JP2000295469A - Image forming device - Google Patents

Abstract

(57) [Summary] [PROBLEMS] To suppress deterioration of image quality when erroneously identified by area identification and to obtain an image with optimum image quality. Kind Code: A1 Abstract: Various document originals are input by an image input means, R, G, and B image data are output, and an image quality parameter input means allows a user to adjust an image quality adjustment parameter according to his or her own image quality preference. Input and image quality parameter storage means 3
The image quality parameter input by the image quality parameter input means 31 is stored in 2 and the image quality processed by the image processing means 3 based on the image quality parameter stored in the image quality parameter storage means 31 by the image quality parameter determination means 33. The parameters are determined, and the image processing means 3 determines the image quality parameter
The image processing unit 3 performs image processing using the image quality parameters determined in step 3 and outputs an image processed by the image processing unit 3.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an image forming apparatus for reading an image of a copying machine or the like to form a duplicate image.

[0002]

2. Description of the Related Art In an image forming apparatus such as a color / monochrome copying machine that reads a color / monochrome image to form a duplicate image, the quality of the duplicated image is important.

[0003] However, the required image quality greatly differs depending on the type of the original to be copied. For example,
In the case of a photo original, reproduction of color and gradation is important, and image quality faithful to the original is required. On the other hand, in a text document mainly composed of characters, sharpness is required more than the color of characters, and image quality that is easy to read is required.

Therefore, a conventional copying machine has a document mode (character / photo mode, character mode, photo mode, map mode, etc.) for optimizing the quality of a reproduced image on various types of documents. The original mode is selected according to the type of original to be copied, and the image is duplicated. Here, the character mode and the photo mode are modes for originals containing only characters and only photos, respectively. If both characters and photographs are mixed, the character / photo mode is used. In text / photo mode,
The apparatus automatically identifies the character area and the photograph area of the document, and realizes image quality suitable for the character and photograph areas as described above.

As described above, in the copying machine, an unspecified number of originals are targeted, and when the content of the image is uniform, the user selects an appropriate mode in the original mode such as the character mode or the photograph mode and outputs the image. are doing. When characters and photographs are mixed, a character / photo mode is selected as a document mode, and the apparatus performs image processing to automatically identify areas and obtain optimum image quality.

[0006] However, the area identification performed by the apparatus in the character / photo mode does not always have perfect identification accuracy, and may cause incorrect identification. If this identification is incorrect, the image quality of the mis-identified area will be significantly degraded depending on the conditions of the image processing, and if the area identified as the same area is incorrectly identified, the image quality will be at the boundary between the two. The problem of being different arises. Further, in order to reduce such a problem of erroneous identification, a difference in processing between categories to be identified (for example, characters and photographs) is reduced so that even if erroneous identification is performed, image quality degradation due to erroneous identification is reduced. It is designed to make it as unobtrusive as possible. However, the smaller the difference in processing between the plurality of categories to be identified, the smaller the degree of improvement in image quality when correctly identified. Therefore, for example, the image quality when a text-only document is output in the character / photo mode is generally inferior to that when the document is output in the character mode even if it is correctly identified.

[0007]

As described above, the area identification performed by the apparatus in the character / photo mode does not always have perfect identification accuracy, and may be erroneously identified. Depending on the conditions of the image processing, there is a problem that the image quality of the mis-identified area is extremely deteriorated, and that if the area identified as the same area is incorrectly identified, the image quality is different at the boundary between the two. In order to reduce the problem of erroneous identification, the processing difference between the identified categories is reduced so that even if the identification is erroneous, the deterioration of the image quality due to the erroneous identification is made as inconspicuous as possible. However, the smaller the difference in processing between the identified categories, the smaller the improvement in image quality when correctly identified,
For example, there is a problem in that the image quality when a text-only document is output in the character / photo mode is inferior to that when the document is output in the character mode even when the document is correctly identified.

SUMMARY OF THE INVENTION It is an object of the present invention to provide an image forming apparatus capable of suppressing deterioration of image quality when erroneously identified by area identification and obtaining an image with optimum image quality.

[0009]

An image forming apparatus according to the present invention includes an identification unit for identifying the type of an entire input original image, and an image processing unit for the original image based on the identification information identified by the identification unit. And output means for outputting a document image processed by the processing means.

An image forming apparatus according to the present invention has an input unit for inputting an original image, an identification unit for identifying the type of the entire original image input by the input unit, and a mode for setting image processing conditions for the original image. Selecting means for selecting information; processing means for performing image processing on the document image based on the mode information selected by the selecting means and the identification information identified by the identifying means; Output means for outputting the original image.

An image forming apparatus according to the present invention includes an input unit for inputting an original image, a first identification unit for identifying the type of the entire original image input by the input unit, and an original input by the input unit. An area is extracted from the image using the characteristics of the pixels, and second identification means for identifying the attribute of the extracted area, identification information identified by the second identification means, and the first identification means The image processing apparatus includes processing means for performing image processing on the document image based on the identified identification information, and output means for outputting the document image image-processed by the processing means.

[0012] An image forming apparatus according to the present invention includes an input means for inputting an original image, a first identification means for identifying the type of the entire original image input by the input means, and an identification means for identifying the type of the image. A second identification unit that identifies the original image input by the input unit on a pixel basis based on the identified identification information, and an image of the original image based on the identification information identified by the second identification unit. It comprises processing means for performing processing, and output means for outputting a document image image-processed by the processing means.

An image forming apparatus according to the present invention has an input unit for inputting an original image, a dividing unit for analyzing a layout of the original image input by the input unit and dividing an image area, and a dividing unit for dividing the image area. First identification means for identifying the type of each of the image areas and outputting first identification information; determination means for determining the accuracy of the division result of the division means or the identification result of the first identification means; A second identification unit that identifies the type of the entire original image input by the input unit and outputs second identification information; and the first identification information or the second identification information based on a determination result of the determination unit. Selecting means for selecting the first identification information, processing means for performing image processing of the document image based on the first identification information or second identification information selected by the selection means, and image processing by the processing means. Output original image And an output means that.

An image forming apparatus according to the present invention comprises: input means for inputting a document image; determining means for determining the complexity of layout of the document image input by the input means; and document image input by the input means. Dividing means for analyzing the layout of the image area to divide the image area; first identifying means for identifying the type of each image area divided by the dividing means and outputting first identification information; Second identification means for identifying the type of the entire input document image and outputting second identification information; and the first identification means based on the determination result of the determination means.
Selecting means for selecting the identification information or the second identification information, and processing means for performing image processing of the document image based on the first identification information or the second identification information selected by the selection means; Output means for outputting a document image subjected to image processing by the processing means.

[0015] An image forming apparatus according to the present invention comprises: input means for inputting a document image; identification means for identifying the type of the entire document image input by the input means and outputting identification information;
A first image processing unit for performing image processing on the original image input by the input unit; a second image processing unit for performing image processing on the original image input by the input unit; Storage means for storing the processed image output from the second image processing means and the processed image output from the first image processing means; and the storage means stored in the storage means based on the identification information of the identification means. Reading means for reading the processed image of the first image processing means or the processed image of the second image processing means, and the first image read by the reading means.
And output means for outputting the processed image of the image processing means or the processed image of the second image processing means.

