Image processing apparatus, image processing method, program, and image forming system

Abstract

Even with strict reading conditions for the concentration test pattern, perform correction for concentration variations. [Solution] The system includes an acquisition means (204) for acquiring image data obtained by reading an image formed on a recording medium using a recording element that ejects ink; a classification means (204) for classifying the image into a mark distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​corresponding to detection marks recorded with ink, and a background distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​where ink has not been ejected, based on a histogram representing the distribution of pixel values ​​in a specified area of ​​the image; and a generation means (204) for generating characteristic data representing the density characteristics of the ink ejected from the recording element based on the mark distribution.

Description

【Technical Field】 【0001】 This disclosure relates to a technique for improving image quality. 【Background Art】 【0002】 In inkjet recording apparatuses, it has been conventionally known that density unevenness occurs in images due to, for example, variations in quality generated during the manufacturing process, aging deterioration, etc. Therefore, in order to improve the density unevenness occurring in images, for example, Patent Document 1 discloses a technique called head shading. The technique described in Patent Document 1 aims to correct density unevenness and equalize the density of an image based on the result of reading a density test pattern. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2001-310535 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 However, in the technique described in Patent Document 1, in a situation where the reading conditions of a density test pattern are severe such that the contrast ratio of the printed color is small compared to the background color, it becomes difficult to read the density test pattern itself, and density unevenness correction may not be possible. 【Means for Solving the Problems】 【0005】 An image processing apparatus according to one aspect of the present disclosure is characterized by comprising: acquisition means for acquiring image data obtained by reading an image formed on a recording medium using a recording element that ejects ink; classification means for classifying the pixel values ​​of the image into a mark distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​corresponding to a detection mark recorded by the ink, and a background distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​where the ink has not been ejected, based on a histogram representing the distribution of pixel values ​​in a specified area of ​​the image; and generation means for generating characteristic data representing the density characteristics of the ink ejected from the recording element, based on the mark distribution. [Effects of the Invention] 【0006】 According to this disclosure, even if the reading conditions for the concentration test pattern are strict, it is possible to correct for concentration unevenness. [Brief explanation of the drawing] 【0007】 [Figure 1] This figure shows an example configuration of the image forming system according to this embodiment. [Figure 2] Figure 1 is a functional block diagram showing an example of the control configuration of an image forming apparatus. [Figure 3] This is a conceptual diagram of a use case for standard printing. [Figure 4] This figure shows an example of a single-color detection pattern. [Figure 5] This figure shows an example of a detection pattern for all colors. [Figure 6] Figure 4 is a conceptual diagram illustrating the process from printing to reading a single-color detection pattern. [Figure 7] This is a flowchart explaining the process shown in Figure 6. [Figure 8] This is a flowchart illustrating the details of the S707 process in Figure 7. [Figure 9] This figure shows an example of the reading result from the scanner unit. [Figure 10] This figure shows an example of calculating the degree of separation between two sets from the distribution of pixel values. [Figure 11] This figure shows an example of detection pattern 401 used in processing S806. [Figure 12] Figure 8 shows an example of a detection pattern 405 in which the S807 process was executed. [Figure 13] This diagram shows a correction table representing the ink density characteristics. [Modes for carrying out the invention] 【0008】 Preferred embodiments of the present invention will be described in detail below with reference to the attached drawings. Note that the following embodiments are not limiting to the scope of this disclosure, and not all combinations of features described in the following embodiments are essential to the solutions of this disclosure. The same reference numerals are used for identical components. 【0009】 (overview) Inkjet recording devices are equipped with recording heads. Mounting errors can occur in the position of these recording heads. Furthermore, mounting errors can also occur in the relative positions of multiple recording heads. These mounting errors can cause deviations in the ink's placement on the recording medium. Therefore, mounting errors in the recording heads can lead to a decrease in recording quality. In addition to recording head mounting errors, errors can also occur during the manufacturing process. For example, variations can occur in the ejection characteristics, such as the amount of ink ejected from each of the multiple nozzles. These variations in the ejection characteristics of each nozzle can also occur due to the aging of the recording heads. Such variations in nozzle-to-nozzle ejection characteristics can lead to density unevenness, thus reducing recording quality. 【0010】 It is known that a technique for detecting and correcting these degradations in recording quality using test patterns is employed. For example, Patent Document 1 discloses the following technique: Test patterns recorded for multiple concentrations are read, and a group of correction tables is selected according to the occurrence of concentration unevenness in each concentration range based on the reading results. This operation eliminates different concentration unevenness that occurs depending on the concentration range, such as low concentration range, medium concentration range, and high concentration range. 【0011】 However, even if the technology described in Patent Document 1 is used to store a test pattern corresponding to a low concentration range and to read that test pattern, detection of the test pattern may be difficult in the following cases. Specifically, if the color of the test pattern is white, or if the test pattern is recorded by the ejection of a primer (also called a reaction solution), the color contrast of the test pattern is small compared to the color of the recording medium. Therefore, reading the concentration test pattern may be difficult. If reading the concentration test pattern is difficult, it may also be difficult to generate characteristic data representing the ink concentration characteristics based on the concentration test pattern. 【0012】 Therefore, in the present disclosure, ink is ejected to read an image formed on a recording medium, and image data is acquired. Based on a histogram of an image representing the distribution of pixel values in a designated area of the image among the pixel values constituting the image data, a mark distribution including the pixel values of a detection mark recorded with ink and a background distribution including the pixel values corresponding to the recording medium are classified. Based on the classified mark distribution, characteristic data representing the density characteristics of the ink is generated. According to this series of operations, the mark distribution and the background distribution are classified using the histogram of the image. Since the histogram of the image distributes the number of occurrences of each pixel value in the image, even if the contrast of the color of the density test pattern is small compared to the recording medium, the mark distribution and the background distribution can be classified. Therefore, characteristic data representing the density characteristics of the ink based on the mark distribution separated from the background distribution can be generated. For this reason, density correction based on this characteristic data becomes possible. Therefore, even if the reading conditions of the density test pattern are strict, the density test pattern can be detected and density unevenness can be corrected. 