Image inspection device, image inspection method, and program

Abstract

To provide an image inspection device which can accurately detect a stripe-shaped defect while suppressing erroneous detection.SOLUTION: A detection unit 433 includes a calculation part 435, a setting part 436 and a determination part 437. The calculation part 435 calculates a first feature amount indicating a feature of a stripe-shaped defect for each pixel of a read image. The setting part 436 calculates the first feature amount and the second feature amount for each pixel of an output object image and sets an allowable range that includes the calculated first feature amount and has the width according to the calculated second feature amount. The determination part 437 determines whether or not the stripe-shaped defect exists in the read image by comparing the first feature amount of each pixel of the read image with the allowable range set for each pixel of the output object image. The absolute value of the second feature amount is larger as a change amount of the concentration along the direction orthogonal to the stripe-shaped defect is larger.SELECTED DRAWING: Figure 3

Description

[Technical Field]

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

[0002] Conventionally, there have been cases where streak-like defects have occurred on paper on which an image has been formed by an image forming apparatus. For this reason, an image inspection device has been developed that inspects paper output from an image forming apparatus. Japanese Patent Application Laid-Open Publication No. 2017-173000 (Patent Document 1) discloses an inspection device that inspects streak-like defects on a read image using a reference image serving as an inspection standard and a read image generated by reading paper using a reading device. This inspection device calculates a difference value between each pixel of a first difference image showing the difference between the reference image and the read image and a pixel a predetermined number of pixels away in a direction perpendicular to the potential streak, and determines whether a streak-like defect exists in the read image using a second difference image in which the calculated difference value is used as the pixel value. The reference image is an output target image that is the basis for the image formed on paper by the image forming apparatus. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2017-173000 A Summary of the Invention [Problem to be solved by the invention]

[0004] The scanned image is an RGB image in which the value of each pixel indicates the RGB density. In contrast, the image to be output is data to be printed, and therefore is a CMYK image in which the value of each pixel indicates the CMYK density. Therefore, in order to compare the scanned image with the image to be output, the image to be output must be color converted to an RGB image. This color conversion is generally performed by processing using a lookup table or the like that takes into account the characteristics of the image forming apparatus and the reading device. However, when generating the scanned image, errors may occur in the image formation by the image forming apparatus and the reading by the reading device. These errors may result in a false detection in which a streak defect is determined to exist even when no streak defect exists.

[0005] The present disclosure has been made to solve the above-mentioned problems, and its purpose is to provide an image inspection device, an image inspection method, and a program that can suppress false detection and detect streak defects with high accuracy. [Means for solving the problem]

[0006] According to one aspect, an image inspection device inspects paper on which an image is formed by an image forming device. The image inspection device includes a first acquisition unit that acquires a read image generated by reading the paper, a second acquisition unit that acquires an output target image that is the basis for an image to be formed on the paper by the image forming device, and a detection unit that detects a streak defect on the read image using the read image and the output target image. The detection unit includes a calculation unit, a setting unit, and a determination unit. The calculation unit calculates a first feature amount that indicates a characteristic of the streak defect for each pixel of the read image. The setting unit calculates the first feature amount and the second feature amount for each pixel of the output target image, and sets an allowable range that includes the calculated first feature amount and has a width corresponding to the calculated second feature amount. The determination unit determines whether a streak defect is present in the read image by comparing the first feature amount of each pixel of the read image with the allowable range set for each pixel of the output target image. The absolute value of the second feature amount increases as the amount of change in density along a direction perpendicular to the streak defect increases.

[0007] According to another aspect, an image inspection method inspects paper output from an image forming apparatus. The image inspection method includes the steps of: acquiring a scanned image by scanning the paper; acquiring an output target image that is the basis for an image to be formed on the paper by the image forming apparatus; and detecting a streak defect on the paper using the scanned image and the output target image. The detecting step includes the steps of: calculating a first feature amount indicating a characteristic of the streak defect for each pixel of the scanned image; and calculating the first feature amount for each pixel of the output target image. The detecting step further includes the steps of calculating a second feature amount for each pixel of the output target image; and setting, for each pixel of the output target image, an allowable range that includes the calculated first feature amount and has a width corresponding to the calculated second feature amount. The detecting step further includes the step of determining whether a streak defect exists in the scanned image by comparing the first feature amount for each pixel of the scanned image with the allowable range set for each pixel of the output target image. The absolute value of the second feature amount increases as the amount of change in density along a direction perpendicular to the streak defect increases. [Effects of the Invention]

