Image forming apparatus, image processing method, and program

Abstract

To provide an image forming apparatus, an image processing method, and a program that can perform set-off correction according to various conditions related to read data.SOLUTION: An image forming apparatus comprises: a reading unit that performs a reading operation for a document to obtain first read data; an acquisition unit that acquires a learning condition related to the first read data; a generation unit that generates learning data including the first read data and learning condition to be used for learning processing through machine learning; and a correction unit that performs set-off correction for second read data to be corrected that is read by the reading unit, by using a learning model generated through the learning processing using the learning data.SELECTED DRAWING: Figure 4

Description

[Technical Field]

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

[0002] 2. Description of the Related Art Image data obtained by reading an original document using a reading device such as a scanner may include an image of the surface of the original document opposite to the surface (front side) that has been read, a phenomenon known as show-through.

[0003] As a technique for correcting such show-through, a configuration has been disclosed in which, in order to improve the image quality of the read image, a learning process is performed based on first image data generated by reading an image from the first side of a learning chart medium, and a correction process is performed to correct second image data generated by reading an image from a document medium using the data obtained from the learning process (for example, Patent Document 1).

[0004] Furthermore, in order to prevent actual image abnormalities from being overlooked in areas where show-through occurs, a configuration has been disclosed in which areas on the recording medium where show-through is possible are identified based on the results of analysis by a read image analysis unit, and whether the abnormality on the recording medium is of a predetermined type is determined, and if the abnormality is of a predetermined type, a judgment criterion for identifying the abnormality in the show-through possible area is set as a judgment criterion different from the judgment criterion for identifying abnormalities other than the above-mentioned predetermined types, and abnormalities in the show-through possible area are identified based on the set judgment criterion (for example, Patent Document 2). Summary of the Invention [Problem to be solved by the invention]

[0005] However, the conventional technology has a problem in that it is not possible to perform show-through correction according to various conditions related to the read data.

[0006] The present invention has been made in view of the above, and has as its object to provide an image forming apparatus, an image processing method, and a program that can perform show-through correction according to various conditions related to read data. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, the present invention is characterized by comprising a reading unit that performs a reading operation on a document to obtain first read data, an acquisition unit that acquires learning conditions related to the first read data, a generation unit that generates learning data including the first read data and the learning conditions for use in a learning process by machine learning, and a correction unit that uses a learning model generated by the learning process using the learning data to perform show-through correction on second read data that is the target of correction and that is read by the reading unit. [Effects of the Invention]

[0008] According to the present invention, show-through correction can be performed according to various conditions related to the read data. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of the overall configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of the image forming apparatus according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a hardware configuration of a machine learning server according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of the functional block configuration of the image forming apparatus and the machine learning server according to the embodiment. [Figure 5] FIG. 5 is a flowchart showing an example of the flow of the learning process of the information processing system according to the embodiment. [Figure 6] FIG. 6 is a flowchart showing another example of the flow of the learning process of the information processing system according to the embodiment. [Figure 7]FIG. 7 is a flowchart showing an example of the flow of the show-through correction process of the image forming apparatus according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments of an image forming apparatus, an image processing method, and a program according to the present invention will be described in detail with reference to the drawings. Furthermore, the present invention is not limited to the following embodiments, and the components in the following embodiments include those that would be easily conceived by a person skilled in the art, those that are substantially the same, and those that are within the scope of what is called equivalents. Furthermore, various omissions, substitutions, modifications, and combinations of the components can be made without departing from the spirit of the following embodiments.

[0011] (Overall configuration of information processing system) 1 is a diagram showing an example of the overall configuration of an information processing system according to an embodiment, and the overall configuration of the information processing system 1 according to this embodiment will be described with reference to FIG.

[0012] 1 includes an image forming apparatus 10, a machine learning server 20, a data server 30, and a general-purpose computer 40. These apparatuses are capable of communicating data with each other via a network N, which may be a LAN (Local Area Network) or the Internet. Note that the network N may include a wired or wireless network.

[0013] The image forming apparatus 10 is an image forming apparatus such as a multifunction peripheral (MFP) or a fax machine capable of reading an original. The image forming apparatus 10 performs show-through correction on the read data using a learning model (described later) generated by a learning process performed by the machine learning server 20. Here, show-through correction is a correction process for reducing or eliminating show-through that occurs in the read data as described above.

