Image processing method and image processing device

Abstract

To determine, with high accuracy, whether a noise point in an object image is a sheet noise.SOLUTION: A processor 80 selects an object sheet from a plurality of predetermined sheet candidates. In addition, the processor 80 derives, from an object image g1 obtained through image reading processing on an output sheet from an image forming apparatus 2, feature information on a noise point Ps13 being a point-like singular part included in the object image g1. Further, the processor 80 applies the feature information to one determination algorithm corresponding to the object sheet among a plurality of determination algorithms associated with the plurality of sheet candidates to determine whether or not the noise point Ps13 is a point-like sheet noise included in the sheet itself in the output sheet.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an image processing method and an image processing device for determining whether or not a noise point in an image is sheet noise. [Background technology]

[0002] 2. Description of the Related Art Image forming apparatuses such as printers or multifunction peripherals execute a printing process to form an image on a sheet. In the printing process, image defects such as vertical streaks, horizontal streaks, or noise dots may occur in the image formed on the output sheet.

[0003] For example, when the image forming apparatus is an apparatus that executes the printing process by an electrophotographic method, the cause of the image defect is considered to be various parts such as a photoconductor, a charging unit, a developing unit, a transfer unit, etc. Furthermore, skill is required to determine the cause of the image defect.

[0004] It is also known that in an image processing device, a phenomenon that causes vertical streaks, which is an example of an image defect, and characteristic information such as the color, density or screen line number of the vertical streaks are previously associated as table data, and the phenomenon that causes the vertical streaks is identified based on the information on the color, density or screen line number of the image of the vertical streaks in a test image and the table data (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2017-83544 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, there are cases where the output image of the image forming apparatus contains dot-like sheet noise contained in the sheet itself. If an erroneous determination is made as to whether a noise point in the output image is the sheet noise or the image defect, an erroneous response will be taken.

[0007] An object of the present invention is to provide an image processing method and an image processing device that can determine with high accuracy whether a noise point in a target image obtained through an image reading process for an output sheet of an image forming device is sheet noise. [Means for solving the problem]

[0008] An image processing method according to one aspect of the present invention includes a processor selecting a target sheet from a plurality of predetermined sheet candidates according to selection information input through an input device. The image processing method further includes the processor deriving, from a target image obtained through an image reading process for an output sheet of an image forming apparatus, feature information on noise points, which are point-like noise images included in the target image. The image processing method further includes the processor executing a sheet noise determination process for determining whether or not the noise points are point-like sheet noise included in the sheet itself in the output sheet by applying the feature information to one of a plurality of determination algorithms associated with the plurality of sheet candidates, which corresponds to the target sheet.

[0009] An image processing device according to another aspect of the present invention includes a processor that executes the process of the image processing method. Effect of the Invention

[0010] According to the present invention, it is possible to provide an image processing method and an image processing device that can determine with high accuracy whether a noise point in a target image obtained through an image reading process for an output sheet of an image forming device is sheet noise. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram showing the configuration of an image processing apparatus according to an embodiment. [Diagram 2] FIG. 2 is a block diagram showing the configuration of a data processing unit in the image processing device according to the embodiment. [Diagram 3] FIG. 3 is a flowchart showing an example of a procedure of an image defect determination process in the image processing device according to the embodiment. [Figure 4] FIG. 4 is a flowchart illustrating an example of a procedure of the specific defect determination process in the image processing device according to the embodiment. [Diagram 5] FIG. 5 is a flowchart showing an example of a procedure of the sheet noise removal process in the image processing device according to the embodiment. [Figure 6] FIG. 6 is a diagram showing an example of a test image including a singular portion, and an example of a preprocessed image and a feature image generated based on the test image. [Figure 7] FIG. 7 is a diagram showing an example of a region of interest and adjacent regions sequentially selected from a test image in the main filtering process by the image processing device according to the embodiment. [Figure 8] FIG. 8 is a diagram showing an example of a noise point, a pixel value distribution in a traversing pixel column, and a differential value distribution in the traversing pixel column; FIG. 9A is a diagram showing a case where the noise point symptom is mild; FIG. 9B is a diagram showing a case where the noise point symptom is moderate; and FIG. 9C is a diagram showing a case where the noise point symptom is severe. [Figure 9] FIG. 9 is a flowchart showing an example of a procedure of a feature image generation process in the first application example of the image processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the following embodiment is an example of the present invention, and is not intended to limit the technical scope of the present invention.

[0013] [Configuration of image processing device 10] As shown in Fig. 1, an image processing device 10 according to an embodiment includes an image forming device 2 that executes a print process. The print process is a process for forming an image on a sheet. The sheet is an image forming medium such as paper or a sheet-like resin member.

[0014] The image processing device 10 further includes an image reading device 1 that executes a reading process for reading an image from a document. For example, the image processing device 10 is a copying machine, a facsimile machine, a multifunction machine, or the like.

[0015] In addition to the image forming device 2 and the image reading device 1, the image processing device 10 includes a data processing unit 8 and a human interface device 800. The human interface device 800 includes an operation unit 801 and a display unit 802.

[0016] The image to be printed is an image read from the document by the image reading device 1 or an image represented by print data received from a host device (not shown), etc. The host device is an information processing device such as a personal computer or a mobile information terminal.

[0017] Furthermore, the image forming apparatus 2 may form a predetermined original test image g01 on the sheet by the print process (see FIG. 6). The original test image g01 is an image that is the basis of a test image g1 that is used to determine the presence or absence of an image defect and its cause in the image forming apparatus 2 (see FIG. 6). The test image g1 will be described later.

[0018] The process including the reading process by the image reading device 1 and the print process by the image forming device 2 based on the image obtained by the reading process is a copy process.

[0019] 1, the image forming apparatus 2 includes a sheet transport mechanism 3 and a print unit 4. The sheet transport mechanism 3 includes a sheet sending mechanism 31 and a plurality of pairs of sheet transport rollers 32.

[0020] The sheet sending mechanism 31 sends out the sheet from the sheet storage unit 21 to the sheet transport path 30. A plurality of sheet transport roller pairs 32 transport the sheet along the sheet transport path 30 and discharge the sheet on which an image has been formed onto the discharge tray 22.

[0021] The printing unit 4 performs the printing process on the sheet transported by the sheet transport mechanism 3. In this embodiment, the printing unit 4 performs the printing process by electrophotography.

[0022] The print section 4 includes an image forming section 4x, a bias output circuit 430, a laser scanning unit 4y, a transfer device 44, and a fixing device 46. The image forming section 4x includes a drum-shaped photoconductor 41, a charging device 42, a developing device 43, and a drum cleaning device 45.

[0023] The photoreceptor 41 rotates, and the charging device 42 uniformly charges the surface of the photoreceptor 41. The charging device 42 includes a charging roller 42a that rotates in contact with the surface of the photoreceptor 41. The charging device 42 charges the surface of the photoreceptor 41 by outputting a charging voltage to the photoreceptor 41 through the charging roller 42a.

[0024] The laser scanning unit 4y writes an electrostatic latent image on the charged surface of the photoconductor 41 by scanning with a laser beam.

[0025] The developing device 43 develops the electrostatic latent image into a toner image. The photoconductor 41 is an example of an image carrier that carries the toner image. The developing device 43 includes a developing roller 43a, a developing tank 43b, and a regulating blade 43c. The developing tank 43b is a container that contains toner.

[0026] The developing roller 43a rotates while carrying the toner in the developing tank 43b, thereby supplying the toner to the surface of the photoconductor 41. The bias output circuit 430 applies a developing bias to each of the developing rollers 43a. The reference potential of the developing bias is the potential of the photoconductor 41. In this embodiment, the bias output circuit 430 is capable of correcting the developing bias.

[0027] The regulating blade is a member that limits the thickness of the layer of the toner carried on the developing roller 43a. Each of the four developing devices 43 corresponding to the four types of developing colors is an example of a developing unit.

[0028] The transfer device 44 transfers the toner image on the surface of the photoconductor 41 onto the sheet. The toner is an example of a granular developer.

[0029] The fixing device 46 heats the toner image on the sheet to fix it to the sheet. The fixing device 46 includes a fixing rotor 46a that rotates in contact with the sheet, and a fixing heater 46b that heats the fixing rotor 46a.

[0030] The image forming apparatus 2 shown in Fig. 1 is a tandem color printing apparatus and is capable of executing the printing process of a color image. Therefore, the printing unit 4 has four image forming units 4x, each of which corresponds to a different color toner. Each of the four image forming units 4x develops a different color.

[0031] In the tandem image forming apparatus 2, the transfer device 44 includes four primary transfer rollers 441 corresponding to the four photoconductors 41, an intermediate transfer belt 440, a secondary transfer roller 442, and a belt cleaning device 443.

[0032] The four image forming units 4x respectively form the cyan, magenta, yellow and black toner images on the surface of the photoconductor 41. Each of the primary transfer rollers 441 is also a part of each of the image forming units 4x.

[0033] In each of the image forming units 4x, the primary transfer roller 441 rotates and presses the intermediate transfer belt 440 against the surface of the photoconductor 41. The primary transfer roller 441 transfers the toner image from the photoconductor 41 to the intermediate transfer belt 440. As a result, a color image made up of the four color toner images is formed on the intermediate transfer belt 440.

[0034] In each of the image forming units 4 x , the drum cleaning device 45 removes and collects from the photoconductor 41 the toner that has not been transferred to the intermediate transfer belt 440 and remains on the photoconductor 41 .

[0035] The secondary transfer roller 442 transfers the four-color toner image on the intermediate transfer belt 440 onto the sheet. In the image processing device 10, the intermediate transfer belt 440 is an example of a transfer body that transfers the toner image onto the sheet.

[0036] The belt cleaning device 443 removes and collects from the intermediate transfer belt 440 the toner that has not been transferred to the sheet and remains on the intermediate transfer belt 440 .

