JP6474315B2 - Image processing apparatus, image forming apparatus, image processing method, image processing program, and recording medium therefor - Google Patents

Description

  The present invention relates to an image processing apparatus and an image processing method for detecting a signal level of a background of a document based on document image data.

  Conventionally, in a digital copying machine or a multifunction peripheral, a histogram of an image signal read by a scanner is created, and based on the created histogram, the background level of a scanned document is detected, and the detected background signal level is set. Accordingly, a technique for removing the background from the image is known.

  For example, in Patent Document 1, a maximum frequency value of a density histogram is set as a first maximum frequency value, and a maximum frequency value other than a density category adjacent to the density category indicating the first maximum frequency value is set as a second maximum frequency value. A technique is disclosed in which the presence / absence of a background is determined based on a comparison result between a first maximum power value and a first threshold value, and a comparison result between (first maximum power value + second maximum power value) and a second threshold value.

JP 2004-64532 A (published February 26, 2004) Japanese Patent Laid-Open No. 2002-232708 (released on August 16, 2002) JP 2000-354167 A (published on December 19, 2000)

  However, in the technique disclosed in Patent Document 1, in the case of a document including a colored background image output by a printer, the background image portion may be erroneously determined as a background. In particular, such an erroneous determination is likely to occur when the background image is a document printed with a light density (light density). When such an erroneous determination occurs, there arises a problem that a background image that is not originally a background is removed.

  The present invention has been made in view of the above problems, and an object of the present invention is to appropriately identify the background of an original and a background image printed by a printer.

  An image processing apparatus according to an aspect of the present invention includes a histogram generation unit that generates a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in document image data, and whether or not background removal is necessary based on the histogram. A background determination unit that determines a maximum value that is equal to or greater than a predetermined first threshold value among the maximum values of the histogram and that has the lowest density, and the maximum value The ratio of the frequency of the second density section, which is the density section located on the side where the density is lighter than the first density section, which is the corresponding density section, is equal to or higher than a predetermined second threshold, and It is characterized in that it is determined that the background removal is necessary when the first density category is present on the darker side than the predetermined density category threshold value.

  According to the above configuration, it is possible to appropriately identify the background of the original and the background image printed by the printer. In other words, for a document printed with ink on paper that is not white, such as a newspaper, the background is appropriately removed (paper color removal), and the background portion is an image printed on the entire paper with a highlight density. For an output document or the like, it is possible to prevent the highlight density portion from being erroneously determined as the background and removed.

1 is a block diagram illustrating a schematic configuration of an image forming apparatus according to a first embodiment of the present invention. FIG. 2 is a block diagram illustrating a configuration of a document feature determination unit provided in the image forming apparatus illustrated in FIG. FIG. 3 is a flowchart showing a flow of processing in a document feature determination unit shown in FIG. 2. FIG. FIG. 4 is an explanatory diagram illustrating a method for setting an exclusion area to be excluded from a histogram generation target in the histogram generation processing performed by the document feature determination unit illustrated in FIG. 2. FIG. 3 is a block diagram illustrating a configuration of a background determination unit provided in the document feature determination unit illustrated in FIG. 2. It is a flowchart which shows the flow of the determination process whether the background removal performed by the background determination part shown in FIG. 5 is performed. (A) is a graph showing an example of a histogram that is determined to be subjected to background removal in the background determination unit shown in FIG. 5, and (b) is a background removal in the background determination unit shown in FIG. It is a graph which shows an example of the histogram determined not to be. 6 is a graph illustrating an example of a histogram that is determined not to perform background removal in the background determination unit illustrated in FIG. 5. It is a block diagram which shows the structure of the image reading apparatus concerning Embodiment 2 of this invention.

Embodiment 1
An embodiment of the present invention will be described.

(1-1. Overall Configuration of Image Forming Apparatus 1)
FIG. 1 is a block diagram illustrating a schematic configuration of an image forming apparatus 1 according to the present embodiment. In this 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 an image with respect to image data of a document is not limited. 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 2, a color image processing device 3, a color image output device 4, an operation panel 5, and a control unit 6. The color image processing apparatus 3 includes an A / D (analog / digital) 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, A black generation and under color removal unit 17, a spatial filter processing unit 18, an output tone correction unit 19, and a tone reproduction processing unit 20 are provided.

  The color image input device 2 reads a document to generate image data of the document, and outputs the generated image data to the color image processing device 3. The configuration of the color image input device 2 is not particularly limited as long as it 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 an RGB (R: red, G: green, B: blue) analog signal is obtained by reading a reflected light image from an original with the CCD. It is also possible to use a configuration that generates image data consisting of:

  The color image processing device 3 converts the image data input from the color image input device 2 into an A / D conversion unit 11, a shading correction unit 12, a document feature determination unit 13, an input tone correction unit 14, and a region separation processing unit 15. , Color correction unit 16, black generation and under color removal unit 17, spatial filter processing unit 18, output gradation correction unit 19, and gradation reproduction processing unit 20, and finally CMYK (C: cyan, M: magenta) , Y: yellow, K: black), the image data represented by the digital color signal is output to the color image output device 4.

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

  The shading correction unit 12 performs various distortions generated in the illumination system, the imaging system, and the imaging system of the color image input device 2 with respect to image data of digital signals corresponding to RGB sent from the A / D conversion unit 11. Apply a process to remove. Further, the shading correction unit 12 adjusts the color balance.

  The document feature determination unit 13 converts the RGB signal (RGB reflectance signal), from which 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 printed photograph document, or a character printed photograph document in which characters and a printed photograph are mixed, and (ii) Background determination processing is performed to determine whether the document is to be subjected to background removal processing. Further, the document feature determination unit 13 generates a document feature 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 and under color removal unit 17, and the spatial filter processing unit 18. , And the gradation reproduction processing unit 20. The details of the document feature determination unit 13 will be described later.

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

  In other words, the color of the background of the document (paper on which characters are printed) varies, and depending on the color of the background, if the white background (background) is not treated as white (or colorless), the recording material (toner or ink) May be used excessively. For example, when forming an image in monochrome mode on a yellowish paper like straw half paper or a document with a colored background, if the background color is not treated as white, the recording material will also be printed on the white background (background part) when the image is output. Will be used. For this reason, in order to suppress the use of an excess recording material, the input tone correction unit 14 performs a background density removal process (that is, a process for changing the density of the background to a white density) and performs contrast adjustment. Perform the adjustment process.