According to the image forming apparatus of the present invention, an input means for inputting an original image, an identification means for identifying the type of the entire image by the presence or absence of characters in the original image input by the input means, The image processing apparatus includes processing means for performing image processing on the document image based on the identified identification information, and output means for outputting the document image image-processed by the processing means.

According to the image forming apparatus of the present invention, there is provided an input means for inputting a document image, and a uniform background image, a halftone dot background image, a halftone dot photograph image, and a continuous photograph as types of the whole document image input by the input means. Identification means for identifying one of the images, processing means for performing image processing of the original image based on the identification information identified by the identification means, and output means for outputting the original image image-processed by the processing means It is composed of

According to the image forming apparatus of the present invention, an input means for inputting an original image, a dividing means for analyzing a layout of the original image input by the input means to divide an image area, and a dividing means for dividing the image area First identifying means for identifying the type of each image area and outputting first identification information, measuring means for measuring a processing time of the first identifying means, and a document image inputted by the input means A second identification unit that identifies the entire type and outputs second identification information, and a selection unit that selects the first identification information or the second identification information based on a measurement result of the measurement unit. Processing means for performing image processing of the document image based on the first identification information or second identification information selected by the selection means, and output means for outputting the document image image-processed by the processing means It is composed of

According to the image forming apparatus of the present invention, an input means for inputting a document image, a dividing means for analyzing a layout of the document image inputted by the input means to divide an image area, and a dividing means for dividing the image area First identifying means for identifying the type of each image area and outputting first identification information, measuring means for measuring a processing time of the first identifying means, and a document image inputted by the input means A second identification unit that identifies the overall type and outputs second identification information; and a first identification unit that, when the identification processing of the first identification unit is completed within a predetermined time by the measurement by the measurement unit, The first identification information output from the identification means is selected, and the first identification information is measured by the measurement means.
Selecting means for selecting the second identification information output from the second identification means when the identification processing of the identification means exceeds a predetermined time; and selecting the first identification information or the first identification information selected by the selection means. The image processing apparatus includes processing means for performing image processing on the document image based on the second identification information, and output means for outputting the document image subjected to image processing by the processing means.

An image forming apparatus according to the present invention comprises: input means for inputting an original image; identification means for identifying the type of the entire original image input by the input means and outputting identification information;
First output means for mapping the identification information by the identification means as parameter information used for image processing and outputting identification map information; and a plurality of images based on the identification map information output from the first output means. It comprises an image processing means for performing the processing, and a second output means for outputting the document image subjected to the image processing by the processing means.

According to the image forming apparatus of the present invention, there is provided an input means for inputting a document image, a first identification means for identifying the type of the entire document image input by the input means and outputting first identification information. Changing the processing conditions based on the first identification information output from the first identification means, identifying the type of the original image input by the input means on a pixel-by-pixel basis, and outputting the second identification information A second identification unit that performs image processing by changing an image processing condition based on the second identification information output from the second identification unit, and an image processing unit that performs image processing. And second output means for outputting a document image.

An image forming apparatus according to the present invention analyzes an input means for inputting an original image and a layout of the original image input by the input means, and obtains an area of a uniform background, a halftone dot background, a halftone dot, and a continuous photograph. Dividing means, an identifying means for identifying each area divided by the dividing means on a pixel basis, a processing means for performing image processing of the original image based on the identification information identified by the identifying means, Output means for outputting a document image subjected to image processing by the processing means.

According to the image forming apparatus of the present invention, an input means for inputting a document image, a dividing means for analyzing a layout of the document image input by the input means to divide an image area, and a dividing means for dividing the image area First identifying means for identifying the type of each image area and outputting first identification information, measuring means for measuring a processing time of the first identifying means, and a document image inputted by the input means A second identification unit that identifies the type in pixel units and outputs second identification information; and a second identification unit that determines when the identification processing of the first identification unit exceeds a predetermined time in the measurement by the measurement unit. Selecting means for selecting the second identification information output from the identification means, and processing for performing image processing of the document image based on the first identification information or the second identification information selected by the selection means Means and image processing by this processing means. And an output means for outputting the document image is.

According to the image forming apparatus of the present invention, an input means for inputting a document image, a dividing means for analyzing a layout of the document image input by the input means to divide an image area, and a dividing means for dividing the image area A first identification unit for identifying the type of each image area and outputting first identification information; and a second identification unit for identifying the type of the entire original image input by the input unit and outputting second identification information. (2) identification means, selection means for selecting mode information for setting image processing conditions for the document image, and first identification means corresponding to the image processing conditions set in the mode information selected by the selection means Processing means for performing image processing of the document image based on the first identification information output from the CPU or the second identification information output from the second identification means; and a document image-processed by the processing means. image And an output means for outputting.

[0025]

An embodiment of the present invention will be described below with reference to the drawings.

An electronic copying machine usually comprises image input means such as a scanner, image processing means, and image output means such as a printer. The electronic copying machine is provided with an operation unit (control panel) for a user to make various settings. The operation unit is provided with an image quality parameter input unit, which will be described in detail later, and inputs an image quality adjustment parameter according to the user's preference of the image quality.

FIG. 1 is a diagram schematically showing the configuration of the image forming apparatus of the present invention. That is, the image forming apparatus includes an image input unit 1, a page information identification unit 2, an image processing unit 3,
And image output means 4.

Further, the image forming apparatus stores image quality parameter input means 31 for inputting image quality adjustment parameters by a user according to his / her own preference of image quality, and image quality parameters input by the image quality parameter input means 31. An image quality parameter storage unit 32 connected to the image processing unit 3 and an image quality parameter determination unit 33 for determining an image quality parameter to be processed by the image processing unit 3 based on the image quality parameter stored in the image quality parameter storage unit 32 are connected.

Hereinafter, an embodiment of the present invention will be described in detail with reference to FIG.

First, the image input means 1 is, for example, a color CC.
A unit image (for example, 400 dpi) obtained by reading a color image serving as an original by a D scanner and dividing the image into three primary color electric signals of R (red), G (green), and B (blue) vertically and horizontally.
The data is converted into 8-bit digital data for each color and output as R, G, and B, respectively.

Each of the RGB image signals is input to the page information identifying means 2 and the image processing means 3 for identifying the type of the entire image.

FIG. 2 shows an example of the image processing means 3, which includes a color conversion means 51, a spatial filter means 52, and an inking means 5.
3, a γ correction unit 54 and a gradation processing unit 55, and to each block, the page information output by the page information identification unit 2 is input together with the image signals output by all the blocks.

The color conversion means 51 converts the R, G, and B signals input from the scanner according to the following equation (1), and outputs C (cyan) and M corresponding to the signals of the image output means 4.
(Magenta) and Y (yellow) signals are obtained.

Dr = −logR Dg = −logG Db = −logB

[0035]

(Equation 1)

This operation is constituted by the circuit shown in FIG.
The color conversion means 51 includes look-up tables (LUTs) 61a to 61c for performing log conversion, nine multipliers 62a to 62i for performing a 3 × 3 matrix operation, and three adders 63a to 63c. You.

