Image forming apparatus

Abstract

To provide a technique to prevent a reduction in the accuracy of calibration.SOLUTION: An image forming apparatus comprises: image forming means that performs image formation on a sheet; prediction means that uses values of a plurality of parameters to predict the density of an image formed by the image forming means according to a prediction model; and control means that, based on the density of the image predicted by the prediction means, controls execution of prediction calibration of generating first density control information for controlling the density of the image. The control means determines, at a determination timing, whether to execute the prediction calibration based on whether each of determination values of one or more parameters to be determined in the plurality of parameters is within an allowable range set to each of the one or more parameters to be determined.SELECTED DRAWING: Figure 8

Description

[Technical field]

[0001] The present invention relates to a calibration technique in an image forming apparatus. [Background technology]

[0002] The density of an image (output image) formed by an image forming apparatus changes due to environmental changes and changes over time. In order to suppress density changes in the output image, the image forming apparatus performs calibration. Patent Document 1 discloses a configuration in which the image forming apparatus performs calibration by reading a gradation pattern formed on a sheet (recording material). Patent Document 2 discloses a configuration in which the image forming apparatus performs calibration by predicting the density of an output image based on the values ​​of various parameters.

[0003] In the configuration of Patent Document 2, since it is not necessary to form a gradation pattern for calibration, downtime due to calibration does not occur. Hereinafter, calibration that predicts density without forming a gradation pattern as disclosed in Patent Document 2 will be referred to as "predictive calibration." [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2000-238341 A [Patent Document 2] JP 2019-074574 A Summary of the Invention [Problem to be solved by the invention]

[0005] In predictive calibration, a predictive model is generated based on the relationship between various values ​​of multiple parameters and the density of an output image, and the values ​​of the multiple parameters are input to the predictive model to predict the density of the output image. Here, if the parameter values ​​input to the predictive model are significantly different from the multiple parameter values ​​used to generate the predictive model, the prediction accuracy may decrease. This decrease in prediction accuracy also decreases the accuracy of the calibration.

[0006] The present invention provides a technique for suppressing a decrease in calibration accuracy. [Means for solving the problem]

[0007] According to one aspect of the present invention, an image forming apparatus includes an image forming means for forming an image on a sheet, a prediction means for predicting the density of an image formed by the image forming means in accordance with a prediction model using values ​​of a plurality of parameters, and a control means for controlling the execution of predictive calibration for generating first density control information for controlling the density of the image based on the density of the image predicted by the prediction means, and the control means determines whether to execute the predictive calibration based on whether a judgment value of one or more judgment target parameters among the plurality of parameters at a judgment timing is within an acceptable range set for each of the one or more judgment target parameters. Effect of the Invention

[0008] According to the present invention, it is possible to suppress a decrease in the accuracy of calibration. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a configuration diagram of an image forming system according to an embodiment. [Diagram 2] FIG. 1 is a hardware configuration diagram of an image forming apparatus according to an embodiment. [Diagram 3] FIG. 1 is a hardware configuration diagram of a machine learning server according to one embodiment. [Figure 4] 1 is a cross-sectional view of an image forming apparatus according to one embodiment. [Diagram 5] 1 is a functional block diagram of an imaging system according to one embodiment. [Figure 6] 4 is a flow chart of a main calibration according to one embodiment. [Figure 7] 4 is an illustration of a method for generating base and revision tables according to one embodiment. [Figure 8] 4 is a flowchart of a printing process according to one embodiment. [Figure 9] 4 is a flow chart of halftone calibration according to one embodiment. [Figure 10] 1 is a flowchart of predictive calibration, according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the embodiments will be described in detail with reference to the attached drawings. Note that the following embodiments do not limit the invention according to the claims. Although the embodiments describe a number of features, not all of these features are essential to the invention, and the features may be combined in any manner. Furthermore, in the attached drawings, the same reference numbers are used for the same or similar configurations, and duplicated descriptions are omitted.

[0011] 1 shows an image forming system used to explain the embodiment. An image forming apparatus 100, a machine learning server 102, a general-purpose computer 103, and a data server 105 are configured to be able to communicate with each other via a network 104. The image forming apparatus 100 is, for example, a printer, a multifunction machine, a FAX machine, etc. The general-purpose computer 103 transmits a print job to the image forming apparatus 100 to cause the image forming apparatus 100 to form an image.

