JP2020069717A - Image processing device, image formation apparatus, image processing method, image processing program and recording medium - Google Patents

Abstract

To provide an image processing device and the like which can increase the determination accuracy of the line number by adding not only a feature amount indicating the frequency of the concentration difference change between adjacent pixels but also a feature amount or concentration distribution indicating the degree of magnitude of the concentration difference change to the feature amount, perform image processing according to the determination result and output an image in which Moire is hardly perceived while keeping the sharpness.SOLUTION: An image processing device includes: an image data input unit which scans a document to input as image data; a determination unit which determines the line number of dots of the document on the basis of the image data feature amount including the first feature amount indicating the frequency of the concentration difference change between adjacent pixels of the image data and the second feature amount indicating the degree of magnitude of the concentration difference change of the image data; and an image processing unit which performs image processing on the image data in accordance with the determination result of the determination unit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an image processing device, an image processing method, and an image processing program, and to a method for determining the number of halftone dots based on image data in order to perform appropriate image processing on the image data.

  In addition to the conventional analog type, digital type is widely used as the image forming apparatus such as an electronic copying machine, and due to the progress of digital image processing technology, a full-color digital copying machine that reproduces a color image with high image quality is available. It has been commercialized.

  In a digital copying machine, the number of halftone dots (number of halftone dots) of a document is determined from the image data of the document read by the scanner of the image reading unit, and image processing is performed according to the determination result.

  In Patent Document 1, G image data of RGB data is input, a matrix of a predetermined size (for example, 3 × 3 pixels) is used to detect whether the central pixel is a peak pixel, and a predetermined region (for example, 20 × 9 pixels) is detected. If the number of peak pixels is large, the number of lines is determined to be high, and if it is small, the number of lines is determined to be low.

Japanese Unexamined Patent Publication No. 2008-078830 (Published April 3, 2008) Japanese Patent Laid-Open No. 2002-232708 (published on August 16, 2002) Japanese Patent Laid-Open No. 2000-354167 (Published December 19, 2000)

  However, if the number of lines is determined only by the feature amount indicating the frequency of light and shade change between adjacent pixels such as the number of peak pixels, paper quality, paper density, print quality, presence of show-through, etc. affect the number of inversions. To do. For example, even if the originals have the same number of lines, if the paper quality is poor, the print quality is poor due to the quality of the paper, the paper is a little dark instead of pure white, and there is show-through, etc. It tends to be blurred and the number of inversions tends to decrease. In that case, it is easy to determine that the document is a document with a low number of lines.

  Even if the originals have the same number of lines, the tendency of the number of times of inversion of the pixel values is different between the monochrome halftone dots and the mixed color halftone dots. For example, when the image data of the original read by the reading device is RGB data, the G image data is theoretically composed of only magenta having a complementary color relationship, but it is unnecessary due to the reading characteristics of the original in the reading device. Cyan, yellow, and black halftone dot components are also mixed. Therefore, the determination result changes depending on the configuration of the color mixture of halftone dots of the document.

  The present invention has been made in view of such circumstances, and adds not only a feature amount indicating the frequency of grayscale changes between adjacent pixels but also a feature amount and a density distribution indicating the magnitude of the grayscale change to the feature amounts. Thus, it is an object of the present invention to provide an image processing device or the like capable of increasing the accuracy of determining the number of lines, performing image processing according to the result of the determination, and outputting an image in which moire is hardly perceived while maintaining sharpness. To do.

In order to solve the above-mentioned problems, the image processing device of the present invention is
An image data input unit that scans a document and inputs it as image data,
The original document based on the image data characteristic amount including a first characteristic amount indicating a frequency of gradation change between adjacent pixels of the image data and a second characteristic amount indicating a magnitude of the gradation change of the image data. A determination unit for determining the number of lines of the halftone dots of
An image processing unit that performs image processing on the image data according to the determination result of the determination unit;
It is characterized by including.

The image processing method of the present invention is
An image data input step of scanning a document and inputting it as image data,
The original document based on the image data characteristic amount including a first characteristic amount indicating a frequency of gradation change between adjacent pixels of the image data and a second characteristic amount indicating a magnitude of the gradation change of the image data. A determination step of determining the number of lines of the halftone dot
An image processing step of performing image processing on the image data according to the determination result of the determination step;
It is characterized by including.

The image processing program of the present invention is
In the processor of the image processing device,
An image data input step of scanning a document and inputting it as image data,
The original document based on the image data characteristic amount including a first characteristic amount indicating a frequency of gradation change between adjacent pixels of the image data and a second characteristic amount indicating a magnitude of the gradation change of the image data. A determination step of determining the number of lines of the halftone dot of
An image processing step of performing image processing on the image data according to the determination result of the determination step;
Is executed.

The computer-readable recording medium of the present invention,
In the processor of the image processing device,
An image data input step of scanning a document and inputting it as image data,
The original document based on the image data characteristic amount including a first characteristic amount indicating a frequency of gradation change between adjacent pixels of the image data and a second characteristic amount indicating a magnitude of the gradation change of the image data. A determination step of determining the number of lines of the halftone dot of
An image processing step of performing image processing on the image data according to the determination result of the determination step;
An image processing program for executing is recorded.

  According to the image processing apparatus and the like of the present invention, by adding the feature amount indicating the magnitude of the change in shading to the parameter of the line number determination, it is possible to determine the paper quality, the density of the paper, the print quality, the presence or absence of show-through, and the like. The result of the number judgment is less likely to be affected. Therefore, by determining the number of lines based on only the feature amount that indicates the frequency of shade changes between adjacent pixels, the number of lines can be determined based on the paper quality, paper density, print quality, show-through, halftone dot color mixing configuration, etc. It is possible to prevent the result of (1) from being influenced.

It is a block diagram showing a schematic configuration of an image forming apparatus in the present embodiment. It is a block diagram showing a configuration of a document feature determination unit in the present embodiment. 6 is a flowchart showing a flow of processing in a document characteristic determination unit of the present embodiment. FIG. 6 is an explanatory diagram showing a method of setting an exclusion area to be excluded from the histogram generation target in the image data of the document. It is a figure which shows the operation example of the determination process which classifies the halftone frequency in the area pixel determination process. It is an example of a filter applied to a halftone dot area. FIG. 3 is a block diagram showing a schematic configuration of a part related to a scan output function of the image forming apparatus in the present embodiment. It is a figure which shows the example of the operation panel which sets the threshold value of a line number determination.