The color conversion means 51 uses the page identification signal.
The usage method is as follows, for example. First, the page identification information
As information, uniform background (with characters), halftone background (characters
Yes), halftone photos (only photos), continuous photos (only photos)
Is defined as Generally, in these four types of images,
In the case of continuous photographs using paper, it is known that blueness will increase.
Have been. Therefore, the color reproducibility is changed only for continuous photos.
Is desirable. To change the color reproducibility,
Color conversion matrix coefficient a₁₁~ A₃₃Need to change
is there. That is, the coefficient a for the continuous photograph₁₁~ A₃₃And other
Coefficient a for image ₁₁~ A₃₃Prepare the page identification information
Switch back to the original.

The spatial filter means 52 comprises, for example, a high-frequency component calculating section 71 as shown in FIG. 4, a multiplying section 72 for calculating the weight of the high-frequency component, and a subtraction section 73 from the original image. The high-frequency component calculation section 71 calculates, for example, a 3 × 3 Laplacian filter to emphasize the high-frequency component of the original image, and is configured by a filter as shown in FIG.

FIG. 6 shows a specific circuit configuration example of the spatial filter means 52. The high-frequency component calculating section 71 includes flip-flop circuits 71a to 71f and multipliers 71g to 71f.
p and an adder 71q. This circuit
It is required for each of the colors C, M, and Y. Here, the weight coefficient K
Is the image quality parameter determined by the image quality parameter determining means 33. By adjusting the weight coefficient K, it is possible to adjust the sharpness of the image.

The method of using the page identification information in the spatial filter means 52 is a method of changing the filter coefficient or the weight coefficient K shown in FIG. 5 based on the page identification information. For example, the weight coefficient K of the filter is set large for a uniform background or a continuous photograph, and the weight coefficient K is set small for a halftone background or a halftone photograph in order to suppress halftone moire.

The inking means 53 converts C (cyan), M (magenta) and Y (yellow) signals into C (cyan), M
This is a process for generating signals of (magenta), Y (yellow), and K (black), and is performed, for example, by the UCR process shown by the following equation.

K = a × min (C, M, Y) C ′ = CK M ′ = M−K Y ′ = Y−K a: Parameter for determining the amount of black It consists of the circuit shown. This circuit includes comparators 81a and 81b, selectors 82a and 82
b, and subtracters 83a to 83c.

As a method of using the page identification in the inking means 53, for example, there is a method of changing the inking rate a for each type of image. By setting the black ratio a large in a uniform background or a halftone background in the presence of characters, black characters can be more easily reproduced in a single black color, and the reproduction of characters can be improved.
In the case of a halftone dot photograph or a continuous photograph, the color reproducibility is emphasized by making the black ratio a small.

The gamma correction means 54 is a block used when correcting the density characteristics of the C, M, and Y printer units and when the user adjusts the density. The simplest configuration is shown in FIG. A look-up table (LUT) 90 of 8 bits input and 8 bits output as shown. In this table, for example, a density conversion curve as shown in FIG. 9 is set. By default, for example, a curve of 0 (curve in which the input and the output are equal) is set, and according to the image quality parameter determined to adjust the density by the user, -3 to -3.
The density curve corresponding to +3 is selected and set.

The γ correction means 54 has the following setting method based on the page identification information. For example, in the case of a uniform background or a halftone background when there are characters, γ used as γ correction
A high γ table is prepared and set as a curve. By doing so, the reproducibility of characters is improved. On the other hand, in a halftone photograph or a continuous photograph, it is preferable to set a linear input / output table with an emphasis on gradation reproducibility.

The gradation processing means 55 has eight C, M, Y, and K
This is a process of converting a bit signal into, for example, one bit (binary), and a typical method is an “error diffusion method”.

The "error diffusion method" is a method of adding a value obtained by multiplying the density of a target pixel by a weighting coefficient to a binarization error of a peripheral pixel that has already been binarized, and binarizing the pixel with a fixed threshold. FIG. 10 is a block diagram showing a configuration of the binarization processing by the “error diffusion method”. In FIG. 10, reference numeral 40 denotes an input image signal;
Is a correction means for correcting the image information of the target pixel, 411 is a corrected image signal, and 42 is the corrected image information of the target pixel.
A binarizing means for binarizing, 421 is a binarized image signal, 43 is a binarizing error calculating means for calculating a binarizing error of the binarized target pixel, 431 is a binarizing error signal, and 44 is a binarizing error signal. Weight coefficient storage means 45 for storing a weight coefficient for calculating a weight error, wherein a weight error is calculated by multiplying the binary error calculated by the binary error calculation means 43 by the weight coefficient of the weight coefficient storage means. Weight error calculating means, 451 is a weight error signal,
46 is an error storage means for storing the weight error calculated by the weight error calculation means 45, and 461 is an image correction signal. Hereinafter, the binarization processing of the “error diffusion method” will be described in detail.

The input image signal 40 of the γ correction means 55 is subjected to correction processing by an image correction signal 461 described later in the correction means 41, and a corrected image signal 411 is output. The corrected image signal 411 is compared with a binarization threshold Th (for example, 80h: h indicates a hexadecimal number) by the binarization unit 42, and the corrected image signal 411 is converted to a binarization threshold Th. If larger, "1" (black pixel) is output as the binary image signal 421, and if smaller, "0" (white pixel) is output. The binarization error calculating means 43 calculates the corrected image signal 411 and the binarized image signal 421 (here, 0h when the binarized image signal is “0” and ffh when the binarized image signal is “1”). , And outputs this as a binarized error signal 431. In the weight error calculating means 45, the weighting coefficients A, B, C, D (where A = 7/16, B = 1) of the weighting coefficient storage means 44 are added to the binary error signal 431.
/ 16, C = 5/16, D = 3/16) are calculated. Here, * in the weighting coefficient storage means 44 indicates the position of the pixel of interest, and the binarization error of the pixel of interest is multiplied by the weighting coefficients A, B, C, and D, and four pixels around the pixel of interest (the weighting coefficients A, A weight error of pixels corresponding to the positions B, C, and D) is calculated. The error storage unit 46 stores the weight error 451 calculated by the weight error calculation unit 45. The weight errors of the four pixels calculated by the weight error calculation unit are eA, e
The values are added to the areas B, eC, and eD and stored. The above-described image correction signal 461 is a signal at the position of *, and is a signal in which weight errors for a total of four pixels calculated by the above procedure are accumulated.

In the above description of the gradation processing means 55, the case where the output is binary has been described. However, by preparing a plurality of thresholds Th for binarization and comparing with the input image signal, the binary value is obtained. It is possible to perform multi-value processing in the same manner as in.

The gradation processing means 55 uses the page identification information as follows, for example. First, FIG.
(B) shows two cases in which the gradation processing means 55 outputs the two cases.

FIG. 11A shows a case in which a laser modulator (not shown) of the image output means 4 is modulated in units of two pixels. Since the pixel size is large even at the tonal level, the gray scale output is strong against fluctuations in recording and can be output stably.

On the other hand, FIG. 11B shows a case in which the laser is driven in units of one pixel, and the resolution is high although the stability of density fluctuation is lacking. In other words, a one-pixel modulation method with high resolution is used in the case of a uniform background or a halftone background in the presence of a character, and a two-pixel modulation with high density stability is used in the case of a halftone or continuous photo Use a method.