[0037] The data processing unit 8 executes various data processing operations related to the printing process or the reading process, and further controls various electrical devices.

[0038] The operation unit 801 is an example of an input device that inputs information according to a user's operation. For example, the operation unit 801 includes one or both of a push button and a touch panel. The display unit 802 includes a display panel that displays information provided to the user.

[0039] As shown in FIG. 2, the data processing unit 8 includes a central processing unit (CPU) 80, a random access memory (RAM) 81, a secondary storage device 82, and a communication device 83.

[0040] The CPU 80 is capable of processing data received by the communication device 83, various types of image processing, and controlling the image forming device 2. The received data may include the print data. The CPU 80 is an example of a processor that executes data processing including the image processing. The CPU 80 may be realized by another type of processor, such as a DSP (Digital Signal Processor).

[0041] The communication device 83 is a communication interface device that communicates with other devices such as the host device through a network such as a LAN (Local Area Network). The CPU 80 performs all data transmission and reception between the CPU 80 and the external devices through the communication device 83.

[0042] The secondary storage device 82 is a computer-readable non-volatile storage device. The secondary storage device 82 stores the computer programs executed by the CPU 80 and various data referenced by the CPU 80. For example, one or both of a flash memory and a hard disk drive are adopted as the secondary storage device 82.

[0043] The RAM 81 is a computer-readable volatile storage device that temporarily stores the computer programs executed by the CPU 80 and data output and referenced in the process of the CPU 80 executing the programs.

[0044] The CPU 80 includes a plurality of processing modules that are realized by executing a computer program. The plurality of processing modules include a main control unit 8a and a job control unit 8b. Note that some or all of the plurality of processing modules may be realized by a processor independent of the CPU 80, such as a DSP.

[0045] The main control unit 8a executes a process of selecting a job in response to an operation on the operation unit 801, a process of displaying information on the display unit 802, a process of setting various data, etc. Furthermore, the main control unit 8a also executes a process of determining the contents of data received by the communication device 83.

[0046] The job control unit 8b controls the image reading device 1 and the image forming device 2. For example, when the received data of the communication device 83 includes the print data, the job control unit 8b causes the image forming device 2 to execute the received print process.

[0047] In addition, when the main control unit 8a detects a copy request operation on the operation unit 801, the job control unit 8b causes the image reading device 1 to execute the reading process, and causes the image forming device 2 to execute the printing process based on the image obtained by the reading process.

[0048] In the printing process, noise images such as vertical streaks Ps11, horizontal streaks Ps12, or noise points Ps13 may appear in the image formed on the output sheet (see FIG. 6). Vertical streaks Ps11 are linear noise images extending along the sub-scanning direction D2. Horizontal streaks Ps12 are linear noise images extending along the main scanning direction D1. Noise points Ps13 are point-shaped noise images.

[0049] As described above, the image forming apparatus 2 executes the print process by electrophotography. In this case, the noise image is considered to be an image defect caused by any of various parts such as the photoconductor 41, the charging device 42, the developing device 43, and the transfer device 44. Skill is required to determine the cause of the noise image.

[0050] In this embodiment, the image forming apparatus 2 executes a test print process for forming a predetermined original test image g01 on the sheet (see FIG. 6).

[0051] For example, when the main control unit 8a detects a test output operation on the operation unit 801, the job control unit 8b causes the image forming device 2 to execute the test print process. In the following description, the sheet on which the original test image g01 is formed is referred to as a test output sheet 9 (see FIG. 1).

[0052] Furthermore, when the test print process is executed, the main control unit 8a causes the display unit 802 to display a predetermined guidance message. This guidance message is a message that prompts the user to set the test output sheet 9 in the image reading device 1 and then to perform a reading start operation on the operation unit 801.

[0053] Then, when the main control unit 8a detects a reading start operation on the operation unit 801 after the guidance message is displayed on the display unit 802, the job control unit 8b causes the image reading device 1 to execute the reading process. As a result, the original test image g01 is read by the image reading device 1 from the test output sheet 9 output by the image forming device 2, and a read image corresponding to the original test image g01 is obtained.

[0054] As described later, when a noise image such as a noise point Ps13 is included in the test image g1, the CPU 80 determines the cause of the noise image. The test image g1 is the scanned image or an image obtained by compressing the scanned image. The CPU 80 is an example of a processor that executes the process of an image processing method for determining the cause of the noise image.

[0055] The device that reads the original test image g01 from the test output sheet 9 may be, for example, a digital camera. The process in which the image reading device 1 or the digital camera reads the original test image g01 from the test output sheet 9 is an example of an image reading process for the test output sheet 9.

[0056] The test output sheet 9 is an example of an output sheet of the image forming apparatus 2. The test image g1 is an example of a target image obtained through the image reading process for the test output sheet 9.

[0057] Incidentally, there are cases where the test image g1, which is an output image of the image forming apparatus 2, contains sheet noise. The sheet noise is a point-like noise image contained in the sheet itself of the test output sheet 9. If an incorrect determination is made as to whether the noise point Ps13 in the test image g1 is the sheet noise or the image defect, an incorrect response will be taken.

[0058] The CPU 80 executes an image defect determination process (see FIGS. 3 to 5) to be described later. As a result, the CPU 80 determines whether the noise point Ps13 in the test image g1 is the sheet noise. Furthermore, the CPU 80 determines the state of the image defect based on the test image g1 from which the sheet noise has been removed.

[0059] In the following description, images such as the test image g1 to be processed by the CPU 80 are digital image data. The digital image data constitutes map data including a plurality of pixel values ​​corresponding to two-dimensional coordinate regions in a main scanning direction D1 and a sub-scanning direction D2 intersecting the main scanning direction D1 for each of the three primary colors. The three primary colors are, for example, red, green, and blue. The sub-scanning direction D2 is perpendicular to the main scanning direction D1. The main scanning direction D1 is the horizontal direction in the test image g1, and the sub-scanning direction D2 is the vertical direction in the test image g1.

[0060] In this embodiment, the test image g1 is a mixed-color halftone image formed by combining a plurality of uniform monochromatic halftone images corresponding to a plurality of developed colors in the image forming apparatus 2. The monochromatic halftone images are each uniformly formed at a predetermined intermediate gradation reference density.

[0061] For example, the original test image g01 and the test image g1 are mixed-color halftone images formed by combining a plurality of uniform monochromatic halftone images corresponding to a plurality of developed colors in the image forming apparatus 2. The monochromatic halftone images are each uniformly formed at a predetermined intermediate gradation reference density.

[0062] In this embodiment, the original test image g01 and the test image g1 are mixed-color halftone images obtained by combining four uniform single-color halftone images corresponding to all the developed colors in the image forming apparatus 2. In the test print process, one test output sheet 9 including one original test image g01 is output. Therefore, one test image g1 corresponding to the original test image g01 is the target for identifying the image defect. The test image g1 in this embodiment is an example of a mixed-color test image.

[0063] In addition, the multiple processing modules in CPU 80 further include a feature image generation unit 8c, a singular part identification unit 8d, a color vector identification unit 8e, a periodicity determination unit 8f, a pattern recognition unit 8g and a noise point determination unit 8h in order to execute the image defect judgment process (see Figure 2).

[0064] [Image defect judgment processing] An example of the procedure of the image defect determination process will be described below with reference to the flowchart shown in Fig. 3. In the following description, S101, S102, ... represent identification codes of a plurality of steps in the image defect determination process.

[0065] After the guidance message is displayed on the display unit 802, when the reading process is executed in response to the reading start operation on the operation unit 801, the main control unit 8a causes the characteristic image generation unit 8c to execute the processing of step S101 in the image defect judgment processing.

[0066] <Process S101> In step S101, the characteristic image generating unit 8c generates a test image g1 from the read image obtained in the image reading process for the test output sheet 9.

[0067] For example, the characteristic image generating unit 8c extracts a portion of the original image excluding the outer margin area and the character portion from the scanned image as a test image g1.

[0068] Alternatively, the characteristic image generating unit 8c generates a test image g1 by a compression process that compresses the original image portion, excluding the outer margin area and the character portion, from the scanned image to a predetermined standard resolution. The characteristic image generating unit 8c compresses the scanned image when the resolution of the scanned image is higher than the standard resolution. After generating the test image g1, the main control unit 8a shifts the process to step S102.

[0069] <Process S102> In step S102, the characteristic image generating unit 8c starts a specific defect determination process, which will be described later. The specific defect determination process is a process for determining the presence or absence of image defects such as vertical streaks Ps11, horizontal streaks Ps12, or noise points Ps13 in the test image g1 and the cause of the image defects (see FIG. 6).

[0070] Furthermore, when the specific defect determination process is completed, the main control unit 8a shifts the process to step S103.

[0071] <Process S103> In step S103, if it is determined in the process of step S102 that the image defect has occurred, the main control unit 8a shifts the process to step S104, and if not, shifts the process to step S105.

[0072] <Process S104> In step S104, the main control unit 8a executes a defect handling process that is associated in advance with the type and cause of the image defect that has been determined to have occurred in the process of step S102.

[0073] For example, the defect response process includes one or both of a first response process and a second response process shown below. The first response process is a process for displaying a message indicating a result of determining the cause of the image defect and a measure to address the cause of the image defect on the display unit 802.

[0074] When the cause of the image defect includes the cause of the noise point Ps13, the first response process is an example of a process of notifying the determination result of the noise point Ps13 through a notification device. The display unit 802 is an example of the notification device. The message indicating the countermeasure is, for example, a message encouraging replacement of a part corresponding to the cause of the image defect.

[0075] The second response process is a process for correcting image forming parameters in order to eliminate or mitigate the image defect. The image forming parameters are parameters related to the control of the image forming unit 4x.

[0076] After executing the defect handling process, the main control unit 8a ends the image defect determination process.

[0077] <Process S105> On the other hand, in step S105, the main control unit 8a issues a normal notification indicating that the image defect has not been identified, and then ends the image defect determination process.

