JPH07287767A - Document picture processor - Google Patents

Abstract

PURPOSE:To provide a document picture processor capable of simplifying an indication method for an object to be edited and executing specific edition such as the reduction of density in a part of a document without requiring complicated operation. CONSTITUTION:When an out-of-edition area indicating means 102 indicates an area not to be edited on a document picture of an input document to be edited, an indication area discriminating means 103 adds an indication area flag indicating corresponding relation between the area indicated by the means 102 and the document picture of the inputted original. An out-of-edition area discriminating means 104 converts the indication area flag added by the means 103 into an edition area flag indicating the editing area of the document picture. A document picture converting means 105 changes the density of an area extracted from the editing area indicated by the editing area flag and outputs a document picture 106 for an output document.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a document image processing apparatus capable of density conversion of a part of a document in a digital copying machine or the like.

[0002]

2. Description of the Related Art In recent years, the copying performance and various functions of digital copying machines have been remarkably improved. When copying a document of a paper manuscript using various functions of such a copying machine, for example, by lowering the density of characters that are not desired to stand out in the document, the distinction from the part to stand out can be made clear. , By reducing the character density of the text,
In some cases, it may be desirable to add a fashionable image, or to copy long texts by suppressing the contrast with the background to make high-quality documents that are easy on the eyes. is there.

In order to edit such a character, the conventional technique is not a copying machine, but the technique of the desktop publishing system can be used to perform the character modification on the character string. As such a technique, for example, Japanese Laid-Open Patent Publication No. 3-156666.
The technique of "document edit processing device" described in Japanese Patent No. 7 can be used. Here, a technique has been proposed in which the headline character string in a document can be modified by a simple operation based on the structure of the document. For documents that are not electronically encoded, for example, Japanese Patent Laid-Open No. 2-223275.
The technique of a digital color copying machine with an editing function can be used as in the "editing control system of image processing apparatus" described in Japanese Patent Publication No. By using this technique, it is possible to reduce the density of the characters of the document output on the paper by designating the color conversion as the editing method, and designating the editing range and the color.

[0004]

However, in the case of using the editing method such as the conventional digital color copying machine with the editing function, the range to be edited is designated first, and then the color (density) is designated. Two operations are required. Further, in this case, it is not possible to deal with a case where a part of the document is to be edited and left. For this reason, for example, when reducing the density of the entire text of a document, if there are several emphasized parts in it and you do not want to reduce the density of that emphasized part, the edit target area is selected in correspondence with the emphasized part. It is necessary to divide the image into a plurality of areas and perform an edit instruction operation as an edit object for each of the divided edit object areas. Therefore, there are problems that the editing operation becomes very complicated and complicated.

The present invention has been made in order to solve these problems, and an object of the present invention is to simplify the method of designating an object to be edited and to perform a part of a document without performing a complicated operation. With respect to the document image processing apparatus, it is possible to perform editing to reduce the density.

[0006]

In order to achieve the above object, the document image processing apparatus, which is the first feature of the present invention, is a non-editing target area designating means for designating an unedited area on a document image. (102), an instruction area discriminating means (103) for attaching an instruction area flag indicating the correspondence between the area instructed by the non-editing area instruction means and the document image of the input document, and the instruction area discriminating means. Based on the designated area flag, the edit area determining unit (10) converts the edit area into the edit area flag indicating the edit area.
4) and a document image conversion unit (105) for converting the density of the extracted area with respect to the edit target area designated by the edit area flag.

A second feature of the present invention, a document image processing apparatus, is an area dividing means (2) for dividing a collection of pixels on a document image into small areas as meaningful blocks of document elements.
02) and the small area divided by the area dividing means,
The lowest element counting means (203) for counting the number of the lowest elements in it, and the long sentence area discrimination for discriminating a long sentence area from the number of the lowest elements in the small areas counted by the lowest element counting means It is characterized by comprising means (204) and document image conversion means (205) for converting the density of the long sentence of the region extracted by the long sentence region discrimination means.

A document image processing apparatus as a third feature of the present invention is an area dividing means (3) for dividing a group of pixels on a document image into small areas as meaningful blocks of document elements.
02), a logical identifier assigning means (303) for assigning an identifier that gives a logical structure of a document to each of the small areas divided by the area dividing means, and an identifier assigned by the logical identifier assigning means. It is characterized by comprising an edit area discrimination means (304) for determining an area to be a density conversion target, and a document image conversion means (305) for converting the density of the area discriminated by the edit area discrimination means.

[0009]

In the first embodiment of the document image processing apparatus of the present invention, when the non-editing area designating means designates an area which is not edited on the document image, the designated area determining means causes the non-editing area designating means. A designated area flag indicating the correspondence between the area designated by and the document image of the input document is added. Based on the designated area flag added by the designated area determination means, the edit target area determination means converts the edit area flag into the edit area flag indicating the edit target area of the document image. Then, the document image converting means converts the density of the extracted area with respect to the edit target area designated by the edit area flag.

As described above, the user designates the area by the non-editing area designating means, but the area is designated as the area not edited. On the contrary, the edit target area discriminating means extracts the area which is not instructed to be the edit area. Then, the document image converting means changes the density of the edited area. As a result, even when a complicated edit area is designated, the designation of the area is simplified by designating the area that is not edited. Further, for example, the designation of the region is further simplified by designating the region in combination with the designation of the region to be edited.

In the document image processing apparatus which is the second feature of the present invention, the area dividing means divides a group of pixels on the document image into small areas as meaningful blocks of the document elements. When the lowest element counting means counts the number of lowest elements in the small areas divided by the area dividing means, the long sentence area determining means determines the lowest of the small areas counted by the lowest element counting means. The area of a long sentence is determined from the number of lower elements. Then, the document image converting means converts the long sentence density of the region extracted by the long sentence region discriminating means.

As described above, the least significant element counting means counts the number of the least significant elements (characters) of a meaningful block of the document element of the collection of pixels on the document image from the divided small areas,
That is, since the number of characters in each block of the character area is counted, the long-sentence area discriminating means discriminates and extracts a block corresponding to a long sentence from the character area based on the counted value. The document image conversion means changes the density of the extracted block area. Therefore, for example, if the area where the density of the image is changed is defined as the preliminary character area,
The instruction of the area can be omitted.

In the document image processing apparatus of the third aspect of the present invention, similarly, the area dividing means divides each group of pixels on the document image into small areas as meaningful blocks of the document elements. Therefore, the logical identifier assigning means
Each small area divided by the area dividing means is provided with an identifier that means the logical structure of the document. The editing area determination means determines the area to be the density conversion target, corresponding to the identifier assigned by the logical identifier assigning means.
Then, the document image converting means converts the density of the area discriminated by the editing area discriminating means.

