JP2005142740A - Ink jet original discriminating method, image processing apparatus, image reading apparatus, image forming apparatus, ink jet original discriminating program and recording medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing apparatus capable of discriminating an ink jet gloss paper original. <P>SOLUTION: An original type automatic discriminating unit for discriminating the original type on the basis of image data of an original is provided with an ink jet gloss paper original discriminating unit. In this discriminating unit, an RGB signal is converted into a luminance value (S11), a luminance histogram is generated(S12), the number of pixels from the generated luminance histogram to a predetermined luminance segment N is added to obtain a ratio T to the number of all pixels (S13), and the ratio T is compared with a threshold A (S14). Thus, it is determined an original is an ink jet gloss paper original (S15, S16). <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to an inkjet document determination method, an image processing apparatus, an image reading apparatus, an image forming apparatus, and an inkjet document that can determine an inkjet document image output by an inkjet method such as an inkjet printer based on image data of the document. The present invention relates to a discrimination program and a recording medium.

  Image forming devices such as copiers and printers that use electrophotographic processes and inkjet systems are commercialized as full-color digital copiers and digital multi-function printers that reproduce color images with high image quality due to advances in digital image processing technology. Has been. There are characters, line drawings, photographs, and combinations of these documents that can be copied using these image forming apparatuses. It is necessary to perform the appropriate image processing.

  Under such circumstances, conventionally, the image forming apparatus is provided with a character mode, a character / photo mode, a photo mode, and the like, and an operator appropriately selects a mode according to a document. However, the operation of the operator himself discriminating the document type and switching the mode is a very troublesome operation, and when an inappropriate mode is selected, there are many cases where significant image deterioration is observed. Useless copying is also performed. In order to solve such problems, it has been proposed to automatically determine the document type.

  In particular, Patent Document 1 discloses a document type to be conventionally determined, that is, a copy document (output image of a color copying machine), a silver salt photograph document (corresponding to a photographic paper photograph document), and a halftone print document (printing). In addition to a photographic manuscript), a manuscript that is output from an ink jet printer is also disclosed. According to this, from the digital color signal obtained by reading the original, the feature quantity relating to the color gamut and the feature quantity relating to the texture are extracted, and it is determined whether or not the original is output from the ink jet printer.

  This will be described in more detail. An image output from an inkjet printer has a feature that the saturation of cyan and magenta is higher than that used in a general halftone printing document. It is possible to discriminate between halftone print originals. However, there is a difference between the blue and purple color gamuts of fluorescent colors and the cyan and magenta color gamuts used in inkjet printers when compared with read signal values read by an input device such as a color scanner. Few. For this reason, it is difficult to discriminate between a manuscript written with a highlighter pen and an output image by an ink jet printer only by the characteristics of the color gamut. In the above-mentioned Patent Document 1, texture is used in addition to the color gamut. Yes. As an image output method of an ink jet printer, an error diffusion method and a dither method are mainly employed. In these image output methods, there are many textures composed of dots on the white ground of paper. In contrast, a document written with a fluorescent color pen has a feature that many solid areas appear. Therefore, both can be distinguished by using the texture.

Patent Document 2 discloses an image processing apparatus that determines for each pixel whether a pixel of interest belongs to a character area, a halftone dot area, a background area, or a photographic paper photograph area. For the discrimination of the image, a preset threshold value is used, and each pixel is discriminated as one of the above areas. If this image discrimination configuration is used for discrimination of the document type, the document type is determined using a local feature amount with respect to the entire document, so that the document type can be accurately determined.
Japanese Patent Laid-Open No. 10-126631 (published on May 15, 1998) Japanese Patent Laid-Open No. 2002-232708 (released on August 16, 2002)

  With the configuration of Patent Literature 1, it is possible to determine whether the document is an output document by an ink jet printer, which cannot be implemented with the configuration of Patent Literature 2.

  However, in Patent Document 1, color determination (color reproduction area determination) and density level determination (texture extraction) must be performed on the entire image in order to determine that the document is an inkjet document. This is a time-consuming process and a large processing burden. In addition, inkjet originals are identified as having a saturation of cyan and magenta higher than that used for ordinary halftone print originals, but inkjet glossy paper originals using glossy paper and plain papers are used. No distinction is made to distinguish from a conventional inkjet plain paper document. Even if the same inkjet document is used, it is necessary to perform different image processing on the inkjet glossy paper document and the inkjet plain paper document. to degrade. Therefore, it is necessary to discriminate inkjet glossy paper originals.

  SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and an object of the present invention is to determine an ink jet glossy paper document that could not be determined by the conventional method, an image processing apparatus, an image reading apparatus, and an image forming apparatus. An apparatus, an ink jet document discrimination program, and a recording medium are provided.

In order to solve the above-described problem, the inkjet document discrimination method of the present invention creates a histogram indicating the relationship between the gray value indicating the pixel density and the number of pixels based on image data obtained by reading the document. And the histogram created in the first step, a feature value of a predetermined gray value region is obtained, and based on the obtained feature value, whether the document is an inkjet glossy paper document or not And a second step of determining the above. The gray value includes luminance, density, brightness, etc., and details will be described later.

In addition to the above-described configuration, the inkjet document determination method of the present invention further includes a printed photograph as a result of determining the document type based on the image data when it is determined in the second step that the document is an inkjet glossy paper document. It is characterized in that it includes a third step for determining whether or not the document is a document and making the determination in the second step correct if the determination result is a document including a printed photograph.

  In order to solve the above-described problem, the image processing apparatus of the present invention creates a histogram indicating the relationship between the gray value indicating the pixel density and the number of pixels based on the image data obtained by reading the document. And determining whether or not the original is an inkjet glossy paper original based on the obtained characteristic quantity from the histogram created by the histogram generation means. And an inkjet document discriminating means including the means. Similar to the above, the gray value includes luminance, density, brightness, and the like.

  In the image processing apparatus of the present invention, in addition to the above-described configuration, the inkjet document determination unit determines whether the document type determination result based on the image data is a document including a printed photograph, and the print When the result is a document including a printed photograph, the image processing apparatus further includes a comprehensive determination unit that validates the determination that the determination unit is an inkjet glossy paper document.

  In order to solve the above problems, an image reading apparatus according to the present invention includes an image reading apparatus that includes a reading unit that reads a document and an image processing apparatus that receives image data read by the reading unit. The image processing apparatus according to claim 3 or 4 is provided as the processing apparatus.

  In order to solve the above problems, an image forming apparatus of the present invention includes a reading unit that reads a document, an image processing device that receives image data read by the reading unit, and performs image processing on the image data. An image forming apparatus including an output unit that outputs image data processed by the image processing apparatus, wherein the image processing apparatus includes the image processing apparatus according to claim 3 or 4. Yes.