[0008] According to the present disclosure, false detections are suppressed and streak defects are detected with high accuracy. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram illustrating a schematic configuration of an image inspection system including an image inspection device according to an embodiment of the present disclosure. [Figure 2] FIG. 2 is a block diagram showing an example of the configuration of a control system of the image forming apparatus. [Figure 3] FIG. 2 is a block diagram showing an example of the configuration of a control system of the image inspection device according to the embodiment. [Figure 4] FIG. 10 is a diagram illustrating an example of a second-order differential filter. [Figure 5] FIG. 10 is a diagram illustrating an example of a first-order differential filter. [Figure 6]10 is a diagram showing the relationship between the change in pixel value in a gradation area of ​​an image to be output, the first feature amount, and the second feature amount. FIG. [Figure 7] 1 is a flowchart showing an example of the flow of an image inspection method according to an embodiment. [Figure 8] FIG. 10 is a block diagram showing an example of the configuration of a control system of an image inspection device according to Modification 2. DETAILED DESCRIPTION OF THE INVENTION

[0010] An image inspection device according to an embodiment of the present disclosure will be described below with reference to the drawings. In the following description, identical parts and components are denoted by the same reference numerals. Their names and functions are also the same. Therefore, detailed descriptions thereof will not be repeated. Note that the embodiments and modifications described below may be selectively combined as appropriate.

[0011] <Image forming system> 1 is a diagram showing a schematic configuration of an image inspection system including an image inspection device according to an embodiment of the present disclosure. As shown in FIG. 1, the image inspection system 1 includes an image forming device 2 and an image inspection device 3.

[0012] The image forming apparatus 2 is an example of an image forming apparatus that forms an image on paper by an electrophotographic method that uses static electricity to form an image. The image forming apparatus 2 forms a color image on paper by, for example, a tandem method in which toner images of four colors, yellow (Y), magenta (M), cyan (C), and black (K), are superimposed. A PC (Personal Computer) operated by an operator is connected to the image forming apparatus 2 via a LAN (Local Area Network) (not shown). A job is then input from the PC to the image forming apparatus 2 via the LAN. The image forming apparatus 2 performs various processes, such as image formation, in accordance with the input job.

[0013] The image forming apparatus 2 includes an operation display unit 23, an image input unit 24, a paper feed unit 28, a conveyance unit 25, and an image forming unit 26.

[0014] The operation display unit 23 includes a display unit consisting of a liquid crystal panel or the like, and an operation unit consisting of a touch sensor or the like. The display unit and operation unit are integrally formed, for example, as a touch panel. The operation display unit 23 generates an operation signal representing the operation content input by the operator to the operation unit, and supplies the operation signal to the control unit 20 (see FIG. 2, which will be described later). Furthermore, the operation display unit 23 displays the operation content by the operator, setting information, etc., on the display unit based on the display signal supplied from the control unit 20. Note that the operation unit can also be configured as a mouse, tablet, etc., and configured separately from the display unit.

[0015] The image input unit 24 optically reads an image from a document on a platen and generates image data by A / D converting the read image. The image input unit 24 can also read an image from a document on a platen glass.

[0016] The paper feed unit 28 has a paper feed mechanism consisting of multiple paper feed trays, paper feed rollers provided for each paper feed tray, separation rollers, paper feed / separation rubber, delivery rollers, etc. Each paper feed tray stores paper sheets that have been identified in advance by type (paper type, basis weight, paper size, etc.), and the paper sheets are transported one by one from the top by the paper feed mechanism toward the transport unit 25.

[0017] The transport unit 25 includes a plurality of transport rollers for transporting the paper, and transports the paper fed from the paper feed unit 28 to the image inspection device 3 via the image forming unit 26.

[0018] Image forming section 26 performs electrophotographic image formation processing to form an image made up of four colors, C, M, Y, and K, on ​​paper. Image forming section 26 includes four image forming units 263 for forming Y, M, C, and K toner images, respectively, an intermediate transfer belt 264, a transfer section 265, and a fixing device 266. Note that, although this embodiment describes image forming section 26 that employs electrophotography, it is not limited to this example of employing electrophotography, and image forming sections that employ other printing methods, such as inkjet printing or thermal dye sublimation printing, may also be used.