As described above, in the document image processing apparatus, which is the third feature of the present invention, the "text", "heading",
Alternatively, an identifier such as "Note" that gives a logical structure of the document is given. In accordance with the assigned identifier, the editing area determination means determines, for example, a non-main character area to which the identifier “Note” is assigned, and based on the result of this determination, the document image conversion means determines Change the density of the area. Also in this case, as in the case described above, if the area in which the density of the image is to be changed is defined by the predetermined identifier, the instruction of the area can be omitted.

[0015]

Embodiments of the present invention will be specifically described below with reference to the drawings. FIG. 1 is a block diagram showing the basic configuration of the first embodiment of the document image processing apparatus of the present invention. In FIG. 1, 101 is an edit target document image, 102 is a non-edit target area designating section, 103 is a designated area determining section, 104 is an edit target area determining section, 105 is a document image converting section, and 106 is an edited document image. .

The non-editing target area designating section 102 is a functional element for inputting coordinates of a non-editing area, and a coordinate input device such as a digitizer, a light pen, a mouse, or a pointing device is used. Designated area discrimination unit 103
Is a processing function element for determining which region in the document image data of the document input as the editing target image 101 corresponds to the region designated by the non-edition region designating unit 102. The edit target area determination unit 104 is a processing function element that conversely extracts the edit target area so that the designated area is excluded from the edit target. The document image conversion unit 105 is a processing function element that converts the density or contrast of the image of the area to be edited extracted by the editing area determination unit 104 and generates an output image. The edited document image 106 is output from the document image conversion unit 105. A normal image forming processing device is used as the document image converting unit 105.

Next, the case where the document image processing apparatus constituted by such respective functional elements is applied to a digital color copying machine will be described as an example. Each functional element that constitutes the device is a publicly known example described above.
Since each functional element in the digital color copying machine as described in Japanese Patent No. 223275 can be used, description of each individual functional element will be omitted, and in the following description, the operation of document image processing will be described in order. I will explain later.

FIG. 3 is a block diagram for explaining the arrangement of the main part of the document image processing apparatus applied to the digital color copying machine. In FIG. 3, 20 is a document image processing device, 21 is an image scanner, 22 is a non-editing target area designation module, 23 is a designated area determination module, 24 is an edit target area determination module, 25 is a document image conversion module, 2
6 is a printer mechanism, 27 is a control module, and 28
Is the control panel section.

The control panel unit 28 is a functional element that receives an instruction such as density conversion from a user, and is composed of a keyboard including ten keys and function keys, a display, and the like. The control module 27 is a control unit that performs control processing such as data input / output processing for the control panel unit 28, image scanner 21 startup processing, and printer mechanism 26 startup processing. The control unit is configured by mounting a control microprocessor, and these control processing programs are programmed inside.

FIG. 2 is a diagram showing an example of a console panel in a digital copying machine. As shown in FIG. 2, the console panel 30 includes a ten-key unit 31 for designating the number of copies, a display unit 32 for the set number of copies, a copy button 33 for instructing a normal copy mode, and a partial density. A density conversion button 34 for instructing a conversion mode, a copy start button 35, and a status display section 36 are provided. The copy button 33 and the density conversion button 34 are internally provided with LED lamps indicating whether or not their functions are designated. In the state shown in FIG. 2, the state in which the density conversion mode is selected is displayed. is doing. next,
The operation of the processing when such a density conversion mode is selected will be described with reference to the flowchart.

FIG. 4 is a flow chart showing the flow of processing when density conversion is performed on a specified area.
The outline of the processing will be described with reference to FIG. When the power is turned on and the process is started, first, in step 40, a startup process is performed. Next, in step 41, it is determined whether or not the density conversion mode is designated. If the density conversion mode is not designated, the routine proceeds to step 42, where normal copying processing is performed. Then, the process returns to step 41 again, and the designation of the density conversion mode is determined.

When it is determined in step 41 that the density conversion mode is designated, step 43
The density conversion process is performed by designating a part of the area. In this process, first, in step 43, it is determined whether or not the start is instructed. If the start instruction is not determined, the process proceeds to step 44, the area instruction input acceptance processing is performed, the process returns to step 43, and it is determined again whether the start instruction has been performed. That is, the process of accepting the area instruction input in step 44 is repeated until the start is instructed. In this area instruction input, an area to be excluded from editing is designated.

When the area instruction input acceptance processing is completed and the start is further instructed, the density conversion processing from step 45 is performed in accordance with the input instruction area. In this process, the document reading process is performed in step 45, and then the designated area determination process is performed in step 46. Since the area specified here is the area to be excluded from the editing target for image editing, the next step 4
At 7, the editing area is extracted from the designated area. Next, in step 48, the character image of the extracted editing area is converted, and in the next step 49, the image is output. Then, the process returns to step 41, and the process is repeated from step 41 on the next document image according to the same process flow.

Next, a specific document image processing example of the partial density conversion processing in which such an area is designated will be described. FIG. 5 is a diagram showing an example of a monochrome input document input as a document image to be processed, and FIG.
FIG. 10 is a diagram illustrating an operation example when a region to be processed is specified in an input document. Further, FIG. 7 is a diagram partially showing image data of a document image in 256 gray scales, and FIG. 8 is a diagram partially showing image data when a designated area flag is provided in the image data. And FIG.
FIG. 6 is a diagram partially showing image data in a state in which a designated area flag is inverted to be an edit target area flag. Further, FIG. 10 is a diagram partially showing the image data in the state where the density conversion is performed on the designated area.
FIG. 1 is a diagram showing an example of a document image of an output document in which density conversion is finally performed. FIG. 12 is a diagram showing an example of an area table in a state where an area is designated.

Next, with reference to these FIGS. 5 to 12, the processing when the density conversion is performed for the designated area will be described. In the following description, an example of the operation will be sequentially described with reference to FIGS. 6 to 12 by taking the case of density conversion of the input document shown in FIG. 5 as an example. It should be noted that although coordinate values of Cartesian coordinates are used as a position reference when processing a document image, this coordinate axis is, as shown in FIG. Toward the y-axis.

When the power is turned on, the control module 27
Performs a startup process (step 40: FIG. 4), and the control panel unit 28 displays an initial screen on the status display unit 36 of the console panel. Next, when the user presses the density conversion button 34 on the console panel while the initial screen is displayed, the density conversion mode is instructed and the density conversion mode is set. If the density conversion mode is not designated, normal copying processing is performed. After entering the density conversion mode, the area instruction input is accepted until the copy start button 35 is pressed (steps 41 to 4).
4).