  Further, the input tone correction unit 14 converts image data consisting of RGB density signals (hereinafter, unless otherwise specified, the RGB signal represents a density signal (a signal representing a pixel value)) to an area separation processing unit. 15 is output.

  The region separation processing unit 15 determines whether each pixel in the input image data belongs to a background region, a photographic region (continuous tone region), a character region, or a halftone region based on the RGB density signal. Process. The region separation processing unit 15 generates a region identification signal indicating which region each pixel belongs to based on the result of the region separation processing, and the color correction unit 16, the black generation lower color removal unit 17, the space While outputting to the filter process part 18 and the gradation reproduction process part 20, the RGB signal input from the input gradation correction part 14 is output to the subsequent color correction part 16 as it is.

  The color correction unit 16 converts the RGB signal (input signal) input from the region separation processing unit 15 into a CMY signal according to the region identification signal input from the region 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 material including unnecessary absorption components in order to realize faithful color reproduction. The color correction unit 16 performs color conversion processing based on the document feature determination signal input from the document feature determination unit 13.

  The black generation / under color removal unit 17 subtracts the black generation process for generating a black (K) signal from the CMY signal after color correction by the color correction unit 16 and the K signal obtained by the black generation process from the original CMY signal. Under color removal processing for generating a new CMY signal 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 and under color removal unit 17 performs black generation using skeleton black as the black generation processing. In this black generation process using skeleton black, the input / output characteristics of the skeleton curve are y = f (x), the densities corresponding to the input C, M, and Y are C, M, and Y, respectively, and the output C is output. , M, Y, K, respectively, C ′, M ′, Y ′, K ′ and UCR (Under Color Removal) rate α (0 <α <1)
K ′ = f {min (C, M, Y)}
C ′ = C−αK ′
M ′ = M−αK ′
Y ′ = Y−αY ′
Thus, the CMY three-color density signals are converted into CMYK four-color density signals.

  The spatial filter processing unit 18 corrects the spatial frequency characteristics of the image data of the CMYK signal input from the black generation and under color removal unit 17 to prevent the output image from blurring and graininess deterioration. In accordance with the region identification signal input from the separation processing unit 15, a spatial filter process using a digital filter set in advance for each region type is performed.

  The output tone correction unit 19 performs output tone correction processing based on the output characteristics of the color image output device 4 on the image data of the CMYK signal input from the spatial filter processing unit 18.

  The gradation reproduction processing unit 20 is predetermined for each type of region in accordance with the region identification signal input from the region separation processing unit 15 with respect to the image data of the CMYK signal input from the output gradation correction unit. Process.

  For example, with respect to the region separated into character regions by the region separation processing unit 15, in order to improve the reproducibility of black characters or color characters in particular, the spatial filter processing unit 18 increases the high frequency enhancement amount by sharp enhancement processing, The gradation reproduction processing unit 20 performs binarization or multilevel conversion on a high-resolution screen suitable for high frequency reproduction.

  In addition, with respect to the regions separated into halftone dot regions by the region separation processing unit 15, the spatial filter processing unit 18 performs low-pass filter processing for removing the input halftone component, and the gradation reproduction processing unit 20 A gradation reproduction process (halftone generation) is performed so that the gradation of the pixel can be reproduced.

  Further, with respect to the region separated into the photographic regions by the region separation processing unit 15, the gradation reproduction processing unit 20 performs binarization or multi-value processing on the screen with an emphasis on gradation reproducibility.

  The image data output from the gradation reproduction processing unit 20, that is, the image data subjected to the above-described processes is temporarily stored in a storage unit (not shown), and is read out at a predetermined timing to be a color image output device. 4 is output.

  The color image output device 4 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 4 forms an image on a recording medium using recording materials of 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 4. However, the configuration of the color image output device 4 is not limited to this, and a printer device of another method such as an ink jet method may be used.

  The operation panel 5 receives an instruction input from the user and transmits it to the control unit 6. The operation panel 5 includes, for example, a display unit such as a liquid crystal display and operation keys that receive user operation inputs. Alternatively, the operation panel 5 may be a touch panel.

  The control unit 6 is a computer device that includes an arithmetic processing unit such as a CPU and a dedicated processor, and a storage unit (not shown) such as a RAM, a ROM, and an HDD. The control unit 6 includes various information stored in the storage unit, a program for performing various controls, an instruction input from a user input through the operation panel 5, and various sensors provided in the image forming apparatus 1. The operation of the color image input device 2, the color image processing device 3, the color image output device 4, and the operation panel 5 is controlled in accordance with the detection result.

(1-2. Configuration of Document Feature Determination Unit 13)
FIG. 2 is a block diagram illustrating the configuration of the document feature determination unit 13, and FIG. 3 is a flowchart illustrating the flow of processing in the document feature determination unit 13.

  As shown in FIG. 2, the document feature determination unit 13 includes a pixel determination unit 31, a region pixel count unit 32, a data selection unit 33, a histogram generation unit 34, a background determination unit 35, a document type determination unit 36, and a background removal unit. 37.

  In the document feature discriminating unit 13, as shown in FIG. 3, the pixel determining unit 31 first converts each pixel of the RGB signal (image data) input from the shading correction unit 12 into a background pixel, a photographic pixel, a character pixel, and a network. A region pixel determination process for classifying the pixel into any of the point pixels is performed (S1). In the following description, pixels classified as background pixels, photographic pixels, character pixels, and halftone pixels are referred to as region pixels.

The algorithm for classifying the pixels 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 the method of Patent Document 2, the region 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 × 15 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) Calculate the total density busyness (for example, the sum of values calculated in the main scanning direction and the sub-scanning direction), which is the sum of absolute values of density differences between pixels adjacent to the target pixel.
(4) A comparison between the calculated maximum density difference and the maximum density difference threshold and a comparison between the calculated total density busyness and the total density busyness threshold are performed.
(5) When the maximum density difference <the maximum density difference threshold and the total density busyness <the total density busyness threshold, it is determined that the target pixel belongs to the background / photo area.
(6) When the above condition is not satisfied, it is determined that the target pixel belongs to the character / halftone dot region.