As described above, an example of the method of using the page identification information in each process has been described. However, the method of use is not limited thereto, and various methods can be considered.

The above is an example of the configuration of the image processing means 3.
The C (cyan), M (magenta), Y (yellow), and K (black) signals processed as described above are input to the image output means 4, and are recorded on paper and output.

Next, an embodiment of the page information identification means 2 will be described in detail.

FIG. 12 shows an example of the configuration of the page information identification means 2. The page information identification unit 2 includes an area identification unit 21 and a document type determination unit 22.

The page information identification means 2 takes in the document image, and the area identification means 21 physically or logically connects the pixels and neighboring pixels based on the data state of each pixel and neighboring pixels as one area. After extracting,
Measure the amount of features such as position, size, shape, structure, density distribution, etc. of each area on the image, and use the measurement results as text components such as characters, photographs, halftone dots, etc. based on predetermined rules. Identify as an area with attributes. Based on the attribute information and the like, the document type is determined from the characteristics of the entire document image input by the document type determination unit 22, and the image data format can be converted according to the document type.

Next, a specific embodiment of the page information identification means 2 will be described with reference to the drawings.

The area identifying means 21 is for arranging pixels having characters from the image data input by the image input means 1.

First, the image data input by the image input means 1 is separated into a plurality of binary image data according to the state such as the density difference and the saturation of the peripheral pixels. Divide and extract each region that is physically or logically connected, measure the position, size, shape, structure, density distribution, etc. of that region and determine the attribute as a document element I do.

As the types of document elements, characters, photographs, figures,
A table, a halftone dot, etc. are mentioned. As a specific method of separating the image data into a plurality of binary image data, there is a known method. For example, the method may be realized by a method disclosed in Japanese Patent Application No. 10-053317. In this case, the output of the image separation includes a character image, a halftone image, a background image,
Seven types of halftone image, color image, gray image, black image
Value-separated image data is generated.

As a specific method for extracting and identifying document elements, there is a known method. For example, the method may be realized by a method disclosed in Japanese Patent Application No. 8-34702. The region identification means 21 integrates the feature amounts of not only single image data but also a plurality of image data according to rules, and determines the region attribute of the input image data. For example, when an area is extracted at the same position from both the character image and the halftone image, the type of the area and the size of the area are determined. As a specific example, when a photographic area exists on a character image and a halftone pixel exists in the halftone image at the same position, it is determined as a gradation photographic area. As a specific method of determining an area attribute from a plurality of pieces of image data, there is a known method. For example, the method may be realized by a method disclosed in Japanese Patent Application No. 10-053317.

As will be described in detail later, the document type determining means 22 becomes a key such as a halftone dot or a photograph based on the result of each area being identified by the area identifying means 21 as a character, photograph, figure, table, halftone dot, or the like. By determining a feature amount such as the complexity of the document structure based on the presence or absence of a region and the degree of overlap of the rectangular regions, it is determined what type of document the input image data is.

The types of image data referred to here are, for example, 1 those in which the background is uniform and only characters, figures, tables, etc. exist.

(2) A halftone dot on the background, which has only characters, figures, tables, etc.

(3) An image having only halftone dots.

4 Those in which only continuous photographs exist.

5 At least one of a character, a figure, a table, and a halftone photograph are mixed, and a rectangular area can be extracted. A series of continuous photos, and a rectangular area can be extracted.

6 At least one of a character, a figure, a table, and a halftone picture are mixed, and a rectangular area cannot be extracted, or at least one of a character, a figure, a table, and a halftone dot One is a mixture of one and a series of photographs, and it is impossible to extract a rectangular area.

And so on.

FIG. 13 is a flowchart showing an example of a processing procedure in the page information identification means 2 shown in FIG. The processing flow of the image forming apparatus according to the present invention will be described with reference to this flowchart and the configuration of FIG.

First, an input image is captured by the image input unit 1 (step ST201). That is, an image is read from a document using an image input device such as a scanner, and is converted into image data by the image input unit 1.

The area identification means 21 reads one line or several lines at a time from the image input device, and separates it into a plurality of binary image data according to the state of each pixel such as the density difference and the saturation of the peripheral pixels. And figures are divided and extracted for each region that is physically or logically connected, and the position, size, shape, structure, density distribution, etc. of that region are measured, and the The type, importance, and the like are identified, and as a result, characters, photographs, figures, tables, and halftone dot regions are extracted (step ST202). Repeat until processing is completed for all pixels of the input image (step ST
203).

After all the pixel attributes have been determined, the document type determination means 22 identifies the characters such as characters, photographs, figures, tables and halftone dots for each area, and becomes a key such as a halftone dot or a photograph. By determining a feature amount such as the complexity of the document structure based on the presence or absence of a region and the degree of overlap of rectangular regions, it is determined what type of document the input image data is (step ST204). The details of the specific processing contents in the document type determination means 22 will be described later with reference to FIG.

After determining the type of the image data input as a document by the page information identification means 2 shown in FIG. 1, the image processing means 3 performs a conversion process of the image data format according to the document type ( Step ST20
5) Output the converted image data (step ST208).

FIG. 14 is a flowchart showing the details of the document type determination process of the document type determination unit 22 in the image forming apparatus of the present invention.
4 is a flowchart of a process performed in Step 4. The document type determination process is a process of determining what type of input image data is a document by using the region type result for each pixel.

First, an example of a document type classified in this processing will be described.

A document with a uniform base document means a document in which a photograph area and a halftone area do not exist. Therefore, either the character area alone or a blank state where nothing is applied corresponds to this.

A halftone dot original refers to a document in which a halftone area exists and a character area exists in the halftone area.

The halftone photo original is one in which a halftone dot region exists, a photograph region exists in the halftone dot region, and no character region exists.

A continuous tone photographic original is one in which a halftone area and a character area do not exist and only a photographic area exists.

The rectangular identification document does not satisfy any of the conditions of a uniform background document, a halftone background document, a halftone photographic original, and a continuous tone photographic original, and has no complicated layout structure. , Photos, figures and tables that can be divided for each area.

A document which has a complicated layout structure and cannot be divided into regions such as characters, halftone dots, photographs, charts, etc. is distinguished from other documents as an unidentifiable document.

In FIG. 14, pixel attribute data 151 is obtained by determining the attribute of each pixel of the input image data using the type and importance of the area of the complex image data identified by the area identification means 21. It is represented as an area for each document element.

First, data is read from the pixel attribute data 151 to check whether a halftone dot area exists (step ST).
301). If a halftone dot region exists, it is checked whether or not a photograph region exists (step ST302). If a photograph area exists, it is checked whether or not a character area further exists (step ST303). If there is a character area, it becomes the rectangle identification candidate document 152. Rectangle identification candidate document 152
Performs a process of verifying the complexity of the layout structure, and classifies the document into a rectangular identification document or an unidentifiable document. A detailed description of this processing will be described later with reference to FIG.

If the character area does not exist in step ST303, a halftone photographic original 153 is obtained.

If no photograph area exists in step ST302, it is checked whether a character area exists in the halftone dot area (step ST304). If a character area exists in the halftone dot area, the halftone dot original document 154 is obtained.