[0014] The machine learning server 20 is a server device that performs a learning process by machine learning using learning data about the read data and generates a learning model (trained model). Here, the learning data used in the learning process by the machine learning server 20 may be learning data generated in the image forming apparatus 10, or may be learning data generated in the data server 30 from the read data obtained by the image forming apparatus 10.

[0015] The data server 30 is a server device that collects read data from external devices such as the image forming apparatus 10, generates learning data to be used in the learning process in the machine learning server 20, and transmits the learning data to the machine learning server 20.

[0016] The general-purpose computer 40 is an information processing device such as a PC (Personal Computer) that transmits print data to be printed out by the image forming apparatus 10 to the image forming apparatus 10.

[0017] Although the learning model is generated in the machine learning server 20, this is not limited to this, and the image forming apparatus 10 may have a learning processing function and generate the learning model.

[0018] (Hardware configuration of image forming device) 2 is a diagram showing an example of the hardware configuration of the image forming apparatus 10 according to the embodiment, and the hardware configuration of the image forming apparatus 10 according to the embodiment will be described with reference to FIG.

[0019] As shown in FIG. 2, the image forming apparatus 10 includes a controller 910, a short-range communication circuit 920, an engine control unit 930, an operation panel 940 (input unit), a network I / F 950, and a sensor 960.

[0020] The controller 910 includes a CPU (Central Processing Unit) 901, which is the main part of the computer, a MEM-P (system memory) 902, a NB (north bridge) 903, a SB (south bridge) 904, an ASIC (Application Specific Integrated Circuit) 906, a MEM-C (local memory) 907, an HDD (Hard Disk Drive) controller 908, and an HD 909. Of these, the NB 903 and the ASIC 906 are connected by an AGP (Accelerated Graphics Port) bus 921.

[0021] The CPU 901 is a computing device that performs overall control of the image forming apparatus 10. The NB 903 is a bridge that connects the CPU 901 with the MEM-P 902, the SB 904, and the AGP bus 921. The NB 903 also includes a memory controller that controls reading and writing to the MEM-P 902, a PCI (Peripheral Component Interconnect) master, and an AGP target.

[0022] The MEM-P 902 includes a ROM (Read Only Memory) 902a, which is memory for storing programs and data that realize the functions of the controller 910, and a RAM (Random Access Memory) 902b, which is used for expanding the programs and data and as a drawing memory during memory printing. The programs stored in the RAM 902b may be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM (Compact Disc Read Only Memory), a CD-R (Compact Disc Recordable), or a DVD (Digital Versatile Disc).

[0023] The SB 904 is a bridge for connecting the NB 903 with PCI devices, peripheral devices, etc. The ASIC 906 is an integrated circuit (IC) for image processing applications that has hardware elements for image processing and functions as a bridge connecting the AGP bus 921, PCI bus 922, HDD controller 908, and MEM-C 907. The ASIC 906 includes a PCI target and AGP master, an arbiter (ARB) that forms the core of the ASIC 906, a memory controller that controls the MEM-C 907, multiple direct memory access controllers (DMACs) that perform image data rotation using hardware logic, etc., and a PCI unit that transfers data between the scanner 931 and printer 932 via the PCI bus 922. A USB interface or an IEEE 1394 (Institute of Electrical and Electronics Engineers) interface may be connected to the ASIC 906.

[0024] The MEM-C 907 is a local memory used as a copy image buffer and a code buffer. The HD 909 is a storage for storing image data, font data used during printing, and forms. The HDD controller 908 is a controller that controls reading and writing of data from and to the HD 909 under the control of the CPU 901. The HDD controller 908 and the HD 909 may be SSDs (Solid State Drives).

[0025] The AGP bus 921 is a bus interface for a graphics accelerator card proposed to speed up graphics processing, and by directly accessing the MEM-P 902 at high throughput, the graphics accelerator card can be made faster.

[0026] The short-range communication circuit 920 is a communication circuit such as NFC (Near Field Communication) or Bluetooth (registered trademark). The short-range communication circuit 920 is electrically connected to the ASIC 906 via a PCI (Peripheral Component Interconnect) bus 922. An antenna 920a for wireless communication is connected to the short-range communication circuit 920.

[0027] The engine control unit 930 includes a scanner 931 and a printer 932. The scanner 931 is a device that performs a reading operation on an original document and obtains read data. The printer 932 is a device that prints on printing paper. The scanner 931 and the printer 932 include image processing functions such as error diffusion and gamma conversion.