(7) For a pixel determined to belong to the background / photo area, the target pixel is determined to be a background pixel when the maximum density difference <the background / photographic paper determination threshold value is satisfied, and when this condition is not satisfied, It is determined to be a photographic pixel.
(8) For a pixel determined to belong to the character / halftone dot region, when the target pixel satisfies the condition of total density busyness <(value obtained by multiplying the maximum density difference by the character / halftone determination threshold), the character pixel When this condition is not satisfied, it is determined that the pixel is a halftone pixel.

  Note that the region pixel determination processing may be performed using, for example, pre-scanned image data, or may be performed using image data temporarily stored in a storage unit such as a hard disk.

  Next, based on the result of the region pixel determination process in the pixel determination unit 31, the region pixel count unit 32 performs each region type (for each region of the background pixel, the photographic pixel, the character pixel, and the halftone pixel). Then, a region pixel counting process for counting the number of classified pixels (region pixels) is performed (S2).

  Next, the data selection unit 33 separates the document image region in the RGB signal input from the shading correction unit 12 into a target region to be described later and an exclusion region to be excluded from the target of the histogram generation processing. A region selection process is performed (S3). That is, in the present embodiment, histogram generation is not performed for all pixels of the input image, but is performed by excluding some 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 read by the color image input device 2 is subjected to processing for removing various distortions generated in the illumination system, the imaging system, and the imaging system of the color image input device 2 in the shading correction unit 12. Appropriate correction is not performed on the area. For example, when the color image input apparatus 2 reads a document, a region (end region of the document) arranged at the end of the document table in the document may be a relatively dark signal.

  Therefore, in the present embodiment, as shown in FIG. 4, the data selection unit 33 is located at the end of the glass surface of the document table in the color image input device 2 at the time of image reading out of the image data of the document. Image data in a predetermined range is excluded from the histogram generation target area, and the other areas are set as histogram generation target areas.

  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 document reading is subject to histogram generation. You may make it exclude from. The void area is an area in which nothing is printed and exists with a width of about several mm (for example, about 4 mm) from the end (peripheral edge) of the document printed or copied by the printer.

  Next, the histogram generation unit 34 belongs to the region of the RGB signals input from the shading correction unit 12 that is determined as a background pixel in the region pixel determination process and that is determined as a histogram generation target region in the region selection process. A pixel is extracted as a target pixel, and a histogram generation process (minimum value histogram generation process) is performed (S4).

  Specifically, the histogram generation unit 34 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 a plurality of preset density categories. Then, 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 from the smallest pixel value (density value), and the section having the largest pixel value is the 32nd density section. Set to category. In this embodiment, since RGB signals are used, when the pixel value (density value) is closer to “0” (the smaller the density value), the actual density becomes higher, and the pixel value (density value) becomes “ The closer to “255” (the higher the density value), the lower the density (lighter).

  In order to create a histogram using the minimum value between color components, the density value of the darkest color component of the background (the color component having the minimum density value) is set as the background density, and correction corresponding to the density value is performed. This is because by applying the amount 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.

  Thereafter, the document feature determination unit 13 determines whether or not the processing of S1 to S4 has been performed for all the pixels (S5), and when there is an unprocessed pixel, the process returns to the processing of S1 and is unprocessed. Processes S1 to S4 are performed on the pixels.

  On the other hand, if it is determined in S5 that the processing of S1 to S4 has been completed for all the pixels, the background determination unit 35 performs a background determination process for determining whether or not the background removal should be performed (S6). Details of the background determination processing will be described later.

  After performing the background determination process in S6, the document type determination unit 36 performs the document type determination process (S7).

  Specifically, the document type determination unit 36 determines the number of area pixels counted by the area pixel counting unit 32 and thresholds respectively corresponding to a predetermined background area, photo area, halftone area, and character area. By comparing, the type of the entire document is determined.

  For example, when the detection accuracy is higher in the order of characters, halftone dots, and photographic paper photographs, if the ratio of the pixels in the character area is 30% or more of the total number of pixels, it is determined that the document is a character document. When the ratio is 20% or more of the total number of pixels, it is determined as a half-tone original (printed photo original). When the ratio of the pixels in the photographic paper photo area is 10% or more of the total number of pixels, the photographic paper photograph is used. It is determined that the document is a manuscript. If the ratio of the character area and the ratio of the halftone dot area are equal to or greater than the threshold value, respectively, it is determined that the character / halftone original (character-printed photo original) is present.

  The document type determination unit 36 outputs a document feature determination signal indicating the determination result of the document type to the background removal unit 37, the input tone correction unit 14, the color correction unit 16, the black generation and under color removal unit 17, and the spatial filter process. To the unit 18 and the gradation reproduction processing unit 20.

  Next, the background removal unit 37 determines whether the document is to be subjected to background removal based on the document type determination result by the document type determination unit 36 (S8). That is, the background removal unit 37 determines whether or not the document type determined by the document type determination unit 36 is a type set in advance as a document type to be subjected to background removal.

  For example, as a manuscript for background removal, a character manuscript, a manuscript that does not include a photographic area, a manuscript / half-tone manuscript (a character-printed photo manuscript), and a manuscript with a small halftone dot area ratio (for example, a halftone dot area ratio over the whole manuscript For example, a document of 40% or less) may be set.

  If it is determined in step S8 that the document is not to be removed, the document feature determination unit 13 ends the process without removing the background.

  On the other hand, if it is determined in S8 that the document is to be subjected to background removal, the background removal unit 37 performs background removal processing (S9) and ends the processing.

  The method for ground removal processing is not particularly limited, and an existing ground removal method can be used.

  For example, the background 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, a 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 of each background pixel plane (each color component), the background removal process may be performed by selecting the correction amount table corresponding to the minimum value for all color components.

(1-3. Configuration of Background Determination Unit 35)
FIG. 5 is a block diagram illustrating a configuration of the background determination unit 35. As illustrated in FIG. 5, the background determination unit 35 includes a peak value calculation unit 41, a total calculation unit 42, and a determination unit 43.

  The peak value calculation unit 41 examines the histogram frequency from the thinner one (the one with the larger density value), and firstly a background determination threshold (first threshold) T1 (T1 = 70 in the present embodiment) in which the histogram frequency is preset. The density classification that exceeds 10,000 pixels and has a peak value (maximum value) is obtained. As described above, when RGB signals are used, the actual density is higher when the pixel value (density value) is closer to “0” (the smaller the density value), and the pixel value (density value) is “ The closer to “255” (the higher the density value), the lower the density.