[0019] The four image forming units 263 are arranged in series (tandem) along the belt surface of the intermediate transfer belt 264 and form C, M, Y, and K images, respectively. The four image forming units 263 have the same configuration, but differ only in the colors of the images they form. As shown in FIG. 1, each of the four image forming units 263 has an exposure unit 263a, a photosensitive drum 263b, a development unit 263c, a charging unit 263d, a cleaning unit 263e, and a primary transfer roller 263f.

[0020] In each image forming unit 263, the photosensitive drum 263b is charged by the charging section 263d, and then the exposure section 263a irradiates the photosensitive drum 263b with light based on the input job, thereby forming an electrostatic latent image on the photosensitive drum 263b. Next, the developing section 263c supplies toner onto the photosensitive drum 263b, and a toner image is formed on the photosensitive drum 263b. The toner image formed on the photosensitive drum 263b is (primary transfer) onto the intermediate transfer belt 264 by the primary transfer roller 263f. As a result, an image made up of each color is formed on the intermediate transfer belt 264. After the primary transfer, the cleaning section 263e removes any toner remaining on the photosensitive drum 263b.

[0021] The transfer unit 265 transfers (secondarily transfers) the toner image on the intermediate transfer belt 264 onto a sheet of paper.

[0022] The fixing device 266 applies heat and pressure to the paper onto which the toner image has been transferred, thereby performing a fixing process. The paper onto which the toner image has been fixed by the fixing device 266 is transported by the transport unit 25 to the image inspection device 3.

[0023] The image inspection device 3 includes a reading unit 30 and a detection device 4. The reading unit 30 includes, for example, a linear image sensor (e.g., a CCD line sensor), an optical system, a light source, etc. The reading unit 30 generates analog image data by reading a paper sheet on which an image has been formed, and outputs the generated analog image data to the detection device 4. The detection device 4 detects streak defects on the paper sheet based on the analog image data input from the reading unit 30.

[0024] <Configuration of image forming device> 2 is a block diagram showing an example of the configuration of a control system of the image forming apparatus 2. As shown in Fig. 2, the image forming apparatus 2 includes a control unit 20, a communication I / F unit 21, and a storage unit 22 in addition to the operation display unit 23, image input unit 24, paper feed unit 28, conveyance unit 25, and image forming unit 26 described above.

[0025] The communication I / F unit 21 is an interface for transmitting and receiving data to and from a PC 6, which is a terminal operated by an operator, via a network or a dedicated line. As the communication I / F unit 21, for example, a NIC (Network Interface Card) is used.

[0026] The control unit 20 includes a central processing unit (CPU) 201, a read only memory (ROM) 202, a random access memory (RAM) 203, and an input image processing unit 204.

[0027] The input image processing unit 204 performs predetermined image processing (e.g., rasterization processing) on ​​the image included in the job input from the PC 6 via the communication I / F unit 21, and generates print image data in which the value of each pixel indicates the density of CMYK. The input image processing unit 204 also performs image processing on the image data acquired from the document read by the image input unit 24, and creates print image data. The print image data is sent to the image forming unit 26 and the image inspection device 3.

[0028] The ROM 202 stores programs executed by the CPU 201, data used when the programs are executed, etc. The CPU 201 controls each part constituting the image forming apparatus 2 by reading out the programs stored in the ROM 202. Variables, parameters, etc. generated during the calculation processing of the CPU 201 are temporarily written to the RAM 203.

[0029] For example, the CPU 201 controls the conveying unit 25 to drive a conveying roller and convey the paper. The CPU 201 outputs the output target image created by the input image processing unit 204 to the image forming unit 26, and controls the image forming unit 26 to form the image on the paper.

[0030] Furthermore, the CPU 201 outputs a display signal to the operation display unit 23, causing the operation display unit 23 to display various setting screens, various processing results, etc. The information displayed on the operation display unit 23 also includes the streak detection results output from the image inspection device 3.

[0031] The storage unit 22 stores parameters used when the CPU 201 executes a program, data obtained by executing the program, etc. For example, the storage unit 22 stores information such as image formation conditions for each density level. Note that the storage unit 22 may also store the program executed by the CPU 201.