[0028] The operation panel 940 includes a panel display section 940a such as a touch panel that displays the current setting values ​​or a selection screen, etc., and accepts input from the user, and an operation key section 940b that includes a numeric keypad that accepts setting values ​​for image formation conditions such as density setting conditions, and a start key that accepts a copy start instruction.

[0029] Image forming apparatus 10 can sequentially switch among document box function, copy function, printer function, and fax function using the application switching key on operation panel 940. When the document box function is selected, the device enters document box mode, when the copy function is selected, the device enters copy mode, when the printer function is selected, the device enters printer mode, and when the fax function is selected, the device enters fax mode.

[0030] The network I / F 950 is an interface for data communication via a network, and is an interface capable of communication conforming to, for example, Ethernet (registered trademark), TCP (Transmission Control Protocol) / IP (Internet Protocol), etc. The network I / F 950 is electrically connected to the ASIC 906 via the PCI bus 922.

[0031] The sensor 960 is a sensor for detecting the paper type and thickness of the document to be read by the scanner 931, temperature and humidity, or the presence or absence of condensation.

[0032] The hardware configuration of the image forming apparatus 10 shown in FIG. 2 is an example, and it is not necessary to include all of the components shown in FIG. 2, or other components may be included.

[0033] (Machine learning server hardware configuration) 3 is a diagram illustrating an example of the hardware configuration of the machine learning server according to the embodiment. The hardware configuration of the machine learning server 20 according to the embodiment will be described with reference to FIG.

[0034] As shown in Figure 3, the machine learning server 20 includes a CPU 701, a ROM 702, a RAM 703, an auxiliary storage device 705, a media drive 707, a display 708, a network I / F 709, a keyboard 711, a mouse 712, and a DVD drive 714.

[0035] The CPU 701 is a computing device that controls the overall operation of the machine learning server 20. The ROM 702 is a non-volatile storage device that stores programs for the machine learning server 20. The RAM 703 is a volatile storage device that is used as a work area for the CPU 701.

[0036] The auxiliary storage device 705 is a storage device such as an HDD or SSD that stores various data, programs, etc. The media drive 707 is a device that controls reading and writing of data from and to a recording medium 706 such as a flash memory under the control of the CPU 701.

[0037] The display 708 is a display device configured with a liquid crystal or organic EL (Electro-Luminescence) display, etc., that displays various information such as a cursor, a menu, a window, characters, or an image.

[0038] The network I / F 709 is an interface for communicating data with external devices such as the image forming apparatus 10, the data server 30, and the general-purpose computer 40 via the network N. The network I / F 709 is, for example, a NIC (Network Interface Card) that is compatible with Ethernet and capable of wired or wireless communication compliant with TCP / IP or the like.

[0039] The keyboard 711 is an input device for selecting letters, numbers, and various instructions, moving the cursor, etc. The mouse 712 is an input device for selecting and executing various instructions, selecting a processing target, moving the cursor, etc.

[0040] The DVD drive 714 is a device that controls reading and writing of data from and to a DVD 713 such as a DVD-ROM or a DVD-R (Digital Versatile Disk Recordable) as an example of a removable storage medium.

[0041] The above-mentioned CPU 701, ROM 702, RAM 703, auxiliary storage device 705, media drive 707, display 708, network I / F 709, keyboard 711, mouse 712 and DVD drive 714 are communicatively connected to each other via a bus 710 such as an address bus and a data bus.

[0042] Note that the hardware configuration of the machine learning server 20 shown in Figure 3 is an example, and does not need to include all of the components shown in Figure 3, or may include other components. Furthermore, the machine learning server 20 is not limited to being configured with a single information processing device as shown in Figure 3, but may be configured with multiple information processing devices. Furthermore, the hardware configurations of the data server 30 and the general-purpose computer 40 are also similar to the hardware configuration shown in Figure 3.

[0043] (Configuration and operation of the functional blocks of the image forming device and machine learning server) 4 is a diagram showing an example of the functional block configuration of the image forming apparatus 10 and the machine learning server 20 according to the embodiment. The configuration and operation of the functional block of the image forming apparatus 10 and the machine learning server 20 according to the embodiment will be described with reference to FIG.

[0044] As shown in FIG. 4, the image forming device 10 includes a reading unit 101, a scanner correction processing unit 102, a backlight correction unit 103 (correction unit), a gamma conversion unit 104, a filter processing unit 105, a color conversion unit 106, a magnification processing unit 107, an image area separation unit 108, a separation decoding unit 109, a condition acquisition unit 111 (acquisition unit), a learning management unit 112 (generation unit), and a memory unit 113.