  Specifically, the peak value calculation unit 41 sequentially increases the frequency value when the frequency of each density category is viewed in order from the lower density (the higher density value). When it is detected that the numerical value has decreased, the peak value is the concentration segment immediately before the concentration segment where the frequency has started to decrease.

  The value of the background determination threshold T1 may be set as appropriate so that the background density component can be appropriately detected and a noise component that is not the background density component can be excluded, and is not particularly limited. It is preferable to set P2 = P1 × 1/2 within a range of 60% to 80%, where P1 is the number of pixels in the void image generation area in the original image data. The size of the void area varies depending on the printer that performs printing. Further, the reading position of the original varies depending on the scanner, and the area excluded from the histogram generation target in the original image data also varies. Further, in order to accurately detect the background (paper color) from the void region, the background determination threshold T1 is preferably a small value. Considering these points, in the present embodiment, the threshold T1 is set in a range of 60% to 80% of P2. However, the range of the threshold T1 is not limited to this. Since the optimum range of the threshold value T1 varies depending on the printer or scanner as described above, an appropriate value may be set by performing a measurement test in advance using many printers and scanners.

  For example, the document size: A4, the resolution: 600 dpi, the size of the area excluded from the generation target of the histogram in the document image data (for example, the left side and the top side of the document) is 3 mm in both the main scanning direction and the sub-scanning direction. When the size is 2 mm in both the main scanning direction and the sub-scanning direction (both four sides of the document), the number of pixels P1 included in the void area in the histogram generation target in the document image data is P1 = 553899 pixels. Since the density values of the pixels in the void area are not all the same but have a distribution, assuming that the pixels in the void area are equally distributed to two adjacent density sections, the density sections The pixel number P2 of P2 is 276994.5 pixels. In this case, the background can be properly detected by setting the background determination threshold T1 to about 200,000 pixels.

  Also, the document size is A4, the resolution is 600 dpi, the size of the area excluded from the histogram generation target in the document image data is 3 mm in both the main scanning direction and the sub-scanning direction, and the size of the void area is the main scanning direction and the sub-scanning. When both directions are 3 mm, P1 = 823410 pixels and P2 = 411705 pixels. In this case, the background can be appropriately detected by setting the background determination threshold T1 to about 300,000 pixels.

  Also, the document size is A4, the resolution is 600 dpi, the size of the area excluded from the histogram generation target in the document image data is 3 mm in both the main scanning direction and the sub-scanning direction, and the size of the void area is the main scanning direction and the sub-scanning. If both directions are 4 mm, P1 = 1103560 pixels and P2 = 551780 pixels. In this case, by setting the background determination threshold T1 to about 400,000 pixels, the background can be detected appropriately.

  When the density category of the peak value specified by the peak value computing unit 41 is X, the total calculating unit 42 calculates the total value of histogram frequencies from the density category (X + i + 1) to the density category 32. Note that i is an integer equal to or greater than 1, and i = 2 in this embodiment. Therefore, in the present embodiment, the total sum calculation unit 42 calculates the total value of the histogram frequencies from the density section (X + 3) to the density section 32.

  The determination unit 43 determines whether the background removal process should be performed based on the peak value specified by the peak value calculation unit 41 and the total value calculated by the total calculation unit 42.

  FIG. 6 is a flowchart showing a flow of determination processing for determining whether or not to perform background removal in the background determination unit 35. FIG. 7A is a graph illustrating an example of a histogram that is determined to be subjected to background removal in the background determination unit 35, and FIG. 7B is a graph that illustrates that background removal should not be performed in the background determination unit 35. It is a graph which shows an example of the histogram determined as. In the histogram shown in FIG. 7, the horizontal axis indicates the density value indicating the density category (the smaller the number, the higher the density), and the vertical axis indicates the frequency value indicating the frequency of the minimum value belonging to each density category. Further, the histogram frequency for the density category X is H (X).

  First, the peak value calculation unit 41 sets the attention density category for determining whether or not the peak value is X = 32 (the density category having the highest density value, that is, the density category having the lowest actual density). Set (S11).

  Then, the peak value calculation unit 41 determines whether or not the histogram frequency H (X) of the target density category X is equal to or greater than the background determination threshold value T1 (S12).

  When it is determined in S12 that H (X) is less than the background determination threshold value T1, the peak value calculation unit 41 sets the attention density section to X = X−1 (the density section having the next lowest density value after the previous attention density section). ) (S13), and the process returns to S12.

  When it is determined in S12 that the histogram frequency H (X) is greater than or equal to the background determination threshold T1, the peak value calculation unit 41 determines whether or not H (X)> H (X-1) (S14). . That is, the peak value calculation unit 41 has the histogram frequency H (X−) of the density section (X−1) having the density value next to the current target density section, which is the histogram frequency H (X) of the current target density section X. It is determined whether it is larger than 1).

  When it is determined in S14 that H (X)> H (X-1) is not true, the peak value calculation unit 41 performs the process of S13 and returns to the process of S12.

  On the other hand, when the peak value calculation unit 41 determines in S14 that H (X)> H (X−1), the determination unit 43 determines that H (X) / H (X + i) ≧ T2 (i is 1 or more). It is determined whether or not an integer (i = 2 in this embodiment) (S15). In other words, the determination unit 43 divides H (X) by the histogram frequency of the density segment whose density value is i steps larger than the current target density category (the density segment that is thinner than the i density category) (H (X) It is determined whether or not (/ H (X + i)) is greater than or equal to a preset background presence / absence determination threshold (second threshold) T2.

  The background presence / absence determination threshold T2 is set in advance based on the image sample. For example, in the case of a newspaper manuscript, the value of H (X) / H (X + 2) is about 500 at minimum, and in the case of a print manuscript, the value of H (X) / H (X + 2) is about 13 at maximum. is there. For this reason, it is preferable to set the background presence / absence determination threshold T2 within a range of 50 to 300. In this embodiment, the background presence / absence determination threshold T2 is set to 100. The background presence / absence determination line threshold T2 is obtained by performing a measurement test in advance using a newspaper document or a magazine document and a printer output document (print document) in which a background portion is printed on the entire paper with a highlight density. It is only necessary to set an appropriate value so that both can be discriminated.