[0012] The data server 105 collects learning data used for machine learning in the machine learning server 102 from the image forming apparatus 100 and stores it. The machine learning server 102 performs machine learning based on the learning data stored in the data server 105 to generate a learning model (prediction model). A learning model can be generated for each color used by the image forming apparatus 100 for image formation, for example. Note that instead of separating the machine learning server 102 and the data server 105, a configuration can be adopted in which a function for collecting learning data and a function for generating a learning model by machine learning are provided in the same computer. The image forming apparatus 100 performs predictive calibration using the learning model generated by the machine learning server 102.

[0013] The data server 105 and the machine learning server 102 may be installed in the same place as the image forming apparatus 100 or in different places. Furthermore, the learning data collected by the data server 105 is not limited to only that collected from the image forming apparatus 100 that uses a learning model based on the learning data. For example, learning data collected from a different individual of the same type as the image forming apparatus 100 can also be used to generate a learning model used by the image forming apparatus 100.

[0014] 2 is a hardware configuration diagram of the image forming apparatus 100. The operation unit 140 provides an input / output interface for a user of the image forming apparatus 100. The reader 250 reads an original and outputs image data in accordance with a user operation via the operation unit 140. The printer 260 forms an image on a sheet. The image data of the image formed on the sheet by the printer 260 is image data from the reader 250 or image data received from the general-purpose computer 103. The controller 1200 controls the entire image forming apparatus 100.

[0015] The configuration of the controller 1200 will be described below. First, the devices connected to the system bus 1207 will be described. The network interface (IF) 1210 is an interface with the network 104. The operation unit IF 1206 is an interface with the operation unit 140. The CPU 1201 controls the image forming apparatus 100 in an integrated manner. The RAM 1202 functions as a work memory for the CPU 1201. The ROM 1203 stores a boot program executed by the CPU 1201. The hard disk drive (HDD) 1204 stores system software and the like. The HDD 1204 can also be used to store image data. The reader-printer communication IF 1208 is an interface between the devices connected to the system bus 1207 and the reader 250 and printer 260. The GPU 1291 performs, for example, a prediction process using a learning model. The bus IF 1205 connects the system bus 1207 and the image bus 2008.

[0016] Next, the devices connected to the image bus 2008 will be described. A raster image processor (RIP) 1260 expands the PDL code included in the print job received from the general-purpose computer 103 into a bitmap image. A reader image processing unit 1280 performs various image processing on the image data from the reader 250. A printer image processing unit 1290 performs various image processing such as resolution conversion to generate image data to be output to the printer 260. An image rotation unit 1230 performs image rotation processing. An image compression unit 1240 performs compression and decompression processing such as JPEG. A device IF 1220 is an interface between the devices connected to the image bus 2008 and the reader 250 and printer 260.

[0017] FIG. 3 is a hardware configuration diagram of the machine learning server 102. The CPU 1301 controls the entire machine learning server 102. The RAM 1302 functions as a system work memory for the CPU 1301. The ROM 1303 stores a BIOS (Basic Input Output System) and a program for starting the OS, setting files, etc. The HDD 1304 stores system software, etc. The network IF 1310 is an interface with the network 104. The IO 1305 provides an input / output interface. The GPU 1306 performs machine learning based on the learning data to generate a learning model. Although not shown, the hardware configuration of the data server 105 is the same as that of the machine learning server 102.

[0018] FIG. 4 is a schematic cross-sectional view of the printer 260 and the reader 250 of the image forming apparatus 100. First, the printer 260 will be described. In FIG. 4, the letters a, b, c, and d are added to the end of the reference symbols of the components whose images are formed in yellow, cyan, magenta, and black. In the following description, when it is not necessary to distinguish the colors of the images to be formed, the reference symbols with the letters omitted will be used. The photoconductor 201 is rotated counterclockwise in the figure during image formation. The charger 202 charges the surface of the photoconductor 201 by outputting a charging voltage. The scanner 200 exposes the charged photoconductor 201 based on image data to form an electrostatic latent image on the photoconductor 201. The developer 203 has a developing roller 225 and toner, and develops the electrostatic latent image with toner by outputting a developing voltage to form an image (toner image) on the photoconductor 201 by the toner. The transfer blade 204 outputs a primary transfer voltage to transfer the toner image on the photoconductor 201 to the intermediate transfer body 205. Note that by transferring the images of the photoconductors 201 to the intermediate transfer body 205 in an overlapping manner, it is possible to reproduce colors other than yellow, cyan, magenta, and black.