[0045] The reading unit 101 is a functional unit that performs a reading operation on a document to be read and obtains read data (image data). The reading unit 101 is realized by the scanner 931 shown in FIG.

[0046] The scanner correction processing unit 102 is a functional unit that corrects the read data read by the reading unit 101 for reading irregularities such as shading that occur due to the mechanism of the scanner 931 .

[0047] The show-through correction unit 103 is a functional unit that references a learning model stored in the storage unit 113 and performs show-through correction using the learning model on the read data corrected by the scanner correction processing unit 102. Specifically, when performing show-through correction on the read data, the show-through correction unit 103 acquires the same learning conditions as those included in the learning data used to generate the learning model, and performs show-through correction using the learning model based on the read data and the conditions. This makes it possible to apply correction that matches the conditions at the time of show-through correction.

[0048] The learning model may, for example, take the read data and the conditions as input and output the data itself after the show-through correction has been performed on the read data, or may output various appropriate parameters or coefficients to be used for the show-through correction. When the learning model outputs various parameters or coefficients to be used for the show-through correction, the show-through correction unit 103 may use the parameters or coefficients to perform show-through correction on the read data. In this case, a known method may be used for the show-through correction.

[0049] Furthermore, conditions similar to the learning conditions included in the learning data used to generate the learning model may be acquired by the condition acquisition unit 111. A method for acquiring the conditions will be described later in the description of the condition acquisition unit 111.

[0050] The gamma conversion unit 104 is a functional unit that performs scanner characteristic correction (gamma correction) on the read data that has been subjected to the show-through correction by the show-through correction unit 103 so that the data changes to linear brightness.

[0051] The filter processing unit 105 is a functional unit that performs image processing to make the image clearer and smoother by correcting the MTF (Modulation Transfer Function) characteristics of the scanner 931 for the read data corrected by the gamma conversion unit 104 and by changing the frequency characteristics of the read data to prevent moire.

[0052] The color conversion unit 106 is a functional unit that converts the color of the read data that has been subjected to image processing by the filter processing unit 105 into a predetermined color space.

[0053] The magnification processing unit 107 is a functional unit that performs magnification processing to enlarge or reduce the scanned data that has been color converted by the color conversion unit 106 by changing the aspect ratio.

[0054] The image area separation unit 108 is a functional unit that extracts characteristic areas of the read data corrected by the scanner correction processing unit 102. For example, the image area separation unit 108 extracts halftone dots formed by general printing, extracts edge portions of characters and the like, determines whether the read data is chromatic or achromatic, and determines whether the background image is white.

[0055] The separation decoding unit 109 is a functional unit that decodes the image area separation signal from the image area separation unit 108 into an amount of information required for subsequent processing and outputs the decoded signal.

[0056] The condition acquisition unit 111 is a functional unit that acquires learning conditions to be included in the learning data in the learning management unit 112. Examples of learning conditions include the paper type and thickness, which have a particularly large effect on show-through, the type and color of toner and ink, the temperature and humidity inside the image forming device 10, the presence or absence of condensation inside the image forming device 10, data and processing conditions when the scanned data is processed (density adjustment, background removal, color adjustment, etc.), the edge amount calculated for the scanned data (particularly focusing on the low-frequency edge between the show-through area and the low-contrast area), and data obtained by binarizing the scanned data. Regarding the paper type of the document, for example, reflective paper such as coated paper tends to be less likely to show-through. Regarding the paper thickness of the document, thinner paper tends to be more susceptible to show-through.

[0057] The condition acquisition unit 111 may acquire, as the learning conditions, at least one of the paper type or thickness of the document, or the type or color of toner or ink. The condition acquisition unit 111 may also acquire, as the learning conditions, at least one of the temperature or humidity inside the image forming apparatus 10, the presence or absence of condensation, or data obtained by processing the read data. The condition acquisition unit 111 may also acquire, as the learning conditions, at least one of the edge amount calculated for the read data or the binarized data of the read data.