  In the present embodiment, the value of i is set to 2. This is because even if the background density is originally a density corresponding to the density section X, the background density may be reflected in the density section X + 1 due to an error at the time of image reading. This is because it is excluded. However, the value of i is not limited to 2, and may be appropriately set according to the number of density categories. For example, when the number of density categories is greater than 32, i may be set to an integer of 3 or more. If the number of density categories is less than 32, i may be set to 1.

  If it is determined in S15 that H (X) / H (X + i) ≧ T2, the determination unit 43 calculates the sum of histogram frequencies from the density section (X + i + 1) to the density section 32 calculated by the sum calculation section 42 {H It is determined whether (32) +... + H (X + i + 1)} is less than a preset threshold (third threshold) T3 (S16).

  The threshold T3 may be set as appropriate depending on how much the influence of the mount is considered when the document image is an image of a document pasted on the mount, and is not particularly limited. Of the areas to be generated by the histogram, when the number of pixels in the area of the mount read from the document pasted on the mount is P3, it is preferably set to about 60% to 80% of P3. For example, when the document size is A4, the resolution is 600 dpi, the area excluded from the generation of the histogram: main scanning direction = sub-scanning direction = 3 mm, and the interval between the mount and the pasted document: 2 mm, the histogram generation target area Of these, the number P3 of pixels of the mount area to be read is P3 = 553899 pixels. For this reason, in this embodiment, the threshold value T3 is set to 400,000 pixels.

  In the case of a document pasted on a mount, the threshold value T3 may be set in consideration of how much the mount area is read and fluctuations in the reading position of the document. Decreasing the threshold value T3 can suppress the background of the pasted document from being determined as the background. For this reason, in the present embodiment, the threshold T3 is set to a value of about 60% to 80% of the P3. However, the range of the threshold value T3 is not limited to this, and it is appropriately determined by performing a measurement test in advance using various image samples in which the distance between the mount and the original to be pasted is changed and the color and density of the mount are changed. You only have to set it.

  Note that a value of 100% or more may be set as a coefficient for multiplying the threshold value T1. For example, when reading a cut-out original of an irregular newspaper whose size is between B5 and A4, the original size to be output by manual operation can be designated as A4. In this case, the color of the document table is read in an area other than the irregular document size. As described above, when the threshold value T1 is set in the range of 60% to 80% of P1 × 1/2, the area other than the irregular document size is determined as the background, and the background of the newspaper can be removed. There is a risk of disappearing. In such a case, the threshold value T1 may be set to 100% or more of P1 × 1/2. For example, when an irregular size is selected as the document size using the operation panel, the threshold value T1 may be switched to a value of 100% or more of P1 × 1/2. In this case as well, by performing a measurement test using various irregular-size originals, a value to be multiplied by P1 × 1/2 is set so that an area other than the irregular-size original size is not detected as a background. That's fine.

  Further, when the threshold T1 is set to 100% or more of P1 × 1/2, the threshold T3 is also set to a value of 100% or more of P3, and it is determined as YES in S16 of FIG. Is preferred. Thus, by setting the threshold value T3 to a value of 100% or more of the above P3, the frequency of the area other than the irregular document size is added to prevent erroneous determination as no background in the determination of S16. it can. In this case as well, a value to be multiplied by P3 may be set so that an irregular cut-out original is not erroneously determined as having no background by performing a measurement test using originals of various irregular sizes.

  If it is determined in S16 that the total value is less than T3, the determination unit 43 determines that background removal should be performed, and sets the background density classification to X (S17).

  On the other hand, if it is determined in S15 that H (X) / H (X + i) ≧ T2, and if it is determined in S16 that the total value is equal to or greater than T3, the determination unit 43 should not perform background removal. Therefore, the background density classification is set to 32 (S18). That is, for example, as shown in FIG. 8, the determination unit 43 performs background removal when the sum of the frequencies of the density sections (X + i + 1 to 32) that are lighter than the density sections (X + i) considered to be the density of the background portion is greater than T3. It is determined that it should not be (no background).

  In S15, it may be determined whether or not the current target density category is less than a predetermined density category threshold T4 (T4 = 31 in the present embodiment).

  As described above, in the present embodiment, the histogram generation unit 34 generates a histogram indicating the frequency for each predetermined density section of the density value of each pixel in the document image data, and the background determination unit 35 removes the background based on the histogram. Whether or not is necessary is determined. Specifically, the background determination unit 35 has a maximum value that is equal to or higher than a predetermined background determination threshold value T1 and is located on the lowest density value side (thin density side) among the frequency maximum values in the histogram, A second concentration category (this implementation) that is a concentration category that is located on the lower concentration side by a predetermined division (2 divisions in the present embodiment) with respect to the first concentration division (X) that is a concentration division corresponding to the maximum value. In the embodiment, when the ratio H (X) / H (X + 2) to the frequency of X + 2) is equal to or higher than a predetermined background presence / absence determination threshold T2, it is determined that background removal is necessary, and is less than the background presence / absence determination threshold T2. It is determined that the background removal is unnecessary.

  In the present embodiment, the background determination unit 35 calculates the sum of the frequencies for each density section (X + 3 to 32) having a density value lower than that of the second density section (X + 2), and the sum total. Is larger than a predetermined third threshold value T3, it is determined that the background removal is not performed regardless of the comparison result between the ratio H (X) / H (X + 2) and the background presence / absence determination threshold value T2.

  Thus, for example, in the case of a document printed with ink on a non-white paper such as a newspaper, the density distribution of the base (the unprinted portion of the paper) is narrow, so as shown in FIG. In addition, the peak of the histogram becomes steep, the frequency H (X) of the density section X is equal to or higher than the background determination threshold T1, H (X) / H (X + 2) is equal to or higher than the background presence / absence determination threshold T2, and the above sum value Is less than T3 and it is determined that the background should be removed (background density division = X). Further, the background removal processing is performed with the density section that is the peak of the histogram (or the density section that is the peak of the histogram and the density section adjacent thereto) as the density of the background portion.