  The inkjet document discrimination program of the present invention is a program for causing a computer to execute each step in the above-described inkjet document discrimination method of the present invention in order to solve the above problems.

  In order to solve the above-mentioned problems, the recording medium of the present invention is a computer-readable recording medium that records the above-described inkjet document discrimination program of the present invention.

  As described above, the inkjet document discrimination method according to the present invention includes a first step of creating a histogram indicating the relationship between the gray value indicating the pixel density and the number of pixels, based on the image data obtained by reading the document. A feature value of a predetermined gray value region is obtained from the histogram created in the first step, and it is determined whether or not the document is an inkjet glossy paper document based on the obtained feature value. Therefore, it is possible to discriminate an inkjet glossy paper document that could not be discriminated conventionally.

  That is, in the case of an inkjet glossy paper document, in a luminance histogram created based on image data obtained by reading the document (histogram when the gray value is luminance), the number of pixels in the low-luminance region with low luminance is the luminance It is characterized by more than a high high luminance area. Similarly, the density histogram (histogram when the density value is density) has a feature that the number of pixels in the high density area with high density is larger than that in the low density area with low density.

  Therefore, as described above, a predetermined luminance area (tone value area) of the luminance histogram, that is, information on the low luminance area, or a predetermined density area (light value area) of the density histogram, that is, the high density area. It is possible to determine that the document is an inkjet glossy paper document.

  The characteristics used for discriminating such inkjet glossy paper originals are not found in inkjet plain paper originals that are imaged on plain paper by the inkjet method, but in printed photographic originals that use halftone gradation. Have similar characteristics. Therefore, with such a method, it is not possible to distinguish between an inkjet glossy paper original and a photographic paper photographic original, but the color reproduction area of the inkjet glossy paper original is closer to that of the photographic paper photographic original. It is preferable that the same color correction processing as that for the photographic paper photographic original is performed, and it is not always necessary to distinguish between the inkjet glossy paper original and the photographic paper photographic original.

  Further, as described above, when the ink jet document discrimination method of the present invention is determined to be an inkjet glossy paper document in the second step, the document type determination result based on the image data is a document including a printed photograph. If the determination result is an original including a printed photograph, the ink jet glossy paper original and the photographic paper are further included because the third step is made to correct the determination of the second step. It is possible to distinguish from a photographic document, and the discrimination accuracy can be improved.

  In other words, as described above, in the method of determining an inkjet glossy paper document using the luminance histogram or the density histogram as described above, the photographic paper photograph document has similar characteristics. Cannot be distinguished from the manuscript. Therefore, the third step described above is provided so that the determination in step 2 is correct when it is determined that the document includes a printed photograph (printed photograph document, character-printed photograph document, etc.) from the determination result of the document type. Yes. Since a photographic paper photo is not determined to be a manuscript including a printed photo, the ink-jet glossy paper manuscript and the photographic paper are made effective by enabling the determination of the ink-jet glossy paper manuscript in the case of the manuscript including the printed photo in this way. A photo manuscript can be distinguished. As a result, it is possible to cause the color correction processing unit of the image processing apparatus to perform color correction processing dedicated to inkjet glossy paper originals.

  As described above, the image processing apparatus of the present invention creates a histogram indicating the relationship between the gray value of the pixel and the number of pixels based on the image data obtained by reading the document, and the histogram generating unit. An inkjet including a determination unit that obtains a feature value of a predetermined gray value area from the histogram created in step S1 and determines whether the document is an inkjet glossy paper document based on the obtained feature value. Since the document discriminating means is provided, it is possible to discriminate an ink-jet glossy paper manuscript that could not be discriminated conventionally, as already described as the ink-jet manuscript discrimination method.

  In the image processing apparatus of the present invention, as described above, the ink jet document discrimination means further determines whether or not the document type determination result is a document including a printed photograph, and the determination result is a printed photograph. In the case of a manuscript including an image, it includes comprehensive judgment means for validating the judgment that the judgment means is an ink jet glossy paper original, so that the ink jet glossy paper original and the photographic paper photo original can be distinguished. The discrimination accuracy can be improved.

  As described above, since the image reading apparatus of the present invention includes the image processing apparatus of the present invention as an image processing apparatus, it is possible to determine an ink-jet glossy paper document that could not be determined conventionally, and then the inkjet Even if the original document is an inkjet glossy paper document, it is possible to reproduce a high-quality copy image, a display image, or the like by performing appropriate image processing on the glossy document document. The quality of image data (for example, image data captured in a computer and displayed on a display or stored in a storage device or the like) can be improved.

  As described above, since the image forming apparatus of the present invention includes the image processing apparatus of the present invention as an image processing apparatus, it is possible to determine an inkjet glossy paper document, and image processing suitable for an inkjet glossy paper document. Thus, even if the original document is an inkjet glossy paper document, it is possible to reproduce a high-quality copy image.

  As described above, the ink jet document discrimination program of the present invention is a program for causing a computer to execute each step in the ink jet document discrimination method of the present invention. This inkjet document discrimination method can be realized in a computer. Therefore, this inkjet document discrimination method can be general purpose.

  As described above, the recording medium of the present invention is a computer-readable recording medium on which the ink jet document discrimination program of the present invention is recorded. A processing program for the document discrimination method can be easily supplied to a computer.

  An embodiment of the present invention will be described with reference to FIGS. 1 to 11 as follows.

  FIG. 2 is a block diagram showing a schematic configuration of a digital color copying machine (image forming apparatus) 1 provided with a color image processing apparatus (image processing apparatus) 20 according to an embodiment of the present invention.

  As shown in FIG. 2, the color image processing apparatus 20 includes an A / D conversion unit 21, a shading correction unit 22, a document type automatic determination unit 23, an input tone correction unit 24, a region separation processing unit 25, and a color correction unit 26. A black generation and under color removal unit 27, a spatial filter processing unit 28, an output tone correction unit 29, and a tone reproduction processing unit 30. A color image input device (image reading means) 40 and a color image output device (image output means) 41 are connected to the color image processing apparatus 20 to constitute the digital color copying machine 1 as a whole. The digital color copying machine 1 is provided with an operation panel 42.

  The color image input device 40 is composed of, for example, a scanner unit having a charge coupled device (hereinafter referred to as a CCD), and a reflected light image from a paper on which an original image is recorded is converted into RGB by the CCD. It is read as an analog signal (R: red, G: green, B: blue) and input to the color image processing apparatus 20.

  An analog signal read by the color image input device 40 is converted into an A / D conversion unit 21, a shading correction unit 22, a document type automatic discrimination unit 23, an input tone correction unit 24, and an area separation in the color image processing device 20. The processing unit 25, the color correction unit 26, the black generation and under color removal unit 27, the spatial filter processing unit 28, the output gradation correction unit 29, and the gradation reproduction processing unit 30 are sent in this order, and as CMYK digital color signals, It is output to the color image output device 41.