In the process of accepting the area instruction input (step 44), the user places an original on the digitizer of the non-editing area instruction module 22, and here, the user inputs the area of the area not edited. . That is, in this area instruction input processing, the area designation method and coordinates are input.
As the area specifying method, for example, the shape of an area such as a rectangle, a square, or a circle is specified, and the coordinates for the shape are input. As shown in FIG. 12, for example, when inputting a region in a rectangular shape, a rectangle is designated as the region designation method, and two points on the diagonal of the rectangle are designated as the start point and the end point. Although not shown, for example, when a circle is designated as the area designation method, the center point of the circle and one point on the circumference are designated as the start point and the end point. The area specified here is processed as an area not edited.

For example, with respect to a document image 51 of an input document as shown in FIG. 5, an image in which the density remains unchanged only in the area of a certain character string and the density is suppressed (decreased density) in the other areas. In the case of editing, the area designating method and the coordinates of the start point and the end point are input to the area of the portion not to be edited, as shown in FIG. In this case, for the document image 51 of the input document, a rectangle is designated as the first edit area 52 by the area designation method, the start point 53 and the end point 54 thereof are designated, and the area is designated as the second edit area 55. Specify the rectangle by the method and its start point 56 and end point 57
Instruct.

As described above, according to the contents of the designated area designating method and the input of the coordinates (start point, end point) thereof, the control module 27 sets the coordinate values designated as the area in FIG.
As shown in, the data is sequentially written in the area table 60. The example of the area written in the area table 60 is an example in which two rectangular areas in the document are designated as areas not to be edited. Then, when all areas not to be edited are designated for the document image, the original is placed on the original table (platen) and the copy start button 35 is pressed. When the copy start button 35 is pressed, the control module 27 subsequently sends a reading instruction signal to the image scanner to start reading the original image (step 45: FIG. 4).

When the original image is read, FIG.
As shown in FIG. 5, the read image data 61 is represented by tabular data and stored in an image memory (not shown). In this embodiment, the case where the input document is a monochrome document and the image scanner 21 reads the image data from the input document in a gray scale of 256 gradations is described as an example. However, in the case of a color document, R (red), G
For each of the three colors of (green) and B (blue), the same processing can be performed and the same effect can be obtained by performing image processing with 256 gradations as in the case of gray scale. Further, even in the case of a binary image, by setting the gradation of the white part to "0" and the gradation of the black part to "255", it is possible to treat it in the same manner as the case of the gray scale.

When the reading of the original image is completed, the read image data 61 and the coordinate data (area table 60) of the area designated and input as the non-editing target are sent to the designated area determination module 23, and the designated area determination is performed. Is performed (step 46). That is, in the designated area determination module 23, first, in the image data 61, an area designated as a non-editing target area and a non-designated area are distinguished. Therefore, the image data 61 is set as the image data 62 to which the designated area flag 63 is added as shown in FIG. When adding the designated area flags 63 to the image data 62, first, “0” is written as an initial value in all the designated area flags 62, and further, the area table 60 (see FIG.
Writing is performed with the designated area flag set to "1" only in the designated area based on the coordinate data of 2). For example,
In the area table 60 shown in FIG. 12, x1 ≦ x <x2 and y1 ≦ y <depending on the coordinates (x, y) of the start point and the end point.
A rectangular area satisfying y2 and x3 ≦ x <x4 and y3 ≦
Since two areas of the rectangular area satisfying y <y4 are designated, the designated area flag 63 of the point (dot) of the image data within the range of these two areas is set to "1". As a result, as shown in FIG. 8, the designated area flag 63 is set to "1" or "0", respectively.

In order to facilitate understanding in the description of this embodiment, the values set in the designated area flag 63 are only "0" and "1", but this designated area flag 63 is shown. Simultaneously uses another editing method, that is, in order to distinguish the area to be designated according to each editing method, the value of the designated area flag 63 is “0”.
Alternatively, a value other than "1" may be set. For example, when designating a region by another editing method (such as when converting to another density), to designate that region,
The value of the designated area flag is set to "2". As a result, the area can be designated separately from the first designated area. As a result, the region can be unaffected by the editing of the first density conversion.

In this way, the image data 62 to which the designated area flag 63 has been added is sent to the editing area discrimination module 24, and the editing area extraction processing is performed (step 47). That is, the edit target area determination module 2
4 is the image data 62 to which the designated area flag 63 is added.
When receiving the instruction area flag 6 of the image data 62,
As shown in FIG. 9, 3 is inverted and changed to the edit target area flag 64, and the image data 65 is processed. Specifically, when the designated area flag 63 is “1”, the edit target area flag 64 is set to “0”, and the designated area flag 63 is set.
If the value is "0", the edit target area flag 64 is changed to "1". As described above, if another editing method is also used and the value of the designated area flag is another value other than “1” or “0”, the designated area flag is set here. The value of 63 is the edit target area flag 64.
Since it is not changed to a value such as, it is not affected by extracting that area. The image data 65 after the editing area extraction process is performed is sent to the document image conversion module 25.

In the document image conversion module 25, based on the image data 65 having the edit target area flag 64,
A document image conversion process is performed (step 48). That is,
The document image conversion module 25 uses the edit target area flag 6
When the image data 65 to which 4 is added is received, the edit target area flag 64 is read dot by dot, and if the edit target area flag 64 is set (the edit target area flag is "1"), the dot The value of the image data of is read. Then, the value of the read image data is rewritten so as to have a density difference from the area other than the area to be edited (area where the area flag to be edited is “0”).

As a specific example of editing for making a density difference,
For example, as shown in FIG. 10, the value (density value) of the image data is set to 0.6 times only for the dot of the pixel whose edit target area flag is “1”. The value of the image data is rewritten in this way to obtain the edited image data 66. In this embodiment, the coefficient is multiplied by 0.6 when the density is converted. However, in the case of a copying machine which records using toner, it is about 0.3 to 0.
A coefficient of about 8 is applied.

Further, in the image conversion processing, an editing method may be used in which the background portion of the edit target area is gray instead of reducing the density of dots in the edit target area. In that case, instead of multiplying by a coefficient, for example, a coefficient 25 is added to the density value of the image data of all pixels in the editing target area (however, the maximum value of the added values does not exceed 255). To do. In the process of adding the coefficient 25, the background is grayed by 10%. Further, the user may individually specify the density to reduce the density. Further, an individual editing method such as a method of making the background gray may be selected by operating the control panel unit 28. The image data in which the value of the image data of each pixel is rewritten in this way is sent to the printer mechanism 26 and printed out (step 4).
9).