[0019] During image formation, the intermediate transfer body 205 is rotated clockwise in the drawing. Therefore, the image transferred to the intermediate transfer body 205 is transported to a position facing the secondary transfer roller 222. The secondary transfer roller 222 outputs a secondary transfer voltage to transfer the image on the intermediate transfer body 205 to the sheet S transported from the cassette 209 or the manual feed tray 210 along the transport path. The fixing device 40 pressurizes and heats the sheet to which the image has been transferred, thereby fixing the image to the sheet S. During double-sided printing, the sheet S that has passed through the fixing device 40 is transported again to a position facing the secondary transfer roller 222 via the double-sided reversing path 212 and the double-sided path 213. Finally, the sheet S on which the image has been formed is discharged to the outside of the image forming apparatus 100 by the discharge roller 208. The in-line sensor 215 detects the density of the image formed on the sheet S upstream of the discharge roller 208. The density sensor 716 detects the density of the image transferred to the intermediate transfer body 205. The density sensor 716 is, for example, an optical sensor having a light emitting element and a light receiving element, and measures reflected light from the intermediate transfer body 205 or a toner image transferred thereon. The environment sensor 71 detects environmental information such as temperature, humidity, etc.

[0020] Next, the reader 250 will be described. The light source 23 irradiates light onto the original 21 placed on the original platen glass 22. The optical system 24 forms an image of the light reflected from the original 21 on the CCD sensor 25. The CCD sensor 25 generates image data of the original 21 based on the light reflected from the original 21, and outputs it to the reader image processing unit 1280 of the controller 1200.

[0021] Fig. 5 is a functional block diagram of the image forming system shown in Fig. 1. The functional blocks shown in Fig. 5 can be realized by causing a processor such as a CPU in each device to execute an appropriate program.

[0022] The collection unit 410 of the data server 105 collects learning data from the image forming apparatus 100 and stores it in the storage unit 412. The preprocessing unit 413 of the machine learning server 102 performs preprocessing on the learning data stored in the storage unit 412 of the data server 105. The preprocessing may include, for example, a process of removing unnecessary data that becomes noise from the learning data. The machine learning unit 414 performs machine learning based on the learning data preprocessed by the preprocessing unit 413 to generate a learning model. The learning model of this embodiment predicts the density of an image formed by the image forming apparatus 100 based on the values ​​of various input parameters, and is also called a prediction model or prediction information. In this embodiment, the GPU 1306 performs machine learning. However, the CPU 1301 may be configured to perform machine learning alone, or the CPU 1301 and the GPU 1306 may be configured to perform machine learning in cooperation with each other. The machine learning unit 414 stores the generated learning model in the storage unit 415.

[0023] The learning model generated by the machine learning unit 414 may be a neural network. The neural network outputs the density of the output image and the amount of density change relative to the reference density based on various input parameters. As an example that does not limit the invention, the input parameters may include temperature, humidity, temperature of the fixing unit 40, the amount of toner replenishment, the amount of toner consumption, the total rotation distance of the developing roller 225 of the developing unit 203, the total rotation distance of the photoconductor 201, and the standing time that is the elapsed time since the previous image formation was completed. The total rotation distance of the developing roller 225 is the product of the total number of rotations of the developing roller 225 and the circumference. The same applies to the total rotation distance of the photoconductor 201. Note that the present invention is not limited to prediction using a neural network. For example, the density may be predicted using a nearest neighbor method, a naive Bayes method, a decision tree, a support vector machine, or the like.

[0024] Next, functional blocks of the image forming apparatus 100 will be described. A control unit 403 controls the entire image forming apparatus 100. An image reading unit 404 controls the reading of an original by the reader 250 and the reading operation of a sheet S by the inline sensor 215. A prediction processing unit 405 performs prediction processing based on a learning model. In this embodiment, the prediction processing is performed by the GPU 1291. However, a configuration in which the CPU 1201 performs the prediction processing alone, and the CPU 1201 and the GPU 1291 perform the prediction processing in cooperation with each other, may also be used.