  The A / D (analog / digital) converter 21 converts the input RGB analog signal into a digital signal. The shading correction unit 22 performs processing for removing various distortions generated in the illumination system, imaging system, and imaging system of the color image input device 40 on the RGB digital signals sent from the A / D conversion unit 21. Is. The shading correction unit 22 performs color balance adjustment.

  The automatic document type discrimination unit 23 is easy to handle an image processing system employed in the color image processing apparatus 20 such as a density signal using RGB signals (RGB reflectance signals) from which various distortions have been removed by the shading correction unit 22. In addition to conversion into a signal, document type discrimination processing for discriminating the document type is performed. Although details will be described later, the document type automatic determination unit 23 generates a luminance histogram (histogram) from the RGB digital signal by using the luminance that is the gray value, and the luminance histogram (histogram) cannot be conventionally determined using the luminance histogram. An inkjet glossy paper document can be discriminated. Then, based on the determination result, the document type automatic determination unit 23 outputs a document type determination signal indicating the document type to the color correction unit 26, the black generation and under color removal unit 27, and the spatial filter processing unit 28. Then, the input signal output from the shading correction unit 22 is output to the input tone correction unit 24 at the subsequent stage as it is.

  The input tone correction unit 24 performs image quality adjustment processing such as background density removal and contrast. The region separation processing unit 25 separates each pixel in the input image into, for example, a character region, a halftone dot region, or a photographic region from the RGB signal. Then, the region separation processing unit 25 outputs a region identification signal indicating which region the pixel belongs to based on the separation result, a color correction unit 26, a black generation and under color removal unit 27, a spatial filter processing unit 28, and The output signal is output to the tone reproduction processing unit 30 and the input signal output from the input tone correction unit 24 is output to the subsequent color correction unit 26 as it is.

  The color correction unit 26 performs color correction processing for removing color turbidity based on spectral characteristics of CMY (C: cyan, M: magenta, Y: yellow) color materials including unnecessary absorption components in order to faithfully reproduce colors. Is what you do. As the color correction table used in the color correction processing, in this embodiment, for a photographic paper document suitable for a photographic paper document, for a print document suitable for a print document, and for an inkjet glossy paper document suitable for an inkjet glossy paper document. The color correction table suitable for the document type is used based on the document type determination signal input from the document type automatic determination unit 23.

  The black generation and under color removal unit 27 generates a black (K) signal from the CMY three-color signal after color correction, and subtracts the K signal obtained by black generation from the original CMY signal to generate a new CMY signal. The CMY three-color signal is converted into a CMYK four-color signal.

  As an example of the black generation process, there is a method (general method) of generating black using a predetermined black generation curve. In this method, the input / output characteristic of the black generation curve is y = f (x), the input data is C, M, Y, the output data is C ′, M ′, Y ′, K ′, UCR (Under When the color removal rate is α (0 <α <1), the black generation and under color removal processing is expressed by the following Equation 1.

  In the present embodiment, the black generation processing includes black generation processing for an inkjet glossy paper document suitable for an inkjet glossy paper document, and is based on a document type determination signal input from the document type automatic determination unit 23. If the determination result is an inkjet glossy paper document, black generation processing for the inkjet glossy paper document is performed.

  The spatial filter processing unit 28 performs spatial filter processing using a digital filter on the image data of the CMYK signal input from the black generation and under color removal unit 27 to correct the spatial frequency characteristics by performing a spatial filter process using a digital filter. The gradation reproduction processing unit 30 performs processing so as to prevent blurring of the output image and deterioration of graininess. Similarly to the spatial filter processing unit 28, the gradation reproduction processing unit 30 also uses a region identification signal based on the image data of the CMYK signal. Is subjected to predetermined processing.

  For example, a region separated as a character region by the region separation processing unit 25 is a high-frequency enhancement amount by sharp enhancement processing in the spatial filter processing by the spatial filter processing unit 28 in order to improve the reproducibility of black characters or color characters. Is increased. At the same time, the tone reproduction processing unit 30 selects binarization or multi-value processing on a high-resolution screen suitable for high-frequency reproduction.

  Further, with respect to the region separated as the halftone dot region by the region separation processing unit 25, the spatial filter processing unit 28 performs low-pass filter processing for removing the input halftone dot component. The output tone correction unit 29 performs output tone correction processing for converting a signal such as a density signal into a halftone dot area ratio that is a characteristic value of the color image output device 50, and then the tone reproduction processing unit 30. Then, gradation reproduction processing (halftone generation) is performed so that the image is finally separated into pixels and each gradation is reproduced. For the region separated as the photographic region by the region separation processing unit 25, the binarization or multi-value processing on the screen is performed with emphasis on gradation reproducibility.

  In this embodiment, the spatial filter processing unit 28 includes a digital filter for inkjet glossy paper, and the determination result is determined based on the document type determination signal input from the document type automatic determination unit 23. In the case of a glossy paper document, spatial filter processing is performed using the digital filter for inkjet glossy paper.

  The operation panel 42 includes, for example, a touch panel in which a display unit such as a liquid crystal display and an operation unit such as a setting button are integrated. Based on information input from the operation panel 42, the color image input device 40, Each operation of the color image processing device 20 and the color image output device 41 is controlled.

  The image data subjected to the above-described processes is temporarily stored in a storage unit (not shown), read at a predetermined timing, and input to the color image output device 41. The color image output device 41 outputs image data on a recording medium (for example, paper). Examples of the color image output device 41 include a color image output device using an electrophotographic method or an inkjet method, but are not particularly limited. It is not something. The above processing is controlled by a CPU (Central Processing Unit) (not shown).

  Hereinafter, the details of the automatic document type discrimination unit 23 will be described with reference to FIGS. 1 and 3 to 11. As shown in FIG. 1, the automatic document type determination unit 23 includes an inkjet glossy paper document determination unit (inkjet document determination unit) 10 that performs inkjet glossy paper document determination processing, a document determination unit 11 that performs document determination processing, and a comprehensive determination. A comprehensive determination unit (inkjet document determination means, comprehensive determination means) 12 that performs processing is provided.

  Then, in the automatic document type discrimination unit 23, as shown in the flowchart of FIG. 3, the inkjet glossy paper document discrimination unit 10 performs the inkjet glossy paper document discrimination process (S (step) 1), and at the same time. The document determination unit 11 performs document determination processing (S2), and using these processing results, the comprehensive determination unit 12 performs comprehensive determination processing (S3) to determine the final document type.

  First, the configuration of the inkjet glossy paper document discrimination unit 10 and the inkjet glossy paper document discrimination process will be described. As shown in FIG. 4, the inkjet glossy paper document determination unit 10 includes a luminance conversion unit 15, a histogram generation unit (histogram generation unit) 16, a dynamic range determination unit (determination unit) 17, and a memory 18.