【0013】 (Overall Configuration) FIG. 1 is a diagram showing a configuration example of an image forming system according to the present embodiment. The image forming system includes an image forming apparatus 100, a terminal device 119, and a UI operation panel 101. The image forming apparatus 100 is an apparatus that forms an image on continuous paper 111 (hereinafter also referred to as paper 111). The paper 111 used in the present embodiment is a long printing medium on which an image can be continuously formed. That is, the paper 111 is a long sheet on which continuous printing is possible. Note that the paper 111 may be continuous forms. In the present embodiment, the image forming apparatus 100 includes a paper feeding unit 104, a first recording unit 116, a second recording unit 115, and a winding unit 105. <​​​The paper feeding unit 104 is arranged on the front stage side of the image forming apparatus 100. The paper feeding unit 104 includes a skew correction unit 110. The skew correction unit 110 includes, for example, a plurality of rollers. When the paper 111 is conveyed obliquely to the skew correction unit 110, the skew correction unit 110 adjusts the rotation amounts of the plurality of rollers as appropriate to adjust the orientation of the obliquely conveyed paper 111 to an orientation along the conveyance direction. The paper feeding unit 104 is a unit that supplies the paper 111 to the first recording unit 116. The paper feeding unit 104 can accommodate the paper 111. The paper 111 is accommodated in the paper feeding unit 104 in a state of being wound around a paper tube. The paper feeding unit 104 rotates the paper tube of the paper 111 around the rotation axis 117. By this operation, the paper 111 is conveyed toward the image forming apparatus 100 at a constant speed via a plurality of rollers such as conveyance rollers and paper feeding rollers. 【0015】 (First recording unit 116) The first recording unit 116 includes a first recording head 103, a drying unit 112, a cooling unit 113, and a cooling unit 114. From the upstream side to the downstream side in the conveyance direction of the paper 111, the first recording head 103, the drying unit 112, the cooling unit 113, and the cooling unit 114 are arranged in order. The first recording head 103 is a unit that performs special color printing other than the printing basic colors (CMYK). In special color printing, for example, colors other than the printing basic colors such as white ink and reaction liquid are recorded on the paper 111. The drying unit 112 heats and dries the ink ejected from the first recording head 10303 to the paper 111. The cooling units 113 and 114 cool the ink ejected and heated onto the paper 111. Also, a plurality of conveyance rollers are provided in the first recording unit 116. The conveyance rollers of the first recording unit 116 convey the paper 111 from the paper feeding unit 104 to the second recording unit 115 along the conveyance direction. 【0016】 (Second recording unit 115) The second recording unit 115 includes a mark detection sensor 120, a second recording head 102, a drying unit 106, a cooling unit 108, a cooling unit 109, and a scanner unit 107. The mark detection sensor 120, the second recording head 102, the drying unit 106, the cooling unit 108, the cooling unit 109, and the scanner unit 107 are arranged in order from upstream to downstream in the paper transport direction of the paper 111. The second recording head 102 is a unit that prints in the basic printing colors (CMYK). The second recording unit 115 is also provided with multiple transport rollers. The transport rollers of the second recording unit 115 transport the paper 111 from the first recording unit 116 to the winding unit 105 along the transport direction. 【0017】 (Winding unit 105) The winding unit 105 is positioned downstream of the image forming apparatus 100. The winding unit 105 is a unit that winds the paper 111, which is transported from the image forming apparatus 100, into a roll shape around the rotation axis 118 of the paper tube. The winding unit 105 can hold the paper 111 in a roll shape by winding the paper 111 onto the paper tube, for example as shown in Figure 1. The winding unit 105 rotates the paper tube of the paper 111 around the rotation axis 118 of the paper tube. Through this operation, the paper 111 is wound up as the output product of the paper 111 around the rotation axis 118 at a constant speed, passing through multiple rollers such as transport rollers and paper feed rollers. 【0018】 (Preparing for printing) Before printing begins, as a pre-printing preparation, for example, the paper 111 is fed from the paper feed unit 104 to the take-up unit 105 by an operator. Specifically, first, the paper 111 is set in the paper feed unit 104, and the leading edge of the paper 111 is passed over the skew correction unit 110. Next, the paper 111 is passed under the first recording head 103 of the first recording unit 116. Next, the paper 111 is passed under the drying unit 112 and over the cooling units 113 and 114. Next, the paper 111 is passed under the mark detection sensor 120 and the second recording head 102 of the second recording unit 115, and over the cooling units 108 and 109 while passing under the drying unit 106. In this embodiment, the use of a scanner unit 107 is assumed as a unit for alignment when forming an image. After the paper 111 passes through the scanner unit 107, it is wound onto the winding unit 105. After the paper 111 has passed through the image forming apparatus 100 in this way, the print job is submitted to the terminal device 119. After the print job is submitted, printing starts when the print start button displayed on the UI operation panel 101 is pressed. The printed image is read by the scanner unit 107. The image read by the scanner unit 107 is analyzed by the terminal device 119 to check whether there are any defects in the printed material. 【0019】 (Control configuration) Figure 2 is a functional block diagram showing an example of the control configuration of the image forming apparatus 100 shown in Figure 1. As shown in Figure 2, the image forming apparatus 100 includes, for example, a paper transport unit 201, an image forming unit 202, a communication unit 203, a control unit 204, a storage unit 205, an operation display unit 206, and an inspection unit 207. The paper transport unit 201 is a paper transport mechanism for paper 111 inside the image forming apparatus 100. For example, the paper transport unit 201 is composed of a plurality of rollers. The paper transport unit 201 transports the paper 111 transported from the paper feeding unit 104 to the image forming unit 202 using a plurality of rollers. The paper transport unit 201 transports the paper 111 that has passed through the image forming unit 202 to the winding unit 105 using a plurality of rollers. The image forming unit 202 is composed of a first recording head 103 and a second recording head 102. The image forming unit 202 forms an image on paper 111 supplied from the paper feeding unit 104 based on a print job. The communication unit 203 communicates between the image forming apparatus 100 and an external device (e.g., a personal computer). The communication unit 203 includes a wired communication function, which is composed of a communication control card such as a LAN (Local Area Network) card. The external device is connected to a communication network such as a LAN or WAN (Wide Area Network). Therefore, the communication unit 203 transmits and receives various data between the image forming apparatus 100 and the external device via the communication network. The control unit 204 is composed of, for example, a CPU (Central Processing Unit) and RAM (Random Access Memory). The CPU of the control unit 204 reads various programs such as system programs and processing programs stored in the memory unit 205, loads them into RAM, and executes various processes according to the loaded programs. For example, the control unit 204 can perform image forming processing to execute a print job (hereinafter also referred to as a job) in response to user instructions. The storage unit 205 is composed of, for example, a non-volatile semiconductor memory (e.g., flash memory), an HDD (Hard Disk Drive), etc. The storage unit 205 may also be composed of an SSD (Solid State Drive).The memory unit 205 stores various programs, such as system programs and processing programs, that are executed by the control unit 204, as well as various data necessary for the execution of these programs. 