[0025] The density detection unit 408 controls the density sensor 716 to measure the density of the image formed on the intermediate transfer body 205. The environment detection unit 409 acquires environment information including information indicating temperature and information indicating humidity from the environment sensor 71. The counter unit 406 counts the number of sheets S on which an image is formed when an image is formed based on a print job. The memory unit 401 stores a basic table 725, a correction table 726, setting value information 727, and a conversion table 728. The contents of the information / tables stored in the memory unit 401 will be described later.

[0026] <Calibration> The control unit 403 performs calibration (density correction control) so that the density of an output image formed by the image forming apparatus becomes a target density according to image data. Calibration is performed for each color. In this embodiment, the control unit 403 performs three types of calibration. The first calibration is performed by forming a gradation pattern on the sheet S, and is hereinafter referred to as a main calibration. A basic table 725 (FIG. 5) for each color is generated by the main calibration and stored in the storage unit 401. The second calibration is performed by forming a gradation pattern on the intermediate transfer body 205 and detecting the density of the gradation pattern with a density sensor 716, and is hereinafter referred to as a halftone calibration. The third calibration is performed based on a predicted value of density by the prediction processing unit 405, and is hereinafter referred to as a predictive calibration. A correction table 726 for each color is generated by the halftone calibration and predictive calibration.

[0027] In terms of calibration accuracy, main calibration performed by forming a gradation pattern on sheet S is the most accurate, followed by mid-tone calibration performed by forming a gradation pattern on intermediate transfer body 205, which is not a sheet S. On the other hand, in terms of downtime, main calibration performed by forming a gradation pattern on sheet S is the longest, followed by mid-tone calibration performed by forming a gradation pattern on intermediate transfer body 205. On the other hand, no downtime occurs with predictive calibration.

[0028] <Main calibration> FIG. 6 is a flowchart of the main calibration. The main calibration may be started in response to a command to execute the main calibration by the user via the operation unit 140 or the general-purpose computer 103. In S10, the control unit 403 acquires environmental information from the environment detection unit 409, determines the values ​​of the charging voltage and the developing voltage, which are image formation conditions related to the maximum density, based on the environmental information, and stores the determined values ​​in the storage unit 401 as the set value information 727. For example, the conversion table 728 (FIG. 5) indicates the relationship between the value indicated by the environmental information and the values ​​of the charging voltage and the developing voltage, and the control unit 403 determines the values ​​of the charging voltage and the developing voltage by referring to the conversion table 728 based on the value of the environmental information acquired from the environment detection unit 409. The control unit 403 controls the charging voltage and the developing voltage to be the determined values.

[0029] In S11, the control unit 403 determines the exposure intensity of the photoconductor 201 by the scanner 200. The exposure intensity is an image formation condition related to the maximum density. Specifically, the control unit 403 sets the charging voltage and the developing voltage to the values ​​determined in S10, and forms a plurality of images on the sheet S using a plurality of exposure intensities. Next, the control unit 403 causes the reader 250 to read the sheet S on which the plurality of images are formed through a user operation, and determines the density of each of the plurality of images. Then, the control unit 403 determines the exposure intensity for making the maximum density a target value based on the density of each of the plurality of images, and stores it in the storage unit 401 as the setting value information 727. Note that the configuration may be such that the density of the image formed on the sheet S is determined using the inline sensor 215 instead of the reader 250.

[0030] In S12, the control unit 403 forms a first gradation pattern of each color on the sheet S. The first gradation pattern includes images of multiple densities formed with multiple different gradation values. As an example, the first gradation pattern includes images of 64 different densities formed with 64 different gradation values. In S13, the control unit 403 determines the density of each of the multiple images of the first gradation pattern by having the reader 250 read the first gradation pattern formed on the sheet S via a user operation. In S14, the control unit 403 generates a basic table 725 based on the determined density for each of the multiple images of the first gradation pattern and the target density for each of the multiple images, and stores the basic table 725 in the storage unit 401. The basic table 725 is a table for converting gradation values ​​indicated by image data.