  The luminance conversion unit 15 converts the RGB signal input from the shading correction unit 22 (see FIG. 2) into a luminance value L. As the conversion formula, for example, the following formula can be used.

L = 0.3 × R + 0.6 × G + 0.1 × B
In addition,
L = 0.33 × R + 0.34 × G + 0.33 × B
A conversion equation such as

  The histogram generation unit 16 generates a luminance histogram of the document, and generates a histogram of the luminance value L converted by the luminance conversion unit 15. As the horizontal axis of the luminance histogram, the luminance division is necessary, but here, the luminance division is 8 intervals from 0 to 255. In that case, the total number of sections is 32. FIG. 5 shows an example of a brightness histogram of an inkjet glossy paper document with brightness intervals of 8 intervals. The sorting method may be two intervals, four intervals, etc. However, although the discrimination accuracy is improved as the interval is reduced, there is a demerit that the consumption of the memory 18 and the complexity of the calculation are increased. The vertical axis of the luminance histogram is the ratio of the number of pixels to the total number of pixels determined by the document size (A4 size, B4 size, etc.). The document size is detected by various methods such as providing a plurality of photoelectric sensors according to the document size in the document table of the image forming apparatus and detecting the presence or absence of light detection by a document size detection unit (not shown). .

  In generating a luminance histogram, the histogram generation unit 16 counts up for each pixel the luminance value L input from the luminance conversion unit 15 and enters the pixel for each division with respect to the entire surface of the document. The number is obtained and held in the memory 18.

The dynamic range determination unit 17 uses the luminance histogram generated by the histogram generation unit 16 to determine whether the document is an inkjet glossy paper document. First, the dynamic range determination unit 17 adds the number of pixels from the segment 0 to a predetermined segment N from the luminance histogram generated by the histogram generator 16 to obtain the pixel number Nk. If the number of pixels on the entire surface determined by the document size is Mk, based on the following formula:
T = Nk × 100 / Mk
A ratio (%) T of the number of pixels Nk from section 0 to section N with respect to the total number of pixels Mk is obtained. Then, the ratio T thus obtained is compared with a predetermined threshold A, and if T> A, it is determined as an inkjet glossy paper document.

  Here, an example of how to set (determine) the category N and the threshold A will be described. For category N, the difference between the ratio T of the printed photographic document and the inkjet plain paper document and the ratio T of the inkjet glossy paper document is as large as possible. It is desirable to select the section N so that the ratio T is as small as possible. Setting the section N in this way makes it easier to set the threshold A.

  FIGS. 6A to 6F are graphs in which the ratio T is obtained by changing the value of the section N in six levels from 1 to 6, based on the luminance histogram for each document. 6A to 6F, the horizontal axis represents T. In addition, four types of printed photo originals # 1 to # 4, one type of photographic paper photo original, two types of inkjet glossy paper originals # 1 and # 2, and three types of inkjet plain paper originals # 1 to # are used as originals. 3 is used.

  6A to 6F, the difference between the ratio T between the printed photo original and the inkjet plain paper original and the ratio T between the inkjet glossy paper originals, which is the setting condition of the above-described category N, and In order to satisfy “the ratio T of the printed photo original and the inkjet plain paper original is as small as possible”, the sections 1 to 5 in FIG. 6E, that is, the section N = 5 are selected. Hereinafter, in the present embodiment, description will be made assuming that N = 5.

  On the other hand, as the threshold A, as shown in FIG. 7, A = 10.00, the printed photograph original (# 1 to # 4), the inkjet plain paper original (# 1 to # 3), and the inkjet glossy paper original (# It is desirable to set a threshold value that can distinguish between 1 and # 2) and the photographic paper photographic original. The reason for this is that the color reproduction areas of inkjet glossy paper originals and photographic paper photo originals are relatively close, and the color reproduction areas of printed photo originals and inkjet plain paper originals are also relatively close. This is because it is possible to perform appropriate processing by switching the subsequent image processing (for example, by switching the color correction processing correction table (LUT: lookup table)).

  Also, the inkjet plain paper original is higher in the ratio T than the printed photograph original as shown in the inkjet plain paper originals # 1 to # 3 and the printed photograph originals # 1 to # 4 in FIGS. Since the threshold value A is set as described above, it is possible to discriminate between an inkjet glossy paper document and an inkjet plain paper document.

  The procedure of the inkjet glossy paper document discrimination process in the inkjet glossy paper document discrimination unit 10 will be described based on the flowchart of FIG. First, the luminance conversion unit 15 converts the input RGB signal into a luminance value L (S11), and the histogram generation unit 16 creates a luminance histogram using the luminance value L (S12). Next, the dynamic range determination unit 17 uses the luminance histogram generated by the histogram generation unit 16 to add the frequency (that is, the number of pixels) up to a predetermined predetermined luminance category N, as described above. Then, a ratio T to the total number of pixels is obtained (S13). Then, the obtained ratio T is compared with a predetermined threshold A (S14). If T> A, the dynamic range determination unit 17 determines that the original is an inkjet glossy paper document (S15), and T> If not A, the dynamic range determination unit 17 determines that the document is other than an inkjet glossy paper document (S16).

  In the present embodiment, the luminance conversion unit 15 obtains the luminance value L of the pixel from the RGB signal, the histogram generation unit 16 generates a luminance histogram, and the dynamic range determination unit 17 uses a predetermined gray value area. The inkjet glossy paper document is discriminated based on the information of a certain low luminance area. However, the density value is used as the gray value, and instead of the luminance conversion unit 15, the density value of the pixel is extracted from the RGB signal with the extraction signal selection unit. The histogram generation unit generates a density histogram indicating the relationship between the pixel density and the number of pixels from the density value selected by the signal selection unit, and the dynamic range determination unit determines a high density region (predetermined in advance). It may be determined that the document is an ink-jet glossy paper document using the information on the density value area.

  An RGB signal, that is, a density value is used. For example, a G (green) signal or an M (magenta) signal obtained by complementary color inversion of the G signal can be used. In this case, the setting of the ratio T and the threshold value A is almost the same as the case of the luminance value L, and a description thereof will be omitted.

  Furthermore, the RGB signal can be converted into an L * a * b * signal (L *: brightness, a * · b *: chromaticity), and this brightness can be used as a gray value instead of the luminance. As a method of converting the RGB signal into the L * a * b * signal, first, each color patch of the color chart original is measured with a colorimeter to obtain the L * a * b * value, and then the color chart original is obtained. Are read from the color image input device to obtain RGB data. Then, in order to associate the measured L * a * b * value with the read RGB value, a coefficient between the L * a * b * value and the RGB value is obtained by a neural network or a masking calculation coefficient determination method. And the like.