【0020】 The operation display unit 206 is composed of, for example, a liquid crystal display (LCD) with a touch panel. The operation display unit 206 comprises a display unit 206a and an operation unit 206b. The display unit 206a displays various information on the screen displayed on the liquid crystal display according to the display control signal input from the control unit 204. The operation unit 206b accepts operation of various operation keys such as a numeric keypad and a start key. The various operation keys are displayed on the liquid crystal display, for example, and the operation unit accepts the user's operation by recognizing that the user has operated an operation key on the touch panel. The operation unit 206b accepts the user's operation and generates an operation signal. The operation unit 206b outputs the generated operation signal to the control unit 204. 【0021】 Next, the process by which the image forming apparatus 100 forms an image on paper 111 will be described. First, when the user operates an external device, the external device creates the background data and overprint data for the job and sets the print settings for the job. The external device transmits the job, including the background data, overprint data, and print settings, to the image forming apparatus 100 via a communication network. The control unit 204 of the image forming apparatus 100 receives various data and print settings included in the job transmitted from the external device via the communication unit 203. The control unit 204 checks whether the printed image can be printed without density unevenness. The control unit 204 has the image forming unit 202 print the pattern data received via the communication unit 203, and then has the scanner unit 107 read the printed pattern data to detect density unevenness. The control unit 204 calculates a correction table based on the detected density unevenness. In addition, the control unit 204 can also check several other items, such as checking for ejection defects and checking for misalignment of the color register, but in this embodiment, only the inspection of density unevenness will be described. 【0022】 Figure 3 is a conceptual diagram of a normal printing use case. The image forming apparatus 100 continuously transports the paper 111 in the transport direction. The image forming apparatus 100 prints image 300 on the transporting paper 111 by ejecting ink from the first recording head 103. The image forming apparatus 100 fixes the printed image 300 to the paper 111 using the drying unit 112 and the cooling unit 113. After fixing image 300 to the paper 111, the image forming apparatus 100 performs overprinting of image 301 by ejecting ink from the second recording head 102. The image forming apparatus 100 fixes the printed image 301 to the paper 111 using the drying unit 106, the cooling unit 108 and the cooling unit 109. The second recording unit 115 has the image 301 fixed to the paper 111 read by the scanner unit 107. In this embodiment, as shown in Figure 3, two scanner units 107 are installed. Each scanner unit 107 is arranged in a staggered configuration. 【0023】 Figures 4 through 67 show examples of various patterns used to calculate the density unevenness correction table. These will be explained in order below. 【0024】 Figure 4 shows an example of a single-color detection pattern 400, 401. This single-color detection pattern 400, 401 is used to calculate a density unevenness correction table. This single-color detection pattern 400, 401 is printed to detect density unevenness. Specifically, it is printed sequentially for each color at the start of printing by the image forming apparatus 100. Figure 4(A) shows an example of a single-color detection pattern 400. Figure 4(B) shows an example of a white ink detection pattern 401. In both Figure 4(A) and Figure 4(B), the detection pattern consists of a gradation area with different densities and a detection mark area. The detection pattern is printed with each ink color of the image forming apparatus 100. 【0025】 Figure 5 shows examples of detection patterns 402, 403, and 404 for all colors. The detection patterns 402, 403, and 404 for all colors in Figure 5 are the same as the single-color detection patterns 400 and 401 in Figure 4. Figure 5(A) shows the detection pattern 402 for four color inks. Figure 5(B) shows the detection pattern 403 for four color inks and white ink. Figure 5(C) shows the detection pattern 404 for one white ink. 【0026】 Figure 6 is a conceptual diagram illustrating the process from printing to reading of the monochrome detection patterns 400 and 401 shown in Figure 4. Figure 6(A) shows an example of paper 111 being transported along the transport direction before printing the detection pattern 400. Figure 6(B) shows an example of the state after the monochrome detection pattern 400 has been printed on paper 111 and before reading by the scanner unit 107. Figure 6(C) shows an example of the state in which the monochrome detection pattern 400 is being read by the scanner unit 107 and the white ink detection pattern 401 is being printed on paper 111. Figure 6(D) shows an example of the white ink detection pattern 401 being read by the scanner unit 107. 【0027】 Figure 7 is a flowchart illustrating the process shown in Figure 6. Figure 8 is a flowchart illustrating the details of the process S707 in Figure 7. In this embodiment, an example is described in which the control unit 204 of the image forming apparatus 100 executes each process in the flowcharts of Figures 7 and 8, but the embodiment is not limited to this. The CPU of the terminal device 119 may execute each process in the flowcharts of Figures 7 and 8. Alternatively, the image forming apparatus 100 may perform some of the processes in the flowcharts of Figures 7 and 8, and the terminal device 119 may perform the remaining processes. The process shown in Figure 7 may be executed, for example, when the density unevenness correction process is selected via the UI operation panel 101. That is, the process shown in Figure 7 is implemented by the CPU of the control unit 204. Note that some or all of the functions of the steps in Figures 7 and 8 may be implemented by hardware such as an ASIC or electronic circuit. The symbol "S" in the description of each process means that it is a step in the flowchart. Also, when referring collectively to the device that executes the processes of each step in Figures 7 and 8, it is also called an image processing device. 【0028】 In S701, the control unit 204 initiates the image forming apparatus 100 to correct density unevenness from the state shown in Figure 6(A) based on instructions from the user. In S702, the control unit 204 sets the color information of the object to be analyzed as one of the analysis parameters. For example, if the object to be analyzed is white ink, the control unit 204 sets the color information of the object to be analyzed to the color value corresponding to white. Specifically, if the object to be analyzed is a CMYK pattern, the analysis parameters as the color information of the object to be analyzed may consist of parameters representing four colors. Alternatively, if the object to be analyzed is a white pattern, the analysis parameters as the color information of the object to be analyzed may consist of parameters representing one color (white background). Alternatively, if the object to be analyzed is a CMYK pattern and a white pattern, the analysis parameters as the color information of the object to be analyzed may consist of parameters representing four colors + one color (white background). 【0029】 In S703, the control unit 204 decides whether or not to perform a correction process for uneven density of the white ink. If it is decided in S703 to perform a correction process for uneven density of the white ink, the process in S703 proceeds to the process in S704. In S704, the control unit 204 causes the second recording head 102 of the second recording unit 115 to print a detection pattern 400 for analyzing uneven density of the color inks onto the paper 111. Specifically, the second recording head 102 forms a detection pattern 400 for each ink color (Figure 6B). In other words, a detection pattern 400 is formed on the paper 111 for each ink color. In S705, after the printing of the color ink detection patterns 400 is completed (Figure 6C), the control unit 204 causes the first recording unit 116 to start printing the white ink detection pattern 401 (Figure 6C). The processes in S704 and S705 form a detection pattern 403 printed with four color inks and white ink (Figure 5(B)). In S706, the control unit 204 has the scanner unit 107 read the detection pattern 401. In S707, the control unit 204 performs the correction processing necessary for detection. Details of the process in S707 will be described later with reference to Figure 8. 