[0031] FIG. 7A is an explanatory diagram of a method for creating a basic table 725 for one color. The horizontal axis of FIG. 7A indicates the ratio of the gradation value to the maximum value. The black circles in FIG. 7A indicate the densities determined in S13 for the gradation values ​​used to form each image of the first gradation pattern. Hereinafter, the densities of the black circles shown in FIG. 7A are referred to as the reference densities at the gradation values. Reference numeral 1803 in FIG. 7A indicates the reference density characteristics of the image forming apparatus 100 obtained from the gradation values ​​used to form the first gradation pattern and the densities determined in S13. Reference numeral 1801 indicates the target characteristics indicating the relationship between the gradation values ​​and the target densities. The basic table 725 is created by inverting (reverse-converting) the reference density characteristics 1803 with respect to the target characteristics 1801. The basic table 725 is density control information for bringing the density of the output image closer to the target density. In other words, the tone values ​​indicated by the image data are converted using the basic table 725, and an image is formed using the converted tone values, thereby making it possible to bring the density of the output image closer to the target density. The density control information is one of the image formation conditions relating to density.

[0032] After generating the basic table 725, the control unit 403 determines in S15 whether the value of the environmental information detected by the environment detection unit 409 is within the allowable range. The allowable range may be set separately for the temperature and the humidity. That is, in S15, the control unit 403 determines that the value of the environmental information is within the allowable range when both the temperature and the humidity detected by the environment detection unit 409 are within the allowable range set for each. In addition, in S15, the control unit 403 may be configured to determine whether only the temperature is within the allowable range, or to determine whether only the humidity is within the allowable range. The allowable range may be determined based on the range of the value of the environmental information used in generating the learning model used by the prediction processing unit 405. For example, the range from the minimum value to the maximum value of the temperature used in generating the learning model used by the prediction processing unit 405 can be set as the allowable range for the temperature. Alternatively, for example, the range from the minimum value of the temperature used in generating the learning model used by the prediction processing unit 405 plus a first predetermined value to the maximum value plus a second predetermined value can be set as the allowable range for the temperature. The first and second predetermined values ​​may be positive or negative, and the positive and negative of the first and second predetermined values ​​may be the same or different. The same applies to the allowable range for humidity. The allowable range may be determined by the machine learning server 102 and acquired from the machine learning server 102 together with the learning model. Alternatively, the control unit 403 may acquire the range of values ​​of the environmental information used in generating the learning model from the machine learning server 102 together with the learning model, and determine the allowable range based on the range of values. If the value of the environmental information is within the allowable range, the control unit 403 sets the permission flag to 1 in S16, and otherwise sets the permission flag to 0 in S17.

[0033] In S15, the value (judgment value) of the environmental information (temperature, humidity) for judging whether it is within the allowable range may be, for example, a value detected by the environment detection unit 409 at the timing of executing the process of S15. Alternatively, the judgment value in S15 may be, for example, a plurality of values ​​detected by the environment detection unit 409 while performing the main calibration, or a value based on the plurality of values. Alternatively, the judgment value in S15 may be a plurality of values ​​detected by the environment detection unit 409 within a predetermined period in the past from the timing of executing the process of S15 or the timing of starting the main calibration, or a value based on the plurality of values. In addition, when a plurality of values ​​are used as the judgment value, if all of the plurality of values ​​are within the allowable range, the permission flag is set to 1, and if not, the permission flag is set to 0. Furthermore, the value based on a plurality of values ​​is a statistical value based on the plurality of values, such as an average value of the plurality of values.

[0034] When the control unit 403 performs the process of FIG. 6 to create the basic table 725, it forms an image using the basic table 725 until it performs the halftone calibration and predictive calibration described below. That is, it converts the gradation value indicated by the image data using the basic table 725, and forms an output image based on the converted gradation value. This allows the density of the output image to approach the gradation value indicated by the image data. However, if the reference density characteristic 1803 changes due to environmental changes or changes over time, the difference between the density of the output image and the target density may become large. In order to suppress the change in density of the output image, if the main calibration is performed more frequently, the downtime will be longer. For this reason, in this embodiment, it performs halftone calibration and predictive calibration to generate the correction table 726. When the correction table 726 is generated, the control unit 403 also uses the correction table 726 to convert the gradation value indicated by the image data during image formation.