[0058] The condition acquisition unit 111 may acquire, for example, information on the paper type and thickness of the document, the type and color of toner and ink, or processing conditions for processing the scanned data, from setting information input in advance via the operation panel 940. The condition acquisition unit 111 may acquire, for example, information on the paper type and thickness of the document, the temperature and humidity inside the image forming apparatus 10, or the presence or absence of condensation inside the image forming apparatus 10, from information detected by the sensor 960. The condition acquisition unit 111 may acquire, for example, processed data, calculated edge amounts, or binarized data for the scanned data read by the scanning unit 101, from the learning conditions. The condition acquisition unit 111 may acquire the learning conditions in various states or after intentionally changing them, so that the learning management unit 112 can generate various learning data.

[0059] The learning management unit 112 is a functional unit that generates learning data by embedding the learning conditions acquired by the condition acquisition unit 111 into the read data read by the reading unit 101. That is, the learning data includes the read data and the learning conditions. In this case, the learning conditions can be considered as feature quantities for the learning data. The read data itself can also be considered as feature quantities. The learning management unit 112 also transmits the generated learning data to the machine learning server 20 via the network I / F 950 to perform learning processing by machine learning using the generated learning data. The learning management unit 112 also receives a learning model generated by the learning processing by the machine learning server 20 via the network I / F 950 and stores it in the storage unit 113.

[0060] In addition, when the learning process by the machine learning server 20 is, for example, supervised learning, the learning data may be assigned labels such as image data in which show-through correction has been properly performed on the read data.

[0061] The storage unit 113 is a functional unit that stores the learning model and the like generated by the learning process performed by the machine learning server 20. The storage unit 113 is realized by the HD 909 shown in FIG.

[0062] The scanner correction processing unit 102, the show-through correction unit 103, the gamma conversion unit 104, the filter processing unit 105, the color conversion unit 106, the scaling processing unit 107, the image area separation unit 108, the separation decoding unit 109, the condition acquisition unit 111, and the learning management unit 112 are realized by executing a program by the CPU 901 shown in Fig. 2. Note that at least some of the scanner correction processing unit 102, the show-through correction unit 103, the gamma conversion unit 104, the filter processing unit 105, the color conversion unit 106, the scaling processing unit 107, the image area separation unit 108, the separation decoding unit 109, the condition acquisition unit 111, and the learning management unit 112 may be realized by a hardware circuit such as an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit).

[0063] In the example shown in Figure 4, the show-through correction by the show-through correction unit 103 is performed before the gamma conversion unit 104, but this is not limited to this, and the show-through correction may be performed after gamma correction, etc. is performed by the gamma conversion unit 104, or the show-through correction may be performed before or after color conversion by the color conversion unit 106.

[0064] Furthermore, the functions of each functional unit of the image forming apparatus 10 shown in Fig. 4 are conceptually illustrated, and the configuration is not limited to this. In other words, each functional unit of the image forming apparatus 10 does not need to be configured as a clear software module as the block shown in Fig. 4, but the functions of each functional unit as a whole may be realized by executing a program in the image forming apparatus 10. For example, multiple functional units illustrated as independent functional units in the image forming apparatus 10 shown in Fig. 4 may be configured as a single functional unit. On the other hand, the function of one functional unit in the image forming apparatus 10 shown in Fig. 4 may be divided into multiple units and configured as multiple functional units.

[0065] As shown in FIG. 4, the machine learning server 20 includes a learning unit 201.

[0066] The learning unit 201 is a functional unit that generates a learning model through machine learning learning processing using learning data received from the learning management unit 112 via the network I / F 709. The learning model is, for example, a model that receives read data to which the above-mentioned conditions have been added as input and outputs data that has been subjected to show-through correction for the read data. The learning unit 201 also transmits the generated learning model to the image forming apparatus 10 via the network I / F 709.

[0067] As described above, the learning model may output various appropriate parameters or coefficients to be used for show-through correction. Furthermore, the learning unit 201 may perform learning processing using learning data generated by the data server 30 instead of or in addition to using learning data generated by the image forming apparatus 10.

[0068] (Learning process flow of information processing system) Fig. 5 is a flowchart showing an example of the flow of the learning process of the information processing system according to the embodiment. Fig. 6 is a flowchart showing another example of the flow of the learning process of the information processing system according to the embodiment. The flow of the learning process of the information processing system 1 according to the present embodiment will be described with reference to Figs. 5 and 6. First, the operation of acquiring learning conditions before a reading operation by the scanner 931 will be described with reference to Fig. 5.