[0078] [Specific defect judgment processing] Next, an example of the procedure of the specific defect determination process in step S102 will be described with reference to the flowchart shown in Fig. 4. In the following description, S201, S202, ... represent identification codes of multiple steps in the specific defect determination process. The specific defect determination process starts from step S201.

[0079] <Process S201> First, in step S201, the feature image generating unit 8c generates a plurality of feature images g21, g22, and g23 by executing a predetermined feature extraction process on the test image g1. Each of the feature images g21, g22, and g23 is an image in which a specific type of singular part Ps1 of the test image g1 is extracted.

[0080] In this embodiment, the multiple characteristic images g21, g22, and g23 include a first characteristic image g21, a second characteristic image g22, and a third characteristic image g23 (see FIG. 6).

[0081] The first characteristic image g21 is an image in which the vertical streaks Ps11 in the test image g1 are extracted. The second characteristic image g22 is an image in which the horizontal streaks Ps12 in the test image g1 are extracted. The third characteristic image g23 is an image in which the noise points Ps13 in the test image g1 are extracted.

[0082] In this embodiment, the feature extraction process includes a first pre-processing process, a second pre-processing process, and a singular part extraction process. In the following description, a pixel sequentially selected from the test image g1 is referred to as a pixel of interest Px1 (see FIGS. 6 and 7).

[0083] The feature image generating unit 8c generates a first preprocessed image g11 by executing the first preprocessing on the test image g1 with the main scanning direction D1 as the processing direction Dx1 (see FIG. 6).

[0084] Furthermore, the feature image generating unit 8c generates a second preprocessed image g12 by executing the second preprocessing on the test image g1 with the sub-scanning direction D2 as the processing direction Dx1 (see FIG. 6).

[0085] Furthermore, the feature image generating unit 8c generates three feature images g21, g22, and g23 by executing the singular part extraction process on the first preprocessed image g11 and the second preprocessed image g12.

[0086] The first pre-processing includes a main filtering process in which the main scanning direction D1 is set as a processing direction Dx1. The main filtering process converts the pixel values ​​of the target pixels Px1 selected sequentially from the test image g1 into conversion values ​​obtained by processing that emphasizes the difference between the pixel values ​​of the target area Ax1 and the pixel values ​​of two adjacent areas Ax2 (see FIGS. 6 and 7).

[0087] The region of interest Ax1 is a region that includes the pixel of interest Px1, and the two adjacent regions Ax2 are regions that are adjacent to both sides of the region of interest Ax1 in a processing direction Dx1 that is set in advance. Each of the region of interest Ax1 and the adjacent region Ax2 is a region that includes one or more pixels.

[0088] The sizes of the attention area Ax1 and the adjacent area Ax2 are set according to the width of the vertical streaks Ps11 or horizontal streaks Ps12 to be extracted, or the size of the noise points Ps13 to be extracted.

[0089] Each of the region of interest Ax1 and the adjacent region Ax2 occupies the same range in a direction intersecting the processing direction Dx1. In the example shown in FIG. 7, the region of interest Ax1 is a region of 21 pixels across 3 columns and 7 rows with the pixel of interest Px1 at the center. Each of the adjacent regions Ax2 is also a region of 21 pixels across 3 columns and 7 rows. Note that in each of the region of interest Ax1 and the adjacent region Ax2, the number of rows is the number of lines along the processing direction Dx1, and the number of columns is the number of lines along the direction intersecting the processing direction Dx1. The size of each of the region of interest Ax1 and the adjacent region Ax2 is set in advance.

[0090] In the main filter process, each pixel value of the region of interest Ax1 is converted to a first correction value using a predetermined first correction coefficient K1, and each pixel value of each adjacent region Ax2 is converted to a second correction value using a predetermined second correction coefficient K2.

[0091] For example, the first correction coefficient K1 is a coefficient of 1 or more by which each pixel value in the region of interest Ax1 is multiplied, and the second correction coefficient K2 is a coefficient of less than 0 by which each pixel value in the adjacent region Ax2 is multiplied. In this case, the first correction coefficient K1 and the second correction coefficient K2 are set so that the sum of the value obtained by multiplying the first correction coefficient K1 by the number of pixels in the region of interest Ax1 and the value obtained by multiplying the second correction coefficient K2 by the number of pixels in the two adjacent regions Ax2 is zero.

[0092] The feature image generating unit 8c derives the first correction value corresponding to each pixel of the attention area Ax1 by multiplying each pixel value of the attention area Ax1 by a first correction coefficient K1, and derives the second correction value corresponding to each pixel of the two adjacent areas Ax2 by multiplying each pixel value of the two adjacent areas Ax2 by a second correction coefficient K2. Then, the feature image generating unit 8c derives a value obtained by integrating the first correction value and the second correction value as the conversion value of the pixel value of the attention pixel Px1.

[0093] Furthermore, the characteristic image generation unit 8c derives the conversion value by adding the sum or average value of multiple first correction values ​​corresponding to multiple pixels in the attention area Ax1 and the sum or average value of multiple second correction values ​​corresponding to multiple pixels in two adjacent areas Ax2.

[0094] The absolute value of the conversion value is a value obtained by amplifying the absolute value of the difference between the pixel values ​​of the attention area Ax1 and the pixel values ​​of the two adjacent areas Ax2. The process of deriving the conversion value by integrating the first correction value and the second correction value is an example of a process of emphasizing the difference between the pixel values ​​of the attention area Ax1 and the pixel values ​​of the two adjacent areas Ax2.

[0095] It is also possible that the first correction coefficient K1 is a negative number and the second correction coefficient K2 is a positive number.

[0096] For example, it is conceivable that the feature image generating unit 8c generates, as the first preprocessed image g11, first main map data including a plurality of the converted values ​​obtained by the main filtering process in which the main scanning direction D1 is set as the processing direction Dx1.

[0097] As shown in Figure 6, when test image g1 includes one or both of vertical streaks Ps11 and noise points Ps13, the first main map data in which one or both of the vertical streaks Ps11 and noise points Ps13 included in test image g1 are extracted is generated by the main filter processing in which the main scanning direction D1 is the processing direction Dx1.

[0098] Furthermore, when the test image g1 includes horizontal streaks Ps12, the first main map data from which the horizontal streaks Ps12 included in the test image g1 have been removed is generated by the main filtering process in which the main scanning direction D1 is set as the processing direction Dx1.

[0099] The vertical streak Ps11 corresponds to the first unique portion, the horizontal streak Ps12 corresponds to the second unique portion, and the noise point Ps13 corresponds to the third unique portion.

[0100] On the other hand, the second pre-processing includes the main filtering process in which the sub-scanning direction D2 is set as the processing direction Dx1.

[0101] For example, it is conceivable that the feature image generating unit 8c generates, as the second pre-processed image g12, second main map data including a plurality of the integrated values ​​obtained by the main filtering process with the sub-scanning direction D2 as the processing direction Dx1.

[0102] As shown in Figure 6, when test image g1 contains one or both of horizontal streaks Ps12 and noise points Ps13, the second main map data in which one or both of the horizontal streaks Ps12 and noise points Ps13 contained in test image g1 are extracted is generated by the main filter processing in which the sub-scanning direction D2 is the processing direction Dx1.

[0103] Furthermore, when the test image g1 includes vertical streaks Ps11, the second main map data from which the vertical streaks Ps11 included in the test image g1 have been removed is generated by the main filtering process in which the sub-scanning direction D2 is set as the processing direction Dx1.

[0104] However, in the main filter process, an erroneous integrated value having a positive and negative sign opposite to the integrated value expressing the original state of the singular part Ps1 may be derived at the edge parts at both ends of the singular part Ps1 in the processing direction Dx1. If such an erroneous integrated value is processed as a pixel value expressing the singular part Ps1, it may adversely affect the determination of the image defect.

[0105] Therefore, in this embodiment, the first pre-processing further includes an edge enhancement filtering process in which the main scanning direction D1 is the processing direction Dx1, in addition to the main filtering process in which the main scanning direction D1 is the processing direction Dx1.

[0106] Similarly, the second pre-processing further includes the edge emphasis filtering process in which the sub-scanning direction D2 is the processing direction Dx1, in addition to the main filtering process in which the sub-scanning direction D2 is the processing direction Dx1.

[0107] The edge enhancement filter process is a process for performing edge enhancement on the region of interest Ax1 and one of the two adjacent regions Ax2 that is determined in advance.

[0108] Specifically, the edge enhancement filter process converts the pixel value of a pixel of interest Px1, which is sequentially selected from the test image g1, into an edge intensity that combines a third correction value obtained by correcting the pixel value of the region of interest Ax1 with a positive or negative third correction coefficient K3, and a fourth correction value obtained by correcting the pixel value of one of the adjacent regions Ax2 with a fourth correction coefficient K4 whose positive and negative sign is opposite to that of the third correction coefficient K3 (see Figure 6).

[0109] 6, the third correction coefficient K3 is a positive coefficient, and the fourth correction coefficient K4 is a negative coefficient. The third correction coefficient K3 and the fourth correction coefficient K4 are set so that the sum of a value obtained by multiplying the third correction coefficient K3 by the number of pixels in the region of interest Ax1 and a value obtained by multiplying the fourth correction coefficient K4 by the number of pixels in one of the adjacent regions Ax2 is zero.

[0110] The edge emphasis filter process is performed with the main scanning direction D1 as the processing direction Dx1, thereby generating horizontal edge strength map data in which each pixel value of the test image g1 is converted into the edge strength.

[0111] Similarly, the edge emphasis filter process is performed with the sub-scanning direction D2 as the processing direction Dx1, whereby vertical edge strength map data is generated in which each pixel value of the test image g1 is converted into the edge strength.

[0112] In this embodiment, the characteristic image generating unit 8c generates the first main map data by the main filtering process with the main scanning direction D1 as the processing direction Dx1.