[0035] <Midtone Calibration / Predictive Calibration> The halftone calibration and the predictive calibration are each started when a predetermined execution condition is satisfied. In this embodiment, the execution conditions of the two calibrations are set so that the execution frequency of the predictive calibration, which does not actually need to form a gradation pattern, is greater than the execution frequency of the halftone calibration. For example, the execution condition may be a condition based on the number of sheets S on which images are formed in a print job. In this case, the number of sheets for which it is determined that the predictive calibration should be executed may be less than the number of sheets for which it is determined that the halftone calibration should be executed. Furthermore, the execution condition of the predictive calibration or the halftone calibration may be a condition based on a change in environmental information or a condition based on a change in the state of the image forming apparatus 100, such as when the image forming apparatus 100 is turned on or when the image forming apparatus 100 returns from a sleep mode.

[0036] FIG. 8 is a flowchart of a process related to calibration performed by the control unit 403 during image formation based on a print job. In S20, the control unit 403 initializes the value N of the number of sheets to be formed to 1, and in S21 performs image formation on the Nth sheet S. In S22, the control unit 403 determines whether a first condition, which is a condition for performing predictive calibration, is satisfied. The first condition may be a condition based on the value of N. If the first condition is satisfied, the control unit 403 determines whether the permission flag is 1 in S24. If the permission flag is not 1, the control unit 403 advances the process to S26. On the other hand, if the permission flag is 1, the control unit 403 performs predictive calibration, which will be described later, in S28. After performing predictive calibration, the control unit 403 advances the process to S26. In this way, in this embodiment, if the permission flag is not 1, the execution of predictive calibration is prohibited even if the first condition is satisfied. In other words, if the value of the environmental information detected by the image forming apparatus 100 is outside the allowable range based on the value of the environmental information used to generate the learning model, execution of predictive calibration is prohibited.

[0037] On the other hand, if the first condition is not satisfied in S22, the control unit 403 determines whether a second condition, which is a condition for performing the halftone calibration, is satisfied in S23. The second condition may be a condition based on the value of N. If the second condition is satisfied, the control unit 403 executes the halftone calibration described below in S25. After executing the halftone calibration, the control unit 403 advances the process to S26. If the second condition is not satisfied in S23, the control unit 403 advances the process to S26. In S26, the control unit 403 determines whether printing is completed, that is, whether all image formation in the print job has been performed. If printing is completed, the control unit 403 ends the process of FIG. 8. On the other hand, if printing is not completed, the control unit 403 increments N by 1 in S27 and repeats the process from S21.

[0038] <Midtone Calibration> FIG. 9 is a flowchart of the intermediate tone calibration executed in S25 of FIG. 8. In S30, the control unit 403 forms the second tone pattern of each color on the intermediate transfer body 205. The second tone pattern includes a plurality of images of different densities formed with a plurality of different tone values. As an example, the second tone pattern includes 10 images of different densities. In S31, the control unit 403 acquires the density of each image of the second tone pattern detected by the density sensor 716 from the density detection unit 408. In S32, the control unit 403 generates a correction table 726 based on the density of each image of the second tone pattern detected by the density sensor 716 and the tone value used to form each image of the second tone pattern, and stores the correction table 726 in the storage unit 401.

[0039] FIG. 7B is an explanatory diagram of a method for generating the correction table 726. The white circles in FIG. 7B indicate the gradation values ​​used to form the image of the second gradation table and the densities determined in S31 for the images formed with the gradation values. Reference numeral 1804 in FIG. 7B indicates the current density characteristics of the image forming apparatus 100 obtained from the gradation values ​​used to form the second gradation table and the densities determined in S31. The correction table 726 is information for bringing the current density characteristics 1804 closer to the reference density characteristics 1803 acquired in the main calibration. Specifically, the control unit 403 creates the correction table 726 by inversely converting the current density characteristics 1804 with respect to the reference density characteristics 1803.

[0040] The correction table 726 is information for converting input gradation values, and is also density control information for bringing the density of an output image closer to a target density. The control unit 403 converts the gradation values ​​indicated by the image data using the correction table 726, and further converts the gradation values ​​converted by the correction table 726 using the basic table 725, and performs image formation using the gradation values ​​converted by the basic table 725. Alternatively, the control unit 403 creates a composite table by combining the correction table 726 and the basic table 725, stores the composite table in the storage unit 401, converts the gradation values ​​indicated by the image data using the composite table, and performs image formation using the gradation values ​​converted by the composite table.