  Next, document discrimination processing in the document discrimination unit 11 will be described. As the document discrimination process, for example, various methods such as the method described in Patent Document 2 described above can be used, and the specific processing method is not particularly limited. Here, the document determination unit 11 includes a minimum density value calculation unit, a maximum density value calculation unit, a maximum density difference calculation unit, a total difference value calculation unit, a background determination unit, a photographic paper determination unit, a character determination unit, and a halftone dot determination. A description will be given by exemplifying a configuration including a portion (none of which is shown).

  The document determination unit 11 performs processing using n × m pixels including the target pixel as a determination block, using pixels only in the main scanning direction and pixels only in the sub-scanning direction. Since the processing content is the same in both the main scanning direction and the sub-scanning direction, the case of one direction will be described below as an example.

  The minimum density value calculation unit calculates the minimum density value of the pixels in the main scanning direction including the target pixel. The maximum density value calculation unit calculates the maximum density value of the pixels in the main scanning direction including the target pixel. The maximum density difference calculator calculates the maximum density difference using the minimum density value and the maximum density value calculated by the minimum density value calculator and the maximum density value calculator. The total difference value calculation unit calculates the total sum (total difference value) of absolute values of density differences between adjacent pixels for the pixels in the main scanning direction including the target pixel.

  The background determination unit, the photographic paper determination unit, the character determination unit, and the halftone determination unit are the maximum density difference calculated by the maximum density difference calculation unit and the total difference calculated by the total difference value calculation unit for the target pixel. By comparing the value with a preset threshold value, each pixel is classified as either a background, a character, a halftone dot, a photographic paper photograph, or an indeterminate pixel that does not belong to any of these (see FIG. 10). ).

  The background determination unit is a background maximum density difference threshold setting unit / background total difference value threshold setting unit, and the photographic paper determination unit is a photographic paper minimum density difference threshold setting unit / printing paper maximum density difference threshold setting unit / printing paper. The determination threshold setting unit, the character determination unit includes a character minimum density difference threshold setting unit / character determination threshold setting unit, and the halftone dot determination unit includes a halftone dot total difference value setting unit / halftone determination threshold setting unit, Each corresponding threshold value is set.

  Based on the flowchart of FIG. 9, the procedure of document discrimination processing for discriminating the type of document image from the entire document image in the document discrimination unit 11 will be described. First, the maximum density value calculation unit calculates the maximum density value in the block of n × m pixels including the pixel of interest from the read density value of each pixel (S21). Next, the minimum density value calculation unit calculates the minimum density value in the block of n × m pixels including the target pixel (S22).

  Next, the maximum density difference calculation unit calculates the maximum density difference using the calculated minimum density value and maximum density value (S23). Further, the total difference value calculation unit takes the absolute value of the density difference between adjacent pixels and takes the sum of the absolute values. That is, the total difference value calculation unit calculates the total difference value (S24).

  Next, the background determination unit determines whether the target pixel is a background pixel (S25). That is, the background determination unit compares the calculated maximum density difference with the background maximum density difference threshold stored in advance in the background maximum density difference threshold setting unit, and calculates the calculated total difference value and the background total difference value threshold. Comparison with the background sum total difference value threshold value preset in the setting unit is performed.

  If it is determined that the conditions of maximum density difference <background maximum density difference threshold and total difference value <background total difference value threshold are satisfied (S25, YES), the background determination unit determines that the target pixel is the background pixel. Determination is made (S36).

  On the other hand, if NO is determined in step S25, the photographic paper determination unit determines whether or not the pixel of interest is a photographic paper photographic pixel (S26). That is, the photographic paper determination unit is stored in advance in the photographic paper minimum density difference threshold and the photographic paper maximum density difference threshold setting unit that are stored in advance in the calculated maximum density difference and photographic paper minimum density difference threshold setting unit. Comparison with the photographic paper maximum density difference threshold and comparison between the calculated total difference value and a value obtained by multiplying the maximum density difference by the photographic paper determination threshold set in advance in the photographic paper determination threshold setting unit are performed.

  If it is determined that the minimum density difference threshold value of the photographic paper <maximum density difference <maximum density difference threshold value of the photographic paper and the total difference value <maximum density difference × the photographic paper determination threshold value is satisfied (S26, YES), the photographic paper. The determination unit determines that the target pixel is a photographic paper photographic pixel (S35).

  On the other hand, if NO is determined in step S26, the character determination unit determines whether or not the target pixel is a character pixel (S27). That is, the character determination unit compares the calculated maximum density difference with the character minimum density difference threshold value stored in advance in the character minimum density difference threshold setting unit, and calculates the total sum difference value and the character determination threshold value setting unit. Is compared with a value obtained by multiplying the maximum density difference by a preset character determination threshold.

  When it is determined that the condition of minimum character density difference threshold <maximum density difference and total difference value <maximum density difference × character determination threshold is satisfied (S27, YES), the character determination unit determines that the target pixel is a character pixel. It is determined that there is (S34).

  On the other hand, if NO is determined in step S27, the halftone dot determination unit determines whether or not the target pixel is a halftone pixel (S28). That is, the halftone dot determination unit compares the calculated maximum density difference with the halftone dot total difference value threshold value stored in advance in the halftone dot total difference value threshold value setting unit, and calculates the calculated total difference value and the halftone dot. Comparison is made with a value obtained by multiplying the maximum density difference by a halftone dot determination threshold preset in the determination threshold setting unit.

  Then, when it is determined that the condition of total sum difference value> halftone dot total difference value threshold and total difference value> maximum density difference × halftone dot determination threshold is satisfied (YES in S28), the halftone dot determination unit determines that the target pixel is It is determined that the pixel is a halftone pixel (S33). On the other hand, if NO is determined in step S28, the halftone dot determination unit determines that the pixel of interest is an indeterminate pixel (S29).

  When the determination of the pixel type in the target pixel is completed, the document determination unit 11 determines whether or not to perform another pixel type determination (S30). In step S30, if another pixel type is determined, the process returns to step S25. On the other hand, if it is determined not to perform another pixel type determination, the process proceeds to step S31. In this way, for example, the type determination of all the pixels in the block is performed.

  In S31, the document discrimination section 11 counts the type discrimination results for each pixel. Specifically, the results of pixel determination performed in steps S33 to S36 are totaled. Then, in step S31, the document determination unit 11 determines the document type based on the counted number of pixels (S32).

  For example, when the ratio of the character area and the ratio of the halftone dot area are equal to or greater than the threshold values, the original determination unit 11 determines that the character / halftone original (character-printed photo original) is present. Also, assuming that the detection accuracy is higher in the order of characters, halftone dots, and photographic paper photographs, when the ratio of the character area is 30% of the total number of pixels, the ratio of the character original and the halftone area is 20% of the total number of pixels. In this case, when the ratio of the halftone dot original (printed photo original) and the photographic paper photo area is 10% of the total number of pixels, it is determined that the image is a photographic paper photo original. In this case, the document type is determined to be a character document, a character printed photo document, a printed photo document, a photographic paper photo document, or a character photographic paper photo document.