In this way, for the document image 51 of the input document as shown in FIG. 5, two areas are designated in the document, and the designated areas are edited. If you convert only the other background to gray,
As a result, the document image 67 of the output document as shown in FIG.
Is obtained.

By the way, in the above-described first embodiment, the user uses a coordinate input device such as a pointing device or a digitizer to edit the document image 51 of the input document, for example, except for an object to be edited for density conversion. The area to be edited is designated, and the area other than the editing target is designated to determine the editing target area, and the editing process is performed on the input image. In this way, by specifying the area other than the editing target,
By specifying the edit target area, the edit target area up to the peripheral portion of the document can be accurately specified. But,
The designation of such an area is the designation of the area by the user's manual operation, and the manual operation makes the operation complicated. On the other hand, using the conventional technology, the characteristics of the document image such as the character area or the chart area are automatically determined, and the area to be edited is specified (including the specification other than the object to be edited). May be configured to perform. Such a modification will be described as a second embodiment.

(Second Embodiment) FIG. 13 shows a second embodiment of the present invention.
3 is a block diagram showing the basic configuration of the document image processing apparatus of the embodiment. FIG. In FIG. 13, 201 is an edit target document image, 202 is a region division processing unit, 203 is a lowest element counting unit, 204 is a long sentence region determination unit, 205 is a document image conversion processing unit, and 206 is an edited document image.

The area division processing unit 202 is a processing function element that receives a document image and divides it into a character area, a figure area and the like. That is, a collection of pixels on the document image is divided into small areas as meaningful blocks of each document element,
The physical property of the area of the document image is recognized and the processing is divided into areas such as a character area and a figure area. The technology of such a functional element, that is, the technology of inputting a document image and dividing it into a character area or a graphic area based on its physical properties is conventionally known, for example, Japanese Patent Laid-Open No. 64-64-. Since a technique such as that proposed in Japanese Patent No. 15889 or Japanese Patent Publication No. 61-32712 may be used, detailed description thereof will be omitted here.

The area division processing unit 202 divides each area into rectangular areas and outputs the rectangular areas. Before performing the area division processing on the document image, inclination correction,
Preprocessing such as noise removal is performed. Further, in the area division processing unit 202, types of character elements, graphic elements, ruled line elements, and the like are further identified in each area of the document image divided here, and the types of these elements are also identified. It is added and output at the same time. Further, the characteristic of the area is further determined by the data of the element type. The sequence of elements of the document image output from the region division processing unit 202 as a result of dividing the region is called layout structure data of the document.

From the layout structure data obtained by the area division processing section 202, the lowest element counting section 203 determines the number of lowest element areas (areas corresponding to one character) for each character block of the character area. Count as the number of characters. For each area, when the number of characters is counted by the lowest element counting unit 203, the long sentence area determination unit 204 calculates the average value of the counted number of areas, based on the counted value.
The area of the character block larger than the average number of areas is determined as the edit target area. The document image conversion processing unit 205 converts the density and contrast of the area to be edited with respect to the area of the result of this determination, and generates an output image.
It is a processing function element output as the edited document image 206. A normal image forming processing device is used as the document image converting unit 205.

Next, the case where the document image processing apparatus according to the second embodiment configured by each of the above functional elements is applied to a digital color copying machine will be described as an example. Similar to the description of the first embodiment described above, the respective functional elements constituting the apparatus are the same as those in the digital color copying machine described in the above-mentioned publicly known Japanese Patent Application Laid-Open No. 2-223275. Since the functional elements can be used, the description of each individual functional element is omitted, and in the following description, the operation will be sequentially described according to the operation of the document image processing.

FIG. 14 is a block diagram for explaining the arrangement of the essential parts of the document image processing apparatus of the second embodiment applied to a digital color copying machine. In FIG. 14, 70 is a document image processing apparatus, 71 is an image scanner, 72 is an area dividing module, 73 is the lowest element counting module, 74 is a long sentence area discrimination module, 75 is a document image converting module, 76 is a printer mechanism, and 77 is Control module, 78
Is the control panel section.

The control panel unit 78 is a functional element that receives a conversion instruction from the user, and is composed of a keyboard including ten keys and function keys, a display, and the like. The control module 77 inputs / outputs data to / from the control panel unit 78,
The control unit is for performing control processing such as activation processing of the image scanner 71 and activation processing of the printer mechanism 76. A microprocessor for control is installed in the control unit, and a program for control processing is internally programmed in the microprocessor. These are the first
Is the same as that used in the embodiment.

FIG. 15 is a flow chart showing the flow of processing in the case of discriminating a character area of a document image and performing density conversion for the area. The outline of the processing will be described with reference to FIG. When the power is turned on and the process is started, first, in step 80, a startup process is performed. Next, in step 81, it is determined whether the density conversion mode is designated. If the density conversion mode has not been designated, the process proceeds to step 82 and normal copying processing is performed. Then, the process returns to step 81 again, and the designation of the density conversion mode is determined.

When it is determined in step 81 that the density conversion mode is designated, step 83
By the processing from 1), the character area of the document image is discriminated and the density conversion processing is performed on the area. In this process, first, in step 83, it is determined whether or not the start is instructed. If the start instruction has not been determined, the process returns to step 83 again, and it is determined again whether or not the start instruction has been given. In other words, it enters a dynamic loop that waits until the start is instructed.

When it is determined in step 83 that the start is instructed, the process proceeds to step 84,
Performs document scanning processing. Next, in step 85, the process of dividing the area of the document image is performed, the layout structure data is taken out, and in the next step 86, the process of counting the number of characters that counts the region of the lowest element for each divided region. I do. Then, in step 87,
A process of determining a long sentence area is performed from the count value counted as the number of characters for each area. Then, in the next step 88, a character image conversion process is performed in which the density of the character image is converted using the determined long text area as an editing area, and in the next step 89, an image is output. Then, the process returns to step 81, and the process is repeated from step 81 according to the same process flow for the next document image.