[0032] <Configuration of image inspection device> Fig. 3 is a block diagram showing an example of the configuration of a control system of an image inspection device according to an embodiment. As shown in Fig. 3, the image inspection device 3 includes a communication I / F unit 32 and a paper transport unit 33 in addition to the reading unit 30 and detection device 4 described above. The detection device 4 includes a control unit 41 and a storage unit 42. The storage unit 42 is configured, for example, by a large-capacity HDD (Hard Disk Drive) or the like.

[0033] The communication I / F unit 32 is an interface for transmitting and receiving data via a network to and from the image forming apparatus 2. As the communication I / F unit 32, for example, a NIC is used.

[0034] Based on the control of the control unit 41, the paper transport unit 33 drives transport rollers (not shown) to transport the paper output from the image forming device 2.

[0035] The control unit 41 of the detection device 4 includes a CPU 411 , a ROM 412 , and a RAM 413 .

[0036] The ROM 412 stores a program 440 executed by the CPU 411, data used when the program 440 is executed, and the like. The ROM 412 is used as an example of a computer-readable non-transitory recording medium that stores the program 440 executed by the CPU 411.

[0037] The CPU 411 reads out a program 440 stored in the ROM 412, thereby controlling each unit constituting the image inspection device 3. When the CPU 411 executes the program 440 read out from the ROM 412, an image processing unit 431, a color conversion unit 432, and a detection unit 433 are realized.

[0038] The RAM 413 temporarily stores variables and parameters that are generated during the calculation process of the CPU 411 .

[0039] The image processing unit 431 performs various processes such as analog processing, A / D conversion processing, and shading processing on the analog image data received from the reading unit 30, and then generates digital image data (hereinafter referred to as "read image 420") in which the value of each pixel indicates the RGB density. That is, the image processing unit 431 operates as a first acquisition unit that acquires the read image 420 generated by reading the paper output from the image forming apparatus 2. The read image 420 generated by the image processing unit 431 is temporarily stored in the RAM 413.

[0040] The color conversion unit 432 converts the color of the print image data (CMYK image) received from the image forming apparatus 2 via the communication I / F unit 32 into digital image data (hereinafter referred to as "output target image 421") in which the value of each pixel indicates the RGB density. In other words, the color conversion unit 432 operates as a second acquisition unit that acquires the output target image 421, which is the source of the image to be formed on paper by the image forming apparatus 2. The output target image 421 generated by the color conversion unit 432 is temporarily stored in the RAM 413.

[0041] The detection unit 433 detects streak defects on the scanned image 420 using the scanned image 420 and the output target image 421. The detection unit 433 stores the streak detection result 450 in the storage unit 42. The streak detection result 450 may not only be stored in the storage unit 42, but also written to an external storage device 5 connected to the image inspection device 3. The storage device 5 is, for example, a universal serial bus (USB) memory, a solid state drive (SSD), or a hard disk drive (HDD) connected to the image inspection device 3. By sending the streak detection result 450 to the storage device 5, an operator can display the streak detection result 450 stored in the storage device 5 and check its contents. The streak detection result 450 may also be transferred to and stored in a cloud server (not shown) or a PC 6 (see FIG. 2) connected via the communication I / F unit 32.

[0042] <Detection unit configuration> 3, the detection unit 433 has a coordinate conversion unit 434, a calculation unit 435, a setting unit 436, and a determination unit 437. The operation of each unit will be described below with reference to FIGS.

[0043] The coordinate conversion unit 434 aligns the read image 420 with the image to be output 421. A positional deviation may occur between the read image 420 and the image to be output 421 due to a misalignment of the paper when the image forming unit 26 of the image forming device 2 forms an image on the paper, or a misalignment of the paper when the reading unit 30 of the image inspection device 3 reads the image on the paper. To correct such a positional deviation, the coordinate conversion unit 434 aligns the image to be output 421 with the position of the read image 420. Specifically, the coordinate conversion unit 434 generates a coordinate transformation matrix for correcting the positional deviation and applies the generated coordinate transformation matrix to the image to be output 421.

[0044] The calculation unit 435 calculates a first feature amount indicating the feature of the streak defect for each pixel of the scanned image 420.