[0069] <Step S11> The condition acquisition unit 111 of the image forming apparatus 10 acquires the learning conditions that have been changed to various contents to be included in the learning data in the learning management unit 112. For example, the condition acquisition unit 111 acquires, from the setting information input in advance via the operation panel 940, the learning conditions such as the paper type and thickness of the document, the type and color of toner and ink, or information on the processing conditions when processing the scanned data. Then, the process proceeds to step S12.

[0070] <Step S12> The reading unit 101 of the image forming apparatus 10 performs a reading operation (scanning) on ​​the document to be read, and obtains read data (first read data). Note that the read data may be read data corrected by the scanner correction processing unit 102. Then, the process proceeds to step S13.

[0071] <Step S13> The learning management unit 112 of the image forming apparatus 10 generates learning data by embedding the learning conditions acquired by the condition acquisition unit 111 into the read data read by the reading unit 101. The learning management unit 112 also transmits the generated learning data to the machine learning server 20 via the network I / F 950 to perform machine learning using the generated learning data. Then, the process proceeds to step S14.

[0072] <Step S14> The learning unit 201 of the machine learning server 20 generates a learning model through a learning process by machine learning using the learning data received from the learning management unit 112 via the network I / F 709. The learning unit 201 also transmits the generated learning model to the image forming apparatus 10 via the network I / F 709. The learning management unit 112 of the image forming apparatus 10 then receives the learning model generated by the learning process by the machine learning server 20 via the network I / F 950 and stores it in the memory unit 113.

[0073] Next, referring to Figure 6, we will explain the operation of generating learning data after performing a reading operation on a document using the reading unit 101, using various information detected by the sensor 960 (for example, the paper type and thickness of the document, the temperature and humidity inside the image forming device 10, or the presence or absence of condensation inside the image forming device 10, etc.) as learning conditions, or using processed data, calculated edge amount, or binarized data for the read data as learning conditions.

[0074] <Step S21> The reading unit 101 of the image forming apparatus 10 performs a reading operation (scanning) on ​​the document to be read, and obtains read data (first read data). Note that the read data may be read data corrected by the scanner correction processing unit 102. Then, the process proceeds to step S22.

[0075] <Step S22> The condition acquisition unit 111 of the image forming apparatus 10 acquires learning conditions to be included in the learning data in the learning management unit 112. For example, the condition acquisition unit 111 may acquire information detected by the sensor 960 after the reading operation by the reading unit 101 regarding the paper type and thickness of the document, the temperature and humidity inside the image forming apparatus 10, or the presence or absence of condensation inside the image forming apparatus 10, among the learning conditions. Furthermore, the condition acquisition unit 111 may acquire processed data, calculated edge amounts, or binarized data regarding the read data read by the reading unit 101, among the learning conditions. Then, the process proceeds to step S23.

[0076] <Step S23> The learning management unit 112 of the image forming apparatus 10 generates learning data by embedding the learning conditions acquired by the condition acquisition unit 111 into the read data read by the reading unit 101. The learning management unit 112 also transmits the generated learning data to the machine learning server 20 via the network I / F 950 to perform machine learning using the generated learning data. Then, the process proceeds to step S24.

[0077] <Step S24> The learning unit 201 of the machine learning server 20 generates a learning model through a learning process by machine learning using the learning data received from the learning management unit 112 via the network I / F 709. The learning unit 201 also transmits the generated learning model to the image forming apparatus 10 via the network I / F 709. The learning management unit 112 of the image forming apparatus 10 then receives the learning model generated by the learning process by the machine learning server 20 via the network I / F 950 and stores it in the memory unit 113.

[0078] In Figure 5, the learning conditions are acquired before the document reading operation, and in Figure 6, the learning conditions are acquired after the reading operation, but this is not limited to this, and the learning conditions may be acquired before or after the reading operation as necessary.

[0079] (Flow of show-through correction process in image forming device) 7 is a flowchart showing an example of the flow of the show-through correction process of the image forming apparatus 10 according to the embodiment. The flow of the show-through correction process of the image forming apparatus 10 according to the embodiment will be described with reference to FIG.

[0080] <Step S31> The user performs an operation to instruct a scan operation or copy operation on the document via the operation panel 940. Then, the reading unit 101 of the image forming apparatus 10 performs a reading operation (scan) on the document to be corrected and obtains read data (second read data). Then, the scanner correction processing unit 102 corrects reading irregularities, such as shading, that occur due to the mechanism of the scanner 931 for the read data read by the reading unit 101. Then, the process proceeds to step S32.