  Hereinafter, the present invention will be specifically described based on the drawings showing the embodiments.

  FIG. 1 is a block diagram showing a schematic configuration of an image forming apparatus 1 according to this embodiment. In the present embodiment, the case where the image forming apparatus 1 is an electrophotographic digital color copying machine will be described. However, the configuration of the image forming apparatus 1 is not limited to this, and image data of a document is imaged. Any device having a function of performing processing may be used.

  As shown in FIG. 1, the image forming apparatus 1 includes a color image input device 110, a color image processing device 120, a color image output device 130, an operation panel 140, and a control unit 100. Further, the color image processing apparatus 120 includes an A / D (analog / digital) conversion unit 11, a shading correction unit 12, a document feature determination unit 13, an input gradation correction unit 14, a region separation processing unit 15, a color correction unit 16, It includes a black generation undercolor removal unit 17, a spatial filter processing unit 18, an output gradation correction unit 19, and a gradation reproduction processing unit 20.

  The color image input device 110 inputs the image data of the original by reading the original and generating image data of the original. Then, the generated (input) image data is output to the color image processing device 120. The configuration of the color image input device 110 is not particularly limited as long as it is a configuration that can generate image data of a document, and various conventionally known image input devices can be used. For example, a scanner unit (not shown) having a CCD (Charge Coupled Device) is provided, and a reflected light image from a document is read by the CCD and RGB (R: red, G: green, B: blue) analog signals are read. It is also possible to use a configuration that generates image data consisting of

  The color image processing device 120 converts the image data input from the color image input device 110 into an A / D conversion unit 11, a shading correction unit 12, a document feature determination unit 13, an input gradation correction unit 14, and a region separation processing unit 15. The color correction unit 16, the black generation undercolor removal unit 17, the spatial filter processing unit 18, the output gradation correction unit 19, and the gradation reproduction processing unit 20 are sequentially sent, and finally CMYK (C: cyan, M: magenta). , Y: yellow, K: black), and outputs the image data represented by digital color signals to the color image output device 130.

  The A / D converter 11 converts the image data of analog signals corresponding to each of RGB into image data of digital signals.

  The shading correction unit 12 performs various distortions on the image data of the digital signal corresponding to RGB sent from the A / D conversion unit 11 in the illumination system, the imaging system, and the imaging system of the color image input device 110. Is removed. Further, the shading correction unit 12 adjusts the color balance.

  The document characteristic determination unit 13 converts the RGB signal (the RGB reflectance signal) for which the various distortions have been removed by the shading correction unit 12 and the color balance has been adjusted, into a density signal. Further, the document feature determination unit 13 (i) a document type determination process for determining whether the document is a character document, a print photo document, a character print photo document in which characters and print photos are mixed, and ( ii) A background determination process is performed to determine whether or not the document is a background removal process. In the document type determination process, a line number determination process is performed to determine the number of halftone dots printed on the document. Then, the document characteristic determination unit 13 generates a document characteristic determination signal indicating the result of the document type determination process, and the input tone correction unit 14, the color correction unit 16, the black generation undercolor removal unit 17, and the spatial filter processing unit 18 are generated. , And the gradation reproduction processing unit 20. The input gradation correction unit 14, the color correction unit 16, the black generation undercolor removal unit 17, the spatial filter processing unit 18, and the gradation reproduction processing unit 20 perform image processing on the image data in accordance with the document characteristic determination signal. .. The details of the document characteristic determination unit 13 will be described later.

  The input tone correction unit 14 performs background density removal and image quality adjustment processing such as contrast.

  In other words, the colors of the background (paper on which characters, etc. are printed) of the original are various, and depending on the background color, the white background (background) should be treated as white (or colorless), and the recording material (toner or ink). May be used extra. For example, when forming an image of a yellowish document such as straw paper or a document with a colored background in monochrome mode, if the background color is not treated as white, the recording material will be printed on the white background (background) when the image is output. Will be used. Therefore, in order to suppress the use of an extra recording material, the input tone correction unit 14 performs the background density removal process (that is, the process of changing the background density to a white density) and the contrast Perform adjustment processing.

  The input tone correction unit 14 also divides the image data including RGB density signals (hereinafter, RGB signals represent density signals (signals representing pixel values) unless otherwise specified) into area separation processing units. Output to 15.

  The area separation processing unit 15 determines each pixel in the image data output from the input tone correction unit 14 based on the RGB density signal as a background region, a photograph region (continuous tone region), a character region, and a halftone dot region. Region separation processing is performed to determine which of the two belongs to. Further, the area separation processing unit 15 generates an area identification signal indicating which area each pixel belongs to, based on the result of the area separation processing, and the color correction unit 16, the black generation undercolor removal unit 17, and the space. The RGB signal input from the input tone correction unit 14 is output to the color correction unit 16 in the subsequent stage as it is while being output to the filter processing unit 18 and the tone reproduction processing unit 20.

  The color correction unit 16 converts the RGB signal input from the area separation processing unit 15 into a CMY signal according to the area identification signal input from the area separation processing unit 15. In addition, the color correction unit 16 performs a process of removing color turbidity based on the spectral characteristics of the CMY color materials including unnecessary absorption components in order to realize faithful color reproduction.

  The black generation undercolor removal unit 17 subtracts the black generation process for generating a black (K) signal from the CMY signal after the color correction by the color correction unit 16 and the K signal obtained by the black generation process from the original CMY signal. Undercolor removal processing for generating new CMY signals is performed. As a result, the CMY signals are converted into CMYK four-color signals (hereinafter referred to as CMYK signals).

For example, the black generation undercolor removal unit 17 performs black generation by skeleton black as the black generation processing. In the black generation processing using this skeleton black, the input / output characteristics of the skeleton curve are set to y = f (x), and the densities corresponding to the C signal, M signal, and Y signal of the input CMY signal are respectively C, M, and Let Y be the C, M, Y and K densities of the C, M, Y and K signals of the CMYK signal that are output, and C ′, M ′, Y ′ and K ′ respectively, and the UCR (Under Color Removal) rate to be α. If (0 <α <1),
K '= f {min (C, M, Y)}
C '= C-αK'
M '= M-αK'
Y '= Y-αK'
The CMY density signals of three colors are converted into CMYK density signals of four colors.

  The spatial filter processing unit 18 corrects the spatial frequency characteristic of the image data of the CMYK signals input from the black generation and undercolor removal unit 17 to prevent blurring of the image data and deterioration of graininess. Spatial filter processing is performed by a digital filter that is preset for each type of area according to the area identification signal input from the separation processing unit 15. The details of the spatial filter processing unit 18 will be described later.