[0045] Streak defects are caused by scratches or dirt on the photosensitive drums and rollers provided in the image forming apparatus 2. Therefore, the streak defects are parallel to the paper transport direction in the image forming apparatus 2. Pixels where streak defects occur have density values ​​(brightness values) that the operator did not intend. Therefore, streak defects appear as differences in gradation or uneven density. For example, streak defects include white streaks that are lighter than the original image and black streaks that are darker than the original image. Therefore, the calculation unit 435 calculates a first feature value that indicates a change in density in a direction perpendicular to the paper transport direction in the image forming apparatus 2 and that takes a different value in areas where streak defects exist than in areas where no streak defects exist. Specifically, the calculation unit 435 calculates the first feature value using a second-order differential filter, such as a Laplacian filter.

[0046] Fig. 4 is a diagram showing an example of a second-order differential filter. The second-order differential filter shown in Fig. 4 generates a second-order differential value of a pixel value for a pixel position along a direction D perpendicular to the paper transport direction in the image forming apparatus 2. Specifically, the second-order differential filter generates a value A' by substituting a value A of a pixel of interest 7a and values ​​B and C of pixels 7b and 7c, which are a predetermined number of pixels away from the pixel of interest 7a along the direction D, into the following equation (1): A'=A×2+B×(-1)+C×(-1) Formula (1) The predetermined number of pixels is determined in advance depending on the width of the streak defect to be detected, and is 3 in the example shown in Fig. 4. The value A' generated using the second-order differential filter indicates the amount of change in the values ​​of multiple pixels along direction D centered on the target pixel 7a. By applying the second-order differential filter shown in Fig. 4 to the scanned image 420, an image is generated in which the value of each pixel is A'.

[0047] In an area with uniform density, the difference between the value of the target pixel 7a and the values ​​of pixels 7b and 7c that are a predetermined number of pixels away from the target pixel 7a along direction D is 0. Therefore, when a second-order differential filter is applied to multiple pixels centered around the target pixel 7a, the value of A' becomes 0.

[0048] In contrast, when a streak defect exists in part of an area with uniform density, the value of pixel of interest 7a included in the streak defect differs significantly from the values ​​of pixels 7b and 7c, which are a predetermined number of pixels away along direction D. Therefore, when a second-order differential filter is applied to multiple pixels centered around pixel of interest 7a, the absolute value of A' becomes large. For example, for pixels included in a black streak, A' takes a positive value. For pixels included in a white streak, A' takes a negative value.

[0049] In this way, the first feature amount, which is the difference in value between the pixel of interest 7a and pixels 7b and 7c that are a predetermined number of pixels away from the pixel of interest 7a along direction D, represents the feature of a streak defect. However, the first feature amount also reacts to areas where streak content exists in the scanned image. Since streak content is not a defect, it should not be detected as a defect. Therefore, it is desirable to distinguish between streak content and streak defects.

[0050] The setting unit 436 dynamically sets a threshold value for each pixel to distinguish between streak-like content and streak-like defects in accordance with the output target image 421. Specifically, the setting unit 436 sets upper and lower limit values ​​of an allowable range, which is the range of the first feature amount that can be taken in accordance with the content.

[0051] The determination unit 437 compares the first feature amount of each pixel of the scanned image 420 with the tolerance range set for each pixel of the image to be output, thereby determining whether or not a streak defect exists in the scanned image 420. For example, the determination unit 437 determines that a streak defect exists in the scanned image 420 when a predetermined number of pixels whose first feature amount falls outside the tolerance range continue in succession along the paper conveyance direction.

[0052] The method for setting the tolerance range will be described in detail below. The setting unit 436 calculates a first feature amount for each pixel of the output target image 421. The output target image 421 does not include a streak defect. Therefore, the first feature amount calculated from the output target image 421 indicates a value corresponding to the content. Therefore, the setting unit 436 sets an tolerance range for each pixel that includes the first feature amount calculated from the output target image 421. For example, the setting unit 436 sets an tolerance range with the first feature amount calculated from the output target image 421 as the median value. Two first feature amounts calculated from the scanned image 420 and the output target image 421 for pixels included in the streak-like content are the same or similar. Therefore, the first feature amount of the pixel included in the streak-like content in the scanned image 420 falls within the tolerance range. As a result, by comparing the first feature amount calculated from the scanned image 420 with the tolerance range, it is possible to prevent the streak-like content from being detected as a streak-like defect.