[0113] Furthermore, the characteristic image generating unit 8c generates the horizontal edge strength map data by executing the edge emphasis filter process with the main scanning direction D1 as the processing direction Dx1.

[0114] Furthermore, the characteristic image generating unit 8c generates a first preprocessed image g11 by correcting each pixel value of the first main map data with each corresponding pixel value of the horizontal edge strength map data. For example, the characteristic image generating unit 8c generates the first preprocessed image g11 by adding the absolute value of each pixel value of the horizontal edge strength map data to each pixel value of the first main map data.

[0115] Similarly, the characteristic image generating unit 8c generates the second main map data by executing the main filtering process with the sub-scanning direction D2 as the processing direction Dx1.

[0116] Furthermore, the characteristic image generating unit 8c generates the vertical edge strength map data by executing the edge emphasis filter process with the sub-scanning direction D2 as the processing direction Dx1.

[0117] Furthermore, the feature image generating unit 8c generates a second preprocessed image g12 by correcting each pixel value of the second main map data with each corresponding pixel value of the vertical edge strength map data. For example, the feature image generating unit 8c generates the second preprocessed image g12 by adding the absolute value of each pixel value of the vertical edge strength map data to each pixel value of the second main map data.

[0118] The singular portion extraction process is a process for generating three feature images g21, g22, and g23 in which vertical streaks Ps11, horizontal streaks Ps12, and noise points Ps13 contained in the first preprocessed image g11 or the second preprocessed image g12 are individually extracted. The three feature images g21, g22, and g23 are the first feature image g21, the second feature image g22, and the third feature image g23.

[0119] The first feature image g21 is an image obtained by extracting a singular portion Ps1 that exists in the first preprocessed image g11 and is not common to the first preprocessed image g11 and the second preprocessed image g12, out of the singular portion Ps1 consisting of one or more significant pixels in the first preprocessed image g11 and the second preprocessed image g12. The first feature image g21 does not include horizontal streaks Ps12 and noise points Ps13, but includes vertical streaks Ps11 if the first preprocessed image g11 includes the vertical streaks Ps11.

[0120] The significant pixels are pixels that can be distinguished from other pixels by comparing each pixel value or an index value based on each pixel value in the test image g1 with a predetermined threshold value.

[0121] The second feature image g22 is an image in which, of the singular portions Ps1 in the first preprocessed image g11 and the second preprocessed image g12, the singular portions Ps1 that exist in the second preprocessed image g12 and are not common to the first preprocessed image g11 and the second preprocessed image g12 are extracted. The second feature image g22 does not include vertical streaks Ps11 and noise points Ps13, but if the second preprocessed image g12 includes horizontal streaks Ps12, the second feature image g22 includes the horizontal streaks Ps12.

[0122] The third feature image g23 is an image in which the singular portion Ps1 common to the first preprocessed image g11 and the second preprocessed image g12 is extracted. The third feature image g23 does not include the vertical streaks Ps11 and the horizontal streaks Ps12, but includes the noise point Ps13 if the first preprocessed image g11 and the second preprocessed image g12 include the noise point Ps13.

[0123] There are various possible methods for generating the three feature images g21, g22, and g23 from the first preprocessed image g11 and the second preprocessed image g12.

[0124] For example, the feature image generating unit 8c derives the index value Zi by applying the first pixel value Xi, which is each pixel value in the first preprocessed image g11 that exceeds a predetermined reference value, and the second pixel value Yi, which is each pixel value in the second preprocessed image g12 that exceeds the reference value, to the following formula (1), where the subscript i is an identification number of the position of each pixel.

[0125]

number

[0126] The index value Zi of the pixels that make up the vertical stripes Ps11 is a relatively large positive number. The index value Zi of the pixels that make up the horizontal stripes Ps12 is an undetermined small negative number. The index value Zi of the pixels that make up the noise point Ps13 is 0 or a value close to 0. The index value Zi is an example of an index value of the difference between corresponding pixel values ​​in the first preprocessed image g11 and the second preprocessed image g12.

[0127] The above-mentioned properties of the index value Zi can be utilized to simplify the process of extracting vertical streaks Ps11 from the first preprocessed image g11, extracting horizontal streaks Ps12 from the second preprocessed image g12, and extracting noise points Ps13 from the first preprocessed image g11 or the second preprocessed image g12.

[0128] For example, the feature image generating unit 8c generates the first feature image g21 by converting the first pixel value Xi in the first preprocessed image g11 into a first uniqueness Pi derived by the following formula (2). As a result, the first feature image g21 in which the vertical streak Ps11 is extracted from the first preprocessed image g11 is generated.

[0129]

number

[0130] Furthermore, the feature image generating unit 8c generates a second feature image g22 by converting the second pixel value Yi in the second preprocessed image g12 into a second uniqueness Qi derived by the following formula (3). In this way, a second feature image g22 in which the horizontal streak Ps12 is extracted from the second preprocessed image g12 is generated.

[0131]

number

[0132] Furthermore, the feature image generating unit 8c generates a third feature image g23 by converting the first pixel value Xi in the first preprocessed image g11 into a third uniqueness Ri derived by the following formula (4). As a result, the third feature image g23 in which the noise point Ps13 is extracted from the first preprocessed image g11 is generated.

[0133]

number

[0134] Alternatively, the feature image generating unit 8c may generate the third feature image g23 by converting the second pixel value Yi in the second preprocessed image g12 into a third uniqueness Ri derived by the following formula (5). In this way, the third feature image g23 in which the noise point Ps13 is extracted from the second preprocessed image g12 is generated.

[0135]

number

[0136] As described above, the feature image generating unit 8c generates the first feature image g21 by converting each pixel value of the first preprocessed image g11 by the predetermined formula (2) based on the index value Zi. Formula (2) is an example of the first conversion formula.

[0137] Furthermore, the characteristic image generating unit 8c generates a second characteristic image g22 by converting each pixel value of the second preprocessed image g12 by a predetermined formula (3) based on the index value Zi. Formula (3) is an example of the second conversion formula.

[0138] Furthermore, the feature image generating unit 8c generates a third feature image g23 by converting each pixel value of the first preprocessed image g11 or the second preprocessed image g12 by a predetermined formula (4) or (5) based on the index value Zi. Formulas (4) and (5) are each an example of a third conversion formula.

[0139] The process of generating the first feature image g21, the second feature image g22, and the third feature image g23 in step S201 is an example of a process of extracting vertical streaks Ps11, horizontal streaks Ps12, and noise points Ps13 from one or more singular parts Ps1 in the first preprocessed image g11 and the second preprocessed image g12 as the image defects.

[0140] The process of generating the third feature image g23 in step S201 is an example of a process of generating an extracted image in which, among one or more singular parts Ps1 in the first preprocessed image g11 and the second preprocessed image g12, those common to the first preprocessed image g11 and the second preprocessed image g12 are extracted as noise points Ps13. The third feature image g23 is an example of the extracted image.

[0141] After the characteristic images g21, g22, and g23 are generated, the characteristic image generating unit 8c shifts the process to step S202.

[0142] <Process S202> In step S202, the singular portion identifying unit 8d identifies the position of the singular portion Ps1 in each of the feature images g21, g22, and g23. The processing in steps S201 and S201 is an example of a processing for identifying the singular portion Ps1 consisting of a plurality of significant pixels in the test image g1.

[0143] For example, the singular part identifying unit 8d determines that a portion having a pixel value outside a predetermined reference range in each of the feature images g21, g22, and g23 is the singular part Ps1. In step S202, a vertical streak Ps11 is identified from the first feature image g21, a horizontal streak Ps12 is identified from the second feature image g22, and a noise point Ps13 is identified from the third feature image g23.

[0144] Furthermore, the unique portion identifying unit 8d executes a combining process for each of the feature images g21, g22, and g23. The combining process is a process for combining a plurality of unique portions Ps1 into a single series of unique portions Ps1 when the plurality of unique portions Ps1 are present within a predetermined proximity range in each of the main scanning direction D1 and the sub-scanning direction D2.

[0145] For example, if the first feature image g21 includes two vertical streaks Ps11 spaced apart in the sub-scanning direction D2 within the proximity range, the singular part identification unit 8d combines the two vertical streaks Ps11 into a single vertical streak Ps11 by the combining process.

[0146] Similarly, when the second feature image g22 includes two horizontal streaks Ps12 spaced apart in the main scanning direction D1 within the proximity range, the unique part identification unit 8d combines the two horizontal streaks Ps12 into a single horizontal streak Ps12 by the combining process.

[0147] In addition, when the third feature image g23 includes multiple noise points Ps13 arranged at intervals in the main scanning direction D1 or the sub-scanning direction D2 within the proximity range, the singular part identification unit 8d combines the multiple noise points Ps13 into a single noise point Ps13 by the combining process.

[0148] Then, when the position of the unique part Ps1 is not identified in any of the three characteristic images g21, g22, and g23 by the processing in step S202, the unique part identifying unit 8d ends the unique defect determination processing.

[0149] On the other hand, if the position of the unique portion Ps1 is identified for one or more of the three characteristic images g21, g22, and g23, the unique portion identifying unit 8d shifts the process to step S203.

[0150] <Process S203> In step S203, the color vector specifying unit 8e specifies a detection color vector that represents a vector in color space from one of the color of the unique portion Ps1 in the test image g1 and the color of a reference area including the periphery of the unique portion Ps1 to the other.

[0151] The reference region is a region of a predetermined range determined based on the unique portion Ps1. For example, the reference region is a region that includes a peripheral region adjacent to the unique portion Ps1 and does not include the unique portion Ps1. The reference region may also include the unique portion Ps1 and a peripheral region adjacent to the unique portion Ps1.

[0152] The test image g1 is originally a uniform halftone image. Therefore, when a good test image g1 is formed on the test output sheet 9, the singular portion Ps1 is not identified, and the color vectors at any positions in the test image g1 are generally zero vectors.