  Note that a wider range of processing can be performed by arbitrarily adjusting each of the threshold values set above. For these threshold values, a plurality of expected values can be stored in advance in a storage medium such as a ROM (Read Only Memory), and values stored in storage means such as a memory can be set by a switch or the like as necessary. Just do it.

  Here, the reason why the type of the pixel of interest can be determined in S33 to S36 in the processing of steps S25 to S28 in the flowchart of FIG. 9 will be described with reference to FIG. FIG. 10 is a distribution diagram showing the distribution of the maximum density difference and the total difference value in the background, photographic paper photograph, halftone dot, and character area. In FIG. 10, an area where the maximum density difference is equal to or less than the total difference value indicates an area where the total difference value is not equal to or less than the maximum density difference and no pixel exists.

  Since the density distribution of the background area (background pixel) is usually small in density change, both the maximum density difference and the total difference value are very small and are distributed in the area A shown in FIG. The density distribution of the photographic paper photographic area (photographic paper photographic pixel) normally changes smoothly, and the maximum density difference and the total difference value are both small and slightly larger than the background area. Will be distributed in the region B shown in FIG.

  Also, the density distribution of the halftone dot area (halftone dot pixel) varies depending on the halftone dot, but the total difference value is the same as the number of halftone dots. The proportion of increases. For this reason, it becomes distribution like the area | region D shown in FIG. In the density distribution of the character area (character pixel), the maximum density difference is large and the total difference value is accordingly increased. However, since the density change is smaller than that in the halftone area, the total difference value is smaller than that in the halftone area. In particular, since the ratio of the total difference value to the maximum density difference is small, the distribution is as shown in the region C in FIG.

  Then, an area in which the character area and the halftone dot area overlap, an area in which the background area and the photographic paper photograph area overlap, and other areas that are unknown to which area belong, as shown in FIG. The pixels classified into this uncertain area are determined as uncertain pixels.

  As described above, since there is a difference in distribution tendency between the maximum density difference and the total difference value depending on the background area, the photographic paper photograph area, the halftone dot area, and the character area, the maximum density difference and the total difference value at the target pixel are measured. By doing so, the type of pixel can be determined.

  Next, the comprehensive determination process in the comprehensive determination unit 12 will be described. The overall determination unit 12 determines the final document type using the determination results of the inkjet glossy paper document determination unit 10 and the document determination unit 11 described above.

  Based on the flowchart of FIG. 11, the procedure of the comprehensive determination process in the comprehensive determination part 12 is demonstrated. First, the comprehensive determination unit 12 determines whether the determination result by the document determination unit 11 is a character-printed photo document or a printed photo document (S41). Here, if it is not a character-printed photographic document or a printed photographic document, that is, a character document, a photographic paper photographic document, or a character photographic paper photographic document, the determination result of the document determination unit 11 is prioritized, and the result is The final document type is set (S44). That is, if the document determination unit 11 determines that the document is a character document, the document type is a character document, and if it determines that the document type is a photographic paper photo document, the document type is a photographic paper photo document and a character photographic paper photo document. If it is determined, the document type is a character photographic paper photo document.

  On the other hand, when the determination by the document determination unit 11 is a character-printed photo document or a printed photo document (Yes in S41), it is next determined whether or not the determination result of the inkjet glossy paper document determination unit 10 is an inkjet glossy paper document. Determine (S42). Here, in cases other than the inkjet glossy paper document, the determination result of the document determination unit 11 is given priority, and the result is set as the final document type (S44). That is, the character-printed photo document is a character-printed photo document, and the print photo document is a printed photo document.

  On the other hand, when it is determined that the document is a character-printed photo document or a printed photo document and the determination result by the inkjet glossy paper document determination unit 10 is an inkjet glossy paper document (Yes in S42), it is determined that the document is an inkjet glossy paper document. Assuming that it is valid, the final document type is an inkjet glossy paper document (S43). This makes it possible to accurately determine an inkjet glossy paper document.

  As described above, in the color image processing apparatus 20 according to the present embodiment, the comprehensive determination unit 12 is provided in addition to the inkjet glossy paper document determination unit 10. When the inkjet glossy paper document discrimination unit 10 determines that the document is an inkjet glossy paper document, and the document discrimination unit 11 determines that the document is a character-printed photo document or a printed photo document, the document type is set to the inkjet glossy paper document. It is finally confirmed that.

  Therefore, if it is an inkjet glossy paper document based only on the determination by the inkjet glossy paper document discrimination unit 10, the photographic paper photograph document has the same characteristics on the luminance histogram. However, the photographic paper document is also included in the inkjet glossy paper document. By doing so, the inkjet glossy paper document and the photographic paper photographic document can be distinguished.

  However, since the color reproduction range of inkjet glossy paper originals is closer to that of photographic paper photographic originals, it is not a problem if the same image processing is applied to photographic paper photographic originals and inkjet glossy paper originals. 12 is not required to distinguish between an inkjet glossy paper original and a photographic paper photographic original.

  Next, an example of image processing (post-processing) suitable for an inkjet glossy paper document that is performed on a document that is determined to be an inkjet glossy paper document in the color image processing apparatus 20 of the present embodiment will be described. .

  In the case of an inkjet glossy paper document, the color reproduction area is significantly different from that of an inkjet plain paper document, and the color reproduction area of the inkjet glossy paper document is closer to that of a photographic paper document. Therefore, in the color image processing apparatus 20 of the present embodiment, the color correction unit 26 uses a color correction table (LUT) for a photographic paper document suitable for a photographic paper document, for a print document suitable for a print document, And an ink-jet glossy paper document suitable for the ink-jet glossy paper document, and if it is determined to be an ink-jet glossy paper document, color correction processing is performed using a color correction table for the ink-jet glossy paper document. .

  Similarly, the black generation and under color removal unit also includes a black generation process for an inkjet glossy paper document, and if it is determined as an inkjet glossy paper document, the black generation process for the inkjet glossy paper document is performed.

The color correction table for an inkjet glossy paper document described above can be created, for example, by using a color patch made of inkjet glossy paper. That is, RGB color patches are formed on glossy inkjet paper, and the colorimetric values L _* a _* b _* (CIE: Commission International de l'Eclairage: International Lighting Commission. L _* : lightness, a _* · b _* : The color patch is read by a color image input device (scanner) to obtain RGB values, and CMY color patches are output from the color image output device (color patch data is stored as electronic data). The colorimetric value L _* a _* b _* is also obtained. For these, use as many sample data as possible. The relationship between RGB-L _* a _* b _{* and} L _* a _* b _* -CMY obtained in this way is expressed using a transformation matrix or learned using a neural network. , RGB-CMY relationship is obtained and stored in the LUT.