[0041] The correction table 726 generated in the mid-tone calibration or a synthesis table based on the correction table 726 is used until the next mid-tone calibration or predictive calibration is performed to update the correction table 726. Note that when the main calibration is performed, for example, the correction table 726 may be deleted.

[0042] <Predictive Calibration> FIG. 10 is a flowchart of the predictive calibration executed in S28 of FIG. 8. In S40, the control unit 403 obtains the predicted result of the density of the image formed at each gradation value from the prediction processing unit 405. In this embodiment, the prediction processing unit 405 predicts the density of the image formed on the intermediate transfer body 205. In S41, the control unit 403 creates a correction table 726 based on the density predicted by the prediction processing unit 405 in S40. The method of creating the correction table 726 based on the predicted density is the same as the method of creating the correction table 726 in the mid-tone calibration, except for whether the density is predicted or actually measured. That is, the only difference from the mid-tone calibration is that the current density characteristic 1804 in FIG. 7B is determined based on the prediction result by the prediction processing unit 405, rather than based on the detection result of the second gradation pattern.

[0043] The correction table 726 generated by the predictive calibration or a synthesis table based on the correction table 726 is used until the next time a mid-tone calibration or predictive calibration is performed to update the correction table 726. Note that when the main calibration is performed, for example, the correction table 726 may be deleted.

[0044] In addition, in the predictive calibration, the density at each future timing may be predicted, and the correction table 726 at each timing may be created. For example, the prediction processing unit 405 assumes that the timing for performing the prediction process is t=0, and predicts the relationship between the gradation value and the density of the output image at each timing of t=0, t1, t2, . In this case, the control unit 403 may generate the correction table 726 at each timing of t=0, t1, t2, . The correction table 726 at t=0 is used from t=0 to t1. The correction table 726 at t=t1 is used from t=t1 to t2. When the next mid-tone calibration or predictive calibration is performed, the correction table 726 generated in the previous predictive calibration and the composite table based on these correction tables 726 are deleted.

[0045] In this embodiment, it is determined whether or not to perform predictive calibration based on the value of the environmental information. However, the present invention is not limited to a configuration in which it is determined whether or not to perform predictive calibration based on the value of the environmental information. Specifically, one or more parameters among a plurality of parameters used as input to the learning model are set as a determination target parameter. Then, an allowable range is set for each of the one or more determination target parameters. The allowable range set for the determination target parameter is set based on the range of the value of the determination target parameter used in generating the learning model. For example, the allowable range set for the determination target parameter may be the same as the range of the value of the determination target parameter used in generating the learning model. Then, it may be configured to determine that predictive calibration is to be performed when all of the one or more determination target parameters are within the allowable range set for each, and determine that predictive calibration is not to be performed when they are not.

[0046] Furthermore, in this embodiment, the permission flag is set during the execution of the main calibration. That is, in the main calibration, the possibility of executing the predictive calibration is determined. However, the present invention is not limited to the configuration in which the possibility of executing the predictive calibration is determined in the main calibration. The determination timing for determining the possibility of executing the predictive calibration can be, for example, the timing when the first condition is satisfied or the timing when a print job is received. By shortening the time difference between the determination timing and the timing when the execution condition of the predictive calibration can be satisfied, it is possible to prevent the execution of the predictive calibration from being unnecessarily hindered. In addition, the determination timing can be the timing when the image forming apparatus 100 is powered on, the timing when the image forming apparatus 100 returns from a sleep state, or the timing when at least one value of the determination target parameters has changed by more than a threshold value set for the determination target parameter. By setting the timing when the value of the determination target parameter may have changed significantly as the determination timing, it is possible to prevent a correction table 726 with low accuracy from being generated based on low prediction accuracy. The control unit 403 may be configured to determine whether or not to perform predictive calibration based on a judgment value that is the value of the parameter to be judged at the judgment timing, multiple values ​​of the parameter to be judged within a predetermined period of time from the judgment timing, or a value based on the multiple values, depending on whether or not the judgment value is within an acceptable range.

[0047] As described above, when at least one of the one or more determination target parameters used for density prediction is outside the allowable range determined based on the value used to generate the learning model, execution of predictive calibration is prohibited. This configuration can prevent a low-accuracy correction table 726 from being generated based on low prediction accuracy. Therefore, the use of a low-accuracy correction table 726 can prevent the density of the output image from deviating from the target density. In other words, it is possible to prevent the accuracy of the calibration from decreasing.