If no character area exists in the halftone area,
Further, it is checked whether a character area exists outside the halftone dot area (step ST305). If no character area exists outside the halftone dot area, the halftone dot photo document 153 is obtained. If a character area exists outside the halftone dot area, the document becomes the rectangle identification candidate document 152.

If there is no halftone dot area in step ST301, it is checked whether a photographic area exists (step ST301).
306). If there is no photographic area, a uniform base document 156 is obtained. If a photograph area exists, it is checked whether or not a character area further exists (step ST307). If there is no character area, a continuous tone photographic original 155 is obtained.
If a character area exists, the document becomes a rectangular identification candidate document 152.

By the above processing, the input image data is
It is determined to be one of a rectangle identification candidate document 152, a halftone photo document 153, a halftone background document 154, a continuous tone photo document 155, and a uniform background document 156.

FIG. 15 is a flowchart showing the details of the document type determination process of the document type determination means 22 in the image forming apparatus of the present invention, and is a flowchart of the process performed on the rectangular identification candidate document 152 shown in FIG. It is.

If it is determined that the document is a rectangle identification candidate document 152, a process for verifying the complexity of the layout structure is performed.
The document is classified as a rectangular identification document or an unidentifiable document, and as an example of an index for measuring the complexity of the layout structure at that time, the degree of overlap of rectangular regions may be measured. Although the overlap of rectangles may be directly verified, it is assumed that the number of comparisons will dramatically increase as the number of rectangular areas increases.
Therefore, the rectangular size may be voted in a two-dimensional voting space in which the degree of overlap is prepared in advance, and may be estimated from the state of the voting space (step ST401).

Since the voting space is for measuring the degree of overlap of the rectangular areas, the resolution may be lower than the resolution of the original image. The voting is performed by adding a feature such as the rectangular size of the rectangular area to a position where the coordinate position of the rectangular area is converted into the coordinate position of the voting space. As an example of the rectangle size, any of the width, height, area value, and the like of the rectangle can be used. In addition, the voting value may be weighted according to the attributes of the rectangular area, that is, attributes such as characters, photographs, charts, and halftone dots. For example, if an attribute that greatly affects the layout structure, such as a photograph or a chart, is given a higher weight and a character or the like is given a lower weight, the voting value of an area where the picture or chart overlaps becomes larger. Considering the complexity of the layout structure, overlapping of photographs and charts is classified as complicated. Therefore, in this case, it can be easily regarded as complicated. Also,
In order to perform the processing at a higher speed, it is possible to limit the rectangular area to be voted. For example, a small character area may not have a significant effect when determining a layout structure. In such a case, by limiting the size of the rectangle to be voted, the number of votes can be reduced, and as a result, it is expected that the speed will be increased. However, when the character area existing in the image data is composed of only a small character area, it cannot be simply excluded. In such a case, it is also possible to adjust the restriction according to the state of the pixel attribute data output from the area identification unit 21.

After all rectangular-size voting in the voting space is completed, the feature amount of the voting space is measured (step S).
T402). As the feature amount, for example, a statistic amount such as a maximum value or a variance may be used, or a voting space may be regarded as a multi-valued image, and after performing a binarization process, an area may be extracted. . In the former case, the determination can be made by comparing the calculated result with a preset threshold. In the latter case, the determination can be made by measuring the graphic features of the extracted region. is there. In step ST402, the former example is used. In this case, when the maximum value max or the variance value var is smaller than the threshold values a or b, the layout structure is considered to be uncomplicated and the rectangular identification document 157 is determined, and when it is larger, the layout structure is considered to be complex. It is determined that the document 158 cannot be identified (step ST40).
3).

The above is the detailed description of the document type determining means 22. As a result, the input image data is
53, halftone base document 154, continuous tone photographic document 155,
The original is determined to be one of the uniform background original 156, the rectangular identification original 157, and the unidentifiable original 158.

FIG. 16 is a flowchart showing details of the image conversion processing in the image processing means 3 of the image forming apparatus of the present invention, and is a flowchart of the processing performed in step ST205 shown in FIG. The image conversion process is a process of changing the format of input image data using the document type determination result.

The document type information 161 is stored in the document type determination unit 2
2 indicates the type of input image data, and includes a halftone photo original 153, a halftone background original 154, and a continuous tone photo original 15.
5, one of a uniform base document 156, a rectangular identification document 157, and an unidentifiable document 158.

First, it is checked whether the document type information 161 is an unidentifiable document (step ST501). If the original is not an unidentifiable original, it is checked whether the original is a rectangular identification original (step ST502). If the document is a rectangular identification document, an image conversion process is performed on input image data for each rectangular region using the pixel attribute information obtained by the region identification means 21 (step ST503).

The image conversion processing includes, for example, resolution, compression ratio, and number of colors. A rule of the data conversion process may be set in advance for each pixel attribute, and the image conversion process may be performed according to the rule. For example, in the case of a halftone dot photograph region or a continuous photograph region, remarkable image deterioration may not be observed even if conversion for lowering the resolution is performed or the compression ratio is increased, so that the amount of information can be reduced. If only black characters exist in the character area, the amount of information can be reduced by converting the multi-valued data into binary. By setting the rules of the image conversion process for each pixel attribute in advance in this way, it is possible to convert the image data into efficient image data.

As a result of the image conversion processing, the converted image data 16
Output as 2.

If it is determined in step ST502 that the document is not a rectangular identification document, uniform image conversion processing is performed on the entire image (step ST504). As a uniform image conversion process, for example, when the document type information 161 is a halftone photo document or a continuous tone photograph, remarkable image degradation is observed even if conversion is performed to lower the resolution or the compression ratio is increased. May not be
The amount of information can be reduced. Also, the document type information 161
If there are only black characters in a uniform background document, the amount of information can be similarly reduced by converting multi-valued data into binary. By setting the rules of the image conversion process for each type of image in the same manner as in step ST503, it is possible to convert the image data into efficient image data. In this case, since the same processing is performed on the entire image without performing the image conversion processing for each rectangular area as in step ST503, there is an advantage that the processing can be performed at high speed.

As a result of the image conversion processing, step ST503
Is output as the converted image data 162 in the same manner as the above.

If the document is an unrecognizable document in step ST501, the input image data is output as it is as the corrected image data without performing the image conversion processing using the information of the pixel attribute obtained by the area identifying unit 102 ( Step ST505). The image conversion process (step ST50)
3 and step ST504) are not limited to processing of input image data such as resolution, compression ratio, and number of colors, but may be processing of converting attribute area information into image data as described above.

As described above, the type of the input image data is determined from the result of the region identification, and the image conversion processing is performed according to the determined type of the image data, so that efficient image data with little deterioration in image quality can be obtained. It can be converted.

In the above description, an example in which only the page identification information is used to determine the processing conditions of each processing of the image processing means has been described. A method of using the rectangle identification information together with the page identification information will be described below.

FIG. 17 shows an example of a configuration in which page identification information and rectangle identification information are used as processing conditions for each processing of the image processing means. An area identification unit 6 is added to the configuration of FIG. 1, and rectangle identification information output by the area identification unit 6 is input to the image processing unit 7 together with page identification information output by the page information identification unit 2. . By using two pieces of information of the page identification information and the rectangle identification information, the image processing means 7 can set more detailed parameters.