  Note that there is no need to prepare a dedicated color correction table or black generation process for inkjet glossy paper originals, and the color correction unit 26 uses a color correction table as a photographic paper original suitable for a photographic paper original, In the case of a configuration having two types of print photo originals suitable for a print photo original, if it is determined as an inkjet glossy paper original, color correction processing is performed using a color correction table for a photographic paper original. That's fine. Similarly, when the black generation and under color removal unit determines that the original is an inkjet glossy paper document, the black generation process for the photographic paper document may be performed.

  In the color image processing apparatus 20 according to the present embodiment, when it is determined that the document is an inkjet glossy paper document, the spatial filter processing unit 28 performs spatial filter processing using a dedicated filter for inkjet glossy paper. As a filter for an inkjet glossy paper document, for example, a mixed filter that is emphasized in a low frequency portion and smooth in a high frequency portion can be considered. Normally, inkjet glossy paper originals are often printed by error diffusion processing, and the originals may have a rough surface with low density. In that case, a better image can be obtained when a smooth filter is used for output in the high frequency part. Further, when the low frequency component is emphasized, the edge in the photograph of the original is emphasized, and a clear and good image can be obtained. Therefore, a mixing filter as described above is considered desirable.

  In addition, although not adopted in the color image processing apparatus 20 of the present embodiment, the input tone correction unit is configured to output the document type determination signal to the input tone correction unit 24 and the smooth reproduction processing unit 30 as well. 24 or the processing in the smooth reproduction processing unit 30 may be switched according to the type of document, and it may be set so that a process suitable for an inkjet glossy paper document can be performed on a document determined to be an inkjet glossy paper document. It is done.

  Further, in the above description, the inkjet glossy paper document determination unit 10 determines that the inkjet glossy paper original determination unit 10 performs inkjet when the ratio T to the total number of pixels of the frequency (number of pixels) up to the predetermined brightness category N is larger than a predetermined threshold A. Although it is determined that the original is a glossy paper document, the comprehensive determination unit 12 subsequently makes a further determination and finally determines that the original is an inkjet glossy paper document. However, it is not always necessary to determine the document type.

  For example, the ink-jet glossy paper document discrimination unit 10 outputs an effective signal indicating that it is an ink-jet glossy paper document when the above condition is satisfied, and if it does not satisfy the above condition, it is not an ink-jet glossy paper document. The processing method may be switched by outputting the ineffective signal shown. In this case, for example, when a valid signal is output in the color correction unit and the black generation under color removal unit, a color correction table / black generation process for a photographic paper document is selected. Processing may be performed using a color correction table / black generation process for a photographic document.

  Next, a flat head scanner (image reading apparatus) 2 including a color image processing apparatus (image processing apparatus) 20 'according to another embodiment of the present invention will be described with reference to FIG. FIG. 12 is a block diagram showing a schematic configuration of the flat head scanner 2.

  As shown in FIG. 12, the flat head scanner 2 includes a color image processing apparatus including the color image input device 40 described above, the A / D conversion unit 21, the shading correction unit 22, and the document type automatic discrimination unit 23 described above. 20 ′, and based on the image data read by the color image input device 40, document type discrimination including an inkjet glossy paper document as one of the document types is performed. The image data thus subjected to each process and the document type determination signal from the document type automatic determination unit 23 are input to a computer or a printer. The above processing is controlled by a CPU (Central Processing Unit) (not shown).

  When the image data subjected to the image processing is input to the printer, the input image data is subjected to processing such as color correction processing and gradation reproduction processing, and is converted into the printer language by the printer language translation unit. Then, the data is input to an electrophotographic or ink jet printer (image output device) via a communication port driver / communication port (RS232C / LAN, etc.) and then output. The printer may be a digital multifunction machine having a copy function and a fax function in addition to the printer function.

  As another form, the document type automatic determination unit 23 may be provided in a computer. Then, the computer analyzes the RGB signal of the image data transmitted from the flat head scanner (including the color image input device 40, the A / D conversion unit 21, and the shading correction unit 22) to perform image processing. It may be.

  Further, for example, a selection unit (not shown) for inputting whether or not to perform image processing by the color image processing apparatus 20 ′ may be provided on the display panel of the operation unit (not shown) of the flat head scanner 2. Good. A signal may be output so that the type of image processing is changed according to the type of paper on which the original image is recorded, in accordance with an image processing command input to the selection unit.

  Each block (inkjet glossy paper document determining unit 10, document determining unit 11, and comprehensive determining unit 12) may be realized by hardware logic in the automatic document type determining unit 23, as described below. Alternatively, it may be realized by software using a CPU.

  That is, the document type automatic discrimination unit 23 of the color image processing apparatus 20 or 20 ′ includes a CPU (central processing unit) that executes an instruction of an image processing method for realizing the function of each block, and a ROM (read only) that stores the program. memory), a RAM (random access memory) for expanding the program, a storage device (recording medium) such as a memory for storing the program and various data, and the like. The automatic document type discrimination unit 23 can read the program code (execution format program, intermediate code program, source program) of the control program of the color image processing apparatuses 20 and 20 ′, which is software that realizes the above-described functions, by a computer. This can also be realized by supplying the recording medium recorded in (1) to the automatic document type discrimination unit 23 and reading and executing the program code recorded on the recording medium by the computer (or CPU or MPU). In this case, the program code itself read from the recording medium realizes the above-described function, and the recording medium recording the program code constitutes the present invention.

  Thus, in this specification, the means (unit) does not necessarily mean a physical means, but includes cases where the function of each means is realized by software. Further, the function of one means may be realized by two or more physical means, or the functions of two or more means may be realized by one physical means.

  That is, in the present embodiment, an image processing method for determining whether a document image is glossy and determining a document type is recorded on a computer-readable recording medium in which a program to be executed by a computer is recorded. You can also

  As a result, it is possible to provide a portable recording medium on which a program for performing an image processing method for determining glossiness and document type is recorded.

  In the present embodiment, as the recording medium, a memory (not shown) such as a ROM itself may be a program medium because processing is performed by a microcomputer. However, it may be a program medium provided with a program reading device as an external storage device and readable by inserting a recording medium therein.

  In any case, the stored program may be configured to be accessed and executed by the microprocessor, or in any case, the program is read and the read program is illustrated in the microcomputer. The program may be downloaded to a non-program storage area and executed. It is assumed that this download program is stored in the main device in advance.

  Here, the program medium is a recording medium configured to be separable from the main body, such as a tape system such as a magnetic tape or a cassette tape, a magnetic disk such as a floppy (registered trademark) disk or a hard disk, or a CD-ROM / MO /. Optical discs such as MD / DVD, IC cards (including memory cards) / optical cards, mask ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash It may be a medium that carries a fixed program including a semiconductor memory such as a ROM.