【0030】 If it is decided in S703 not to perform correction processing for uneven density of white ink, the process in S703 proceeds to the process in S708. In S708, the control unit 204 causes the second recording head 102 of the second recording unit 115 to print a detection pattern 400 for analyzing uneven density of color inks onto the paper 111. Specifically, the second recording head 102 forms a detection pattern 400 for each ink color (Figure 6B). In other words, a detection pattern 400 is formed on the paper 111 for each ink color. In S709, the control unit 204 causes the scanner unit 107 to read the detection pattern 400. 【0031】 In S710, the control unit 204 acquires the read scan data and calculates a density unevenness correction table. It is assumed that the coordinates, color values, etc. to be used for the analysis are registered in the device in advance as analysis parameters. For example, the coordinates, color values, etc. to be used may be set when setting the analysis parameters in S702. In S711, the control unit 204 transmits the analysis results to the image forming unit 202. The image forming unit 202 updates the density unevenness correction table based on the analysis results. After that, the process ends. 【0032】 (White ink image correction processing) Next, the process in S707 of Figure 7 will be explained using Figure 8. In S801, the control unit 204 starts the correction process. The data to be corrected will be explained with reference to Figure 9 as appropriate. Figure 9 is a diagram showing an example of the reading result by the scanner unit 107. In S802, the control unit 204 converts the detection pattern read by the scanner unit 107 into a grayscale image. In S803, the control unit 204 calculates the distribution of pixel values ​​for the grayscale image converted by the process in S802. In S804, the control unit 204 sets the range of the pixel value distribution that can be used in the process in S805. Figure 9(A) is a diagram showing an example in which the range of the pixel value distribution is set by the process in S804, with the specified area of ​​the image enclosed by the thick black line. Figure 9(B) is a diagram showing an example of an image histogram representing the distribution of pixel values ​​in the specified area of ​​the image enclosed by the thick black line in Figure 9(A). In step S804, the control unit 204 specifies a designated area that includes the pixel values ​​of the paper 111 and the pixel values ​​of the detection pattern 401, which includes the detection marks to be corrected. In step S804, the control unit 204 sets the threshold calculation range by calculating the maximum and minimum pixel values ​​of the designated area. In the example shown in Figure 9(A), 30px from the center of the image is specified, taking into account the size of the detection pattern 401. In the example shown in Figure 9(B), the maximum and minimum pixel values ​​in the designated area are specified. In other words, by focusing on the pixel values ​​between the maximum and minimum pixel values, not only are unnecessary noise components removed, but the dynamic range of the histogram representing the distribution of pixel values ​​is changed to be between the maximum and minimum pixel values. This operation can also improve the contrast of the image. Furthermore, by specifying, for example, 30px from the center of the image in order to focus on the pixel values ​​between the maximum and minimum pixel values, the amount of calculation can be reduced, thus shortening the calculation time. Note that 30px is just an example and is not limited to this. The detection marks should be specified to include at least one mark located in the center of the image. In this embodiment, a cross-shaped mark is used for the mark located in the center of the image, but it is not limited to this shape. 【0033】 Figure 10 shows an example of calculating the degree of separation between two sets from the distribution of pixel values. According to this degree of separation, it is possible to remove pixel values ​​other than the pixel values ​​corresponding to paper 111 and the pixel values ​​of the detection pattern 401 to be corrected as noise. Based on the specified area specified in the processing of S804, the processing of S805 is executed. In S805, the control unit 204 calculates a threshold for binarization from the distribution of pixel values. Since there are two sets, the pixel values ​​of paper 111 and the pixel values ​​of the detection pattern 401 to be corrected, a discriminant analysis method is used to calculate the threshold, which uses the maximum value of the degree of separation between the two sets as the threshold. Other binarization methods include the modal method, the P-tile method, and methods using correlation, but any method that can clearly distinguish between the pixel values ​​corresponding to paper 111 and the pixel values ​​of the detection pattern 401 can be used. For this reason, clustering using k-means in unsupervised learning may also be used. The degree of separation is calculated by the variance within the two sets and the variance between the sets. Specifically, the threshold for binarizing the pixel value when the separation between the two sets is at its maximum is used. The separation is defined as the inter-class variance divided by the intra-class variance. The pixel values ​​of the detection pattern 402 using chromatic ink are smaller than the pixel values ​​of the background color corresponding to the paper 111. On the other hand, the pixel values ​​of the detection pattern 404 using white ink are larger than the pixel values ​​of the background color corresponding to the paper 111. Figure 11 shows an example of the detection pattern 401 used in the processing of S806. In S806, the control unit 204 performs correction processing on all pixel values ​​in Figure 11. 【0034】 In S807, the control unit 204 obtains the difference between the target pixel value and the threshold value obtained by the processing in S805. If the difference is greater than 0, in S808, the control unit 204 sets the target pixel value to 1. If the difference is 0 or less, in S809, the control unit 204 sets the target pixel value to 0. This operation inverts the pixel values ​​of white ink to black, and the pixel values ​​corresponding to paper 111 to white. That is, if the ink is white ink, the pixel values ​​of the parts where the ink has been ejected are inverted to black, and the pixel values ​​of the parts where the ink has not been ejected are inverted to white. After the processing in S807 is completed for all pixel values, in S810, the control unit 204 converts the grayscale image used in the processing in S803 to S809 into RGB. In S811 and S812, the control unit 204 performs edge detection on all pixels of the image generated by the processing in S810. This operation obtains detection marks for white ink. To acquire detection marks, for example, edge detection using a differential filter is used. Therefore, areas with large differences in pixel values ​​are extracted. Figure 12 shows an example of detection pattern 405 after processing S807 in Figure 8 has been performed. In processing S812 and S813, for example, using Figure 12, the control unit 204 acquires the coordinates of the white ink detection marks. That is, in S813, the control unit 204 acquires the coordinates of the detection marks. After edge detection is performed on all pixels, processing S811 is completed and the process moves to S711. In S711, the control unit 204 uses the position of the detection marks acquired by processing S813 as the coordinates of the analysis reference to calculate the density unevenness correction table characteristics. Figure 13 shows a correction table representing the ink density characteristics. Figure 13 shows an example in which the output level is determined according to the input level. The relationship between the input level and the output level is identified by the correction table in Figure 13. The larger the input level, the larger the output level becomes compared to a linear change. On the other hand, the smaller the input level, the smaller the output level becomes compared to a linear change. For example, let's assume the input level corresponds to the input density of the ink, and the output level corresponds to the output density of the ink.In this scenario, referring to Figure 13, the correction amount for the corresponding output density is set to different values ​​for the high-density range and the low-density range (areas with lower densities than the high-density range) within the input density. Specifically, in the correction table in Figure 13, the contrast for bright and high-density areas becomes larger, and the contrast for dark and low-density areas becomes smaller. The number of ink ejections is controlled based on this output level. In other words, the correction table in Figure 13 associates the correction amount that reduces ink density unevenness with the number of ink ejections. Specifically, the correction table in Figure 13 allows conversion between the pixel value before conversion and the pixel value after conversion without calculation by forming a lookup table with the input level and the output level. 