Next, with respect to the processing in the case where the area of the document image to be edited is determined and the density conversion is partially performed according to the result of the area determination, a specific processing example of the document image will be described. To do. FIG. 16 is a diagram showing an example of area determination data obtained as a result of performing area determination on a document image to be processed, and FIG. 17 is a determination result of a hierarchical structure in one character block area of the area determination result. It is a figure explaining the corresponding relationship between and an input document. Also, FIG.
8 is a diagram showing region data of a hierarchical structure of a determination result in one region of the region discrimination data, and FIG. 19 is a diagram showing a character number table storing count data counted as the number of characters for each determination region. . FIG. 20 is a diagram showing an example of an output document of a document image in a state in which the density conversion is finally performed on the determined long text area. In the document image (FIGS. 16 and 20), as in the case described above, since the position of the region is represented, the coordinate value of the Cartesian coordinate is used as the position reference, and this coordinate axis is as shown in the figure. In addition, the x-axis is set to the right of the page, and the y-axis is set to the bottom of the page.

Next, description will be made with reference to FIGS. 16 to 20. When the power is turned on, the control module 77 performs a start-up process to display an initial screen on the control panel unit 78 (step 80). The user
A desired operation is performed on the control panel unit 78 to instruct, for example, a density conversion mode (“density conversion”).
When the button is pressed), the density conversion mode is entered. If not, normal copying processing is performed. After entering the density conversion mode, the process waits until the copy start button for instructing "start" is pressed (steps 81 to 83).

Next, when the user puts the original on the platen and presses the copy start button, the control module 77 is pressed.
Activates the image scanner 71. The original image is read from the image scanner 71, and as the digital image data, the area dividing module 7 of the document image processing apparatus 70.
Handed over to 2. The area division module 72 performs area division processing, for example, performs area division processing on the document image 51 of the input document as shown in FIG. As a result, as shown in FIG. 16, with respect to each area of the document image data 91, an area (character block area) 92 in which characters are arranged side by side, an area (ruled line area) 93 in which a ruled line exists, Other blank area (margin area) 94
Is divided into and

Here, the rectangle representing each area is the smallest rectangle that has sides parallel to the x-axis and y-axis directions of the original image and surrounds the target area. The data expressing this rectangular area is basically expressed by a set of five data of "type, upper left point x coordinate, upper left point y coordinate, width, height". The rectangular data representing the area is each element of the layout structure data, and these elements are hierarchical structure data. For example, when the rectangular area is the character block area, as shown in FIG. 17, the data of the character line area, which is an element of the layout structure data, is set as the lower area data in the character block area. Further, for the data in the character line area, there is character area data for each character, which is the lowest element of the layout structure data, as the lower area data in the character line area.

For example, when the area determination is performed on the document image 51 of the input document as shown in FIG. 5 by the area division, as shown in FIG. 17, the character string "this report The customer satisfaction degree is divided into areas of "○○○○○", and the uppermost character block area 101 has a character line area 102 as a lower area thereof. Further, each area of the character area 103 is determined as an element of the lower layout structure data, and is divided into respective area data. Note that, in FIG. 17, the character string portion of the text and the area data thereof are shown corresponding to each area data having the hierarchical structure 100.

The area data having each hierarchical structure thus divided into areas is expressed as tabular record data as shown in FIG. 18, and each area data is stored in the area table 104. One record data of this area table 104 represents one area data. As described above, the record data of each area data here is “type, upper left point x coordinate, upper left point y.
In addition to the data of each field that represents an area composed of a set of five data of "coordinate, width, and height", in order to express the hierarchical structure of each area, a subelement number field 105 Field data of the lower element start number field 106 is added. The number of character areas in one character block area can be counted as the number of characters by sequentially tracing the hierarchical structure of the two field data of the lower element number field 105 and the lower element start number field 106.

That is, the lowest element counting module 73 performs a process of counting the number of lowest element areas for each character block area from the layout structure data obtained by the area dividing module 72. In this processing, the layout structure data whose topmost area is a character block area, specifically, in the area table 104 as shown in FIG. 18, the data of the type field is “character block” With respect to the record data in the specified area, the elements of the area data on the lower side are traced from the hierarchical structure. Then, finally, the number of elements up to the area data in which the data of the lower element start number field 106 is "0" (that is, the area data of the lowermost element that has no element linked below it) is counted. To do.

Explaining in detail with an example of the data of the area table 104 shown in FIG. 18, the area data of the character block area in which the value of the number field is "1" includes the lower element number field 105 and the lower element start number field. According to the data of 106, the lower element is only the character line area whose value in the number field is "11". Further, in the area data of the character line area having the value of the number field of "11", the lower-order elements are the data of the character area having the values of the number field of "50" to "59". In the area data of these character areas, since there are no elements linked below it, the number of lowest elements is calculated as "10". The result of counting the number of characters for each character block area thus obtained is sent to the long sentence area determination module 74 together with the layout structure data.

In the long sentence area discrimination module 74, the data of the number of characters and the data of its layout structure which have been sent are stored in the character number table 107 for each character block area, as shown in FIG. To do. Then, the average value of the number of characters obtained for each area is calculated, and the character block region having the larger number of characters than the calculated average value is determined as the long sentence area. In the example shown in FIG. 19, two areas having character block numbers “5” and “7” are determined to be long sentence areas, and a determination flag is set in the determination result field.

The long sentence area thus determined is used as the image editing area, and the density conversion is performed here. For example, the document image 51 of the input document as shown in FIG. 5 is divided into regions, and two long sentence regions are determined for the divided character block region, as shown in FIG. Data of the judgment result is obtained. Then, for the character block area determined to be the long sentence area, the area indicated by the area data “upper left point x coordinate, upper left point y coordinate, width, height” is set as the editing area. Next, as in the case of the first embodiment, the edit target area flag is added to the image data of the pixels within the range of the edit area, and the character block area of the character block area determined to be the long sentence area is added. After performing the process of setting the edit target area flag to “1”, the image data is transferred to the document image conversion module 75.

The document image conversion module 75 performs the same processing as that of the first embodiment, and applies the predetermined coefficient (as described above) to the image data of the area in which the edit target area flag is "1". 0.6) is applied to reduce the density, or a predetermined value of the image data in each area is added to perform density conversion to make the background gray. In this way, the image data after the image conversion is transferred to the printer mechanism 76 and output as a document image of an output document. As a result, when the long sentence area is determined and the background image of the area is edited to be gray in the document image 51 of the input document as shown in FIG.
As shown in 0, the document image 108 of the output document obtained as a result of the area in which the character string is collected being edited in gray is output.

In the second embodiment described above,
By using the conventional technology, the physical characteristics of the document image such as the character area or the chart area are automatically determined to specify the editing area of the document image, and the area to be edited is specified (other than the editing object). The specification of the editing area of the document image is performed, and the physical characteristics of the document image such as the character area or the chart area are determined and further edited. The area may be modified based on the logical characteristics peculiar to the document image of the input document. The logical characterization in that case is, for example, by associating regions with logical meanings such as “title”, “author”, “text”, etc., corresponding to each element of the layout structure data. Keep it. Next, a document image processing apparatus of such a modification will be described as a third embodiment.