  In the present embodiment, since the system configuration is such that a communication network including the Internet can be connected, a medium that fluidly carries the program so as to download the program from the communication network may be used. When the program is downloaded from the communication network in this way, the download program may be stored in the main device in advance or may be installed from another recording medium.

  The recording medium is read by a program reading device provided in a digital color image forming apparatus or a computer system, whereby the above-described image processing method is executed.

  A computer system (image forming apparatus) includes an image input device such as a flatbed scanner, a film scanner, and a digital camera, a computer that performs various processes such as the above-described image processing method by loading a predetermined program, and a processing result of the computer Is composed of an image display device such as a CRT display or a liquid crystal display, and a printer that outputs the processing results of the computer to paper or the like. Furthermore, a network card, a modem, and the like are provided as communication means for connecting to a server or the like via a network.

  The present invention can also be expressed as follows. In other words, the image processing apparatus of the present invention includes an automatic document type determination unit that automatically determines a document type from input image data. In the image processing apparatus that performs an optimal process based on the determination result, an automatic document type determination is performed. The unit includes a histogram generation unit that obtains a histogram of the document from the input image data, and uses a predetermined density region feature amount of the histogram generated by the histogram generation unit to determine a predetermined density region feature amount. An inkjet glossy paper document discrimination unit that calculates and determines whether or not a predetermined condition is satisfied is provided.

  According to this, the inkjet glossy paper document discrimination unit uses the histogram information of the low brightness part (high density part) of the document to recognize the document type or whether the condition is satisfied (valid signal, By outputting (invalid signal), the recognition accuracy of the document type can be improved. Further, image quality can be improved by performing image processing suitable for a document.

  In the image processing apparatus of the present invention, the document type automatic discrimination unit further extracts a feature amount from the input image data and discriminates a document type such as a character document, a printed photo document, or a photographic paper photo document. And a comprehensive determination unit that determines the type of document by referring to the result of the inkjet glossy paper document determination unit when at least a printed photo document is included in the determination result of the document determination unit. Accordingly, the accuracy in discrimination from the inkjet glossy paper document can be improved.

The image processing method of the present invention automatically determines the document type from the input image data, and extracts the feature amount from the input image data in the image processing method for performing the optimum processing based on the determination result. A document determination step for determining a document type such as a document, a printed photograph document, a photographic paper photograph document, and the like, a feature value of a predetermined density region of a histogram generated by obtaining a histogram of the document, and a predetermined condition The document type is determined in the step of determining whether or not the above is satisfied. (effect)
According to this, using the histogram information of the low luminance portion (high density portion) of the document, the document type is recognized, or a signal indicating whether the condition is satisfied (valid signal, invalid signal) is output. Thus, the recognition accuracy of the document type can be improved. Further, image quality can be improved by performing image processing suitable for a document.

  It can be applied to full-color digital copiers and digital multifunction peripherals that can reproduce color images with high image quality using an electrophotographic process or an inkjet method, and can also be applied to uses such as flat head scanners.

1, showing an embodiment of the present invention, is a block diagram showing a schematic configuration of an automatic document type discrimination unit. FIG. FIG. 2 is a block diagram illustrating a schematic configuration of a digital color copying machine (image forming apparatus) provided with an automatic document type determination unit in an image processing apparatus. It is a flowchart which shows the process sequence of the said original classification automatic discrimination | determination part. FIG. 3 is a block diagram illustrating a configuration of an inkjet glossy paper document determination unit in the document type automatic determination unit. It is explanatory drawing which shows an example of the brightness | luminance histogram of an inkjet glossy paper original document. (A)-(f) is explanatory drawing which shows how to obtain | require the brightness | luminance classification N used in an inkjet glossy paper original discrimination | determination part. It is explanatory drawing which shows how to obtain | require the threshold value A used in an inkjet glossy paper original discrimination | determination part. It is a flowchart which shows the procedure of an inkjet glossy paper original discrimination | determination process. It is a figure which shows the flowchart which shows the procedure of a document discrimination | determination process. FIG. 6 is an explanatory diagram showing a distribution of areas for each document type in document type determination. It is a flowchart which shows the procedure of a comprehensive determination process. FIG. 10 is a block diagram illustrating a schematic configuration of a flat head scanner (image forming apparatus) that includes another embodiment of the present invention and includes an automatic document type determination unit in an image processing apparatus.

Explanation of symbols

1 Digital color copier (image forming device)
2 Flat head scanner (image reader)
10. Inkjet glossy paper document discrimination section (inkjet document discrimination means)
11 Document Discriminating Unit 12 Comprehensive Determining Unit (Inkjet Document Discriminating Unit / Comprehensive Determination Unit)
15 luminance conversion unit 16 histogram generation unit (histogram generation means)
17 Dynamic range determination unit (determination means)
20 Image processing device 20 'Image processing device 23 Document type automatic determination unit (document type determination means)
40 Image input device (reading means)
41 Color image output device (output means)

Claims (8)

A first step of creating a histogram indicating a relationship between a gray value indicating the pixel density and the number of pixels based on image data obtained by reading a document;
A feature value of a predetermined shade value region is obtained from the histogram created in the first step, and based on the obtained feature value, it is determined whether or not the document is an inkjet glossy paper document. And an ink jet document discrimination method comprising the steps of:   If it is determined in the second step that the document is an inkjet glossy paper document, it is determined whether the document type determination result based on the image data is a document including a printed photograph, and the printed result is a printed photograph. The method according to claim 1, further comprising a third step that corrects the determination in the second step when the document includes a document. Histogram generation means for creating a histogram indicating the relationship between the gray value indicating the pixel density and the number of pixels based on the image data obtained by reading the document;
Determining means for determining a feature value of a predetermined shade value area from a histogram created by the histogram generating means, and determining whether the document is an inkjet glossy paper document based on the determined feature value; An image processing apparatus comprising an ink jet document discrimination means including   The inkjet document determination means determines whether or not the document type determination result based on the image data is a document including a printed photograph, and when the determination result is a document including a printed photograph, The image processing apparatus according to claim 2, further comprising comprehensive determination means for validating determination that the document is an inkjet glossy paper document. In an image reading apparatus including a reading unit that reads a document and an image processing apparatus to which image data read by the reading unit is input,
An image reading apparatus comprising the image processing apparatus according to claim 3 or 4 as the image processing apparatus. Reading means for reading a document, image data read by the reading means, an image processing apparatus for performing image processing on the image data, and output for outputting image data processed by the image processing apparatus An image forming apparatus including:
An image forming apparatus comprising the image processing apparatus according to claim 3 or 4 as the image processing apparatus.   An inkjet document discrimination program for causing a computer to execute each step in the inkjet document discrimination method according to claim 1.   A computer-readable recording medium on which the inkjet document discrimination program according to claim 7 is recorded.

Images