  Also, in the case of a printer output document in which the background part is printed on the entire paper with the highlight density, the highlight density part is often identified as the background pixel, and the density of the background part of the highlight density Since the distribution is wide, the peak of the histogram is not steep as shown in FIG. For this reason, H (X) / H (X + 2) is less than the background presence / absence determination threshold value T2, and it is determined that there is no background, that is, background removal should not be performed (background density classification = 32). As described above, in the present embodiment, the frequency H (X) with respect to the frequency H (X + 2) of the density classification (X + 2) is used as an index indicating the spread (variance) of the histogram of the area where the background candidate is determined. . By using the above H (X) / H (X + 2), a document printed on paper that is not white (a document for which background removal is performed) and a printer output document on which a background (background) is printed (a document for which background removal is not performed) Can be distinguished. It can be said that the threshold value T2 is a value set by the maximum value of the background candidate region and the frequency in the density section representing the spread of the histogram of the background candidate region. As a result, it is possible to prevent a problem that the color of the background portion is removed by erroneous determination even though the background portion of the highlight density is intentionally colored when the document is made.

  Further, for example, in the case of an original or the like in which an image cut from a magazine or the like is pasted on a light color mount, the frequency corresponding to the color of the mount appears on the lower density side than the peak of the histogram of the pasted image. On the other hand, in the configuration described above, the background determination unit 35 includes a sum total calculation unit 42 that calculates the sum of the frequencies for each density category (X + 3 to 32) having a density value lower than that of the second density category (X + 2). If the sum is larger than the predetermined third threshold value T3, it is determined that the background removal is not performed regardless of the comparison result between the ratio H (X) / H (X + 2) and the background presence / absence determination threshold value T2. Thereby, it can prevent that the color of a mount is removed accidentally.

  Further, in the present embodiment, a histogram is generated for pixels determined as background pixels in the region pixels. In this case, based on the histogram generated for the background pixel, it is possible to determine the background (determination of necessity of background removal) and to determine the document type. For example, when the density category of the histogram is 32, it can be determined that the document is a photo (continuous tone photo) document if the frequency is equal to or greater than a predetermined value in a density category of 1/2 or more. However, the present invention is not limited to a configuration for generating a histogram for a background pixel, and a histogram including other region pixels may be generated and the background may be determined based on the histogram.

[Embodiment 2]
Another embodiment of the present invention will be described. For convenience of explanation, members having the same functions as those in the above-described embodiment are denoted by the same reference numerals, and description thereof is omitted.

  In the first embodiment, the configuration has been described in which the histogram generation unit 34 generates a minimum value histogram indicating the frequency of the minimum value of the color components of each pixel for the pixel determined as the background pixel in the region pixel.

On the other hand, in the present embodiment, the histogram generation unit 34 generates an L ^* value histogram (luminance value histogram) instead of the minimum value histogram.

Specifically, the histogram generation unit 34 color-converts the RGB signal input from the shading correction unit 12 into an L ^* a ^* b ^* signal, and for the target pixel determined as the background pixel in the region pixel, L ^* A value histogram generation process is performed. The color conversion process from the RGB signal to the L ^* a ^* b ^* signal is not particularly limited, and a conventionally known method can be used.

The number of density sections of the histogram includes, for example, 32 sections in which the L ^* value (signal value) is the first density section and the second density section from the smallest, and the section having the largest L ^* value is the 32nd density section.

When using the L ^* value histogram, it is possible to determine the background density value in the L ^* value, it is possible to perform the under color removal process using L ^* value. That is, when the L ^* value histogram is created, the background removal unit 37 can select the correction amount table corresponding to the background density value based on the L ^* value and perform the background removal process.

[Embodiment 3]
Still another embodiment of the present invention will be described. For convenience of explanation, members having the same functions as those in the above-described embodiment are denoted by the same reference numerals, and description thereof is omitted.

  In each of the above-described embodiments, the case where the present invention is applied to the image forming apparatus 1 including the color image input device 2, the color image processing device 3, and the color image output device 4 has been described. In contrast, in the present embodiment, an example in which the present invention is applied to an image reading apparatus such as a flat bed scanner will be described.

  FIG. 9 is a block diagram illustrating a configuration of the image reading apparatus 1b according to the present embodiment.

  As shown in FIG. 9, the image reading device 1b includes a color image input device 2 and a color image processing device 3b. The color image processing device 3 b includes an A / D conversion unit 11, a shading correction unit 12, and a document feature determination unit 13.

  The color image input device 2 reads a document to generate image data of the document, and outputs the generated image data to the color image processing device 3. The configuration of the color image input device 2 is not particularly limited as long as it 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 an RGB (R: red, G: green, B: blue) analog signal is obtained by reading a reflected light image from an original with the CCD. It is also possible to use a configuration that generates image data consisting of:

  The color image processing device 3b sends the image data input from the color image input device 2 in the order of the A / D conversion unit 11, the shading correction unit 12, and the document feature determination unit 13.

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

The shading correction unit 12 performs various distortions generated in the illumination system, the imaging system, and the imaging system of the color image input device 2 with respect to image data of digital signals corresponding to RGB sent from the A / D conversion unit 11. Apply a process to remove. Further, the shading correction unit 12 adjusts the color balance.
The image data and document feature determination signal output from the image reading device 40 are transmitted to a printer, a multifunction peripheral, or a computer via a network.

  The document feature determination unit 13 converts the RGB signal (RGB reflectance signal), from which 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 printed photograph document, or a character printed photograph document in which characters and a printed photograph are mixed, and (ii) Background determination processing is performed to determine whether the document is to be subjected to background removal processing. The document feature determination unit 13 also generates a document feature determination signal indicating the result of the document type determination process, and transmits the document feature determination signal to another device (for example, a printer, a multifunction peripheral, a computer, etc.) via the communication network. Note that the configuration of the document feature determination unit 13 is substantially the same as that of the first embodiment, and thus the description thereof is omitted here.

[Embodiment 4]
Still another embodiment of the present invention will be described. For convenience of explanation, members having the same functions as those in the above-described embodiment are denoted by the same reference numerals, and description thereof is omitted.

  The control blocks (particularly the document feature determination unit 13) of the color image processing apparatuses 3 and 3b may be realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like, or a CPU (Central Processing Unit). ) May be implemented by software.

  In the latter case, the color image processing apparatuses 3 and 3b include a CPU that executes instructions of a program that is software that realizes each function, and a ROM (Read that records the above-described program and various data so that the computer (or CPU) can read them. Only Memory) or a storage device (these are referred to as “recording media”), a RAM (Random Access Memory) for expanding the program, and the like. And the objective of this invention is achieved when a computer (or CPU) reads the said program from the said recording medium and runs it. As the recording medium, a “non-temporary tangible medium” such as 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 an arbitrary transmission medium (such as a communication network or a broadcast wave) that can transmit the program. The present invention can also be realized in the form of a data signal embedded in a carrier wave in which the program is embodied by electronic transmission.

