the result of the first color correction unit is distinguished by the pixel value, for example, by expressing the result of the first color correction unit by the pixel value (255, 255, 0) and the result of the second color correction unit by the pixel value (0, 255, 255). In addition, the display control unit 208 may be configured to set the conditions of the first color correction and the second color correction. For example, as shown in FIG. 10, a color correction condition display window 1106 may be further provided, and the correction coefficient calculated in the first embodiment may be displayed in 1106, so that the user can manually set the correction coefficient. A histogram of pixel values ​​of the corrected image and a correction target value may be displayed in the color correction condition display window 1106, and if the pixel values ​​of the upper 5% of the histogram are smaller than the correction target value, guidance may be given to manually set a luminance correction value larger than the automatically calculated value, and a user setting value may be acquired.

[0113] In the above embodiment, the image processing device 100 having the first color correction unit 205 and the second color correction unit 206 has been described as an example, but one of the correction units may be omitted. For example, when the luminance values ​​of pixels in the medium to high luminance region are not corrected, the first color correction unit 205 may be omitted. Furthermore, the image processing device 100 is not limited to the above-mentioned configuration, and for example, the image reading device 105 may be a device separate from the image processing device 100. Furthermore, the image processing device 100 may be configured not to have, for example, the noise reduction unit 209. In this case, the noise reduction process by the noise reduction unit 209 is omitted.

[0114] In the above embodiment, when the noise amount of a pixel is larger than the noise threshold, the region determination unit 204 excludes the pixel from the correction region, i.e., excludes the pixel from the correction target and does not correct the pixel, but the processing for the pixel is not limited to this. For example, the region determination unit 204 may correct a pixel with a large amount of noise by applying a smaller degree of correction than a pixel with a small amount of noise. In addition, when a pixel has a luminance value smaller than the judgment threshold and the noise amount of the pixel is larger than the noise threshold, the region determination unit 204 may exclude the pixel from the correction target, or may cause the color correction units 205 and 206 to weaken the degree of correction, i.e., to reduce the correction coefficient.

[0115] In the above embodiment, an example in which one noise threshold is used has been described, but multiple noise thresholds may be set. For example, the noise threshold may be set according to the sensitivity for detecting defects. Specifically, the noise threshold may be set lower as the sensitivity for detecting defects becomes higher. In particular, in a dark area where the luminance value is low, for example, where the luminance value is smaller than the judgment threshold, the noise threshold may be set lower as the sensitivity for detecting defects becomes higher.

[0116] In the first embodiment described above, the correction is performed by dividing the area into two areas, a low brightness area and a medium to high brightness area, but the number of correction areas is not limited to 2. The correction area may be divided into three or more areas, and correction conditions may be set for each area.

[0117] (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.

[0118] The disclosure of this specification includes the following image processing device, image processing method, and program. (Item 1) A reference image acquisition means for acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition means for acquiring a read image obtained by reading the printed matter; a correction unit that corrects a color of a first region in the reference image and the read image under a first correction condition and corrects a color of a second region in the reference image and the read image under a second correction condition; an inspection means for inspecting the printed matter based on the color of the first region corrected under the first correction condition and the color of the second region corrected under the second correction condition; An image processing device comprising: (Item 2) The correction means corrects the color of the first region where the pixel value is smaller than a threshold value under the first correction condition, and corrects the color of the second region where the pixel value is equal to or larger than the threshold value under the second correction condition. 2. The image processing device according to item 1, (Item 3) The correction means corrects the luminance value of the first region under the first correction condition, and corrects the luminance value of the second region under the second correction condition. 3. The image processing device according to item 1 or 2, (Item 4) The correction means corrects the luminance value of the first region so as to be larger. 4. The image processing device according to item 3, (Item 5) The correction means corrects the color of the first region under the first correction condition, and corrects the color of the second region under the second correction condition having a different correction degree from the first correction condition. 5. The image processing device according to claim 1, wherein the image processing device comprises: (Item 6) The correction means corrects the color of the first region under the first correction condition having a greater degree of correction than the second correction condition. 6. The image processing device according to item 5, (Item 7) The correction means sets the first correction condition and the second correction condition based on a histogram of pixel values ​​of at least one of the reference image and the read image. 7. The image processing device according to claim 1, wherein: (Item 8) 8. The image processing device according to any one of claims 1 to 7, further comprising a noise reduction unit that reduces noise when the amount of noise in pixel values ​​of at least one of the corrected reference image and the corrected read image is greater than a predetermined threshold value. (Item 9) The correction means corrects pixel values ​​of pixels in the first area and the second area based on a correction table for correcting gradations in the first area and the second area. 9. The image processing device according to any one of items 1 to 8, (Item 10) The correction means corrects the saturation value of the first region under the first correction condition, and corrects the saturation value of the second region under the second correction condition. 10. The image processing device according to any one of items 1 to 9, (Item 11) a region determining unit that determines the first region based on pixel values ​​of pixels of at least one of the reference image and the read image, The inspection means inspects the printed matter based on the color corrected under the first correction conditions in the determined first region. 11. The image processing device according to claim 1, wherein: (Item 12) A reference image acquisition means for acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition means for acquiring a read image obtained by reading the printed matter; a correction unit that corrects colors of the reference image and the read image under a first correction condition and a second correction condition; an inspection means for inspecting the printed matter based on the colors of the reference image and the read image corrected under the first correction condition and the colors of the reference image and the read image corrected under the second correction condition; An image processing device comprising: (Item 13) a reference image acquisition step of acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition step of acquiring a read image obtained by reading the printed matter; a correction step of correcting colors of a first region in the reference image and the read image under a first correction condition and correcting colors of a second region in the reference image and the read image under a second correction condition; an inspection step of inspecting the printed matter based on the color of the first region corrected under the first correction condition and the color of the second region corrected under the second correction condition; An image processing method comprising: (Item 14) a reference image acquisition step of acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition step of acquiring a read image obtained by reading the printed matter; a correction step of correcting colors of the reference image and the read image under a first correction condition and a second correction condition; an inspection step of inspecting the printed matter based on colors of the reference image and the read image corrected under the first correction condition and colors of the reference image and the read image corrected under the second correction condition; An image processing method comprising: (Item 15) A program for causing a computer to function as the image processing device according to item 1.