[0153] On the other hand, when a unique portion Ps1 is identified, the direction of the detected color vector between the unique portion Ps1 and the reference area corresponding to the unique portion Ps1 represents an excess or deficiency of toner concentration of any of the four developing colors in the image forming device 2.

[0154] Therefore, the direction of the detected color vector indicates which of the four image forming units 4x in the image forming apparatus 2 caused the occurrence of the singular portion Ps1.

[0155] The color vector specifying unit 8e may specify, as the detection color vector, a vector in a color space from one of the color of the singular part Ps1 in the test image g1 and a predetermined reference color to the other. In this case, the reference color is the original color of the test image g1.

[0156] Furthermore, in step S204, the color vector specifying unit 8e determines, based on the detected color vector, the developed color causing the singular portion Ps1 and the excess or deficiency state of the density of that developed color.

[0157] For example, information on a plurality of unit vectors representing the direction in which the density of each of cyan, magenta, yellow, or black increases and the direction in which the density is insufficient with respect to the reference color of test image g1 is stored in advance in secondary storage device 82.

[0158] The color vector specifying unit 8e normalizes the detected color vector to a predetermined unit length. Furthermore, the color vector specifying unit 8e determines which of the multiple unit vectors the detected color vector after normalization is most similar to. In this way, the color vector specifying unit 8e determines the developing color causing the singular portion Ps1 and the excess or deficiency of the density of the developing color.

[0159] After executing the process of step S203, the color vector specifying unit 8e shifts the process to step S204.

[0160] <Process S204> In step S204, if a singular portion Ps1 is identified in one or both of the second feature image g22 and the third feature image g23, the periodicity determination unit 8f transitions the process to step S205; otherwise, the periodicity determination unit 8f transitions the process to step S207.

[0161] In the following description, one or both of the second feature image g22 and the third feature image g23 in which the peculiar portion Ps1 is identified will be referred to as a periodicity assessment image. The peculiar portion Ps1 in the periodicity assessment image is a horizontal streak Ps12 or a noise point Ps13 (see FIG. 6).

[0162] <Process S205> In step S205, the noise point determination unit 8h performs sheet noise removal processing on the third feature image g23.

[0163] The sheet may have dot-like sheet noise formed during the manufacturing process. The sheet noise is not an image defect and should be excluded from the determination of the cause of the image defect.

[0164] The sheet noise elimination process is a process of detecting the sheet noise from the noise point Ps13 in the third feature image g23 and excluding the sheet noise from the targets for determining the cause of the image defect.

[0165] The sheet noise elimination process will be described in detail later (see FIG. 5). After executing the sheet noise elimination process, the noise point determination unit 8h shifts the process to step S206.

[0166] Note that the noise point Ps13 that is the subject of judgment as to the cause of the image defect in steps S206 to S208 described later is the noise point Ps13 that is judged not to be the sheet noise.

[0167] <Process S206> In step S206, the periodicity determination unit 8f executes a periodic singular part determination process on the periodicity determination image. The periodic singular part determination process includes a number determination process, a singular part periodicity determination process, and a singular part periodicity cause determination process.

[0168] The number determination process is a process for determining the number of unique portions Ps1 arranged in the sub-scanning direction D2 in the periodicity determination image.

[0169] Specifically, the periodicity determination unit 8f determines the number of horizontal stripes Ps12 lined up in the sub-scanning direction D2 in the second feature image g22 by counting the number of horizontal stripes Ps12 lined up in the sub-scanning direction D2 whose portion occupying the same range in the main scanning direction D1 exceeds a predetermined ratio.

[0170] Furthermore, the periodicity determination unit 8f determines the number of noise points Ps13 lined up in the sub-scanning direction D2 by counting the number of noise points Ps13 whose positional deviation in the main scanning direction D1 is within a predetermined range and lined up in the sub-scanning direction D2 in the third feature image g23.

[0171] The periodicity determining unit 8f executes the singular portion periodicity determining process only for the singular portions Ps1 of which the number aligned in the sub-scanning direction D2 is two or more.

[0172] Furthermore, the periodicity determining section 8f determines that the singular portion Ps1 having one line in the sub-scanning direction D2 does not have periodicity, and skips the singular portion periodicity determining process and the singular portion periodicity cause determining process.

[0173] The singular portion periodicity determination process is a process for determining the presence or absence of one or more predetermined periodicities in the sub-scanning direction D2 for the periodicity determination image.

[0174] The periodicity corresponds to the outer circumferential length of a rotating body related to image formation, such as the photoconductor 41, charging roller 42a, developing roller 43a, or primary transfer roller 441 in each of the image forming units 4x or in the transfer device 44. The state of the rotating body related to image formation affects the quality of the image formed on the sheet. In the following description, the rotating body related to image formation is referred to as an image forming rotating body.

[0175] When the image defect occurs due to a defect in the imaging rotor, the periodicity corresponding to the outer circumferential length of the imaging rotor may appear as a spacing in the sub-scanning direction D2 between a plurality of horizontal streaks Ps12 or a plurality of noise points Ps13.

[0176] Therefore, when the periodicity judgment image has a periodicity corresponding to the outer circumferential length of the imaging rotor, it can be said that the imaging rotor corresponding to that periodicity is the cause of the horizontal streaks Ps12 or noise points Ps13 in the periodicity judgment image.

[0177] When the number of unique portions Ps1 aligned in the sub-scanning direction D2 in the periodicity determination image is two, the periodicity determination unit 8f executes an interval derivation process as the unique portion periodicity determination process.

[0178] In the interval derivation process, the periodicity determination unit 8f derives the interval between the two unique portions Ps1 in the sub-scanning direction D2 as the period of the two unique portions Ps1.

[0179] When the number of the singular portions Ps1 aligned in the sub-scanning direction D2 in the periodicity determination image is three or more, the periodicity determination unit 8f executes a frequency analysis process as the singular portion periodicity determination process.

[0180] In the frequency analysis process, the periodicity determination unit 8f identifies a singular part frequency for the periodicity determination image including three or more singular parts Ps1 aligned in the sub-scanning direction D2. The singular part frequency is a dominant frequency in the frequency distribution of the data string of the singular part Ps1 in the periodicity determination image. The periodicity determination unit 8f identifies the singular part frequency by performing frequency analysis such as a Fourier transform.

[0181] Furthermore, the periodicity determining unit 8f derives the period corresponding to the singular part frequency as the periods of three or more singular parts Ps1.

[0182] In the singular part periodicity cause determination process, the periodicity determination unit 8f determines whether or not the outer circumferential length of each of the predetermined candidates for the imaging rotor satisfies a predetermined period approximation condition with respect to the period of the singular part Ps1 for each of the predetermined candidates for the imaging rotor in step S206. The plurality of candidates for the imaging rotor in step S206 are an example of the predetermined plurality of cause candidates corresponding to the horizontal streaks Ps12 or the noise points Ps13.

[0183] In the following description, the singular portion Ps1 of the target that is determined to satisfy the periodic approximation condition for any of the imaging rotor candidates is referred to as a periodic singular portion, and the other singular portions Ps1 are referred to as non-periodic singular portions. The periodic singular portion and the non-periodic singular portion are the singular portions Ps1 included in the second feature image g22 or the third feature image g23.

[0184] The periodicity determination unit 8f determines that one of the imaging rotor candidates determined to satisfy the periodic approximation condition in the singular part periodicity cause determination process is the cause of the periodic singular part, thereby determining the cause of the horizontal streak Ps12 or the noise point Ps13.

[0185] In addition, in step S206, the periodicity determination unit 8f determines, based on the detected color vector identified in step S204, which of the four image forming units 4x, each having a different development color, is the cause of the horizontal streak Ps12 or the noise point Ps13.

[0186] In addition, when three or more singular parts Ps1 arranged in the sub-scanning direction D2 include a non-periodic singular part that does not correspond to the singular part frequency, the periodicity determination unit 8f targets the non-periodic singular part for the feature pattern recognition processing described below.

[0187] For example, the periodicity determining unit 8f generates inverse Fourier transformed data by performing an inverse Fourier transform on the frequency distribution obtained by the Fourier transform, from which frequency components other than the singular part frequency have been removed.

[0188] Furthermore, the periodicity determination unit 8f determines, among the three or more unique parts Ps1 arranged in the sub-scanning direction D2, the one that is located at a position away from the peak position in the waveform in the sub-scanning direction D2 represented by the inverse Fourier transform data, as the non-periodic unique part.

[0189] Then, when it is determined in step S206 that the second feature image g22 and the third feature image g23 do not include the non-periodic singular portion, the periodicity determining unit 8f terminates the singular defect determination process.

[0190] On the other hand, when the periodicity determining unit 8f determines in step S206 that the second feature image g22 or the third feature image g23 includes the non-periodic singular portion, the periodicity determining unit 8f shifts the process to step S207.

[0191] <Process S207> In step S207, the pattern recognition unit 8g performs a feature pattern recognition process on each of the first feature image g21, and the second and third feature images g22 and g23 that include the non-periodic singular portion.

[0192] In the feature pattern recognition process, a first feature image g21, and a second feature image g22 and a third feature image g23 including the undetermined non-periodic singular portion are set as input images. In the feature pattern recognition process, a pattern recognition unit 8g determines whether the input image corresponds to any one of a plurality of predetermined candidate causes corresponding to the image defect by pattern recognition of the input image.

[0193] The input image of the feature pattern recognition process may include the horizontal edge strength map data or the vertical edge strength map data obtained by the edge emphasis filter process. For example, in the feature pattern recognition process for determining a vertical streak Ps11, a first feature image g21 and the horizontal edge strength map data are used as the input image.

[0194] Similarly, in the feature pattern recognition process for determining the horizontal streak Ps12, the second feature image g22 and the vertical edge strength map data are used as the input image.

[0195] Similarly, in the feature pattern recognition process for determining the noise point Ps13, the third feature image g23 and either or both of the horizontal edge strength map data and the vertical edge strength map data are used as the input images.