  As a result, it is possible to provide a portable 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 recorded. Further, the above-described document feature determination process can be executed by causing the image forming apparatus 1, the image reading apparatus 1 b, or the program reading apparatus included in the computer system to read the program recorded on the recording medium.

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

[Summary]
The image processing apparatus (color image processing apparatuses 3 and 3b) according to the first aspect of the present invention includes a histogram generation unit 34 that generates a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data; A background determination unit 35 that determines whether or not background removal is necessary based on the histogram, and the background determination unit 35 is equal to or greater than a predetermined first threshold (background determination threshold T1) among the maximum values of the histogram. Further, the maximum density H (X) located on the side where the density is the thinnest and the side where the density is lower than the first density section X corresponding to the maximum value H (X) by a predetermined density section number i. The background removal is necessary when the ratio H (X) / H (X + i) with the frequency of the second density section X + i, which is the density section located at, is equal to or higher than a predetermined second threshold (background presence / absence determination threshold T2). Judging It is characterized.

  According to the above configuration, it is possible to appropriately identify the background of the original and the background image printed by the printer. In other words, for a document printed with ink on paper that is not white, such as a newspaper, the background is appropriately removed (paper color removal), and the background portion is an image printed on the entire paper with a highlight density. For an output document or the like, it is possible to prevent the highlight density portion from being erroneously determined as the background and removed.

  The image processing apparatus (color image processing apparatuses 3 and 3b) according to aspect 2 of the present invention is the sum for calculating the sum of the frequencies for each density section whose density is lower than that of the second density section X + i in aspect 1. The calculation unit 42 is provided, and the background determination unit 35 is configured not to perform background removal when the sum is larger than a predetermined third threshold T3.

  According to the above configuration, for example, when the original is an original in which an image (an image cut from a magazine or the like) is pasted on a part of the mount, the color of the mount can be prevented from being erroneously removed.

  The image processing apparatus (color image processing apparatuses 3 and 3b) according to the third aspect of the present invention is the image reading apparatus (color image) that reads the original placed on the original table in the first or second aspect. Image data generated by reading an original with the input device 2), and the histogram generator 34 reads the original image data with the image reading device (color image input device 2) in the original. In this configuration, the document image data in the area arranged at the end of the document table is excluded from the histogram generation processing target.

  In general, in an image reading apparatus that reads a document placed on a document table, a document cover that sandwiches the document between the document table and the document table is not placed on the document at a portion near the edge of the document table. The document may be read darker than the part on which the document cover is placed. For this reason, although the density range of the background should originally be narrow, the density range is widened, and it may be erroneously determined that there is no background. On the other hand, according to the above configuration, the original image data in the area arranged at the end of the original table when the image reading apparatus reads the original image data is excluded from the histogram generation processing targets. . As a result, it is possible to prevent erroneous determination of the presence / absence of the background due to an error that occurs during document reading.

  In the image processing apparatus (color image processing apparatuses 3 and 3b) according to aspect 4 of the present invention, in any one of the above aspects 1 to 3, the histogram generation unit 34 uses the color of each pixel in the document image data as the histogram. In this configuration, a histogram of density values having the highest density among density values for each component is generated.

  According to the above configuration, it is possible to appropriately identify the background of the original and the background image printed by the printer.

In the image processing apparatus (color image processing apparatuses 3 and 3b) according to the fifth aspect of the present invention, in any one of the first to third aspects, the histogram generation unit 34 converts the document image data into an L ^* a ^* b ^* signal. Color conversion is performed, and an L ^* histogram for each pixel is generated as the histogram.

  According to the above configuration, it is possible to appropriately identify the background of the original and the background image printed by the printer.

  An image forming apparatus 1 according to an aspect 6 of the present invention includes the image processing apparatus (color image processing apparatus) 3 according to any one of the above aspects 1 to 5.

  According to the above configuration, it is possible to appropriately identify the background of the document and the background image printed by the printer, and perform appropriate image formation according to the identification result.

  An image processing method according to an aspect 7 of the present invention includes a histogram generation step of generating a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data, and whether or not background removal is necessary based on the histogram. In the background determination step, a maximum value that is equal to or greater than a predetermined first threshold value (background determination threshold value T1) among the maximum values of the histogram and is located on the side with the lowest density. H (X) and a second density section X + i which is a density section located on the side where the density is thinner by a predetermined density section number i than the first density section X which is a density section corresponding to the maximum value H (X). When the ratio H (X) / H (X + i) to the frequency is equal to or higher than a predetermined second threshold (background presence / absence determination threshold T2), it is determined that background removal is necessary.

  According to the above method, it is possible to appropriately identify the background of the original and the background image printed by the printer. In other words, for a document printed with ink on paper that is not white, such as a newspaper, the background is appropriately removed (paper color removal), and the background portion is an image printed on the entire paper with a highlight density. For an output document or the like, it is possible to prevent the highlight density portion from being erroneously determined as the background and removed.

  The image processing apparatus according to each aspect of the present invention may be realized by a computer. In this case, the image processing apparatus is realized by a computer by causing the computer to operate as the histogram generation unit and the background determination unit. An image processing program to be executed and a computer-readable recording medium on which the image processing program is recorded are also included in the scope of the present invention.

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

  The present invention can be applied to an image processing apparatus and an image processing method for detecting a signal level of a background of a document based on document image data.