For example, the page identification information is stored in FIG.
Information shown in Here, "0. area identification" indicates that the rectangular identification information output by the area identification means 6 is valid, while "1. uniform background to 4. continuous photograph" indicates page information identification means 2 Indicates that the page identification information output by is valid.

When the page identification information is "0. area identification", the image processing means 3 changes the image processing conditions in rectangular units by using the identification result in rectangular units by the area identifying means 3. On the other hand, when the page identification information is “1. uniform background to 4. continuous photograph”, this information is used as identification information for each page, and the image processing means 4 sets image processing conditions based on this information. , A uniform process is executed for each image. When the page identification information is used as described above, conventionally, five types shown in FIG. 18B are generally used as operation modes (operation modes according to the type of the original to be copied) of the apparatus for copying an image. However, the automatic mode as shown in FIG. 18C (the mode in which uniform processing is performed in image units and the mode in which processing is performed by changing processing conditions in units of rectangles or pixels) are also used as page identification information. And a mode for automatically selecting and outputting the same) can be provided, and an image with higher image quality than the character / photo mode can be obtained.

If the page identification information is “5. Unrecognizable”, it means that any of “0. Area identification to 4. Consecutive photographs” is invalid, and any of the identification information is invalid. Not available. Accordingly, the image processing means 7 performs uniform processing on the entire image without using the identification information, or performs image processing by identifying the type of the image on a pixel-by-pixel basis by the method described below.

FIG. 19 shows an example of the configuration of the image processing means 7 in the case of performing image processing by performing identification on a pixel basis.

The image processing means 7 shown in FIG. 19 has a configuration in which a pixel unit identification means 56 is added to the image processing means 3 for inputting the page identification information shown in FIG. In the configuration of FIG. 2, uniform page identification information for the entire image is input to the color conversion means 51 to gradation processing means 55, and each image processing determines image processing conditions based on the page identification information. . In the configuration of the image processing unit 7 shown in FIG. 19, instead of the page identification information, the pixel unit identification unit 56
Identifies the type of image in pixel units based on the input image information, and sets image processing conditions in each image processing block based on the identification information to perform processing.

As a processing method in the pixel unit identification means 56, for example, as a method of separating three regions of a character, a photograph, and a halftone dot photograph, a document “Dot Photo Identification Processing Method” (Transactions of the Institute of Electronics, Information and Communication Engineers) 87/2 Vol.J70-BN
o. 2) In “Block separation conversion method” (Block Se
parate Transformation Method: BSET method).

In this method, a target image is divided into blocks, and three regions are separated based on density changes in the blocks. At that time, the photograph has a small density change in the block.

In the case of a character or a halftone dot photograph, the density change in the block is large.

A character has a large cycle of density change.

The halftone photograph has a small cycle of density change.

The property of the density change is used.

The details will be described below.

(1) The target image is divided into blocks of (m × n) pixels.

(2) Maximum density signal Dmax in a block
And a minimum density signal Dmin, and a maximum density difference signal ΔDmax in the block is calculated.

(3) Threshold values Th1 and Δ set in advance
Dmax is compared, and a photographic area and a non-photographic area (text and halftone photographic area) are separated under the following conditions.

ΔDmax ≦ Th1 ... Photo area ΔDmax> Th1 ... Non-photo area (4) Each pixel in the block is binarized (0/1) by the average signal Da of the signal in the block.

(5) The number of times of 0/1 change Kh between consecutive pixels in the main scanning direction in a block is determined. Similarly, the number of changes Kv is obtained for the sub-scanning direction.

(6) Threshold values Th2 and K set in advance
h and Kv are compared, and the character area and the halftone picture area are separated under the following conditions.

Kh ≧ Th2 and Kv ≧ Th2... Halftone Photo Area Kh <Th2 or Kv <Th2... Character Area By the above procedure, it is possible to separate a character, a photo, and a halftone photo area. .

FIG. 20 shows an example of the circuit configuration of the pixel unit identifying means 56. The maximum density difference ΔDmax in the 4 × 4 window (the hatched portion represents the target pixel) shown in FIG.
Is a circuit for calculating. This circuit includes a selector 12a,
It comprises comparators 12b to 12g and a subtractor 12h.

Setting the processing conditions of the pixel unit identification means 56 using the page identification information is also an effective method for improving the identification accuracy.

FIG. 22 shows a configuration when the page identification information is used by the pixel unit identification means 8. The operation of the page information identification means 2 is as described above, but the pixel unit identification means 8 inputs the page identification information together with the input image data of the image input means 1 and performs identification based on the page identification information. Set parameters.

First, a case will be described in which the four pieces of information shown in FIG. 18D are output as page identification information, and a character area is identified using the above-described maximum density difference ΔDmax as a pixel-by-pixel identification method. Maximum density difference ΔDm
When ax is used, it is known that it is difficult to separate a halftone dot region from a character region. Therefore, using the page identification information, the threshold value Th = th1 in the uniform background region, Th = th2 in the halftone dot photograph region, and Th = th3 in the halftone dot photograph region and the continuous photograph region (where th1>th2> th3 ≒ 0. ). With this setting, it is possible to prevent the photograph area from being erroneously identified as the character area, and also to reduce the erroneous identification of the non-character area, even for characters in the halftone background area that is difficult to identify.
Very effective pixel-by-pixel identification can be performed.

In FIG. 18A, "6. time over" is provided as page identification information. The document type identification unit 22 shown in FIG. 12 is suitable for a method performed by software, and therefore, the processing time varies depending on the type of the input document. Therefore, the identification processing may not be completed within the processing time required by the image forming apparatus. "6. Time over" of the page identification information is set when the identification processing is not completed within a prescribed processing time defined by the system. In such a case, the image processing unit 7 performs identification in units of pixels without using page identification information, for example, as shown in FIG.
Each image processing can be performed based on this identification information.

In the document type identifying means 22, FIG.
(A), information such as "5. Unrecognizable" is output. This is the case where the flow of the identification processing is step ST403 in FIG.

FIG. 23 and FIG. 24 show an embodiment in such a case.

The image forming apparatus shown in FIG. 23 includes an image input unit 1, a page information identification unit 2, an image division unit 10, an area identification unit 11, an identification accuracy determination unit 12, and a selection unit 1.
3, an image processing means 14, and an image output means 4.

The image forming apparatus shown in FIG. 24 includes an image input unit 1, a page information identifying unit 2, a complexity determining unit 15,
Image dividing means 16, area identifying means 17, selecting means 18,
It comprises an image processing means 19 and an image output means 4.

When the recognition accuracy is low due to such a configuration, or when the complexity of the target image is very large, it is determined that the recognition is not possible. In such a case, the image processing means 1 is used.
For example, as shown in FIG. 19 which has already been described, it is possible to perform the pixel unit identification without using the page identification information and perform each image processing based on this identification information.

The embodiment described above is a typical method using page identification information. FIG. 25 shows another configuration example.

The image forming apparatus shown in FIG. 25 includes an image input unit 1, a page information identification unit 2, an image processing unit 25,
6, storage / readout means 27, storage means 28, and image output means 4. This configuration includes two image processing units 25 and 26 and a storage unit 28 for storing the processing results output by the image processing units 25 and 26. The configuration is such that the image is selectively read out from the image processing result and output as an image.