[0053] The output target image 421 is generated through color conversion by the color conversion unit 432. When image formation is performed normally in the image forming device 2, it is preferable that the density of each pixel between the scanned image 420 and the output target image 421 match. Therefore, the color conversion unit 432 converts the color of the print image data (CMYK image) into the output target image 421 (RGB image) using a lookup table or the like that is predetermined in consideration of the characteristics of the image forming device 2 and the reading unit 30. However, errors may occur in the image formation by the image forming device 2 and the reading by the reading unit 30. In particular, image formation and reading errors are likely to be large in gradation areas where the density changes continuously. As errors become larger, the possibility of false detection increases, in which a streak defect is determined to exist even when one does not. Therefore, the setting unit 436 widens the tolerance range for pixels that are likely to have large image formation and reading errors.

[0054] The setting unit 436 calculates a second feature amount in addition to the first feature amount for each pixel of the output target image 421. The absolute value of the second feature amount increases as the amount of change in density along the direction D perpendicular to the streak defect increases. In other words, the absolute value of the second feature amount is larger in a gradation area where the density changes continuously than in a non-gradation area where the density does not change. The setting unit 436 calculates the second feature amount using, for example, a first-order differential filter.

[0055] FIG. 5 is a diagram showing an example of a first-order differential filter. The first-order differential filter shown in FIG. 5 generates a first-order differential value of a pixel value for a pixel position along direction D. Specifically, the first-order differential filter generates a value A″ for pixel of interest 7a by substituting values ​​B and C of pixels 7b and 7c, which are a predetermined number of pixels away from pixel of interest 7a along direction D, into the following equation (2): A”=B×(+1)+C×(-1) Formula (2) The predetermined number of pixels is determined in advance depending on the width of the streak defect to be detected, and is 3 in the example shown in FIG.

[0056] The setting unit 436 sets the width of the allowable range for each pixel in accordance with the second feature amount calculated from the output target image 421.

[0057] In this way, the setting unit 436 calculates the first feature amount and the second feature amount for each pixel of the image to be output, and sets an allowable range that includes the calculated first feature amount and has a width according to the calculated second feature amount. For example, for each pixel of the image to be output, the setting unit 436 sets the lower limit of the allowable range to (A'-k×|A"|) and the upper limit of the allowable range to (A'+k×|A"|) using the first feature amount A' and second feature amount A" corresponding to the pixel, where k is a predetermined coefficient. The setting unit 436 generates a threshold image 422 in which the value of each pixel indicates the upper and lower limit values ​​of the allowable range. The threshold image 422 is temporarily stored in the RAM 413.

[0058] FIG. 6 is a diagram showing the relationship between changes in pixel values ​​in the gradation region of an image to be output and the first and second feature amounts. In FIG. 6, solid line 60 indicates changes in pixel values. Dashed line 61 indicates changes in the second feature amount. Dashed-dotted line 62 indicates changes in the first feature amount. In the example shown in FIG. 6, pixel values ​​in the gradation region of image to be output 421 change (increase) continuously and monotonically along direction D. Therefore, the first feature amount (A') generated using a second-order differential filter is 0 for each pixel, while the second feature amount (A") generated using a first-order differential filter is a constant positive value for each pixel. Therefore, by setting an allowable range for each pixel that includes the first feature amount and has a width corresponding to the second feature amount, the possibility of erroneous detection is reduced even if errors in image formation and reading become large.

[0059] <Image inspection method> 7 is a flowchart showing an example of the flow of an image inspection method according to an embodiment. As shown in FIG. 7, the CPU 411 of the image inspection device 3 executes step S1 of acquiring a read image 420 and step S2 of acquiring an image to be output 421 in parallel. Specifically, in step S1, the CPU 411 generates the read image 420 by executing various processes on the analog image data received from the reading unit 30. In step S2, the CPU 411 generates the image to be output 421 by color-converting the image data to be printed (CMYK image) received from the image forming device 2.

[0060] After steps S1 and S2, in step S3, the CPU 411 aligns the scanned image 420 with the image to be output 421. Specifically, the CPU 411 aligns the image to be output 421 with the position of the scanned image 420 in order to correct any misalignment between the scanned image 420 and the image to be output 421.

[0061] After step S3, steps S4 and S5 are performed in parallel. Note that steps S4 and S5 may be performed sequentially. In step S4, the CPU 411 calculates a first feature amount for each pixel of the output target image 421 using a second-order differential filter. In step S5, the CPU 411 calculates a second feature amount for each pixel of the output target image 421 using a first-order differential filter.