DESCRIPTION OF SYMBOLS 1 Image forming apparatus 1b Image reading apparatus 2 Color image input apparatus 3, 3b Color image processing apparatus (image processing apparatus)
4 Color image output device 5 Operation panel 6 Control unit 11 A / D conversion unit 12 Shading correction unit 13 Document feature determination unit 14 Input gradation correction unit 15 Area separation processing unit 16 Color correction unit 17 Black generation and under color removal unit 18 Space Filter processing unit 19 Output tone correction unit 20 Tone reproduction processing unit 31 Pixel determination unit 32 Region pixel count unit 33 Data selection unit 34 Histogram generation unit 35 Background determination unit 36 Document type determination unit 37 Background removal unit 40 Image reading device 41 Peak value calculation unit 42 Total calculation unit 43 Determination unit T1 Background determination threshold (first threshold)
T2 Background determination threshold (second threshold)
T3 threshold (third threshold)

Claims (12)

A histogram generation unit that generates a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data;
A background determination unit that determines whether or not background removal is necessary based on the histogram,
The background determination unit
Among the local maximum values of the histogram, a predetermined density section with respect to a local maximum value that is equal to or greater than a predetermined first threshold and is located on the side with the lowest density, and a first density section that is a density section corresponding to the local maximum value It is determined that the background removal is necessary when the ratio with the frequency of the second density section, which is the density section located on the side where the density is lighter than the number, is equal to or greater than a predetermined second threshold value ,
Furthermore, a sum total calculation unit that calculates the sum of the frequencies for each density section having a density higher than that of the second density section,
The image processing apparatus according to claim 1, wherein the background determination unit does not perform background removal when the sum is larger than a predetermined third threshold value . A histogram generation unit that generates a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data;
A background determination unit that determines whether or not background removal is necessary based on the histogram,
The background determination unit
Among the local maximum values of the histogram, a predetermined density section with respect to a local maximum value that is equal to or greater than a predetermined first threshold and is located on the side with the lowest density, and a first density section that is a density section corresponding to the local maximum value It is determined that the background removal is necessary when the ratio with the frequency of the second density section, which is the density section located on the side where the density is lighter than the number, is equal to or greater than a predetermined second threshold value,
The document image data is image data generated by reading a document with an image reading device that reads a document placed on a document table,
The histogram generation unit excludes, from the original image data, original image data of an area arranged at an end portion of the original table when being read by the image reading apparatus from a target for generating a histogram. and images processing apparatus you. A histogram generation unit that generates a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data;
A background determination unit that determines whether or not background removal is necessary based on the histogram,
The background determination unit
Among the local maximum values of the histogram, a predetermined density section with respect to a local maximum value that is equal to or greater than a predetermined first threshold and is located on the side with the lowest density, and a first density section that is a density section corresponding to the local maximum value It is determined that the background removal is necessary when the ratio with the frequency of the second density section, which is the density section located on the side where the density is lighter than the number, is equal to or greater than a predetermined second threshold value,
The histogram generation unit, as the histogram, most-enriched density value images processor you and generating a histogram of the density values of each color component of each pixel in the original image data. A histogram generation unit that generates a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data;
A background determination unit that determines whether or not background removal is necessary based on the histogram,
The background determination unit
Among the local maximum values of the histogram, a predetermined density section with respect to a local maximum value that is equal to or greater than a predetermined first threshold and is located on the side with the lowest density, and a first density section that is a density section corresponding to the local maximum value It is determined that the background removal is necessary when the ratio with the frequency of the second density section, which is the density section located on the side where the density is lighter than the number, is equal to or greater than a predetermined second threshold value,
The histogram generation unit, the original image data to color conversion to L ^* a ^* b ^* signal, as the histogram, images processor you and generates the histogram of L ^* for each pixel. An image forming apparatus characterized by comprising an image processing apparatus according to any one of claims 1 to 4. A histogram generating step for generating a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data;
A background determination step of determining whether or not background removal is necessary based on the histogram,
In the ground determination step,
Among the local maximum values of the histogram, a predetermined density section with respect to a local maximum value that is equal to or greater than a predetermined first threshold and is located on the side with the lowest density, and a first density section that is a density section corresponding to the local maximum value It is determined that the background removal is necessary when the ratio with the frequency of the second density section, which is the density section located on the side where the density is lighter than the number, is equal to or greater than a predetermined second threshold value ,
And a sum total calculating step of calculating the sum of the frequencies for each density section having a density higher than that of the second density section,
In the background determination step, the background removal is not performed when the sum is larger than a predetermined third threshold value .   A histogram generating step for generating a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data;
  A background determination step of determining whether or not background removal is necessary based on the histogram,
  In the ground determination step,
  Among the local maximum values of the histogram, a predetermined density section with respect to a local maximum value that is equal to or greater than a predetermined first threshold and is located on the side with the lowest density, and a first density section that is a density section corresponding to the local maximum value It is determined that the background removal is necessary when the ratio with the frequency of the second density section, which is the density section located on the side where the density is lighter than the number, is equal to or greater than a predetermined second threshold value,
  The document image data is image data generated by reading a document with an image reading device that reads a document placed on a document table,
  In the histogram generating step, the document image data in an area arranged at the end of the document table when the image reading device reads the document image data is excluded from a histogram generation process target. An image processing method.   A histogram generating step for generating a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data;
  A background determination step of determining whether or not background removal is necessary based on the histogram,
  In the ground determination step,
  Among the local maximum values of the histogram, a predetermined density section with respect to a local maximum value that is equal to or greater than a predetermined first threshold and is located on the side with the lowest density, and a first density section that is a density section corresponding to the local maximum value It is determined that the background removal is necessary when the ratio with the frequency of the second density section, which is the density section located on the side where the density is lighter than the number, is equal to or greater than a predetermined second threshold value,
  In the histogram generation step, an image processing method is characterized in that a histogram having a darkest density value among density values for each color component of each pixel in the document image data is generated as the histogram.   A histogram generating step for generating a histogram indicating the frequency for each predetermined density section of the signal value of each pixel in the document image data;
  A background determination step of determining whether or not background removal is necessary based on the histogram,
  In the ground determination step,
  Among the local maximum values of the histogram, a predetermined density section with respect to a local maximum value that is equal to or greater than a predetermined first threshold and is located on the side with the lowest density, and a first density section that is a density section corresponding to the local maximum value It is determined that the background removal is necessary when the ratio with the frequency of the second density section, which is the density section located on the side where the density is lighter than the number, is equal to or greater than a predetermined second threshold value,
  In the histogram generation step, the document image data is converted to L ^* a ^* b ^* The signal is color-converted, and as the histogram, L for each pixel ^* An image processing method characterized by generating a histogram. An image processing program for causing an image processing apparatus according to computer to claim 1, wherein the histogram generation unit computer, before Symbol background determination unit, and an image processing program for functioning as the total sum calculation unit. An image processing program for causing a computer to function as the image processing apparatus according to claim 2 , wherein the computer causes the computer to function as the histogram generation unit and the background determination unit. The computer-readable recording medium which recorded the image processing program of Claim 10 or 11 .

Images