【0035】 From the above description, according to this embodiment, the CPU of the control unit 204 acquires image data obtained by reading an image formed on a recording medium using a recording element that ejects ink. The CPU of the control unit 204 classifies the image into a mark distribution and a background distribution based on a histogram representing the distribution of pixel values ​​in a specified area of ​​the image. The mark distribution includes the pixel values ​​of the part of the image's pixel values ​​that corresponds to the detection marks recorded by ink. The background distribution includes the pixel values ​​of the image's pixel values ​​that do not have ink ejected. Based on the mark distribution, the CPU of the control unit 204 generates characteristic data representing the density characteristics of the ink ejected from the recording element. With this configuration, even if the color contrast of the density test pattern is small compared to the recording medium, the histogram of the image is distributed by the number of times each pixel value appears in the image, so it is possible to classify the mark distribution and the background distribution. Therefore, characteristic data representing the ink density characteristics based on the mark distribution separated from the background distribution can be generated. For this reason, density correction based on this characteristic data becomes possible. Consequently, even if the reading conditions for the density test pattern are strict, it is possible to detect the density test pattern and correct density unevenness. 【0036】 Furthermore, according to this embodiment, the designated area of ​​the image may include the pixel values ​​of the parts where ink has not been ejected and the pixel values ​​of the densest parts among the pixel values ​​of the parts where ink has been ejected. With this configuration, the designated area of ​​the image includes the pixel values ​​of the parts where ink has not been ejected and the pixel values ​​of the densest parts among the pixel values ​​of the parts where ink has been ejected. The parts where ink has not been ejected correspond to the background. The densest parts among the pixel values ​​of the parts where ink has been ejected correspond to the detection marks. Therefore, by narrowing the image to a designated area, not only is the dynamic range of the histogram widened, but it also becomes possible to narrow it down to pixel values ​​including the detection marks. Furthermore, since the number of pixel values ​​required for calculation can be reduced, the calculation time can be shortened and the calculation cost can be reduced. 【0037】 Furthermore, according to this embodiment, a threshold may be set from the pixel value between the pixel value of the area where ink has not been ejected and the pixel value of the darkest part of the pixel value of the area where ink has been ejected. Alternatively, the image data may be binarized based on the threshold, and the coordinates of the detection marks included in the mark distribution may be extracted. With such processing, since binarization is performed based on the threshold, even if the color contrast of the density test pattern is small, the density test pattern and the background color can be clearly distinguished by the binarization process. 【0038】 Furthermore, according to this embodiment, characteristic data may be generated based on the coordinates of the detection marks. This process allows for correction of the shift in the center of the image from the coordinates of the detection marks. The shift in the center of the image is affected by variations in quality that occur during the manufacturing process, deterioration over time, etc. Therefore, the characteristic data can be data that takes into account the effects of variations in quality that occur during the manufacturing process, deterioration over time, etc. 【0039】 Furthermore, according to this embodiment, the number of ink jets ejected may be controlled based on characteristic data. With such processing, the number of ink jets ejected is controlled taking into account the effects of quality variations that occur in the manufacturing process and deterioration over time, thus enabling ink ejection control that takes into account factors that cause density unevenness in images. 【0040】 Furthermore, according to this embodiment, the characteristic data may consist of a correction table that associates a correction amount for reducing density unevenness of the ink ejected from the recording element with the number of ink ejections. With such a configuration, even if the color contrast of the density pattern is low, the number of ink ejections can be controlled to improve the density unevenness of the ink. 【0041】 Furthermore, according to this embodiment, the correction table consists of an input concentration and an output concentration corresponding to the input concentration, and the correction amount for the corresponding output concentration may be set to different values ​​for the high concentration range and the low concentration range, which is a region with a lower concentration than the high concentration range. With such a configuration, it is possible to set different correction amounts for each concentration range. Therefore, when the issue can be addressed by correction on a concentration range basis, it is possible to significantly reduce computation costs and improve processing speed. 【0042】 Furthermore, according to this embodiment, the difference between the contrast of the portion of the recording medium where ink has been ejected and the contrast of the portion of the recording medium where ink has not been ejected may be smaller than the preset contrast. With such a configuration, it is possible to handle situations where the contrast is low and the reading conditions for the density test pattern are strict. 【0043】 Furthermore, according to this embodiment, the ink color may be achromatic. With this configuration, it is possible to handle situations where there is no contrast between the background color and the ink color. 【0044】 Furthermore, according to this embodiment, the ink is at least one of white ink and clear ink, and the recording element may further dispense a reaction liquid that increases the viscosity of the ink in addition to the ink. With such a configuration, it is possible to handle situations where there is no contrast between the background color and the ink color. 【0045】 Furthermore, according to this embodiment, the image may include a gradation region in which multiple patterns of different densities are arranged in steps, and a detection mark region in which detection marks are placed. With such a configuration, it becomes possible to perform gradation correction and density correction simultaneously. 【0046】 Furthermore, according to this embodiment, the decision of whether or not to correct the image contrast may be made based on the difference between the contrast of the portion of the recording medium where ink has been ejected and the contrast of the portion of the recording medium where ink has not been ejected. With such processing, it is also possible to analyze the correction process when the difference in contrast between the two is smaller than a predetermined difference. For example, in the process of S703 in Figure 7, it was decided whether or not to execute the processes from S704 onward based on the analysis parameters obtained in the process of S702. Instead of this process of S703, it is possible to decide whether or not to execute the processes from S704 onward based on the difference in contrast between the two. 