  The output gradation correction unit 19 performs output gradation correction processing on the image data of the CMYK signals input from the spatial filter processing unit 18 based on the output characteristics of the color image output device 130.

  The gradation reproduction processing unit 20 determines the image data of the CMYK signals input from the output gradation correction unit 19 in advance for each type of area according to the area identification signal input from the area separation processing unit 15. Perform the specified treatment.

  For example, with respect to the area separated into the character area by the area separation processing unit 15, the spatial filter processing unit 18 increases the high frequency emphasis amount by the sharpening emphasis process in order to particularly improve the reproducibility of the black character or the color character. The gradation reproduction processing unit 20 performs binarization or multi-value conversion processing on a high resolution screen suitable for reproduction of high frequency.

  Further, with respect to the areas separated into the halftone areas by the area separation processing section 15, the spatial filter processing section 18 performs a low-pass filter processing for removing the input halftone dot components, and the gradation reproduction processing section 20 respectively. A gradation reproduction process (halftone generation) is performed so that the gradation of a pixel can be reproduced.

  Further, with respect to the area separated into the photographic area (continuous gradation area) by the area separation processing unit 15, the gradation reproduction processing unit 20 performs binarization or multi-value conversion processing on the screen with an emphasis on gradation reproducibility. To do.

  The image data output from the tone reproduction processing unit 20, that is, the image data that has been subjected to each of the above-described processes is temporarily stored in a storage unit (not shown) and is read at a predetermined timing to be read by a color image output device. It is output to 130.

  The color image output device 130 outputs an image corresponding to the image data to a recording medium (for example, a sheet body such as paper). The color image output device 130 forms an image on a recording medium using a recording material having two or more colors (four colors of C, M, Y, and K in this embodiment). In this embodiment, an electrophotographic printer device is used as the color image output device 130. However, the configuration of the color image output device 130 is not limited to this, and a printer device of another system such as an inkjet system may be used.

  The operation panel 140 receives an instruction input from the user and transmits it to the control unit 100. The operation panel 140 is configured to include, for example, a display unit such as a liquid crystal display and operation keys that receive a user's operation input. Alternatively, the operation panel 140 may be a touch panel.

  The control unit 100 includes an arithmetic processing unit such as a CPU (Central Processing Unit) and a dedicated processor, and a storage unit such as a RAM (Random Access Memory), a ROM (Read Only Memory), and an HDD (Hard Disk Drive). It is a computer device configured by (not shown) or the like. The control unit 100 includes various programs stored in the storage unit and programs for executing various controls, user instructions input via the operation panel 140, and various sensors provided in the image forming apparatus 1. The operations of the color image input device 110, the color image processing device 120, the color image output device 130, and the operation panel 140 are controlled according to the detection result of the above.

(Details of manuscript feature determination section)
Details of the document characteristic determination unit 13 will be described. FIG. 2 is a block diagram showing the configuration of the document characteristic determination unit 13, and FIG. 3 is a flowchart showing the flow of processing in the document characteristic determination unit 13.

  As shown in FIG. 2, the document feature determination unit 13 includes a pixel determination unit 1301, a region pixel count unit 1302, a data selection unit 1303, a histogram generation unit 1304, a background determination unit 1305, a document type determination unit 1306, and a background removal unit. 1307 is provided.

  In the document characteristic determination unit 13, as shown in FIG. 3, first, the pixel determination unit 1301 determines each pixel of the RGB signal (image data) input from the shading correction unit 12 as a background pixel, a photographic pixel (continuous tone pixel). ), A region pixel determination process for classifying the pixel as either a character pixel or a halftone dot pixel is performed (S1). In the following description, the pixels classified into the background pixels, the photographic pixels (continuous tone pixels), the character pixels, and the halftone pixels are referred to as area pixels.

  The algorithm for classifying into region pixels is not particularly limited, and an existing region separation method can be used. For example, the method described in Patent Document 2 may be used. In this method, the area pixel determination process is performed by the following processes (1) to (8).

(1) The minimum density value and the maximum density value in an n × m (for example, 7 pixels × 7 pixels) pixel block including the target pixel are calculated.
(2) The maximum density difference is calculated using the calculated minimum density value and maximum density value.
(3) The total density busyness (for example, the sum of the values calculated in the main scanning direction and the sub scanning direction) that is the sum of the absolute values of the density differences of the pixels adjacent to the pixel of interest is calculated.
(4) The calculated maximum density difference is compared with the maximum density difference threshold, and the calculated total density busyness is compared with the total density busyness threshold.
(5) When maximum density difference <maximum density difference threshold and total density busyness <total density busyness threshold, it is determined that the pixel of interest belongs to the base / photo area (continuous tone area).
(6) If the above conditions are not satisfied, it is determined that the pixel of interest belongs to the character / dot area.
(7) Regarding the pixel determined to belong to the background / photo area (continuous tone area), when the target pixel satisfies the maximum density difference <the background / photographic paper determination threshold value, it is determined to be the background pixel, and this condition is satisfied. When is not satisfied, it is determined that the pixel is a photographic pixel (continuous tone pixel).
(8) When the pixel of interest determined to belong to the character / halftone dot region satisfies the condition of the total density busyness <(value obtained by multiplying the maximum density difference by the character / halftone dot determination threshold), the character pixel If the above condition is not satisfied, it is determined that the pixel is a halftone dot pixel.
Further, in the area pixel determination processing, pixel classification processing for determining the halftone dot frequency of the document is also performed. Details will be described later.

  The area pixel determination process may be performed using, for example, prescanned image data, or may be performed using image data once stored in a storage unit such as a hard disk.

  Next, the area pixel count unit 1302, based on the result of the area pixel determination processing by the pixel determination unit 1301, for each type of area pixel (base pixel, photographic pixel (continuous tone pixel), character pixel, and halftone pixel). Region pixel count processing for counting the number of classified pixels (region pixels) is performed for each region pixel of point pixels. The number of halftone dot classification results is also counted (S2).

  Next, the data selection unit 1303 separates the image region based on the RGB signals input from the shading correction unit 12 into a target region to be a target of a histogram generation process described later and an exclusion region to be excluded from a target of the histogram generation process. Region selection processing is performed (S3). That is, in this embodiment, the histogram generation is performed not for all the pixels of the input image, but for a part of the pixels.

  FIG. 4 is an explanatory diagram showing a method of setting an exclusion area to be excluded from the histogram generation target in the image data of the document.