[0081] <Step S32> When performing show-through correction on the read data read by the reading unit 101, the show-through correction unit 103 of the image forming apparatus 10 acquires the same conditions as the learning conditions included in the learning data used to generate the learning model. Note that the acquisition of the same conditions as the learning conditions included in the learning data used to generate the learning model may be performed by the condition acquisition unit 111. The method of acquiring the conditions is the same as the operation of acquiring the learning conditions by the condition acquisition unit 111 described above. Then, the process proceeds to step S33.

[0082] <Step S33> The show-through correction unit 103 refers to the learning model stored in the storage unit 113. Then, the process proceeds to step S34.

[0083] <Step S34> The show-through correction unit 103 performs show-through correction using the learning model based on the data read by the reading unit 101 and the conditions. At this time, the correction is performed with a focus on image areas with low frequency edges, such as show-through areas and low contrast areas. Then, the process proceeds to step S35.

[0084] <Step S35> The read data that has been corrected for show-through by the show-through correction unit 103 is further processed by a gamma conversion unit 104, a filter processing unit 105, a color conversion unit 106, and a magnification processing unit 107. Then, if a copy operation is specified, the read data is sent to a printer 932, where an image is formed.

[0085] As described above, in the image forming apparatus 10 according to this embodiment, the reading unit 101 performs a reading operation on a document to obtain read data (first read data), the condition acquisition unit 111 acquires learning conditions related to the read data, the learning management unit 112 generates learning data including the read data and the learning conditions to be used in learning processing by machine learning, and the show-through correction unit 103 uses a learning model generated by learning processing using the learning data to perform show-through correction on the read data to be corrected (second read data) read by the reading unit 101. This makes it possible to perform show-through correction according to various conditions related to the read data.

[0086] In the above-described embodiment, when at least one of the functional units of the image forming apparatus 10 is realized by executing a program, the program is provided by being pre-installed in a ROM or the like. In the above-described embodiment, the program executed by the image forming apparatus 10 may be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM (Compact Disc Read Only Memory), a flexible disk (FD), a CD-R (Compact Disk-Recordable), or a DVD (Digital Versatile Disc). In the above-described embodiment, the program executed by the image forming apparatus 10 may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. In the above-described embodiment, the program executed by the image forming apparatus 10 may be provided or distributed via a network such as the Internet. In the above-described embodiment, the program executed by the image forming apparatus 10 has a modular configuration including at least one of the above-described functional units. In actual hardware, the CPU 901 reads and executes the program from the above-described storage device (e.g., the MEM-P 902 or the HD 909), thereby loading and generating the above-described functional units into a main storage device.

[0087] The aspects of the present invention are as follows. <1> a reading unit that performs a reading operation on the document to obtain first read data; an acquisition unit that acquires a learning condition related to the first read data; a generation unit that generates learning data including the first read data and the learning conditions for use in a learning process by machine learning; a correction unit that performs show-through correction on the second read data to be corrected, which is read by the reading unit, using a learning model generated by the learning process using the learning data; The image forming apparatus is provided with the above. <2> The acquisition unit acquires at least one of the paper type or paper thickness of the document, or the type or color of toner or ink, as the learning condition. <1> 2. The image forming apparatus according to claim 1, wherein: <3> The acquiring unit acquires, as the learning condition, at least one of the temperature or humidity inside the image forming apparatus, the presence or absence of condensation, or data obtained by processing the first read data. <1> or <2> 2. The image forming apparatus according to claim 1, wherein: <4> The acquisition unit acquires at least one of the learning conditions from setting information input in advance via an input unit. <1> ~ <3> The image forming apparatus according to any one of the above items. <5> The acquisition unit acquires at least one of the learning conditions from information detected by a sensor. <1> ~ <4> The image forming apparatus according to any one of the above items. <6> The acquiring unit acquires, as the learning condition, at least one of an edge amount calculated for the first read data and binarized data of the first read data. <1> ~ <5> The image forming apparatus according to any one of the above items. <7> the generating unit generates the learning data using the learning condition acquired by the acquiring unit as embedded data for the first read data. <1> ~ <6> The image forming apparatus according to any one of the above items. <8> When performing the show-through correction, the correction unit acquires the same conditions as the learning conditions of the learning data, and performs the show-through correction using the learning model based on the second read data and the conditions. <1> ~ <7> The image forming apparatus according to any one of the above items. <9> a reading step in which the reading device performs a reading operation on the document to obtain first read data; an acquisition step of acquiring a learning condition related to the first read data; a generating step of generating learning data including the first read data and the learning conditions for use in a learning process by machine learning; a correction step of performing show-through correction on second read data to be corrected, which is read by the reading device, using a learning model generated by the learning process using the learning data; The image processing method has the following features. <10> On the computer, an acquiring step of acquiring learning conditions related to first read data obtained by a reading operation of the reading device on the document; a generating step of generating learning data including the first read data and the learning conditions for use in a learning process by machine learning; a correction step of performing show-through correction on second read data to be corrected, which is read by the reading device, using a learning model generated by the learning process using the learning data; This is a program for executing the above. [Explanation of symbols]