(Third Embodiment) FIG. 21 shows the third embodiment of the present invention.
3 is a block diagram showing the basic configuration of the document image processing apparatus of the embodiment. FIG. In FIG. 21, reference numeral 301 is an edit target document image, 302 is an area dividing processing unit, 303 is a logical identifier assigning unit, 304 is an editing area determining unit, 305 is a document image conversion processing unit, and 306 is an edited document image.

The area division processing unit 302 is the same as the area division processing unit 202 described in the second embodiment, and is a processing function element for dividing a document image into a character area, a figure area and the like. is there. Also in this case, the area division processing unit 302 further identifies character elements, graphic elements, ruled line elements, and the like in each area of the divided document image, and the types of these elements are also area data. The layout structure data added to is output.

The logical identifier assigning unit 303 receives the elements of the layout structure data obtained by the area division processing unit 302 as inputs, and assigns logically meaningful identifiers such as “title”, “author”, and “text” to each. It is a processing function element to be given. Specifically, for example, the technique described in Japanese Patent Laid-Open No. 5-159101 is used. The logical identifier assigning unit 303 registers in advance a document structure model that represents the correspondence between the layout structure to be recognized and the logical structure, and logically assigns a logical structure to each area by matching the area division result data with the structural model. Assign a name that expresses the meaning.

The editing area discriminating unit 304 is a functional element that determines an area to be edited based on the logical identifier given by the logical identifier giving unit 303. For example, when editing the layout structure of a document image to remove large characters such as titles and lighten the density of only small characters, "text", "page number", "header", "footnote" of the document structure , The element to be edited is specified by the name of the logical structure such as "author". As a result, the edit area determination unit 304 determines the edit area in the document image correspondingly, and sets the edit area instruction flag. For the editing area of the result determined in this way,
The document image conversion processing unit 305 is a functional element that converts the density and contrast of the area to be edited, generates a document image of the output document, and outputs the edited document image 306. This is similar to that of the first and second embodiments.

Next, as an example, the document image processing apparatus of the third embodiment constituted by the respective functional elements as described above is applied to a digital color copying machine as in the case described above. An operation example will be described. Similar to the above description of the first embodiment, each functional element constituting the device is
Since the respective functional elements in the digital color copying machine described in the above-mentioned publicly known Japanese Patent Application Laid-Open No. 2-223275 can be used, description of each individual functional element will be omitted, and the following description will be given. Now, description will be made step by step according to the operation of the document image processing.

FIG. 23 is a block diagram for explaining the arrangement of the essential parts of the document image processing apparatus of the third embodiment applied to a digital color copying machine. In FIG. 23, 120 is a document image processing device, 121 is an image scanner, 122 is an area dividing module, 123 is a logical identifier assigning module, 124 is an editing area determination module, 125 is a document image converting module, 126 is a printer mechanism, 127 is a The control module 128 is a control panel unit.

The control panel unit 128 is a functional element that receives a conversion instruction from the user, and is composed of a keyboard including ten keys and function keys, a display, and the like. Control module 127
Is a control unit for performing control processing such as data input / output processing for the control panel unit 128, image scanner 121 startup processing, and printer mechanism 126 startup processing. It is similar to that used in these first embodiments.

FIG. 24 is a flow chart showing the flow of processing in the case where each area of a document image is discriminated by a logical identifier and density conversion is performed on that area. The outline of the processing will be described with reference to FIG. When the power is turned on and the process is started, first, in step 130, a startup process is performed. Next, in step 131, it is determined whether the density conversion mode is designated. If the density conversion mode is not designated, the routine proceeds to step 132, where normal copying processing is performed. And again, step 1
Returning to step 31, the designation of the density conversion mode is judged.

If it is determined in step 131 that the density conversion mode is designated, step 1
By the processing from 33, each area of the document image is discriminated by the logical identifier and the density conversion processing is performed on that area.
In this process, first, it is determined in step 133 whether or not the start is instructed. If the start instruction is not determined, the process returns to step 133 again, it is determined again whether or not the start instruction is given, and the process waits until the start instruction is given.

When it is determined in step 133 that the start is instructed, the process proceeds to step 134, and the document reading process is performed. Then, step 135
In step 1, the document image is divided into areas, the layout structure data is extracted, and in step 136, a process of assigning a logical identifier to the extracted layout structure data is performed. That is, the extracted layout structure data is matched with the held structure model, and an identifier indicating what kind of document structure the topmost element of the layout structure has a logical meaning is given. This identifier is "title", "author",
It is an identifier that means an element of the document structure such as “subtitle”, “text”, and “footnote”.

Next, in step 137, a process of discriminating the region to be edited is performed according to the identifier given to each region. Then, in the next step 138,
A character image conversion process for converting the density of the character image is performed on each of the determined editing areas, and the following step 139 is performed.
At, the image is output. Then, the process returns to step 131, and the process is repeated from step 131 on the next document image according to the same process flow.

In this manner, the process of dividing the area of the document image to be edited and performing the density conversion on the area determined by the logical identifier given to the divided area will be described below. An example of image processing will be described. FIG. 22 is a diagram showing an example of a logical identifier of the document structure, and FIG. 25 is a diagram showing an example of a structural document model associated with each area of the document image. FIG. 26 is a diagram showing the correspondence relationship with the logical identifiers associated with the elements of the layout structure data. In addition, FIG. 27 is a diagram illustrating an example of edit target determination data that specifies an area to be extracted as a candidate for an edit target by a logical identifier. FIG. 28 is a diagram showing an example of area determination data determined by a logical identifier, and FIG. 29 shows a document image in a state in which density conversion is finally performed on an area designated by the area determination data. It is a figure which shows an example of an output document. Note that, as in the case described above, in order to represent the position of the area, the coordinate values of the Cartesian coordinates are used as the reference of the position.
As shown in, the x-axis is set to the right of the page of the document image, and the y-axis is set to the bottom of the page.

This will be described with reference to FIGS. 22 and 25 to 28. When the power is turned on, the control module 12
7 performs the startup process, and the control panel unit 12
The initial screen is displayed at 8 (step 130). The user operates the control panel unit 128 to instruct the density conversion mode (press the "density conversion" button).
Then, the density conversion mode is set, but if not, normal copy processing is performed. After entering the density conversion mode, wait until the "start" button is pressed (steps 131 to 131).
133).

When the user places the manuscript of the document to be edited on the platen and presses the "start" button, the control module 127 activates the image scanner 121, and the document image of the manuscript is read and converted into digital image data. , And is passed to the area division module 122 (step 13).
4). As in the second embodiment, the area division module 122 performs area division processing on the document image and transfers the layout structure data resulting from the processing to the logical identifier assignment module 123 (step 135).

The logical identifier assigning module 123 matches the received layout structure data with the document structure model (FIG. 25) held therein, and the highest element of the divided area data of the hierarchical structure of the layout structure data is
An identifier indicating what kind of logical meaning it has in the document structure is given (step 136).

The identifiers here are, for example, as shown in FIG. 22, "title", "author", "subtitle", "text", "footnote", "footnote" which means each constituent element for the document structure. It is data of a flag that distinguishes each of "ruled lines" and the like. The highest element in the layout structure data is an element that is not a lower element than any of the elements in the layout structure data. For example, the character block area that is the area data of the hierarchical structure is the highest element. One identifier is assigned to the entire character block. Therefore, the character line area and the character area, which are subordinate elements, are not the targets to which the logical identifiers are given individually.

Usually, in a document distributed in a certain range (paper having a predetermined format, report, office communication document, etc.), the “title” and the “author” are vertically arranged, and the design is fixed to some extent. There are many documents. Here, this property is used to assign a logical identifier to the document structure. That is, the structure (arrangement of areas) for each area data of the document image is registered as the document structure model, and the area data of each element of the layout structure data obtained by area division of the document image and the area data of the document structure model are registered. It matches with the arrangement of the areas and gives a logical identifier when the correspondence is established. That is, the document structure model is a template for designing a document to be processed, and a plurality of types of document structure models serving as these templates are registered in a ROM or the like in advance.

Specifically, as shown in FIG. 25, the document structure model is composed of nodes having logical names corresponding to the types of document image elements (character blocks, character lines, ruled lines, etc.), and between these elements. The data has a graph structure represented by link information indicating the relative positional relationship of In that case, in the matching process in the identifier assigning module 123, a process of determining whether or not it matches one registered document structure model is sequentially performed. That is, the registered document structure models are taken out one by one, and the matching process is sequentially executed until the matching process is successful. If the matching with all the document structure models fails, a message indicating that the edit processing for the input document cannot be displayed is displayed on the control panel unit 128, and the subsequent processing is ended without performing any processing. To do. In addition,
In this case, in the subsequent processing, for example, the editing processing by manually specifying the area may be performed as described in the first embodiment.

When the matching process with a certain document structure model is successful, the area data of each element in the layout structure data is associated with each node of the document structure model, and the processing result is as shown in FIG. As shown in FIG. The logical identifier assignment table 140 has an element number field 1
41 and a logical identifier field 142, and is a data table in which the logical identifier is associated with the data of each element number of the layout structure data. The layout structure data of the logical identifier assignment table 140 to which the logical identifier is assigned here is transferred to the editing area determination module 124.

The editing area discrimination module 124 is shown in FIG.
As shown in FIG. 2, edit target judgment data 1 showing a judgment criterion for judging a candidate to be edited corresponding to each logical identifier.
50 is stored in advance, and this edit target judgment data 1
Based on 50, the element of the layout structure data to be edited is determined. For example, the data of the logical identifier assignment table 140 in which the logical identifier is assigned to the element number of the layout structure data as shown in FIG. 26 is passed to the edit area determination module 124, and the edit target determination as shown in FIG. 27 is made. When the area to be edited is determined based on the data 150, area determination result data 160 as shown in FIG. 28 is obtained (step 137).

Based on the result of the determination by the area determination result data 160, the "upper left point x coordinate, upper left point" of the character block area to be edited is set for the area data of the layout structure data, as in the second embodiment. y coordinate, width, height "
The edit area is extracted from the area data indicated by. In the process of designating the edit area of the document image, as in the case of the first embodiment, the edit area flag is added to the image data of the pixel, and the edit area flag of the area to be edited is set to "1". After performing the processing, the image data of the document image is transferred to the document image conversion module 125.

In the document image conversion module 125, the first
As in the case of the embodiment described above, the edit target area flag is "1".
The image data of the area is multiplied by a coefficient to reduce the density, or a predetermined number of values are added to the image data to make the background gray (step 138). The converted image data is delivered to the printer mechanism 126 and output as an image of an output document (step 139). For example, when a document image 51 of an input document as shown in FIG. 5 is subjected to document image conversion by designating an area to be edited from the document structure, the image of the output document of the edited result is as shown in FIG. The document image 170 is output as shown in FIG.

A document image 1 of an output document as shown in FIG.
At 70, the region to be edited is determined based on the edit target determination data 150 shown in FIG. 27, and the image conversion is performed on the determined region. That is, each edit area is determined by the edit target determination data 150 having the instruction content that specifies the logical identifiers of “text”, “page number”, “header”, “footnote”, and “author” as the edit target, This is an example of the document image of the output document whose background is grayed out according to the area data of the element having the logical identifier (element of the layout structure data).

In the description of this embodiment, the character block area having the designated logical identifier is set as the edit target. However, when the edit target area is determined, for example, as in the first embodiment, "title ], “Subtitle”, and other logical identifiers that are not candidates for editing, elements other than those having those logical identifiers may be edited. In addition, by designating a logical identifier of a candidate that is not edited, it is possible to modify the region to which an element having a logical identifier other than that and a margin portion is added as an editing target.

[0085]

As described above, according to the document image processing apparatus of the present invention, the density of an image of a part of a document image can be reduced or the brightness of the background can be reduced by a simple operation. You can Further, by designating an area not to be edited, designation of the area to be edited simplifies the designation of the area to be edited, and in addition, it becomes unnecessary to designate the editing process, which simplifies the operation. In addition, since it is possible to automatically determine the long sentence region from the physical characteristics such as the character region or the drawing region in the document image and perform the process of the edit target, the operation of designating the region becomes unnecessary. Further, since the edit target area such as "text" or "note" is automatically discriminated by the designation by the preliminary logical identifier and the edit target processing is performed, the operation of designating the area becomes unnecessary. Therefore, when the user operates the document image, the user can easily perform the image editing operation without performing a complicated operation.

[Brief description of drawings]

FIG. 1 is a block diagram showing a basic configuration of a first embodiment of a document image processing apparatus of the present invention,

FIG. 2 is a diagram showing an example of a console panel in a digital copying machine,

FIG. 3 is a block diagram illustrating a configuration of a main part of a document image processing apparatus applied to a digital color copying machine,

FIG. 4 is a flowchart showing a flow of processing when density conversion is performed on a designated area,

FIG. 5 is a diagram showing an example of a monochrome input document to be input as a document image to be processed,

FIG. 6 is a diagram for explaining an operation example when designating an area to be processed in an input document;

FIG. 7 is a diagram partially showing image data of a document image in 256 gradation gray scale,

FIG. 8 is a diagram partially showing image data in the case where a designated area flag is provided in the image data,

FIG. 9 is a diagram partially showing image data in a state in which a designated area flag is inverted to be an edit target area flag;

FIG. 10 is a diagram partially showing image data in a state in which density conversion is performed on a designated area,

FIG. 11 is a diagram showing an example of a document image of an output document in a state where density conversion is finally performed;

FIG. 12 is a diagram showing an example of a region table in a state where a region is designated;

FIG. 13 is a block diagram showing the basic arrangement of a document image processing apparatus according to the second embodiment of the present invention,

FIG. 14 is a block diagram illustrating a device configuration of a main part of a document image processing apparatus according to a second embodiment applied to a digital color copying machine;

FIG. 15 is a flowchart showing a flow of processing when a character area of a document image is identified and density conversion is performed on the area.

FIG. 16 is a diagram showing an example of area determination data as a result of area determination performed on a document image to be processed;

FIG. 17 is a diagram illustrating a correspondence relationship between a determination result of a hierarchical structure in one character block area of the area determination result and an input document;

FIG. 18 is a diagram showing region data of a hierarchical structure of a determination result in one region of the region determination data,

FIG. 19 is a diagram showing a character number table storing count data counted as the number of characters for each determination area;

FIG. 20 is a diagram showing an example of an output document of a document image in a state in which density conversion is finally performed on the determined long text area;

FIG. 21 is a block diagram showing the basic arrangement of a document image processing apparatus according to the third embodiment of the present invention,

FIG. 22 is a diagram showing an example of a logical identifier of a document structure,

FIG. 23 is a block diagram illustrating a device configuration of a main part of a document image processing device according to a third embodiment applied to a digital color copying machine;

FIG. 24 is a flowchart showing the flow of processing in the case where each area of a document image is discriminated by a logical identifier and density conversion is performed on that area;

FIG. 25 is a diagram showing an example of a structural document model associated with each area of a document image,

FIG. 26 is a diagram showing a correspondence relationship with a logical identifier associated with an element of layout structure data;

FIG. 27 is a diagram showing an example of edit target determination data in which an area to be extracted as a candidate for edit target is designated by a logical identifier;

FIG. 28 is a diagram showing an example of area determination data determined by a logical identifier;

FIG. 29 is a diagram showing an example of an output document of a document image in which density conversion is finally performed on an area designated by area determination data.

[Explanation of symbols]

20 ... Document image processing device, 21 ... Image scanner, 2
Reference numeral 2 ... Non-editing target area designation module, 23 ... Designated area determination module, 24 ... Edit target area determination module, 2
5 ... Document image conversion module, 26 ... Printer mechanism, 2
7 ... Control module, 28 ... Control panel section, 3
0 ... Console panel, 31 ... Numerical keys 31 and 32
... Display unit, 33 ... Copy button, 34 ... Density conversion button,
35 ... Copy start button, 36 ... Status display section, 51 ...
Document image of input document, 52 ... First edit area, 53 ... Start point, 54 ... End point, 55 ... Second edit area, 56 ... Start point,
57 ... end point, 60 ... area table, 61 ... image data,
62 ... Image data, 63 ... Instruction area flag, 64 ... Editing area flag, 65 ... Image data, 66 ... Image data in edited state, 67 ... Document image of output document, 70 ...
Document image processing device, 71 ... Image scanner, 72 ... Area dividing module, 73 Lowest element counting module, 7
4 ... Long sentence area discrimination module, 75 ... Document image conversion module, 76 ... Printer mechanism, 77 ... Control module,
78 ... control panel section, 91 ... document image data,
92 ... Character block area, 93 ... Ruled line area, 94 ... Margin area, 100 ... Hierarchical structure, 101 ... Character block area,
102 ... Character line area, 103 ... Character area, 104 ... Area table, 105 ... Lower element number field, 106 ...
Lower element start number field, 107 ... Character number table, 108 ... Document image of output document, 120 ... Document image processing device, 121 ... Image scanner, 122 ... Area dividing module, 123 ... Logical identifier assigning module, 12
4 ... Editing area determination module, 125 ... Document image conversion module, 126 ... Printer mechanism, 127 ... Control module, 128 ... Control panel section, 140 ... Logical identifier assignment table, 141 ... Element number field, 14
2 ... Logical identifier field, 150 ... Edit target determination data, 160 ... Region determination result data, 170 ... Output document document image, 301 ... Edit target document image, 302 ... Region dividing processing unit, 303 ... Logical identifier assigning unit, 304 ... edit area discrimination unit, 305 ... document image conversion processing unit, 306 ... edited document image.

 ─────────────────────────────────────────────────── ─── Continuation of front page (72) Inventor Shinya Furusato 134 Kobe-cho, Hodogaya-ku, Yokohama-shi, Kanagawa Yokohama Business Park East Tower Fuji Xerox Co., Ltd.

Claims (3)

[Claims] 1. A non-editing target area designating means for designating an unedited area on a document image, and a designation area flag indicating a correspondence relationship between the area designated by the non-editing target area designating means and a document image of an input document. Based on the designated area discriminating means to be added and the designated area flag added by the designated area discriminating means, an edit target area discriminating means for converting into an edit area flag indicating the edit target area of the document image, and the editing designated by the edit area flag A document image processing device, comprising: a document image conversion means for converting the density of the extracted region with respect to the target region. 2. A region dividing unit that divides a group of pixels on a document image into small regions as meaningful blocks of document elements, and a subregion divided by the region dividing unit from the smallest element among them. The lowest element counting means for counting the number, the long sentence area determining means for determining a long sentence area from the number of the lowest elements in the small areas counted by the lowest element counting means, and the long sentence area determining means. A document image processing device, comprising: a document image conversion means for converting the density of a long sentence of a region. 3. A region dividing unit that divides a group of pixels on a document image into small regions as meaningful blocks of document elements, and a logical structure of a document in each of the small regions divided by the region dividing unit. A logical identifier assigning means for assigning an identifier to give a meaning; an edit area determining means for determining an area to be a density conversion target corresponding to the identifier assigned by the logical identifier assigning means; and an area determined by the edit area determining means. A document image processing apparatus, comprising: a document image conversion unit for converting density.