【0047】 Furthermore, according to this embodiment, the distribution of pixel values ​​in a specified area of ​​an image is calculated from the grayscale image obtained by converting the image data, and a threshold for classifying the mark distribution and the background distribution is calculated from the distribution of pixel values ​​in the specified area of ​​the image. With this process, the image data is converted to a grayscale image and then classified into the mark distribution and the background distribution, making it possible to separate the black and white and classify the distributions of both. 【0048】 Furthermore, according to this embodiment, a first class including a mark distribution may be set, and a second class including a background distribution may be set. Also, based on the variance of the first class and the variance of the second class, an intra-class variance representing the magnitude of the dispersion of the first and second classes may be set, and an inter-class variance representing the degree of dispersion between the first class and the second class may be set. In addition, the pixel value at which the degree of separation obtained by the ratio of the intra-class variance to the inter-class variance is maximized may be used as a threshold. With such a configuration, the mark distribution and the background distribution can be automatically classified using discriminant analysis. 【0049】 Furthermore, according to this embodiment, the image data may be binarized based on a threshold value obtained by discriminant analysis. This process makes it possible to perform binarization on the data classified by discriminant analysis. 【0050】 Furthermore, according to this embodiment, binarization may be performed based on the difference between the pixel value contained in the image data and a threshold. With such a configuration, it is also possible to perform binarization based on whether or not the pixel value contained in the image data is greater than or equal to the threshold. Therefore, it is possible to divide the distribution of pixel values ​​into two sets using a threshold. 【0051】 Furthermore, according to this embodiment, the degree of separation may be determined within the range of the minimum and maximum pixel values ​​specified in the designated area. With such processing, it is possible to determine the degree of separation after expanding the dynamic range, thus increasing the contrast. 【0052】 [Other embodiments] Although various examples and embodiments of this disclosure have been described above, the spirit and scope of this disclosure are not limited to the specific descriptions herein. This disclosure is not limited to the embodiments described above, and various modifications may be made. Furthermore, this disclosure may combine some of the embodiments described above as appropriate. 【0053】 (Variation 1) For example, the image forming apparatus 100 described here includes a paper feeding unit 104, a first recording unit 116, a second recording unit 115, and a winding unit 105, but is not limited to this example. For instance, a scanner unit 107 included in the second recording unit 115 may be positioned between the downstream side of the second recording unit 115 and the winding unit 105. Alternatively, a colorimeter capable of detecting colors with higher accuracy than the scanner unit 107 may be positioned. The colorimeter may be positioned between the downstream side of the second recording unit 115 and the winding unit 105, or it may be located within the second recording unit 115 and downstream of the drying unit 106. 【0054】 (Modification 2) Furthermore, while the color information of the paper 111 is acquired by the scanner unit 107 in the above embodiment, the system is not limited to this. Other sensors may be used to read the color information. For example, a colorimeter (not shown) may be placed in the transport path of the paper 111, and the color information of the paper 111 may be acquired by the colorimeter. 【0055】 (Variation 3) Furthermore, while an example using continuous paper 111 as the recording medium has been described, the invention is not limited to this. For example, cut paper or roll paper may be used instead of continuous paper 111. The recording medium may also be made of film or other materials. The material of the recording medium is also not particularly limited. Furthermore, while an example in which the continuous paper 111 used as the recording medium is colored paper has been described, the invention is not limited to this. The recording medium may be made of a transparent material or a metallic material. The surface color and characteristics of the recording medium are also not particularly limited. 【0056】 (Modification 4) Furthermore, while an example has been described in which images 300 and 301 in Figure 3 are identical in design, the explanation is not limited to this example. Images 300 and 301 in Figure 3 may be different designs. 【0057】 (Variation 5) Furthermore, while an example has been described in which the image forming apparatus 100 includes a first recording unit 116 and a second recording unit 115, it is not particularly limited thereto. Either the first recording unit 116 or the second recording unit 115 may be included. Alternatively, the first recording unit 116 and the second recording unit 115 may be an integrated unit. Alternatively, in addition to the first recording unit 116 and the second recording unit 115, a third recording unit (not shown) may be included. The third recording unit may, for example, be a unit equipped with a colorimeter. Alternatively, the third recording unit may be a unit that includes a function for attaching stickers. Alternatively, the third recording unit may be a unit that includes a function for cutting paper 111. Alternatively, the third recording unit may be a unit that includes a function for printing labels. 【0058】 (Experimental variation 6) Furthermore, while this embodiment describes an example of calculating a correction table for white ink, it is not limited to this. For example, a correction table may be calculated for achromatic inks where pattern detection is difficult, such as reaction solutions or clear inks. 【0059】 (Example 7) Furthermore, while we have described an example using a discriminant analysis method where the maximum degree of separation between the two sets is used as the threshold for binarization, we are not limited to this. For example, methods such as modal methods, P-tile methods, or correlation methods may also be used. In other words, any method that can clearly distinguish between the pixel values ​​of paper 111 and the pixel values ​​of detection pattern 401 can be used. For example, clustering using k-means with unsupervised learning may be used. 【0060】 (Variation 8) Furthermore, while one example of the communication unit 203 including wired communication functionality via a LAN, etc., has been described, it is not limited to this. For example, the communication unit 203 may include wireless communication functionality compliant with standards such as 5G and 6G. Also, while one example of the communication unit 203 sending and receiving various data with external devices connected to a communication network such as a LAN or WAN has been described, it is not limited to this. For example, the communication unit 203 may send and receive various data with a cloud providing various cloud services. With this configuration, the image forming system can organically connect with the cloud, for example, to accept print jobs from external devices located in remote locations and perform image forming. In addition, the image forming system can share the results of various processes with external devices located in remote locations by uploading the results of various processes to the cloud. 【0061】 (Extreme variation 9) Furthermore, in this embodiment, the S702 process describes an example of obtaining the RGB values ​​of the target for analysis as color information to be analyzed, but it is not limited to this. For example, the YUV color space may be used. The YUV color space is a color space used to transmit video signals. The YUV color space differs from the RGB color space in that luminance (Y) and chrominance (U,V) are represented separately. Luminance (Y) corresponds to a black and white image. Chrominance (U,V) represents color information. Since there is a clear difference between white and black in the YUV color space, it can be used as color information for analysis according to this embodiment. Alternatively, the YIQ color space may be used. In the YIQ color space, Y is luminance, and I and Q are obtained by rotating U and V by 33°, so there is a clear difference between white and black, and it can be used as color information for analysis according to this embodiment. Alternatively, HSV may be used. HSV consists of three components: hue, saturation (chroma), and value (brightness). Therefore, since there is a difference between white and black depending on the brightness, it can be used as the color information to be analyzed according to this embodiment. However, additional judgment processing is required. For example, if the brightness (Value) = 100 and the saturation (Saturation) = 0, it is treated as white regardless of the hue value. Also, if the brightness (Value) = 0, it is treated as black regardless of the saturation (Saturation) and hue (Hue) values. Alternatively, the Lab color space may be used. L represents brightness, and since there is a clear difference between white and black, it can be used as the color information to be analyzed according to this embodiment. In other words, the analysis target according to this embodiment is a CMYK pattern or a white pattern. Furthermore, although the RGB color space is used in this embodiment for the color information to be analyzed according to this embodiment, it is not particularly limited to any color space where the values ​​of white and black are far apart. 【0062】 The present invention can also be realized by supplying a program that implements one or more of the functions of the above-described embodiments to a system or device via a network or storage medium, and by having one or more processors in the computer of that system or device read and execute the program. It can also be realized by a circuit (e.g., an ASIC) that implements one or more functions. Furthermore, the program may be recorded on a recording medium readable by a computer and provided. 【0063】 The disclosure of this embodiment includes configurations represented by the following image processing apparatus, image processing method, program, and image forming system. 【0064】 <Configuration 1> An acquisition means for acquiring image data obtained by reading an image formed on a recording medium using a recording element that ejects ink, A classification means that classifies the image into a mark distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​corresponding to the detection marks recorded by the ink, and a background distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​where the ink has not been ejected, based on a histogram representing the distribution of pixel values ​​in a specified area of ​​the image. A generation means for generating characteristic data representing the density characteristics of the ink ejected from the recording element based on the mark distribution, An image processing apparatus characterized by comprising: 【0065】 <Configuration 2> The image processing apparatus according to configuration 1, characterized in that the designated area of ​​the image includes the pixel values ​​of the portion where the ink has not been ejected and the pixel values ​​of the portion with the highest density among the pixel values ​​of the portion where the ink has been ejected. 【0066】 <Structure 3> The classification means sets a threshold value that is set from the pixel value between the pixel value of the portion where the ink has not been ejected and the pixel value of the darkest portion of the pixel value of the portion where the ink has been ejected. The image processing apparatus according to configuration 2, characterized in that the generation means performs a binarization process on the image data based on the threshold to extract the coordinates of the detected marks included in the mark distribution. 【0067】 <Structure 4> The image processing apparatus according to configuration 3, characterized in that the generation means generates the characteristic data based on the coordinates of the detection mark. 【0068】 <Composition 5> The image processing apparatus according to configuration 4, further comprising control means for controlling the number of ink ejections based on the characteristic data. 【0069】 <Composition 6> The image processing apparatus according to configuration 5, characterized in that the characteristic data consists of a correction table that correlates a correction amount for reducing density unevenness of the ink ejected from the recording element with the number of ink ejections. 【0070】 <Composition 7> The image processing apparatus according to configuration 6, wherein the correction table comprises an input density and an output density corresponding to the input density, and the correction amount to the corresponding output density is set to different values ​​for the high density range and the low density range, which is a region with a density lower than the high density range, among the input density. 【0071】 <Structure 8> The image processing apparatus according to configuration 1, characterized in that the difference between the contrast of the portion on the recording medium in which the ink has been ejected and the contrast of the portion on the recording medium in which the ink has not been ejected is smaller than a preset contrast. 【0072】 <Composition 9> The image processing apparatus according to configuration 1, characterized in that the color of the ink is achromatic. 【0073】 <Composition 10> The ink is at least one of white ink and clear ink. The image processing apparatus according to configuration 1, characterized in that the recording element further discharges a reaction liquid that increases the viscosity of the ink, in addition to the ink. 【0074】 <Composition 11> The image processing apparatus according to configuration 1, characterized in that the image includes a gradation region in which multiple patterns of different densities are arranged in steps, and a detection mark region in which the detection marks are arranged. 【0075】 <Composition 12> The image processing apparatus according to configuration 1, further comprising determination means for determining whether or not to correct the contrast of the image according to the difference between the contrast of the portion on the recording medium in which the ink has been ejected and the contrast of the portion on the recording medium in which the ink has not been ejected. 【0076】 <Composition 13> A conversion means for converting the aforementioned image data to a grayscale image, Distribution calculation means for calculating the distribution of pixel values ​​in a specified area of ​​the grayscale image, A threshold calculation means for calculating a threshold for classifying the mark distribution and the background distribution from the distribution of pixel values ​​in a specified area of ​​the image, The image processing apparatus according to configuration 3, further comprising: 【0077】 <Composition 14> A first class including the aforementioned mark distribution is set, A second class is established, which includes the aforementioned substrate distribution. Based on the variance of the first class and the variance of the second class, an intraclass variance representing the magnitude of the dispersion of the first and second classes is set. An inter-class variance is set, which represents the degree of dispersion between the first class and the second class. The image processing apparatus according to configuration 13, characterized in that the generation means uses the pixel value at which the degree of separation obtained by the ratio of the intraclass variance to the interclass variance is maximized as the threshold value. 【0078】 <Composition 15> The image processing apparatus according to configuration 14, characterized in that the generation means performs a binarization process of the image data based on the threshold. 【0079】 <Composition 16> The image processing apparatus according to configuration 15, characterized in that the generation means determines the degree of separation within the range of the minimum pixel value and the maximum pixel value specified in the designated region. 【0080】 <Composition 17> The image processing apparatus according to configuration 16, characterized in that the generation means performs the binarization process based on the difference between the pixel values ​​included in the image data and the threshold. 【0081】 <Composition 18> An acquisition step of acquiring image data obtained by reading an image formed on a recording medium using a recording element that ejects ink, A classification step that classifies the image into a mark distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​corresponding to the detection marks recorded by the ink, and a background distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​where the ink has not been ejected, based on a histogram representing the distribution of pixel values ​​in a specified area of ​​the image. A generation step of generating characteristic data representing the density characteristics of the ink ejected from the recording element based on the mark distribution, An image processing method characterized by including 【0082】 <Composition 19> A program for causing a computer to perform each step of the image processing method described in configuration 18. 【0083】 <Composition 20> An image processing apparatus as described in any one of items 1 to 17, and, A recording head having the recording element and ejecting the ink to form the image on the recording medium, An image forming system characterized by including the following. 【0084】 <Composition 21> An upstream scanning means that reads the aforementioned image and acquires it as upstream image data, A downstream scanning means is arranged in a staggered pattern relative to the upstream scanning means, and reads the image and acquires it as downstream image data. A synthesis means for combining the upstream image data and the downstream image data, The image forming system according to configuration 20, further comprising the features described above. [Explanation of Symbols] 【0085】 100 Image forming apparatus 119 Terminal device 204 Control Unit

Claims

[Claim 1] An acquisition means for acquiring image data obtained by reading an image formed on a recording medium using a recording element that ejects ink, A classification means that classifies the image into a mark distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​corresponding to the detection marks recorded by the ink, and a background distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​where the ink has not been ejected, based on a histogram representing the distribution of pixel values ​​in a specified area of ​​the image. A generation means for generating characteristic data representing the density characteristics of the ink ejected from the recording element based on the mark distribution, An image processing apparatus characterized by comprising: [Claim 2] The image processing apparatus according to claim 1, characterized in that the designated area of ​​the image includes the pixel values ​​of the portion where the ink has not been ejected and the pixel values ​​of the portion with the highest density among the pixel values ​​of the portion where the ink has been ejected. [Claim 3] The classification means sets a threshold value that is set from the pixel value between the pixel value of the portion where the ink has not been ejected and the pixel value of the darkest portion of the pixel value of the portion where the ink has been ejected. The image processing apparatus according to claim 2, characterized in that the generation means performs a binarization process on the image data based on the threshold to extract the coordinates of the detected marks included in the mark distribution. [Claim 4] The image processing apparatus according to claim 3, wherein the generation means generates the characteristic data based on the coordinates of the detection mark. [Claim 5] The image processing apparatus according to claim 4, further comprising control means for controlling the number of ink ejections based on the characteristic data. [Claim 6] The image processing apparatus according to claim 5, characterized in that the characteristic data consists of a correction table that correlates a correction amount for reducing density unevenness of the ink ejected from the recording element with the number of ink ejections. [Claim 7] The image processing apparatus according to claim 6, wherein the correction table comprises an input density and an output density corresponding to the input density, and the correction amount to the corresponding output density is set to different values ​​for the high density range and the low density range, which is a region with a density lower than the high density range, among the input density. [Claim 8] The image processing apparatus according to claim 1, characterized in that the difference between the contrast of the portion on the recording medium in which the ink has been ejected and the contrast of the portion on the recording medium in which the ink has not been ejected is smaller than a preset contrast. [Claim 9] The image processing apparatus according to claim 1, characterized in that the color of the ink is achromatic. [Claim 10] The ink is at least one of white ink and clear ink. The image processing apparatus according to claim 1, characterized in that the recording element further discharges a reaction liquid that increases the viscosity of the ink, in addition to the ink. [Claim 11] The image processing apparatus according to claim 1, characterized in that the image includes a gradation region in which multiple patterns of different densities are arranged in steps, and a detection mark region in which the detection marks are arranged. [Claim 12] The image processing apparatus according to claim 1, further comprising determination means for determining whether or not to correct the contrast of the image according to the difference between the contrast of the portion on the recording medium in which the ink has been ejected and the contrast of the portion on the recording medium in which the ink has not been ejected. [Claim 13] A conversion means for converting the aforementioned image data to a grayscale image, Distribution calculation means for calculating the distribution of pixel values ​​in a specified area of ​​the grayscale image, A threshold calculation means for calculating a threshold for classifying the mark distribution and the background distribution from the distribution of pixel values ​​in a specified area of ​​the image, The image processing apparatus according to claim 3, further comprising: [Claim 14] A first class including the aforementioned mark distribution is set, A second class is established that includes the aforementioned substrate distribution. Based on the variance of the first class and the variance of the second class, an intraclass variance representing the magnitude of the dispersion of the first and second classes is set. An inter-class variance is set, which represents the degree of dispersion between the first class and the second class. The image processing apparatus according to claim 13, characterized in that the generation means uses the pixel value at which the degree of separation obtained by the ratio of the intraclass variance to the interclass variance is maximized as the threshold value. [Claim 15] The image processing apparatus according to claim 14, characterized in that the generation means performs a binarization process of the image data based on the threshold. [Claim 16] The image processing apparatus according to claim 15, characterized in that the generation means determines the degree of separation within the range of the minimum pixel value and the maximum pixel value specified in the designated area. [Claim 17] The image processing apparatus according to claim 16, characterized in that the generation means performs the binarization process based on the difference between the pixel values ​​included in the image data and the threshold. [Claim 18] An acquisition step of acquiring image data obtained by reading an image formed on a recording medium using a recording element that ejects ink, A classification step that classifies the image into a mark distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​corresponding to the detection marks recorded by the ink, and a background distribution, which includes the pixel values ​​of the portion of the image's pixel values ​​where the ink has not been ejected, based on a histogram representing the distribution of pixel values ​​in a specified area of ​​the image. A generation step of generating characteristic data representing the density characteristics of the ink ejected from the recording element based on the mark distribution, An image processing method characterized by including [Claim 19] A program for causing a computer to perform each step of the image processing method described in claim 18. [Claim 20] An image processing apparatus according to any one of claims 1 to 17, and, A recording head having the recording element and ejecting the ink to form the image on the recording medium, An image forming system characterized by including the following. [Claim 21] An upstream scanning means that reads the aforementioned image and acquires it as upstream image data, A downstream scanning means is arranged in a staggered pattern relative to the upstream scanning means, and reads the image and acquires it as downstream image data. A synthesis means for combining the upstream image data and the downstream image data, The image forming system according to claim 20, further comprising:

Images