In the image processing means 25 and the image processing means 26, two types of image processing conditions irrespective of the page identification information,
For example, processing is performed using image processing parameters suitable for character images and image processing parameters suitable for photographic images. 2
Each type of image processing result is stored in a storage unit 28, for example, a memory or an HDD. If the processing result output from the page information storage unit 2 is a uniform background or a halftone background, the image processing unit 25 Is read out from the storage / readout unit 27 and output. On the other hand, if the page information output by the page information identification unit 2 is a halftone or continuous photograph, the image processing unit 26 The image processing result is read out from the storage means 28 and output.

In such a configuration, the processing of the page information identifying means 2 and the processing of the image processing means 25 and 26 are performed in parallel (that is, the image processing means 25 and 26 perform image processing without waiting for the output of the page information identifying means 2). Processing can be performed), and high-speed operation can be performed as an image forming apparatus.

As described above, the image processing means 3 shown in FIG. 1 uses the page identification information used in each image processing shown in FIG. 2, but the original mode and the page identification information indicating the operation mode of the apparatus, and FIG. 26 shows the relationship between the processing conditions of the image processing block.

In FIG. 26, the page identification result indicates the page identification information shown in FIG. 18A, and characters / photographs, characters, maps, printed photographs, and photographic paper photographs are color-converted, ground-processed,. .. Indicates the processing conditions of each image processing of the gradation processing, and indicates that the processing conditions are the same as those when each is selected as the document mode. The processing conditions for each image processing for the same page identification information are not necessarily the same, and symbols such as A, B,... Represent variations of parameters slightly different from those when the original mode is selected. Appropriate grouping and further segmentation are needed.

As described above, according to the embodiment of the present invention, when the contents of an image are uniform, the user can select an appropriate mode in a document mode such as a character mode or a photograph mode and output the image. Is the same as before, but if text and photos are mixed, select the text / photo mode as the original mode and automatically identify the area or the whole image as one category to obtain the optimum image quality It can be performed.

Further, the identification performed by the apparatus in the character / photo mode outputs not only the identification of the area but also the identification information of the entire image, and suppresses the deterioration of the image quality due to erroneous identification when the area is identified. Can be.

Further, in order to reduce such a problem of erroneous identification, the difference in processing between categories to be identified (for example, characters and photographs) is reduced, and even if the identification is erroneous, the image quality due to the erroneous identification is reduced. Is made as inconspicuous as possible, but by outputting the identification information of the entire image, the deterioration of the image quality can be suppressed. As a result, the degree of improvement in image quality when correctly identified is not reduced, and it is possible to obtain an output with higher image quality as compared with the related art.

[0145]

As described in detail above, according to the present invention,
It is possible to provide an image forming apparatus capable of suppressing deterioration of image quality when erroneously identified by region identification and forming an image with optimum image quality.

[Brief description of the drawings]

FIG. 1 is a block diagram schematically showing a configuration of an image forming apparatus of the present invention.

FIG. 2 is a diagram illustrating a configuration example of an image processing unit.

FIG. 3 is a diagram illustrating an example of a circuit configuration of a color conversion unit.

FIG. 4 is a diagram illustrating an example of a circuit configuration of a spatial filter unit.

FIG. 5 is a diagram showing a configuration of a filter.

FIG. 6 is a diagram showing a specific circuit configuration example of a spatial filter means.

FIG. 7 is a diagram showing an example of a circuit configuration of an inking unit.

FIG. 8 is a diagram showing a configuration example of a γ correction unit.

FIG. 9 is a view for explaining setting of a density conversion curve.

FIG. 10 is a diagram showing a configuration of a binarization process by an error diffusion method.

FIG. 11 is a diagram illustrating a gradation processing unit.

FIG. 12 is a diagram showing a configuration example of a page information identification unit.

FIG. 13 is a flowchart illustrating an example of a processing procedure in a page information identification unit.

FIG. 14 is a flowchart illustrating details of a document type determination process.

FIG. 15 is a flowchart illustrating details of a document type determination process.

FIG. 16 is a flowchart illustrating details of an image conversion process.

FIG. 17 is a diagram illustrating a configuration example of an image forming apparatus when using page identification information and rectangle identification information.

FIG. 18 is a view for explaining page identification information and a document mode.

FIG. 19 is a diagram illustrating a configuration example of an image processing unit that performs image processing by performing identification in pixel units.

FIG. 20 is a diagram illustrating a circuit configuration example of a pixel unit identification unit.

FIG. 21 is a view for explaining a 4 × 4 window;

FIG. 22 is a diagram illustrating a configuration example of an image forming apparatus when page identification information is used by a pixel unit identification unit.

FIG. 23 is a diagram illustrating a configuration example of an image forming apparatus when identification becomes impossible.

FIG. 24 is a diagram illustrating a configuration example of an image forming apparatus when identification becomes impossible.

FIG. 25 is a diagram illustrating another configuration example of the image forming apparatus when the page identification information is used.

FIG. 26 is a view showing the relationship between a document mode indicating an operation mode, page identification information, and processing conditions of each image processing block.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 1 ... Image input means (input means) 2 ... Page information identification means (identification means) 3, 7, 9, 14, 19, 25, 26 ... Image processing means (processing means) 4 ... Image output means (output means) 6 .., 11, 17... Area discriminating means (identifying means) 8... Pixel unit discriminating means (identifying means) 10, 16... Image dividing means (dividing means) 12. ... Complexity determination means (determination means) 27... Storage / readout means (readout means) 28... Storage means (storage means)

 ──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor, Naorou Kodaira 1 Toshiba-cho, Komukai Toshiba-cho, Saisaki-ku, Kawasaki-shi, Kanagawa Prefecture (72) Inventor Hiroaki Kubota Toshiba Komukai, Koyuki-ku, Kawasaki-shi, Kanagawa 1-cho, Toshiba R & D Center F-term (reference) PP27 PP28 PP31 PP32 PP33 PP38 PP43 PP47 PP78 PQ08 PQ12 PQ18 PQ22 PQ23 RR04 RR08 RR16 SS02 SS05 TT06 5L096 AA06 AA07 BA07 CA14 DA01 EA21 EA35 EA39 EA43 FA26 FA42 FA43 FA44 FA45 GA40 GA51 KA07

Claims (21)