[0196] For example, the feature pattern recognition process is a process of classifying the input image into one of the multiple candidate causes using a learning model that has been trained in advance using multiple sample images corresponding to the multiple candidate causes as training data.

[0197] For example, the learning model may be a model that employs a classification-type machine learning algorithm called Random Forest, a model that employs a machine learning algorithm called Support Vector Machine (SVM), or a model that employs a Convolutional Neural Network (CNN) algorithm.

[0198] The learning models are prepared individually for the first feature image g21, and the second and third feature images g22 and g23 each including the non-periodic singular portion. In addition, the sample images are used as the teacher data for each of the cause candidates.

[0199] Furthermore, in step S207, the pattern recognition unit 8g determines, based on the detected color vector identified in step S204, which of the four image forming units 4x, each with a different developing color, is the cause of the vertical streak Ps11, the horizontal streak Ps12, or the noise point Ps13.

[0200] By the process of step S207, the cause of the vertical streak Ps11 and the causes of the horizontal streak Ps12 and noise point Ps13 determined as the non-periodic singular portion are determined. After executing the process of step S207, the pattern recognition unit 8g ends the singular defect determination process.

[0201] The process in step S207 is an example of a process for determining the cause of the vertical streaks Ps11, the horizontal streaks Ps12, or the noise points Ps13.

[0202] [Sheet noise removal processing] Next, an example of the procedure of the sheet noise elimination process in step S205 will be described with reference to the flowchart shown in Fig. 5. In the following description, S301, S302, ... represent identification codes of multiple steps in the sheet noise elimination process. The sheet noise elimination process starts from step S301.

[0203] In this embodiment, the noise point Ps13 that is the target of the sheet noise removal process is the noise point Ps13 that is determined to be the non-periodic singular part.

[0204] <Process S301> In step S301, the noise point determination unit 8h selects a target sheet from a plurality of predetermined sheet candidates according to selection information input through the operation unit 801. The noise point determination unit 8h executes a process of inputting the selection information after displaying a sheet selection screen including information on the plurality of sheet candidates as a selection menu on the display unit 802.

[0205] The plurality of sheet candidates are candidates for the type of the sheet in the test output sheet 9. For example, the type of the sheet is determined according to one or more of the material of the sheet, the product name or model, and the production lot.

[0206] The characteristics of the sheet noise differ depending on the type of the sheet, so in step S301, the noise point determination unit 8h selects the target sheet corresponding to the test output sheet 9 from among the multiple sheet candidates.

[0207] On the other hand, there is a case where the image forming apparatus 2 includes a plurality of sheet storage sections 21, and the secondary storage device 82 pre-stores stored sheet data indicating the type of the sheets stored in each of the plurality of sheet storage sections 21.

[0208] In the above case, the stored sheet data may include data on the multiple sheet candidates corresponding to the sheets stored in the multiple sheet storage units 21.

[0209] Furthermore, the noise point determination unit 8h may select, as the target sheet, one of the plurality of sheet candidates in the stored sheet data that corresponds to the sheet storage unit 21 that was the supply source of the sheet in the test print process.

[0210] In the test print process, information for selecting the sheet storage unit 21 is transferred between the multiple processing modules in the CPU 80 through the RAM 81. In this case, the RAM 81 is an example of an input device that inputs the selection information for the target sheet.

[0211] After executing the process of step S301, the noise point determining unit 8h shifts the process to step S302.

[0212] <Process S302> In step S302, the noise point determination unit 8h derives feature information for each noise point Ps13 in the third feature image g23. The feature information is an example of information about the noise point Ps13 included in the test image g1. In this embodiment, the generation of the third feature image g23 by the singular part identification unit 8d in step S201 is part of the process of deriving the feature information.

[0213] For example, the noise point determining unit 8h derives at least one of the degree of flatness of the noise point Ps13 and the color vector difference of the noise point Ps13 as the feature information.

[0214] The noise point determination unit 8h derives the ratio of the length of the noise point Ps13 in the main scanning direction D1 to the length in the sub-scanning direction D2, the circularity or the flattening ratio, or the like, as the degree of flattening.

[0215] In addition, the noise point determination unit 8h may identify the longitudinal direction DL1 of the noise point Ps13 and derive the ratio between the length of the noise point Ps13 in the longitudinal direction DL1 and the length of the noise point Ps13 in the short direction perpendicular to the longitudinal direction DL1 as the degree of flatness (see Figure 8).

[0216] The color vector difference is an index value representing the degree of agreement or difference between the detected color vector of the noise point Ps13 and each of four predetermined reference color vectors. The four reference vectors are predetermined vectors in a color space corresponding to four development colors in the image forming apparatus 2.

[0217] In this embodiment, the four reference color vectors are unit vectors that respectively represent the four colors of cyan, magenta, yellow, and black in the color space. The four reference color vectors are an example of one or more pieces of predetermined reference color information that correspond to one or more development colors in the image forming apparatus 2.

[0218] As described above, the detection color vector of the noise point Ps13 is a vector in the color space from one of the color of the noise point Ps13 in the third feature image g23 and the color of the reference range to the other. In this embodiment, the detection color vector is normalized to a predetermined unit length.

[0219] For example, the color vector difference may be an angle between the detection color vector and each of the reference color vectors. In this case, the closer the color vector difference is to 180 degrees, the closer the color of the noise point Ps13 is to the developed color, and the closer the color vector difference is to 180 degrees, the more different the color of the noise point Ps13 is from the developed color.

[0220] The color vector difference is an example of information that indicates the degree of agreement or difference between the detected color vector and the four reference color vectors.

[0221] The detected color vector is an example of detected color information corresponding to the color of the noise point Ps13 in the third feature image g23.

[0222] The color of the sheet noise may be different from any of the developed colors of the image forming device 2. Therefore, the sheet noise is often distinguishable from the noise point Ps13 caused by the image defect by a previous color vector difference.

[0223] The sheet noise can often be distinguished from the noise point Ps13 caused by the image defect by the color vector difference or the degree of flattening.

[0224] In this embodiment, the noise point determination unit 8h derives the edge strength and the number of edges of the noise point Ps13 as the feature information in addition to the color vector difference and the degree of flatness. In the following description, a pixel row that crosses the noise point Ps13 in the third feature image g23 is referred to as a crossing pixel row AR1 (see FIG. 8).

[0225] The edge strength represents the degree of difference between a pixel value V1 of the noise point Ps13 in the third feature image g23 and a pixel value V1 of an adjacent region AN1 adjacent to the noise point Ps13 (see FIG. 8). For example, the noise point determination unit 8h derives the difference between a representative value of the pixel values ​​V1 of the noise point Ps13 and a representative value of the pixel values ​​V1 of the adjacent region AN1 as the edge strength.

[0226] Furthermore, the noise point determination unit 8h may derive, as the edge intensity, a pixel value V1 of the outer edge portion of the noise point Ps13 in an image obtained by performing a known edge enhancement process on the third feature image g23. For example, the edge intensity of the noise point Ps13 caused by the image defect indicates an edge that is steeper than the edge intensity of the sheet noise.

[0227] The number of edges is the number of points where the change in pixel value V1 in a crossing pixel row AR1, which is a pixel row that crosses the noise point Ps13 in the third feature image g23, exceeds the allowable range (see FIG. 8).

[0228] Specifically, the noise point determination unit 8h sets a traversal line L1 that traverses the noise point Ps13, and identifies pixel rows along the traversal line L1 in the noise point Ps13 and in the adjacent areas AN1 on both sides of the noise point Ps13 as traversal pixel rows AR1.

[0229] For example, the noise point determination unit 8h sets a line that passes through the center of the noise point Ps13 in the short side direction and extends along the longitudinal direction DL1 as the transverse line L1.

[0230] Furthermore, the noise point determining unit 8h derives, as the number of edges, the number of points in the cross-sectional pixel row AR1 where the change in pixel value V1 exceeds the allowable range.

[0231] For example, the noise point determining unit 8h derives, as the number of edges, the number of points where the differential value dV1 of the pixel value V1 in the cross-sectional pixel row AR1 falls outside a predetermined first reference range RA1 (see FIG. 8).

[0232] Furthermore, the noise point determination unit 8h may derive the number of points where the pixel value V1 in the cross-sectional pixel row AR1 crosses the reference value VA1 or the second reference range RA2 as the number of edges (see FIG. 8).

[0233] For example, the noise point determination unit 8h sets the reference value VA1 or the second reference range RA2 based on the pixel value V1 of the adjacent region AN1. The pixel value V1 of the adjacent region AN1 is an example of the pixel value V1 of the cross-sectional pixel row AR1.

[0234] 8A to 8C show an example of a noise point Ps13 caused by abnormal development. The abnormal development is a phenomenon in which a dot-like defective toner image is developed on the surface of the photoconductor 41 by the developing device 43 of the image forming apparatus 2, and then transferred to the sheet. In other words, the noise point Ps13 caused by the abnormal development is one type of the image defect.

[0235] FIG. 8A shows a case where the symptom of the noise point Ps13 is mild, FIG. 8B shows a case where the symptom of the noise point Ps13 is moderate, and FIG. 8C shows a case where the symptom of the noise point Ps13 is severe.

[0236] As shown in FIG. 8, the noise point Ps13 caused by the abnormal development becomes a ring-shaped image as it becomes more severe, and the ring-shaped images are further linked together along a straight line. Usually, the sheet noise does not have such characteristics. Therefore, when the number of edges is large, the noise point Ps13 is likely to be the image defect rather than the sheet noise.

[0237] After executing the process of step S302, the noise point determining unit 8h shifts the process to step S303.

[0238] <Process S303> In step S303, the noise point determination unit 8h selects a target algorithm that corresponds to the target sheet from among a plurality of determination algorithms that are previously associated with the plurality of sheet candidates.

[0239] Each of the determination algorithms corresponds to each of the plurality of sheet candidates, and is an algorithm for determining whether or not the noise point Ps13 is the sheet noise. In this embodiment, each of the determination algorithms is an algorithm for determining whether or not the feature information of the noise point Ps13 derived in step S302 is information representing the sheet noise.

[0240] For example, each of the determination algorithms is an algorithm that determines whether or not the noise point Ps13 is the sheet noise by comparing the value of the feature information or an evaluation value according to the feature information with a predetermined threshold value.

[0241] Further, each of the judgment algorithms may be a learning model having a value of the feature information or an evaluation value according to the feature information as an input parameter. The learning model is a model that is trained in advance using a plurality of sample data corresponding to the sheet noise as teacher data. The sample data is data corresponding to the feature information.

[0242] The learning model is prepared for each of the plurality of sheet candidates. For example, the learning model may be a model using the random forest, a model using the SVM, or a model using the CNN algorithm.

[0243] In this embodiment, the algorithm data DT1 representing the plurality of sheet candidates and the plurality of determination algorithms corresponding to the plurality of sheet candidates are stored in the secondary storage device 82 in advance.

[0244] In step S301, the noise point determination unit 8h generates the selection menu of the sheet selection screen based on the algorithm data DT1. Furthermore, in step S303, the noise point determination unit 8h selects one of the determination algorithms in the algorithm data DT1 that corresponds to the target sheet as the target algorithm.

[0245] After executing the process of step S303, the noise point determining unit 8h shifts the process to step S304.

[0246] <Process S304> In step S304, the noise point determination unit 8h executes a sheet noise determination process. The sheet noise determination process is a process for determining whether the noise point Ps13 is the sheet noise by applying the feature information derived in step S302 to the target algorithm.

[0247] After executing the process of step S304, the noise point determining unit 8h shifts the process to step S305.

[0248] <Process S304> In step S304, the noise point determination unit 8h excludes the noise point Ps13 determined to be the sheet noise from the targets for determining the cause of the image defect in step S207.

[0249] That is, the process of determining the cause of the noise point Ps13 in step S207 is executed for the noise point Ps13 in the third feature image g23 that is determined not to be the sheet noise.

[0250] After executing the process of step S305, the noise point determination unit 8h ends the sheet noise removal process.

[0251] As described above, the noise point determination unit 8h executes the sheet noise determination process in step S304 by applying the feature information to the target algorithm corresponding to the type of the sheet itself of the test output sheet 9. This makes it possible to determine with high accuracy whether the noise point Ps13 in the third feature image g23 is the sheet noise or not.

[0252] Furthermore, in step S302, the noise point determination unit 8h derives at least one of the degree of flattening of the noise point Ps13 in the third feature image g23 and the edge strength of the noise point Ps13 as the feature information.

[0253] In the present embodiment, the noise point determination unit 8h also specifies the number of edges and the color vector difference as the feature information. The degree of flatness, the edge strength, the number of edges, and the color vector difference are information effective for distinguishing between the sheet noise and the image defect.

[0254] [First application example] Next, a first application example of the image processing device 10 will be described.

[0255] In step S302, the noise point determination unit 8h in this application example derives an image of a target region including the noise point Ps13 in the third feature image g23 as the feature information. For example, the target region is a region of a predetermined shape and size centered on the noise point Ps13.

[0256] In addition, each of the judgment algorithms in this application example is an algorithm that represents a sheet noise pattern recognition process in which an image of the target area is used as an input image, and whether or not the input image is an image corresponding to the sheet noise is determined by pattern recognition of the input image.

[0257] In the sheet noise determination process in step S304, the noise point determination unit 8h executes the sheet noise pattern recognition process with the image of the target area as the input image to determine whether the noise point Ps13 is the sheet noise or not.

[0258] In this application example, the sheet noise pattern recognition process is a process of determining whether or not the input image is an image corresponding to the sheet noise using a learning model that has been pre-trained using multiple sample images corresponding to the sheet noise as training data.

[0259] For example, the learning model may be a model employing the random forest, a model employing the SVM, or a model employing the CNN algorithm.

[0260] When this application example is adopted, the same effects as when the first embodiment is adopted can be obtained.

[0261] [Second application example] Next, the procedure of the feature image generating process in the second application example of the image processing device 10 will be described with reference to the flowchart shown in FIG.

[0262] In the following description, S401, S402, ... represent identification codes of a plurality of steps in the feature image generation processing according to this application example. The feature image generation processing according to this application example starts from step S401.

[0263] <Process S401> In step S401, the characteristic image generating unit 8c selects a compression rate to be adopted from a plurality of preset compression rate candidates, and moves the process to step S402.

[0264] <Process S402> In step S402, the characteristic image generating unit 8c compresses the scanned image at the selected compression ratio to generate a test image g1. The processes in steps S401 and S402 are an example of a compression process. After that, the characteristic image generating unit 8c shifts the process to step S403.

[0265] <Process S403> In step S403, the feature image generating unit 8c generates a first preprocessed image g11 by performing the first preprocessing on the compressed test image g1 obtained in step S401. After that, the feature image generating unit 8c shifts the process to step S404.

[0266] <Process S404> In step S404, the feature image generating unit 8c generates a second preprocessed image g12 by performing the second preprocessing on the compressed test image g1 obtained in step S401. After that, the feature image generating unit 8c shifts the process to step S405.

[0267] <Process S405> In step S405, if the processes of steps S401 to S404 have been performed for all of the multiple compression ratio candidates, the characteristic image generation unit 8c transitions to step S406; if not, it performs the processes of steps S401 to S404 for different compression ratios.

[0268] In the compression processing in steps S401 and S402, the characteristic image generating unit 8c generates a plurality of test images g1 having different sizes by compressing the read image at a plurality of compression ratios.

[0269] Furthermore, in steps S403 and S404, the characteristic image generation unit 8c performs the first pre-processing and the second pre-processing on a plurality of test images g1 to generate a plurality of first pre-processed images g11 and a plurality of second pre-processed images g12, each of which corresponds to the plurality of test images g1.

[0270] <Process S406> In step S406, the feature image generating unit 8c executes the singular part extraction process on each of the first preprocessed images g11 and the second preprocessed images. As a result, the feature image generating unit 8c generates multiple candidates for the first feature image g21, the second feature image g22, and the third feature image g23 corresponding to the test images g1. After that, the feature image generating unit 8c shifts the process to step S407.

[0271] <Process S407> In step S407, the feature image generating unit 8c generates a first feature image g21, a second feature image g22, and a third feature image g23 by aggregating the candidates obtained in step S406. Thereafter, the feature image generating unit 8c ends the feature image generation process.

[0272] For example, the feature image generating unit 8c sets a representative value such as the maximum or average value of each pixel value in a plurality of candidates for the first feature image g21 as each pixel value of the first feature image g21. The same applies to the second feature image g22 and the third feature image g23.

[0273] The processes in steps S401 to S404 are an example of a process for generating a plurality of first preprocessed images g11 and a plurality of second preprocessed images g12 by performing the first preprocessing and the second preprocessing multiple times with different size ratios between the test image g1 and the attention area Ax1 and the adjacent area Ax2. Changing the compression rate is an example of changing the size ratio between the test image g1 and the attention area Ax1 and the adjacent area Ax2.

[0274] Furthermore, the processing of steps S406 to S407 is an example of a process for generating a first feature image g21, a second feature image g22, and a third feature image g23 by the singular part extraction process based on a plurality of first preprocessed images g11 and a plurality of second preprocessed images g12.

[0275] By employing this application example, vertical streaks Ps11 or horizontal streaks Ps12 of different thicknesses, or noise points Ps13 of different sizes can be extracted without omission.

[0276] The first pre-processing and the second pre-processing in this application example are an example of a process for generating a plurality of first pre-processed images g11 and a plurality of second pre-processed images g12 by performing the first pre-processing and the second pre-processing multiple times with different size ratios between the test image g1 and the size of the attention area Ax1 and the adjacent area Ax2.

[0277] In addition, the feature image generating unit 8c may generate a plurality of first preprocessed images g11 and a plurality of second preprocessed images g12 by changing the filter size and executing the first preprocessing and the second preprocessing multiple times.

[0278] The filter size is the size of the region of interest Ax1 and the adjacent region Ax2 in the first pre-processing and the second pre-processing. Changing the filter size is an example of changing the size ratio between the test image g1 and the size of the region of interest Ax1 and the adjacent region Ax2.

[0279] In this application example, the feature image generating unit 8c may aggregate each of the multiple first preprocessed images g11 and the multiple second preprocessed images into one.

[0280] For example, the feature image generating unit 8c sets a representative value such as a maximum value or an average value of each pixel value in the multiple first preprocessed images g11 as each pixel value of the aggregated first feature image g21. The same applies to the multiple second preprocessed images g12.

[0281] Furthermore, the feature image generating unit 8c may execute the singular part extraction process on the aggregated first preprocessed image g11 and second preprocessed image g12, thereby generating a first feature image g21, a second feature image g22, and a third feature image g23.

[0282] [Third application example] Next, the feature image generating process in the third application example of the image processing device 10 will be described.

[0283] In this application example, the feature image generating unit 8c identifies a portion in the first preprocessed image g11 and the second preprocessed image g12 where the pixel values ​​are outside a predetermined reference range as the unique portion Ps1.

[0284] That is, in this application example, the feature image generating unit 8c, in the singular portion extraction process, identifies the singular portion Ps1 based on the magnitude of each pixel value in the first preprocessed image g11 and the second preprocessed image g12. The process by the feature image generating unit 8c in this application example is an example of a process for identifying the singular portion Ps1 consisting of one or more significant pixels in the test image g1.

[0285] Furthermore, the feature image generating unit 8c extracts vertical streaks Ps11 from the singular portion Ps1 of the first preprocessed image g11 by removing the singular portion Ps1 common to the first preprocessed image g11 and the second preprocessed image g12.

[0286] Furthermore, the feature image generating unit 8c extracts horizontal streaks Ps12 from the singular portion Ps1 of the second preprocessed image g12 by removing the singular portion Ps1 common to the first preprocessed image g11 and the second preprocessed image g12.