  The image data of the original read by the color image input device 110 is processed by the shading correction unit 12 to remove various distortions generated in the illumination system, the imaging system, and the imaging system of the color image input device 110. The appropriate correction is not performed for all the areas of. For example, when a document is read by the color image input device 110, the region of the document located at the end of the document table (document end region) may be a relatively dark signal.

  In view of this, in the present embodiment, as shown in FIG. 4, the data selection unit 1303 is located at the edge of the glass surface of the document table of the color image input device 110 during image reading of the document image data. The image data of the area of the predetermined range is excluded from the target area of the histogram generation, and the other areas are set as the target area of the histogram generation.

  The predetermined range is not particularly limited and may be set as appropriate. For example, in the void area of the document, a portion adjacent to the edge of the glass surface of the document table at the time of reading the document is a target of histogram generation. May be excluded from. The void area is an area in which nothing is printed, which exists in a width of about several mm (for example, about 4 mm) from the edge (peripheral edge) of the document printed or copied by the printer.

  Next, the histogram generation unit 1304 belongs to an area of the RGB signals input from the shading correction unit 12 that is determined as a background pixel in the area pixel determination processing and is determined as a histogram generation target area in the area selection processing. A pixel is extracted as a pixel of interest, and histogram generation processing (minimum value histogram generation processing) is performed (S4).

  Specifically, the histogram generation unit 1304 compares the target pixel for each plane (for each color component), calculates the minimum value between the color components of the target pixel, and selects among the plurality of preset density categories. , 1 is added to the frequency of the density category to which the calculated minimum value belongs. In the present embodiment, the number of density sections of the histogram is set to the first density section and the second density section in order of increasing pixel value (density value), and the section having the largest pixel value is set as the 32nd density section. It is set as a division. In the present embodiment, since RGB signals are used, the closer the pixel value (density value) is to “0” (the smaller the density value is), the higher the actual density is, and the pixel value (density value) is “0”. The closer to "255" (the higher the density value), the lighter the density (lighter).

  Note that the histogram is created using the minimum value between the color components when the density value of the darkest color component of the background (color component having the minimum density value) is used as the background density and the correction corresponding to the density value is performed. This is because by applying the quantity table to all the color components and performing the background removal processing, the background removal can be performed for the color components other than the darkest color component.

  After that, the document characteristic determining unit 13 determines whether or not the processes of S1 to S4 have been performed for all the pixels (S5), and when there are unprocessed pixels, the process returns to the process of S1 and unprocessed. The processing of S1 to S4 is performed on the pixel.

  On the other hand, if it is determined in S5 that the processes of S1 to S4 have been completed for all pixels, the background determination unit 1305 performs background determination processing for determining whether or not to perform background removal (S6).

  After performing the background determination process in S6, the document type determination unit 1306 performs the document type determination process (S7).

  Specifically, the document type determining unit 1306 determines the number of area pixels counted by the area pixel counting unit 1302, and a predetermined background area, photo area (continuous tone area), halftone dot area, and character area. The type of the entire document is determined by comparing the threshold values corresponding to each other.

  For example, if the detection accuracy is high in the order of characters, halftone dots, and photographs (continuous tone), and if the ratio of pixels in the character region is 30% or more of the total number of pixels, it is determined to be a character original, and the halftone dot region is determined. When the ratio of pixels is 20% or more of the total number of pixels, it is determined to be a halftone dot original (printed photo original), and the ratio of pixels of the photo area (continuous tone area) is 10% or more of the total number of pixels. In the case of, it is determined that it is a photographic paper photograph original. Further, when the ratio of the character area and the ratio of the halftone area are equal to or more than the respective thresholds, it is determined that the character / halftone original (character printed photo original). When the ratio of the character area and the ratio of the photograph area (continuous tone area) are equal to or more than the threshold values, it is determined that the character / photo document (character photographic paper photo document).

  Further, the number of halftone dots printed on the original is determined. The details will be described later.

  The original document type determination unit 1306 outputs an original document characteristic determination signal indicating the determination result of the original document type to a background removal unit 1307, an input tone correction unit 14, a color correction unit 16, a black generation undercolor removal unit 17, a spatial filter processing. It is output to the unit 18 and the gradation reproduction processing unit 20.

  Next, the background removal unit 1307 determines whether or not the document is the one for which the background removal is to be performed, based on the determination result of the document type by the document type determination unit 1306 (S8). That is, the background removal unit 1307 determines whether the document type determined by the document type determination unit 1306 is a preset type as the document type for which the background removal should be performed.

  For example, as a document for which background removal is performed, a character document, a document that does not include a photo region (continuous tone region), or a character / dot document (character printed photo document) with a small halftone dot area ratio (for example, a halftone area) May be set to 40% or less of the entire document).

  If it is determined in S8 that the original is not to be subjected to background removal, the original document feature determination unit 13 ends the process without performing background removal.

  On the other hand, if it is determined in S8 that the original is to be subjected to background removal, the background removal unit 1307 performs background removal processing (S9) and ends the processing.

  The method of the background removal process is not particularly limited, and an existing background removal method can be used.

  For example, the base removal may be performed using the method described in Patent Document 3. In this method, when it is determined that the background is the background, the correction amount table corresponding to the background density value is selected and the background removal processing is performed. When the histogram is created using the minimum value for each plane (for each color component) of the background pixel, the correction amount table corresponding to the minimum value for all color components may be selected to perform the background removal process.

(Pixel classification processing for determining the number of halftone dots of the original in the area pixel determination processing)
The pixel classification process for the halftone dot frequency determination of the document in the area pixel determination process (S1) executed by the pixel determination unit 1301 will be described. For each color component of the RGB image, in the n × m (for example, 7 pixels × 7 pixels) pixel block including the pixel of interest (hatched center pixel in FIG. 5), the two directions shown in FIG. On the other hand, when the density difference between adjacent pixels exceeds the adjacent pixel density difference threshold value, it is determined to be a rising pixel or a falling pixel, and the determined number of pixels is counted as the number of inversions. However, consecutive rising pixels and falling pixels are not counted. The adjacent pixel density difference threshold is determined based on an average value in an n × m (for example, 5 pixels × 5 pixels) pixel block including the target pixel. If the average value is the first predetermined value (eg, 100) or more, the adjacent pixel density difference threshold value is TH1 (eg, 50), and the average value is less than the first predetermined value and the second predetermined value (eg, 70) or more. For example, the adjacent pixel density difference threshold is TH2 (for example, 33), and if the average value is less than the second predetermined value, the adjacent pixel density difference threshold is for TH3 (for example, 15). Adjacent pixel density difference thresholds that count rising pixels or falling pixels depending on the average value in the pixel block are different between the darker pixel and the lighter pixel depending on whether they are dark or light on average. This is because the difference in shade is different. Since the density difference between the darker pixel and the lighter pixel tends to be smaller in the darker portion on average than in the lighter portion, the average value is divided into three and the adjacent pixel density difference threshold value is determined for each. ing. Although the average value is divided into three here, the average value is not necessarily limited to three and the number of divisions may be four or more.

  The maximum value of the inversion number count value of each component of RGB is obtained, and if the maximum value is equal to or larger than the first inversion number threshold value (for example, 30), the first line number pixel, less than the first inversion number threshold value and the second inversion number If it is equal to or more than the threshold value (for example, 15), it is determined to be the second line number pixel, and if it is less than the second inversion number threshold value, it is determined to be the third line number pixel. Here, the number of times of inversion is determined by dividing it into three, but the number of divisions is not necessarily limited to three, and the number of divisions may be four or more. The classification of the number of inversions is performed in the halftone dot area. Since it is performed to determine the number of lines, it may be limited to the pixels determined in the halftone dot area.

(Details of the line number judgment in the document type judgment process)
The line number determination for determining the number of lines of the document in the area pixel determination process (S7) executed by the document type determination unit 1306 will be described. The following count value and histogram frequency are used to determine the number of halftone dots printed on the document. The number of pixels in the halftone dot area (scr0), the number of pixels in the first number of lines (scr1), the number of pixels in the second number of lines (scr2), which is the result of counting the pixels determined to be halftone dots by the area pixel count unit 1302, 3 line number pixel number (scr3), histogram target pixel number in the histogram generation unit 1304 (bgcnt), histogram 16th division frequency (hst16), histogram 17th division frequency (hst17), ..., Histogram 31st division frequency (hst31) To use.

  A feature amount (image data feature amount) related to image data is calculated from the count value and the histogram frequency (S71). For example, the ratio of the first number of lines pixels (scr1) to the number of halftone dot regions (scr0), the ratio of the second number of lines pixels (scr2) to the number of halftone dot regions (scr0), the third number of pixels Based on the ratio of (scr3) to the number of halftone dot pixels (scr0), a feature amount (first feature amount) indicating the frequency of grayscale changes in adjacent pixels is calculated. Further, the ratio of the histogram 16th segment frequency (hst16) to the histogram target pixel number (bgcnt), the ratio of the histogram 17th segment frequency (hst17) to the histogram target pixel number (bgcnt), ..., The 31st segment frequency (hst31) Based on the ratio to the number of pixels (bgcnt) subject to the histogram of (1), the feature amount (second feature amount) indicating the magnitude of the grayscale change of the pixel in the base pixel is calculated. On the basis of these feature amounts, a halftone dot line number determination process is performed to determine whether the document has a high line number or a low line number (S72).

  Even if the number of lines of halftone dots is constant in one document, the number of inversions of light and shade in the mask does not become constant. Further, the quality of paper, the density of paper, the print quality, the presence / absence of show-through, and the like influence the number of times of light and shade inversion. Therefore, the feature amount of the frequency of the number of times of light and shade inversion is increased and the density distribution is added to the feature amount.

  The number of high lines and the number of low lines may be determined by machine learning based on these feature amounts. For example, these feature quantities are input in advance into a mathematical formula based on the learning result of the support vector machine. The support vector machine sets a learning signal having a binary value indicating the number of high lines or the number of low lines as a set to the group of these feature quantities and makes them learn. For example, a set of feature amounts of 500 originals desired to be judged with a high number of lines is prepared, and the teacher signal of these sets is set to 1. A set of feature amounts of 500 originals that should be judged to have a low line count is prepared, and the teacher signals of these sets are set to zero. A set of feature amounts of these 1000 originals and a teacher signal are set as a set for learning. It should be noted that whether the high frequency or the low frequency is not necessarily divided depending on whether or not the predetermined frequency is greater than or equal to the predetermined frequency, and when a high frequency filter is applied to the filter of the halftone dot area of the spatial filter processing unit 18, image quality becomes a problem. You may divide by whether or not appears.

なお、ｘ以外は予め学習結果により求められているものである。ｘ_ｎは１０００組の特徴量から抽出されたＮ組のサポートベクター、ａ_ｎはＮ組のサポートベクターそれぞれに対する重み、ｔ_ｎはＮ組のサポートベクターそれぞれの教師信号、ｂはバイアスと呼ばれ決定境界の位置を表すパラメータである。ｋ（ｘ，ｘ_ｎ）は、学習時にも用いる動径基底関数カーネルというもので、以下の式で定義される。

γは、学習時にも用いるパラメータである。 Based on the learning result, a vector of a set of feature quantities is input, and the number of high lines and the number of low lines are determined by the following mathematical formula (discrimination function).

It should be noted that the values other than x are obtained in advance based on the learning result. x _n is N sets of support vectors extracted from 1000 sets of feature quantities, a _n is a weight for each of the N sets of support vectors, t _n is a teacher signal for each of the N sets of support vectors, and b is a bias. This is a parameter that represents the position of the boundary. k (x, _xn ) is a radial basis function kernel used also at the time of learning, and is defined by the following formula.

γ is a parameter used also during learning.

  The output result of the calculated y (x) becomes the determination result. If y (x) ≧ 0, the number of lines is high, and if y (x) <0, the number of lines is low.

  The number of high lines and the number of low lines may be determined by a machine learning method other than the support vector machine. For example, the number of high lines and the number of low lines may be determined by inputting the feature amount into a mathematical expression learned by a technique such as a decision tree or a neural network (deep learning).

(Details of the spatial filter processing unit 18)
Details of the spatial filter processing unit 18 will be described. FIG. 6 is an example of a filter applied to a halftone dot area. The filter applied to the halftone dot area is different depending on whether the result of the line number determination is a high line number or a low line number. The halftone dot area determined to have a high number of lines is processed to have a higher degree of enhancement and a lower smoothness than the halftone dot area determined to have a low number of lines. In other words, the halftone dot area when the number of lines is determined to be low is subjected to processing in which the degree of enhancement is weaker and the smoothness is stronger than the halftone dot area when determined to be of high line number. FIG. 6A shows the filter coefficient of the halftone dot region when the number of high lines is determined, and FIG. 6B shows the filter coefficient of the halftone dot region when the number of low lines is determined.

  As a result, the image data of the document determined to have a high number of lines can be output as an image with high sharpness without causing moire, which is a problem of image quality, in the halftone dot area. Characters that are erroneously recognized in the halftone dot area and characters on the halftone dot can be output clearly and easily. The image data of a document determined to have a low number of lines can be output without causing moire, which is a problem of image quality, although the sharpness of the halftone dot area is not high.

(Example of having multiple input means)
The color image input device 110 is provided with a document table and a document feeding device, means for placing a document on the document table and moving the CCD to read the document, and a document feeding device for feeding the document while the CCD is fixed. It may have a reading means.

  The image data of a document read by the document feeding device tends to cause a deviation between RGB images as compared with the image data read by a document table. Therefore, an identification function for reading with the document table and an identification function for reading with the document feeder are prepared separately, and the feature amount is input to the identification function corresponding to each input means. Determine the number of lines.

  Further, when the document feeder has a means for reading both sides simultaneously, the reading method may be different between the front side and the back side. The front side may be read by the CCD and the back side may be read by a CIS (Contact Image Sensor).

  The color output characteristics and the sharpness do not match between the front side CCD reading and the back side CIS reading. Therefore, a discrimination function for reading on the front side of the document feeder and a discrimination function for reading on the back side of the document feeder are prepared separately, and the feature amount is input to the discrimination function corresponding to each case. Determine the number of lines.

  Of course, each discriminant function is based on the result of learning a set of feature amounts obtained by reading an original with each input means using machine learning (for example, support vector machine) as a teacher signal and a set. To do.

  As a result, an appropriate line number determination result can be output regardless of which color image input device 110 is read.

(Example of having multiple input resolutions)
The input resolution may differ depending on the process instructed by the user. For example, the user may be able to select input by main scanning 600 dpi and sub-scanning 600 dpi that prioritize image quality and input by main scanning 600 dpi and sub-scanning 400 dpi that prioritize speed.

  Even for the same document, the number of times of reversal is different between input by main scanning 600 dpi and sub-scanning 600 dpi and input by main scanning 600 dpi and sub-scanning 400 dpi, that is, the feature amount input to the discrimination function is also different. .. Therefore, the number of lines is determined by the discrimination function for each of the input of main scanning 600 dpi and sub-scanning 600 dpi, and the input of main scanning 600 dpi and sub-scanning 400 dpi.

  As a matter of course, each discriminant function is based on the result of learning a set of feature amounts obtained by reading an original at each input resolution into a teacher signal and a set.

  As a result, an appropriate line number determination result can be output regardless of which input resolution is read.

(Example of having monochrome output / color output)
In the case of copy output, moire may appear due to the shift of the halftone dot period of the document, the period due to the input resolution, and the period due to the dither processing of the tone reproduction processing unit 20. Note that the original is read by RGB signals, but the dither processing of the gradation reproduction processing unit 20 is processed only by K (black) signals for monochrome output, and CMYK (C: cyan, M: magenta) for color output. , Y: yellow, K: black) signals. Therefore, if the same dither processing as that for the K (black) signal for color output is used for the dither processing for monochrome output, moire tends to appear relatively little. Therefore, the number of lines is determined by the respective discrimination functions for monochrome output and color output.

  Of course, each discriminant function is based on a result obtained by learning a set of feature amounts obtained by reading an original by monochrome output and color output by a teacher signal and a set.

  As a result, it is possible to output appropriate line number determination results for monochrome output and color output.

(Example of having multiple gradation reproduction settings)
In the case of copy output, moire may appear due to the shift of the halftone dot period of the document, the period due to the input resolution, and the period due to the dither processing of the tone reproduction processing unit 20. Therefore, the dither processing of the gradation reproduction processing unit 20 can be selected from two types having different cycles. Different dithering will produce different moire. Moire is relatively easy to appear when the cycle is rough due to the dither processing, and is relatively hard to appear when the cycle is fine due to the dither processing. Therefore, the number of lines is determined by using the respective discrimination functions for the coarse-cycle dither processing and the fine-cycle dither processing.

  The gradation reproduction setting of the gradation reproduction processing unit 20 may be selectable from two types of dither processing and error diffusion processing. The error diffusion process itself has no periodicity, and the moire appears only in the halftone dot period of the document and the period depending on the input resolution. Therefore, the moire is relatively unlikely to appear in comparison with the dither process. Therefore, the number of lines is determined by the discrimination functions for dither processing and error diffusion processing.

  Of course, each discriminant function is a set of feature amounts obtained by reading a document for coarse dither processing and fine dither processing, or for dither processing and error diffusion processing, as a teacher signal. It depends on the result of learning the set. In addition, it goes without saying that gradation reproduction settings other than those described above may be provided.

  Accordingly, when a plurality of gradation reproduction settings are provided, it is possible to output an appropriate line number determination result based on the selected gradation reproduction setting.

(For scan output)
FIG. 7 is a block diagram showing a schematic configuration of a portion related to the scan output function when the image forming apparatus 1 of FIG. 1 has the scan output function.

  As shown in FIG. 7, a color image input device 110, a color image processing device 120, an operation panel 140, and a control unit 100 are provided. The color image processing apparatus 120 also includes an A / D conversion unit 11, a shading correction unit 12, a document feature determination unit 13, an input tone correction unit 14, a region separation processing unit 15, a color correction unit 16, and a spatial filter processing unit 18. An output gradation correction unit 19 is provided.

  The color image input device 110, the operation panel 140, and the control unit 100 are the same as the operation panel 140 and the control unit 100 in the image forming apparatus 1 of FIG.

  The A / D conversion unit 11, the shading correction unit 12, the input gradation correction unit 14, and the area separation processing unit 15 in the color image processing apparatus 120 are the A / D of the color image processing apparatus 120 in the image forming apparatus 1 in FIG. Since the conversion unit 11, the shading correction unit 12, the input gradation correction unit 14, and the area separation processing unit 15 are similar to each other, the description thereof will be omitted.

  The original document feature determination unit 13 performs the same process as the original document feature determination unit 13 of the color image processing apparatus 120 in the image forming apparatus 1 of FIG. Make a number decision.

  In the case of scan output, since the dither processing of the gradation reproduction processing unit 20 is not performed, moire is relatively unlikely to appear as compared with copy output. Therefore, the criterion for determining the high line number or the low line number may be different from that for the copy output. Therefore, the number of lines is determined by the discriminant function for scan output separately from the one for copy output.

  Of course, the discriminant function for scan output is based on the result of learning the set of feature quantities for scan output as a set with the teacher signal.

  The color correction unit 16 differs from the color correction unit 16 of the color image processing apparatus 120 in the image forming apparatus 1 of FIG. 1 in that the RGB signal input from the area separation processing unit 15 is an area input from the area separation processing unit 15. According to the identification signal, it is converted into an RGB signal.

  The spatial filter processing unit 18 differs from the spatial filter processing unit 18 of the color image processing apparatus 120 in the image forming apparatus 1 of FIG. 1 in that the spatial frequency characteristic is applied to the image data of the RGB signal input from the color correction unit 16. In order to prevent blurring of the output image and deterioration of graininess by the correction, spatial filtering processing by a digital filter preset for each area type is performed according to the area identification signal input from the area separation processing unit 15. To do.

  The output tone correction unit 19 differs from the output tone correction unit 19 of the color image processing apparatus 120 in the image forming apparatus 1 of FIG. Tone correction processing is performed.

ａは正の数で、例えば、ａ＝１で良い。 (When the user can change the threshold for judging the number of halftone dots)
The discriminant function output value y (x) is input to the sigmoid function.

a is a positive number, for example, a = 1.

  As a result, the discriminant function passing through the sigmoid function is output with a value larger than 0 and smaller than 1. If the threshold value is thl, the high line number is determined if f (y (x)) ≧ thl, and the low line number is determined if f (y (x)) <thl.

When differentiating the discriminant function according to various conditions, by passing this sigmoid function,
The output values can be unified so that they fall within the range of 0 to 1.

  The operation panel 140 can change the threshold value according to an instruction input from the user.

  FIG. 8 is an example (display example) of the operation panel 140 for setting the threshold value for determining the number of lines. One of five steps can be set, and the threshold value thl = 0.5 corresponds to the initial setting in step 3. If the setting is changed to step 2 or step 1, the number of lines is more likely to be determined, and if the setting is changed to step 4 or step 5, the number of lines is more likely to be determined. The threshold value thl = 0.9 in step 1, the threshold value thl = 0.7 in step 2, the threshold value thl = 0.3 in step 4, and the threshold value thl = 0.1 in step 5. You may input the numerical value of a step | step with an operation key, and you may touch the position of each step | step with a touch panel. Further, the threshold may be set more finely. You may make it possible to input a numerical value directly as a value from 0 to 1.

  As described above, according to the present embodiment, when the number of lines is conventionally determined only by the characteristic amount indicating the frequency of the light and shade change between the adjacent pixels, the paper quality, the density of the paper, the print quality, the presence / absence of show-through, and the color mixture of halftone dots. However, by adding a feature quantity indicating the degree of change in shading to the parameter of line number judgment, the quality of paper, density of paper, print quality, presence or absence of show-through, etc. Therefore, the result of the line number determination is less likely to be affected.

  Further, in the present embodiment, at least one of the feature amount indicating the frequency of the grayscale change between adjacent pixels or the feature amount indicating the magnitude of the grayscale change is a plurality of feature amounts. As a result, when it is difficult to capture the features of halftone dots with only one feature amount indicating the frequency of grayscale changes between adjacent pixels and one feature amount indicating the magnitude of the grayscale changes, there are multiple types. By doing so, it is possible to make an accurate determination.

  In addition, the number of lines of the halftone dots can be accurately determined by limiting the calculation of the feature amount indicating the frequency of the grayscale change between the adjacent pixels to the pixels determined as the halftone dot area pixels.

  Further, by including the feature amount indicating the density distribution in the feature amount indicating the magnitude of the grayscale change, it is possible to make the determination more accurately.

  In addition, by performing a spatial filter process according to the line number determination result as the image process for the image data, it is possible to output an image in which moire is hardly perceived while maintaining sharpness.

  In addition, as the determination of the number of lines, a human determines the threshold value of the determination by determining the number of lines of the halftone dots of the document based on the output value obtained by inputting the image data feature amount into a mathematical expression using the result of machine learning. It is possible to make the determination more accurately than the determination by setting the or boundary.

  This machine learning may be a support vector machine. Since the support vector machine is a relatively simple calculation in machine learning, it can process copy output and scan output without delay.

  Further, when a plurality of image data input means are provided, the original document network is determined by the output value obtained by inputting the image data feature amount into the mathematical expression using the machine learning result corresponding to the input means to which the image data is input. Determine the number of lines of a point. As a result, it is possible to make an accurate determination according to the image data input means.

  Further, when the image data input unit has a plurality of image input resolution settings, a mathematical expression using the result of machine learning corresponding to the image input resolution setting, based on the output value obtained by inputting the image data feature amount, The number of halftone dots on the original is determined. As a result, it is possible to make an accurate determination according to the image input resolution.

  Further, the number of lines of the halftone dots of the original is determined based on the output value obtained by inputting the image data feature amount in the mathematical expression using the result of machine learning corresponding to the output format of the image data. For example, when the output formats are copy output and scan output, it is possible to output an image in which moire is hardly perceived while maintaining the sharpness of each of copy output and scan output.

  Further, the apparatus is provided with a gradation reproduction unit having a plurality of gradation reproduction settings, and based on an output value obtained by inputting the image data feature amount into a mathematical expression using the result of machine learning corresponding to the gradation reproduction setting, Determine the number of halftone dots. As a result, even if the gradation reproduction setting is changed, it is possible to output an image in which moire is hardly perceived while maintaining sharpness.

  Also, based on the output value obtained by inputting the image data feature amount into the mathematical expression using the machine learning result corresponding to either monochrome output or color output, the number of lines of the halftone dot of the document is calculated. judge. As a result, it is possible to output an image in which moire is hardly perceived while maintaining the sharpness of each of monochrome output and color output.

  Also, by allowing the user to change the threshold value for determining the halftone frequency with respect to the output value of the mathematical expression using the result of machine learning, it is easy to determine the high frequency according to the preference of the user. Or, on the contrary, it is possible to make it easier to determine a low number of lines.

  The image processing apparatus according to each aspect of the present invention may be realized by a computer. In this case, an image processing program that causes the computer to operate as the document feature determination unit 13 causes the computer to realize the image processing apparatus. Also, a computer-readable recording medium recording the same is also included in the scope of the present invention.

  The present invention is not limited to the embodiments described above, and various modifications can be made within the scope of the claims. That is, an embodiment obtained by combining technical means appropriately modified within the scope of the claims is also included in the technical scope of the present invention.