[0062] Next, in step S6, the CPU 411 sets, for each pixel, an allowable range that includes the first feature amount calculated in step S4 and has a width corresponding to the second feature amount calculated in step S5. In step S7, the CPU 411 generates a threshold image 422 that indicates the upper and lower limits of the allowable range for each pixel.

[0063] On the other hand, in step S8 after step S2, the CPU 411 calculates a first feature amount for each pixel of the scanned image 420 using a second-order differential filter. In step S9, the CPU 411 compares, for each pixel, the first feature amount calculated in step S8 with the allowable range indicated by the threshold image 422. In step S10, the CPU 411 determines whether or not a streak defect exists in the scanned image 420 based on the comparison result of step S9. After step S10, the processing ends.

[0064] Steps S4 to S9 are performed for each of RGB. Then, in step S10, the CPU 411 determines that a streak defect exists in the scanned image 420 when a predetermined number of pixels whose first feature amount is outside the allowable range continue in the paper transport direction for at least one of RGB. Alternatively, the CPU 411 may determine that a streak defect exists in the scanned image 420 when a predetermined number of pixels whose first feature amount is outside the allowable range continue in the paper transport direction for all of RGB.

[0065] <Advantages> As described above, the image inspection device 3 inspects paper on which an image has been formed by the image forming device 2. The image inspection device 3 includes an image processing unit 431 that acquires a scanned image 420 generated by scanning the paper, a color conversion unit 432 that acquires an output target image 421 that is the basis for the image to be formed on the paper by the image forming device 2, and a detection unit 433. The detection unit 433 detects a streak defect on the scanned image 420 using the scanned image 420 and the output target image 421. The detection unit 433 includes a calculation unit 435, a setting unit 436, and a determination unit 437. The calculation unit 435 calculates a first feature amount that indicates the characteristics of the streak defect for each pixel of the scanned image 420. The setting unit 436 calculates a first feature amount and a second feature amount for each pixel of the output target image 421, and sets an allowable range that includes the calculated first feature amount and has a width corresponding to the calculated second feature amount. The determination unit 437 determines whether or not a streak defect exists in the scanned image 420 by comparing the first feature amount of each pixel of the scanned image 420 with the tolerance range set for each pixel of the output target image 421. The absolute value of the second feature amount increases as the amount of change in density along the direction perpendicular to the streak defect increases.

[0066] As described above, image formation and reading errors tend to increase in gradation areas where the density changes continuously. According to the above configuration, the width of the tolerance range is set according to the second feature value, the absolute value of which increases as the amount of density change in the direction perpendicular to the streak defect increases. Therefore, even if image formation and reading errors increase, the possibility of false detection of content that is not a streak defect as a streak defect is reduced.

[0067] <Variation 1> The likelihood of errors occurring in image formation and reading in gradation areas depends on the color. For example, reddish colors may be particularly susceptible to errors due to the characteristics of the image forming device 2 and the reading unit 30. For this reason, the second feature value for defining the width of the tolerance range may be adjusted according to the color of each pixel of the output target image 421.

[0068] For example, the setting unit 436 calculates the second feature amount for the image to be output 421, in which each pixel indicates an RGB density value, as follows. For each pixel of the image to be output 421, the setting unit 436 calculates the second feature amount by multiplying a value obtained by processing each RGB density value using a first-order differential filter by a coefficient. The coefficient differs for each color. If errors are particularly likely to occur with reddish colors, the coefficient corresponding to R is set to be larger than the coefficients corresponding to G and B. For example, the coefficients corresponding to G and B are 1, and the coefficient corresponding to R is 1.5. This reduces false detection even for colors that are prone to errors.

[0069] The coefficients for each color may be predetermined or may be set according to user input. When the coefficients are set according to user input, the image inspection device 3 provides an input screen for inputting the coefficients. The user simply inputs the coefficients into the provided input screen.

[0070] <Variation 2> In a gradation region, the steeper the gradient of the monotonically changing pixel value with respect to pixel position, the more likely errors are to occur. In such areas, the visual sensitivity of streaks is reduced, so there is no problem in excluding them from detection targets for streak defects.

[0071] Fig. 8 is a block diagram showing an example configuration of a control system of an image inspection device according to Modification 2. As shown in Fig. 8, the image inspection device 3A according to Modification 2 differs from the image inspection device 3 shown in Fig. 3 in that a CPU 411 executes a program 440 to realize a detection area determination unit 438.

[0072] The detection area determination unit 438 determines an area to be subjected to detection of streak defects. The detection area determination unit 438 identifies a non-inspection area in the output target image 421 where the second feature amount exceeds a reference value. The detection area determination unit 438 excludes an area in the scanned image 420 that corresponds to the target area from the areas to be subjected to detection of streak defects. This reduces the inspection load on the CPU 411 for streak defects, as the non-inspection area where detection of streak defects is unnecessary is excluded from the areas to be subjected to detection of streak defects.

[0073] The reference value may be predetermined or may be set according to user input. When the reference value is set according to user input, the image inspection device 3 provides an input screen for inputting the reference value. The user simply inputs the reference value into the provided input screen.

[0074] The embodiments disclosed herein should be considered to be illustrative in all respects and not restrictive. The scope of the present invention is defined by the claims, not by the above description, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0075] 1 image inspection system, 2 image forming apparatus, 3, 3A image inspection apparatus, 4 detection device, 5 storage device, 7a target pixel, 7b, 7c pixel, 20, 41 control unit, 21, 32 communication I / F unit, 22, 42 storage unit, 23 operation display unit, 24 image input unit, 25 transport unit, 26 image forming unit, 28 paper feed unit, 30 reading unit, 33 paper transport unit, 201, 411 CPU, 202, 412 ROM, 203, 413 RAM, 204 input image processing unit, 263 image forming unit, 263a exposure unit, 263b photosensitive drum, 263c development unit, 263d charging unit, 263e cleaning unit, 263f primary transfer roller, 264 intermediate transfer belt, 265 transfer unit, 266 fixing device, 420 Read image, 421 output target image, 422 threshold image, 431 image processing unit, 432 color conversion unit, 433 detection unit, 434 coordinate conversion unit, 435 calculation unit, 436 setting unit, 437 judgment unit, 438 detection area determination unit, 440 program.

Claims

1. An image inspection device that inspects paper on which an image is formed by an image forming device, a first acquisition unit that acquires a scanned image generated by scanning the paper; a second acquisition unit that acquires an output target image that is a source of an image to be formed on the paper by the image forming apparatus; a detection unit that detects streak defects on the read image using the read image and the output target image, The detection unit a calculation unit that calculates a first feature amount indicating a feature of the streak defect for each pixel of the read image; a setting unit that calculates the first feature amount and the second feature amount for each pixel of the image to be output, and sets an allowable range that includes the calculated first feature amount and has a width according to the calculated second feature amount; a determination unit that determines whether or not the streak defect exists in the read image by comparing the first feature amount of each pixel of the read image with the allowable range set for each pixel of the image to be output, The absolute value of the second feature amount increases as the amount of change in density along a direction perpendicular to the streak defect increases.

2. the first feature amount is calculated using a second-order partial filter; The image inspection device according to claim 1 , wherein the second feature amount is calculated using a first-order differential filter.

3. Each pixel of the read image and each pixel of the image to be output indicate density values ​​of a plurality of colors, the second feature amount is calculated for each of the plurality of colors by multiplying a value obtained by processing using the first derivative filter by a coefficient; The image inspection device according to claim 2 , wherein the coefficients are different for each of the plurality of colors.

4. 3. The image inspection device according to claim 2, wherein the detection unit further includes a detection area determination unit that identifies a target area in the output target image in which the second feature amount exceeds a reference value, and excludes an area in the read image that corresponds to the target area from targets for detecting the streak defect.

5. An image inspection method for inspecting a sheet output from an image forming apparatus, comprising: acquiring a read image by reading the paper; acquiring an output target image that is a source of an image to be formed on the paper by the image forming device; detecting a streak defect on the paper using the read image and the image to be output, The detecting step includes: calculating a first feature amount indicating a feature of the streak defect for each pixel of the read image; calculating the first feature amount for each pixel of the image to be output; calculating a second feature amount for each pixel of the image to be output; setting an allowable range for each pixel of the image to be output, the allowable range including the calculated first feature amount and having a width according to the calculated second feature amount; determining whether or not the streak defect exists in the read image by comparing the first feature amount of each pixel of the read image with the allowable range set for each pixel of the image to be output, an image inspection method, wherein the absolute value of the second feature amount is larger as the amount of change in density along a direction perpendicular to the streak defect is larger;

6. A program that causes a computer to execute the image inspection method according to claim 5.

Images