[0287] Furthermore, the feature image generating unit 8c extracts a singular portion Ps1 common to the first preprocessed image g11 and the second preprocessed image g12 as a noise point Ps13.

[0288] For example, the characteristic image generating unit 8c generates a first characteristic image g21 by converting the first pixel value Xi determined to be other than the vertical streak Ps11 in the first preprocessed image g11 into an interpolated value based on the surrounding pixel values.

[0289] Similarly, the characteristic image generating unit 8c generates a second characteristic image g22 by converting the second pixel values ​​Yi determined to be other than the horizontal streak Ps12 in the second preprocessed image g12 into interpolated values ​​based on the surrounding pixel values.

[0290] Similarly, the feature image generating unit 8c generates a third feature image g23 by converting the first pixel value Xi determined to be other than the noise point Ps13 in the first preprocessed image g11 into an interpolated value based on the surrounding pixel values.

[0291] Alternatively, the feature image generating unit 8c may generate the third feature image g23 by converting the second pixel value Yi determined to be other than the noise point Ps13 in the second preprocessed image g12 into an interpolated value based on the surrounding pixel values.

[0292] [Fourth application example] The image defect determination process in the fourth application example of the image processing device 10 will be described below.

[0293] In general, it may be difficult for an image sensor to accurately detect the shade of the yellow part in an image in which yellow and other colors are mixed, depending on the density of each color.Similarly, it may be difficult for an image sensor to accurately detect the shade of the colored part in an image in which black and colored colors are mixed, depending on the density of each color.

[0294] In this application example, the job control section 8b causes two or three test output sheets 9, on which different types of original test images g01 are formed, to be output in the test print process.

[0295] When three test output sheets 9 are output, one sheet is formed with an original mixed color test image formed by combining a uniform cyan monochrome halftone image and a uniform magenta monochrome halftone image, another sheet is formed with an original yellow test image which is a uniform yellow monochrome halftone image, and another sheet is formed with an original gray test image which is a uniform black monochrome halftone image.

[0296] When two test output sheets 9 are output, one sheet has a mixed color test image formed by combining a uniform cyan monochrome halftone image, a uniform magenta monochrome halftone image, and a uniform yellow monochrome halftone image, and the other sheet has the original gray test image formed thereon.

[0297] Therefore, the test image g1 in this application example includes a mixed color test image, a yellow test image, and a gray test image corresponding to the original mixed color test image, the original yellow test image, and the original gray test image, respectively.

[0298] The yellow test image and the gray test image are halftone images of one developed color different from the color mixed into the mixed-color test image. The yellow test image and the gray test image are each an example of a single-color test image.

[0299] In this application example, the characteristic image generating unit 8c generates a first characteristic image g21, a second characteristic image g22, and a third characteristic image g23 for each of the mixed color test image and the single color test image read from the multiple test output sheets 9.

[0300] Furthermore, in this application example, the unique portion identifying unit 8d identifies the position of the unique portion Ps1 for the first feature image g21, the second feature image g22, and the third feature image g23 corresponding to the mixed-color test image and the monochromatic test image, respectively. Note that the mixed test image and the monochromatic test image in this application example are each an example of a target test image for identifying the unique portion Ps1.

[0301] In this application example, the color vector determination unit 8e, the periodicity determination unit 8f, and the pattern recognition unit 8g execute processing to determine the cause of the image defect using the first characteristic image g21, the second characteristic image g22, and the third characteristic image g23 corresponding to the color mixing test image, as in the above embodiment.

[0302] In this application example, the periodicity judgment unit 8f and the pattern recognition unit 8g judge the cause of the image defect corresponding to the singular portion in the color mixing test image from among a plurality of image forming units 4x corresponding to a plurality of developing colors mixed in the color mixing test image.

[0303] Furthermore, in this application example, the periodicity judgment unit 8f and the pattern recognition unit 8g, similar to the above embodiment, perform processing to determine the cause of the image defect using the first characteristic image g21, the second characteristic image g22, and the third characteristic image g23 corresponding to the monochrome test image.

[0304] The periodicity determination unit 8f and the pattern recognition unit 8g in this application example determine the cause of the image defect corresponding to the singular portion in the monochrome test image from one of the multiple image forming units 4x that corresponds to the color of the monochrome test image.

[0305] When this application example is adopted, it is also possible to determine the cause of the image defect based on the test output sheets 9 which are fewer in number than the total number of developing colors of the image forming apparatus 2 . [Explanation of symbols]

[0306] 1: Image reader 2: Image forming device 3: Sheet transport mechanism 4: Printing section 4x: Imaging section 10: Image processing device 41: Photoreceptor 42: Charging device 42a: Charging roller 43: Developing device 43a: Developing roller 43b:Developer tank 43c: Regulatory blade 44: Transcription device 46: Fixing device 430: Bias output circuit 440: Intermediate transfer belt (transfer body) D1: Main scanning direction D2: Sub-scanning direction Pd1: Original drawing part Ps1: Singular part Ps11: Vertical stripes Ps12: Horizontal stripes Ps13: Noise point Px1: Pixel of interest g1: Test image g11: First preprocessed image g12: Second preprocessed image g21: First feature image g22: Second feature image g23: Third feature image

Claims

1. A processor selects a target sheet from a plurality of predetermined sheet candidates according to selection information inputted through an input device; The processor derives, from a target image obtained through an image reading process for an output sheet of an image forming apparatus, feature information regarding noise points, which are point-like noise images included in the target image; The processor executes a sheet noise determination process to determine whether the noise point is a point-like sheet noise contained in the sheet itself in the output sheet by applying the feature information to one of a plurality of determination algorithms corresponding to the target sheet among a plurality of determination algorithms corresponding to the plurality of sheet candidates.

2. The processor deriving the feature information includes: The image processing method according to claim 1, further comprising identifying as the feature information a degree of similarity or difference between detected color information corresponding to the color of the noise point in the target image and one or more predetermined reference color information corresponding to one or more developed colors in the image forming device.

3. the reference color information is a reference color vector corresponding to the developed color in a color space; the detected color information is a detected color vector representing a vector in the color space from one of the color of the noise point in the target image and the color of a reference area including a periphery of the noise point to the other; The image processing method according to claim 2 , wherein the processor identifies a degree of match or a degree of difference between the detected color vector and the reference color vector as the feature information.

4. The processor deriving the feature information includes: generating an extracted image in which the noise points in the target image are extracted; The image processing method according to claim 1 , further comprising: deriving a degree of flattening of the noise points in the extracted image as the feature information.

5. The processor deriving the feature information includes: generating an extracted image in which the noise points in the target image are extracted; The image processing method according to claim 1 , further comprising: deriving edge strength of the noise points in the extracted image as the feature information.

6. The processor deriving the feature information includes: generating an extracted image in which the noise points in the target image are extracted; The image processing method according to claim 1 , further comprising: deriving, as the feature information, a number of edges, which is the number of locations where a change in pixel value in a crossing pixel column, which is a pixel column that crosses the noise point in the extracted image, exceeds an allowable range.

7. The processor executing the sheet noise determination process includes: The image processing method according to claim 1 , further comprising: determining whether the noise point is the sheet noise by comparing a value of the feature information or an evaluation value corresponding to the feature information with a predetermined threshold value.

8. The processor executing the sheet noise determination process includes: and determining whether the noise point is the sheet noise by applying the value of the feature information or an evaluation value according to the feature information as an input parameter of a learning model that is trained in advance using a plurality of sample data corresponding to the sheet noise as teacher data. The image processing method according to claim 1 , further comprising:

9. The processor extracting the feature information comprises: generating an extracted image in which the noise points in the target image are extracted; deriving an image of a target region including the noise points in the extracted image as the feature information; The processor executing the sheet noise determination process includes: The image processing method according to claim 1, further comprising: performing a sheet noise pattern recognition process in which an image of the target area is used as an input image and a pattern recognition process is performed on the input image to determine whether or not the input image is an image corresponding to the sheet noise.

10. 10. The image processing method according to claim 9, wherein the sheet noise pattern recognition process is a process for determining whether or not the input image is an image corresponding to the sheet noise by a learning model that has been pre-trained using a plurality of sample images corresponding to the sheet noise as teacher data.

11. The processor generating the extracted image comprises: generating a first preprocessed image by executing a first preprocessing including a main filter process for converting pixel values ​​of pixels of interest selected sequentially from the target image into converted values ​​obtained by a process for emphasizing a difference between a pixel value of a region of interest including the pixel of interest and pixel values ​​of two adjacent regions adjacent to both sides of the region of interest in a processing direction that is preset for the region of interest, with the horizontal direction of the target image as the processing direction; generating a second preprocessed image by performing a second preprocessing including the main filtering process with the vertical direction of the target image as the processing direction; and generating, as the extracted image, an image in which singular parts consisting of one or more significant pixels in the first preprocessed image and the second preprocessed image, which are common to the first preprocessed image and the second preprocessed image, are extracted as the noise points.

12. The first pretreatment is generating first primary map data by performing the primary filtering process with the horizontal direction as the processing direction; generating lateral edge strength map data by performing edge enhancement filtering on the target image with the lateral direction as the processing direction and the target region and one of the two adjacent regions as targets; generating the first pre-processed image by correcting each pixel value of the first main map data with each pixel value of the corresponding horizontal edge strength map data; The second pretreatment is generating second primary map data by performing the primary filtering process with the vertical direction as the processing direction; generating vertical edge strength map data by performing the edge enhancement filter process on the target image with the vertical direction as the processing direction and targeting the region of interest and the two adjacent regions; 12. The image processing method of claim 11, further comprising: generating the second preprocessed image by correcting each pixel value of the second primary map data with each pixel value of the corresponding vertical edge strength map data.

13. An image processing device comprising a processor for executing the image processing method according to any one of claims 1 to 12.

Images