(Processing by software)
The control block of the color image processing apparatus 120 of FIG. 1 and FIG. 7 (particularly the document feature determination section 13) may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or a CPU. May be realized by software.

  In the latter case, the color image processing apparatus 120 includes a CPU that executes instructions of a program that is software that implements each function, a ROM or a storage device (on which a computer (or CPU) stores the program and various types of data readable by the computer (or CPU)). These are referred to as “recording medium”), and a RAM for expanding the above program is provided. Then, the computer (or CPU) reads the program from the recording medium and executes the program to achieve the object of the present invention. As the recording medium, a “non-transitory tangible medium”, for example, a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. The program may be supplied to the computer via any transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program. The present invention can also be realized in the form of a data signal embedded in a carrier wave, in which the above program is embodied by electronic transmission.

  As a result, it is possible to provide a recording medium on which the program code (execution format program, intermediate code program, source program) for executing the processing of the document feature determination unit 13 is freely carried. Further, the program recorded on the recording medium can be read by the image forming apparatus 1, the image reading apparatus 1b, or the program reading apparatus included in the computer system, so that the above-described document feature determination processing can be executed.

  The computer system includes an image input device such as a flatbed scanner, a film scanner, and a digital camera, a computer on which various processes such as the above-described image processing method are performed by loading a predetermined program code, and a CRT which displays a processing result of the computer. It may be configured by an image display device such as a display or a liquid crystal display, and a printer that outputs the processing result of the computer to paper or the like. Further, a network card, a modem or the like may be provided as a communication means for connecting to a server or the like via a network.

1 image forming apparatus 100 control unit 110 color image input device 120 color image processing device 11 A / D conversion unit 12 shading correction unit 13 original feature determination unit 1301 pixel determination unit 1302 area pixel counting unit 1303 data selection unit 1304 histogram generation unit 1305 Background determination unit 1306 Original type determination unit 1307 Background removal unit 14 Input tone correction unit 15 Region separation processing unit 16 Color correction unit 17 Black generation undercolor removal unit 18 Spatial filter processing unit 19 Output tone correction unit 20 Tone reproduction process 130 Color image output device 140 Operation panel

Claims (19)

An image data input unit that scans a document and inputs it as image data,
The original document based on the image data characteristic amount including a first characteristic amount indicating a frequency of gradation change between adjacent pixels of the image data and a second characteristic amount indicating a magnitude of the gradation change of the image data. A determination unit for determining the number of lines of the halftone dots of
An image processing unit that performs image processing on the image data according to the determination result of the determination unit,
An image processing apparatus comprising:   The image processing apparatus according to claim 1, further comprising a calculation unit that calculates the image data characteristic amount from the image data.   The image processing apparatus according to claim 1, wherein at least one of the first feature amount and the second feature amount includes a plurality of feature amounts.   The image processing device according to claim 1, wherein the first feature amount is a feature amount calculated only for pixels included in a halftone dot area.   The image processing apparatus according to claim 1, wherein the second characteristic amount includes a characteristic amount indicating a density distribution.   The image processing apparatus according to claim 1, wherein the image processing unit performs spatial filter processing as the image processing.   2. The determination unit determines the number of lines of halftone dots of the document based on an output value obtained by inputting the image data feature amount into a mathematical expression using a result of machine learning. 6. The image processing device according to any one of 6.   The image processing apparatus according to claim 7, wherein the machine learning is a support vector machine. A plurality of the image data input section,
The determination unit, based on an output value obtained by inputting the image data feature amount in a mathematical expression using the result of the machine learning corresponding to the image data input unit to which the image data is input, The image processing apparatus according to claim 7, wherein the number of lines of a halftone dot is determined. Having a plurality of image input resolution settings of the image data input unit,
The determination unit determines the number of lines of halftone dots of the document based on an output value obtained by inputting the image data feature amount in a mathematical expression using the result of the machine learning corresponding to the image input resolution setting. The image processing apparatus according to claim 7, wherein:   Based on an output value obtained by inputting the image data feature amount in a mathematical expression using the result of the machine learning corresponding to the output format of the image data, the determination unit determines the number of lines of the halftone dots of the document. The image processing apparatus according to claim 7, wherein the image processing apparatus makes a determination.   The image processing apparatus according to claim 11, wherein the output formats are copy output and scan output. Equipped with a gradation reproduction unit that has multiple gradation reproduction settings,
The determining unit determines the number of lines of halftone dots of the document based on an output value obtained by inputting the image data feature amount in a mathematical expression using the result of the machine learning corresponding to the gradation reproduction setting. The image processing apparatus according to claim 7, wherein:   The determination unit, based on an output value obtained by inputting the image data feature amount in a mathematical expression using the result of the machine learning corresponding to either monochrome output or color output, the halftone dot of the original document. The image processing apparatus according to claim 7, wherein the number of lines of the image processing device is determined.   The image processing apparatus according to claim 7, wherein the determination unit is capable of changing a threshold value for determining a halftone frequency with respect to an output value of a mathematical expression using the result of the machine learning. An image processing apparatus according to any one of claims 1 to 15,
An image forming apparatus including an image forming unit that forms an image based on image data processed by the image processing apparatus. An image data input step of scanning a document and inputting it as image data,
The original document based on the image data characteristic amount including a first characteristic amount indicating a frequency of gradation change between adjacent pixels of the image data and a second characteristic amount indicating a magnitude of the gradation change of the image data. A determination step of determining the number of lines of the halftone dot
An image processing step of performing image processing on the image data according to the determination result of the determination step;
An image processing method comprising: In the processor of the image processing device,
An image data input step of scanning a document and inputting it as image data,
The original document based on the image data characteristic amount including a first characteristic amount indicating the frequency of gradation change between adjacent pixels of the image data and a second characteristic amount indicating the magnitude of the gradation change of the image data. A determination step of determining the number of lines of the halftone dot of
An image processing step of performing image processing on the image data according to the determination result of the determination step;
An image processing program for executing. In the processor of the image processing device,
An image data input step of scanning a document and inputting it as image data,
The original document based on the image data characteristic amount including a first characteristic amount indicating a frequency of gradation change between adjacent pixels of the image data and a second characteristic amount indicating a magnitude of the gradation change of the image data. A determination step of determining the number of lines of the halftone dot
An image processing step of performing image processing on the image data according to the determination result of the determination step;
A computer-readable recording medium recording an image processing program for executing the following.

Images