[0088] 1. Information Processing Systems 10 Image forming device 20 Machine Learning Server 30 Data Server 40 General-purpose computers 101 Reading unit 102 Scanner correction processing unit 103 Bleed-through correction section 104 gamma conversion unit 105 Filter processing section 106 Color conversion unit 107 Magnification processing section 108 Image area separation section 109 Separate Decoder 111 Condition Acquisition Unit 112 Learning Management Department 113 Storage section 201 Learning Department 701 CPU 702 ROM 703 RAM 705 Auxiliary storage 706 Recording Media 707 Media Drive 708 Display 709 Network I / F 710 Bus 711 keyboard 712 Mouse 713 DVD 714 DVD drive 901 CPU 902 MEM-P 902a ROM 902b RAM 903 NB 904SB 906 ASIC 907 MEM-C 908 HDD Controller 909 HD 910 Controller 920 Near field communication circuit 920a antenna 921 AGP Bus 922 PCI bus 930 Engine control unit 931 Printer 932 Scanner 940 Operation Panel 940a Panel display 940b Operation key section 950 Network I / F 960 Sensors N Network [Prior art documents] [Patent documents]

[0089] [Patent Document 1] Japanese Patent Application Publication No. 2019-129485 [Patent Document 2] Patent Publication No. 2021-110813

Claims

1. a reading unit that performs a reading operation on a document to obtain first read data; an acquisition unit that acquires a learning condition related to the first read data; a generation unit that generates learning data including the first read data and the learning conditions for use in a learning process by machine learning; a correction unit that performs show-through correction on the second read data to be corrected, which is read by the reading unit, using a learning model generated by the learning process using the learning data; An image forming apparatus comprising:

2. 2. The image forming apparatus according to claim 1, wherein the acquisition unit acquires, as the learning conditions, at least one of the paper type or thickness of the document, or the type or color of toner or ink.

3. The image forming apparatus according to claim 1 or 2, wherein the acquisition unit acquires, as the learning conditions, at least one of the temperature or humidity inside the image forming apparatus, the presence or absence of condensation, or data obtained when the first read data is processed.

4. 3. The image forming apparatus according to claim 1, wherein the acquisition unit acquires at least one of the learning conditions from setting information input in advance via an input unit.

5. 3. The image forming apparatus according to claim 1, wherein the acquisition unit acquires at least one of the learning conditions from information detected by a sensor.

6. 3. The image forming apparatus according to claim 1, wherein the acquisition unit acquires, as the learning condition, at least one of an edge amount calculated for the first read data and binarized data of the first read data.

7. 3. The image forming apparatus according to claim 1, wherein the generating unit generates the learning data by embedding the learning condition acquired by the acquiring unit into the first read data.

8. The image forming apparatus according to claim 1 or 2, wherein the correction unit, when performing the show-through correction, acquires the same conditions as the learning conditions of the learning data, and performs the show-through correction using the learning model based on the second read data and the conditions.

9. a reading step in which the reading device performs a reading operation on the document to obtain first read data; an acquiring step of acquiring a learning condition related to the first read data; a generating step of generating learning data including the first read data and the learning conditions for use in a learning process by machine learning; a correction step of performing show-through correction on second read data to be corrected, which is read by the reading device, using a learning model generated by the learning process using the learning data; An image processing method comprising:

10. On the computer, an acquiring step of acquiring learning conditions related to first read data obtained by a reading operation of the reading device on the document; a generating step of generating learning data including the first read data and the learning conditions for use in a learning process by machine learning; a correction step of performing show-through correction on second read data to be corrected, which is read by the reading device, using a learning model generated by the learning process using the learning data; A program to execute.

Images