[0048] Furthermore, in this embodiment, whether or not predictive calibration can be performed is determined for all colors at once, but it may be determined for each color individually. For example, if the permission flag for yellow is 1 and the permission flags for the other colors are 0, when the first condition is satisfied, the predictive calibration for yellow alone may be performed in S28 of FIG.

[0049] In the embodiment, the reference density characteristic 1803 indicates the relationship between the gradation value and the density of each image of the first gradation pattern formed on the sheet. However, since the density on the intermediate transfer body 205 is measured in the intermediate gradation calibration and the density on the intermediate transfer body 205 is predicted in the predictive calibration, the reference density characteristic 1803 can also indicate the relationship between the gradation value and the density of each image of the first gradation pattern formed on the intermediate transfer body 205. In this case, in the main calibration, the control unit 403 also acquires the density of each image of the first gradation pattern formed on the intermediate transfer body 205 from the density detection unit 408. Furthermore, in the embodiment, the predictive calibration predicts the density of the image on the intermediate transfer body 205, but the configuration may predict the density of the image formed on the sheet. Furthermore, although the embodiment has been described using an electrophotographic image forming apparatus as an example, the present invention is also applicable to image forming apparatuses of an inkjet type, a dye-sublimation type, or the like.

[0050] [Other embodiments] The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) that implements one or more of the functions.

[0051] The invention is not limited to the above-described embodiments, and various modifications and variations are possible without departing from the spirit and scope of the invention. Accordingly, the following claims are appended to apprise the public of the scope of the invention. [Explanation of symbols]

[0052] 201a to 201d: photoconductors, 202a to 202d: chargers, 200a to 200d: scanners, 203a to 203d: developers, 204a to 204d: transfer blades, 205: intermediate transfer body, 222: secondary transfer roller, 40: fixing unit, 71: environment sensor, 405: prediction processing unit, 403: control unit

Claims

1. An image forming means for forming an image on a sheet based on image forming conditions; a prediction means for predicting the density of an image formed by the image forming means; a detection means for detecting an environmental condition; a control unit that controls whether or not to perform a first calibration that controls the image forming conditions based on the density predicted by the prediction unit, based on the environmental conditions detected by the detection unit; An image forming apparatus comprising:

2. The control means When the environmental condition detected by the detecting means satisfies a predetermined condition, the first calibration is performed; 2. The image forming apparatus according to claim 1, wherein the first calibration is not performed when the environmental conditions detected by the detecting means do not satisfy the predetermined conditions.

3. An image forming apparatus as described in claim 2, wherein the environmental conditions include temperature.

4. An image forming apparatus as described in claim 2, wherein the environmental conditions include humidity.

5. An image forming apparatus as described in claim 2, wherein the environmental conditions include temperature and humidity.

6. Further comprising reading means for reading the test image on the sheet, the image forming means forms the test image on a sheet; The control means generating the image forming conditions based on the reading result of the test image read by the reading means; 2. The image forming apparatus according to claim 1, wherein the detecting means is controlled to detect the environmental conditions when the image forming conditions are generated based on the reading result of the test image.

7. An image carrier; a measuring means for measuring a measurement image formed on the image carrier by the image forming means; Furthermore, 2. The image forming apparatus according to claim 1, wherein the control unit executes a second calibration to control the image forming conditions based on the measurement result of the measurement image measured by the measurement unit.

8. The control means controls the detection means to detect the environmental condition every time the image forming means forms images on a first number of sheets, 8. The image forming apparatus according to claim 7, wherein the control means controls the image forming means to form the measurement image every time the image forming means forms images on a second number of sheets, the second number being greater than the first number.

9. The control means controlling whether or not to perform the first calibration every time the image forming unit forms images on the first number of sheets based on the environmental condition detected by the detection unit; 9. The image forming apparatus according to claim 8, wherein the second calibration is performed every time the image forming unit forms images on the second number of sheets.

10. The image forming apparatus of claim 7, wherein the prediction means predicts the density of the image on the image carrier formed by the image forming means.

11. The image forming conditions are conversion conditions for converting input image data, 2. The image forming apparatus according to claim 1, wherein said image forming means forms said image on a sheet based on said converted image data.

Images