[0119] The invention is not limited to the above-described embodiments, and various modifications and variations are possible without departing from the spirit and scope of the invention. Accordingly, the following claims are appended to apprise the public of the scope of the invention. [Explanation of symbols]

[0120] 100... image processing device, 105... image reading device, 201... reference image acquisition unit, 202... read image acquisition unit, 203... inspection information acquisition unit, 204... area determination unit, 205... first color correction unit, 206... second color correction unit, 207... inspection unit, 209... noise reduction unit, 210... judgment unit, 205... color correction unit.

Claims

1. A reference image acquisition means for acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition means for acquiring a read image obtained by reading the printed matter; a correction unit that corrects a color of a first region in the reference image and the read image under a first correction condition and corrects a color of a second region in the reference image and the read image under a second correction condition; an inspection means for inspecting the printed matter based on the color of the first region corrected under the first correction condition and the color of the second region corrected under the second correction condition; An image processing device comprising:

2. The correction means corrects the color of the first region where the pixel value is smaller than a threshold value under the first correction condition, and corrects the color of the second region where the pixel value is equal to or larger than the threshold value under the second correction condition.

2. The image processing device according to claim 1,

3. The correction means corrects the luminance value of the first region under the first correction condition, and corrects the luminance value of the second region under the second correction condition.

2. The image processing device according to claim 1,

4. The correction means corrects the luminance value of the first region so as to be larger.

4. The image processing device according to claim 3.

5. The correction means corrects the color of the first region under the first correction condition, and corrects the color of the second region under the second correction condition having a different correction degree from the first correction condition.

2. The image processing device according to claim 1,

6. The correction means corrects the color of the first region under the first correction condition having a greater degree of correction than the second correction condition.

6. The image processing device according to claim 5,

7. The correction means sets the first correction condition and the second correction condition based on a histogram of pixel values ​​of at least one of the reference image and the read image.

2. The image processing device according to claim 1,

8. 2. The image processing apparatus according to claim 1, further comprising a noise reduction unit that reduces noise when an amount of noise in pixel values ​​of at least one of the corrected reference image and the corrected read image is greater than a predetermined threshold value.

9. The correction means corrects pixel values ​​of pixels in the first area and the second area based on a correction table for correcting gradations in the first area and the second area.

2. The image processing device according to claim 1,

10. The correction means corrects the saturation value of the first region under the first correction condition, and corrects the saturation value of the second region under the second correction condition.

2. The image processing device according to claim 1,

11. a region determining unit that determines the first region based on pixel values ​​of pixels of at least one of the reference image and the read image, The inspection means inspects the printed matter based on the color corrected under the first correction conditions in the determined first region.

2. The image processing device according to claim 1,

12. A reference image acquisition means for acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition means for acquiring a read image obtained by reading the printed matter; a correction unit that corrects colors of the reference image and the read image under a first correction condition and a second correction condition; an inspection means for inspecting the printed matter based on the colors of the reference image and the read image corrected under the first correction condition and the colors of the reference image and the read image corrected under the second correction condition; An image processing device comprising:

13. a reference image acquisition step of acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition step of acquiring a read image obtained by reading the printed matter; a correction step of correcting colors of a first region in the reference image and the read image under a first correction condition and correcting colors of a second region in the reference image and the read image under a second correction condition; an inspection step of inspecting the printed matter based on the color of the first region corrected under the first correction condition and the color of the second region corrected under the second correction condition; An image processing method comprising:

14. a reference image acquisition step of acquiring a reference image that serves as a reference for inspection of a printed matter; a read image acquisition step of acquiring a read image obtained by reading the printed matter; a correction step of correcting colors of the reference image and the read image under a first correction condition and a second correction condition; an inspection step of inspecting the printed matter based on colors of the reference image and the read image corrected under the first correction condition and colors of the reference image and the read image corrected under the second correction condition; An image processing method comprising:

15. A program for causing a computer to function as the image processing device according to claim 1.

Images