[Claims] 1. An identification means for identifying the type of the whole input document image, a processing means for performing image processing of the original image based on the identification information identified by the identification means, And an output unit for outputting the selected document image. 2. An image forming apparatus according to claim 1, wherein said identification means identifies the type of the entire original image based on a configuration of a base. 3. An input means for inputting a document image, an identification means for identifying the type of the whole document image input by the input means, and a selection means for selecting mode information for setting image processing conditions for the document image Processing means for performing image processing of the document image based on the mode information selected by the selection means and the identification information identified by the identification means; and outputting the document image image-processed by the processing means. An image forming apparatus comprising: an output unit. 4. The image forming apparatus according to claim 3, wherein the identification information identified by the identification unit and the mode information selected by the selection unit are different types of information. 5. An input means for inputting a document image, a first identification means for identifying the type of the whole document image input by the input means, and a feature of a pixel from the document image input by the input means. A second identification means for extracting an area using the identification information, and identifying the attribute of the extracted area; identification information identified by the second identification means; identification information identified by the first identification means; An image forming apparatus comprising: a processing unit that performs image processing of the document image based on the image processing unit; and an output unit that outputs the document image that has been subjected to the image processing by the processing unit. 6. An input means for inputting a document image, a first identification means for identifying the type of the entire document image input by the input means, and identification information identified by the first identification means. A second identification unit that identifies the original image input by the input unit in pixel units; and a processing unit that performs image processing of the original image based on the identification information identified by the second identification unit. And an output unit for outputting a document image subjected to image processing by the processing unit. 7. An input unit for inputting a document image, a dividing unit for analyzing a layout of the document image input by the input unit and dividing an image region, and a type of each image region divided by the dividing unit A first identification unit that identifies the input unit and outputs first identification information; a determination unit that determines the accuracy of the division result of the division unit or the identification result of the first identification unit; A second identification unit for identifying the type of the entire original image and outputting the second identification information; and selecting the first identification information or the second identification information based on a determination result of the determination unit. Selecting means; processing means for performing image processing of the document image based on the first identification information or second identification information selected by the selecting means; outputting the document image image-processed by the processing means Output means for performing An image forming apparatus characterized in that. 8. The dividing means includes a uniform base, a halftone base,
8. The image forming apparatus according to claim 7, wherein the image is divided into halftone dots and continuous photograph areas. 9. The image forming apparatus according to claim 7, wherein said selecting means selects said second identification information when said dividing means cannot divide the image area. 10. An input means for inputting an original image, a determining means for determining the complexity of the layout of the original image input by the input means, and analyzing the layout of the original image input by the input means Dividing means for dividing the image area; first identifying means for identifying the type of each image area divided by the dividing means and outputting first identification information; and whole original image input by the input means A second identification means for identifying the type of the second identification information and outputting the second identification information; a selection means for selecting the first identification information or the second identification information based on a determination result of the determination means; Processing means for performing image processing on the document image based on the first identification information or second identification information selected by the selection means; output means for outputting a document image image-processed by the processing means; Equipped with An image forming apparatus comprising. 11. The image forming apparatus according to claim 10, wherein the selection unit selects the second identification information when the determination unit determines that the complexity is high. 12. An input means for inputting an original image, an identification means for identifying the type of the entire original image input by the input means and outputting identification information, and an input means for inputting the original image by the input means. First image processing means for performing image processing on a document image, second image processing means for performing image processing on a document image input by the input means, and a processed image output from the second image processing means. Storage means for storing the processed image output from the first image processing means; and a processing image of the first image processing means stored in the storage means based on the identification information of the identification means, or Reading means for reading the processed image of the second image processing means; output means for outputting the processed image of the first image processing means or the processed image of the second image processing means read by the reading means; , Image forming apparatus characterized by Bei was. 13. An input means for inputting an original image, an identification means for identifying the type of the entire image by the presence or absence of characters in the original image input by the input means, and identification information identified by the identification means. An image forming apparatus, comprising: processing means for performing image processing of the document image based on the image data; and output means for outputting the document image processed by the processing means. 14. An input means for inputting an original image, and identifying the type of the entire original image input by the input means as one of a uniform background image, a halftone background image, a halftone photographic image, and a continuous photographic image. Identification means for performing image processing of the document image based on the identification information identified by the identification means; and output means for outputting the document image image-processed by the processing means. An image forming apparatus comprising: 15. An input unit for inputting a document image, a dividing unit for analyzing a layout of the document image input by the input unit and dividing an image region, and a type of each image region divided by the dividing unit A first identification unit for identifying the information and outputting first identification information; a measurement unit for measuring a processing time of the first identification unit; and identifying a type of the entire original image input by the input unit. A second identification unit that outputs the second identification information by using the first identification information or the second identification information based on the measurement result of the measurement unit; and a selection unit that selects the first identification information or the second identification information. Processing means for performing image processing of the document image based on the first identification information or the second identification information thus obtained, and output means for outputting the document image image-processed by the processing means. Image forming apparatus characterized by the following . 16. An input means for inputting an original image, a dividing means for analyzing a layout of the original image input by the input means and dividing an image area, and a type of each image area divided by the dividing means A first identification unit for identifying the information and outputting first identification information; a measurement unit for measuring a processing time of the first identification unit; and identifying a type of the entire original image input by the input unit. A second identification unit for outputting the second identification information, and an output from the first identification unit when the identification processing of the first identification unit is completed within a predetermined time by the measurement of the measurement unit. Selecting the first identification information, and selecting the second identification information output from the second identification means when the identification processing of the first identification means exceeds a predetermined time in the measurement by the measurement means; Selecting means, and selecting by this selecting means Processing means for performing image processing on the document image based on the first identification information or the second identification information; and output means for outputting the document image image-processed by the processing means. Image forming apparatus. 17. An input means for inputting an original image, an identification means for identifying the type of the entire original image input by the input means and outputting identification information, and using the identification information by the identification means for image processing. First output means for outputting identification map information by mapping as parameter information; image processing means for performing a plurality of image processes based on the identification map information output from the first output means; To output the original image processed by
An image forming apparatus comprising: an output unit; 18. An input means for inputting an original image, a first identification means for identifying the type of the entire original image input by the input means and outputting first identification information, and the first identification A second identification unit that changes processing conditions based on the first identification information output from the unit, identifies the type of the original image input by the input unit on a pixel-by-pixel basis, and outputs second identification information Image processing means for performing image processing by changing image processing conditions based on the second identification information output from the second identification means; and outputting a document image image-processed by the processing means. 2
An image forming apparatus comprising: an output unit; 19. An input means for inputting an original image, and a dividing means for analyzing a layout of the original image input by the input means and dividing the layout into a uniform background, a halftone background, a halftone dot, and a continuous photograph area. An identification unit that identifies each region divided by the division unit on a pixel-by-pixel basis; a processing unit that performs image processing of the document image based on the identification information identified by the identification unit; And an output unit for outputting the selected document image. 20. An input device for inputting a document image, a dividing device for analyzing a layout of the document image input by the input device and dividing an image region, and a type of each image region divided by the dividing device A first identification unit that identifies the document and outputs first identification information; a measurement unit that measures the processing time of the first identification unit; A second identification unit that identifies and outputs second identification information; and a second identification unit that is output from the second identification unit when an identification process of the first identification unit exceeds a predetermined time in measurement by the measurement unit. Selecting means for selecting the second identification information to be selected; processing means for performing image processing of the document image based on the first identification information or the second identification information selected by the selecting means; The original image processed by An image forming apparatus characterized by including an output means for force, the. 21. An input device for inputting a document image, a dividing device for analyzing a layout of the document image input by the input device and dividing an image region, and a type of each image region divided by the dividing device First identifying means for identifying the document image and outputting first identification information; second identifying means for identifying the type of the entire document image input by the input means and outputting second identification information; Selecting means for selecting mode information for setting image processing conditions for the document image; first output from the first identification means corresponding to the image processing conditions set in the mode information selected by the selecting means; Processing means for performing image processing of the document image based on the identification information of the document or the second identification information output from the second identification means; and output means for outputting the document image image-processed by the processing means When An image forming apparatus comprising: