JP3085604B2 - Document processing device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a document processing apparatus for automatically coloring a document image and outputting it as a color document.

[0002]

2. Description of the Related Art There is a copying machine as a device corresponding to a function of reading a paper document, processing the document, and outputting the processed document. The basic function of a copying machine is to output a document in which a manuscript is faithfully reproduced. However, with the spread of digital copying machines, for example, the processing of documents such as the copying machine disclosed in Japanese Patent Application Laid-Open No. 223275/1990. Some of them have functions. However, these techniques require the user to give detailed instructions on the part to be machined and how to machine it, and to use it requires extremely complicated operations,
In the end, general users do not know how to process which part to produce a high-quality document that matches their intended purpose.As a result, the input document becomes higher-quality. It wasn't very helpful for me. In particular, with the spread of color copiers in recent years,
There are increasing opportunities to convert the color of such documents and add color to black and white documents.

[0003]

However, such a coloring operation is very complicated and time-consuming, and a general user with little knowledge of the color scheme and design sense can provide a high-quality output document. It was an extremely difficult technique. The present invention has been made in view of the above circumstances, and its purpose is to automatically color an input document without receiving an instruction from a user, An object of the present invention is to provide a function of processing and outputting a document of high quality coloring.

[0004]

In order to achieve the above object, a document processing apparatus according to the present invention has a document image holding means (111) for holding a document image and a document image holding means for holding the document image. (12) that divides a set of pixels on a document image into regions each having a meaningful block as a document element, and relates to coloring of an output document by referring to a result output by the region dividing unit. Color parameter determining means (1) for determining parameter values for each area
3) cutting out each area image for each area divided by the area dividing means from the document image held in the document image holding means, and converting the image into color parameter values for each area determined by the color parameter determining means. Therefore, it has a basic configuration including output image generating means (14) for processing each area image to generate an output image.

In the above-structured document processing apparatus, the document image holding means holds a document image in which, for example, a paper document is input as a black-and-white digital image, and the document image is subjected to character block, graphic, and silicon by the area dividing means. It is divided into areas (layout elements) that are meaningful as document elements such as lines. The color parameter determining means holds information on color parameters predetermined for each type of area in the form of, for example, a table (131 in FIG. 1, FIG. 7), and outputs the information by referring to the result output from the area dividing means. The color parameter value of each area of the document is determined and passed to the output image generation means. The output image generating means cuts out each area image, and according to the color parameter value for each area received from the color parameter determining means, for example, colors the background of the graphic area or colors the ruled line, etc. Is processed to generate an output image. According to the present invention, the document image is divided into regions by the region dividing unit, the coloring parameter is determined for each region by the color parameter determining unit, and the document image colored by the output image generating unit based on the parameters is obtained. Since it is generated, the user does not need to perform any operation or instruction regarding document coloring, and therefore, without having to know the document coloring, it can be displayed on the basis of existing documents written on paper etc. Good documents can be easily obtained.

A document processing apparatus according to another aspect of the present invention includes a document image holding unit (1111 in FIG. 11) for holding a document image, and a document image holding unit for holding a document image. An area dividing unit (112 in FIG. 11) that divides a set of pixels into regions each having a meaning as a document element, and a logical region of the document divided into each region on the document image divided by the region dividing unit. Parameter assigning means (113 in FIG. 11) for assigning logical identifiers representing various meanings, and color parameter determination for determining parameter values related to coloring of an output document for each logical identifier with reference to the result output by the logical identifier assigning means Means (114 in FIG. 11), and each of the logical identifiers assigned by the logical identifier assigning means from the document image held in the document image holding means. Output image generating means (115 in FIG. 11) for cutting out the area image, processing each area image in accordance with the color parameter value for each logical identifier determined by the color parameter determining means, and generating an output image. I have. This document processing device corresponds to a configuration in which a logical identifier assigning means is added to the above-described basic configuration of the present invention. The logical identifier assigning means assigns a logical identifier to each area obtained by the area dividing means, so that not only the area but also each area can be further distinguished by the logical identifier within the same type, so that more varied coloring is provided. Can be performed, and a more attractive document can be obtained.

In a specific embodiment of the document processing apparatus having the above configuration according to the present invention (FIG. 11), the area dividing means includes area information including a layout identifier, an area type, an area size and a position, and a relation between the areas. And outputting a layout structure including information representing

In a specific embodiment of the document processing apparatus having such a region dividing means, the logical identifier assigning means stores a plurality of structural models representing a relationship between a layout structure and a logical structure. (1131 in FIG. 11), matching processing means (1132 in FIG. 11) for comparing the layout structure obtained by the area dividing means with the structural model, and a structural model which is matched by the result of the comparison. , A logical structure determining means (1133 in FIG. 11) for assigning a logical identifier to each area. In this configuration, only a plurality of structural models expressing the correspondence between the layout structure and the logical structure to be recognized are registered in advance in the structural model storage unit, and the matching processing unit performs a matching process between the region division result and the structural model. The logical structure determining unit assigns a name expressing a logical meaning to each of the elements of the layout structure. Thus, the logical identifier assigning unit recognizes the logical structure based on the layout structure,
Logical identifiers can be automatically and reliably assigned. At the same time, the type of the input document can be estimated from the information on which model was obtained from among the plurality of registered structural models, so that the color parameter information of the color parameter determining means was determined for each type of document. By preparing and selecting according to the input document type information, it is possible to perform abundant coloring according to the document.

According to one embodiment, the color parameter determining means for that purpose comprises: a first table indicating the correspondence between the type of the input document recognized by the logical identifier assigning means and the corresponding table number; Identifiers and coloring
A color parameter table (1141 in FIG. 11) including a second table indicating correspondence with parameters related to

According to another aspect, the color parameter determining means stores the knowledge base (1842 in FIG. 18) storing the knowledge information on the coloring of the document and the knowledge base based on the output of the logical identifier assigning means. An inference processing means (1841 in FIG. 18) for determining a parameter value relating to coloring of the output document by executing an inference process using the stored knowledge information. According to this, more advanced coloring suitable for each document can be performed.

[0011]

DESCRIPTION OF THE PREFERRED EMBODIMENTS (First Embodiment) An embodiment will be described below with reference to the accompanying drawings. FIG. 1 shows the configuration of an embodiment in which the present invention is applied to a copying machine. As shown in FIG. 1, the apparatus of this embodiment includes a document image input module 11, an area division module 12, a color parameter determination module 13, an output image generation module 14, and a printout module 15. I have.

The original image input module 11 is a mechanism of an image scanner itself, and irradiates an elongated area in the main scanning direction with a light source while shifting a reading unit including a light source and an image sensor in a sub-scanning direction, and transmits reflected light to a lens. The light is condensed and converted into an electric signal by a CCD image sensor or the like, and is taken into an input image memory as a binary digital image. Of course, the intensity of the reflected light may be input as a multi-valued image through an AD converter and binarized by digital image processing.

The area dividing module 12 performs processing of dividing a document image into a character area, a chart area, and the like by using the image of the document as an input, and corresponds to the area dividing processing in the document recognition technology. This is realized by a known technique. For example, JP-A-64-15889 or JP-B-61-3
A technique disclosed in Japanese Patent No. 2712 corresponds to this. The area dividing module 12 divides each area into rectangles, adds a layout identifier, and outputs the result. It goes without saying that pre-processing such as inclination correction and noise removal may be performed before performing this processing. The areas divided by this processing are identified as characters, figures, ruled lines, etc., and these types are also added and output at the same time. The sequence of elements output from the area division module as a result of division is called a document layout structure.

The color parameter determination module 13 stores a color parameter table 13 registered in advance for each element of the layout structure using the type of the area as a key.
1, adding parameter data, and passing the data to the output image generation module 14. The color parameter table 131 is a ROM (Read Only Memory).
To be stored. The color parameter table 131 is a table indicating the foreground color, the background color, and the like for the type of the document image area. Here, the foreground color refers to the color of a character or graphic line in the output document image (that is, a black pixel portion in a black-and-white image), and the background color corresponds to the ground portion of each region in the output document image. Color. These represent how each final document element must be colored. The data held by these parameter tables is, for example, “19
Proceedings of the 42nd IPSJ Annual Conference 1991, 7Q-7
Quantitative data obtained by methods such as subjective evaluation as described in "Evaluation Scale for Document Expression Quality" and "Xerox Presentation and Documentation", Fuji Xerox, 198
Nine Years ”and“ Fuji Xerox D Promotion Group, Core Design Production Division, “Business Document Production Techniques-II
Qualitative or quantitative data as described in "Colorization", Nihon Keizai Shimbunsha, 1992, etc., or data expressing each rule according to company rules.
The determination is made based on various knowledge necessary for determining the coloring of the document.

The output image generation module 14 receives color parameter data from the color parameter determination module 13, receives layout structure data from the area division module 12, and receives an input image from the document input module 11. Then, according to the parameters received from the color parameter determination module 13, the partial images of the input document corresponding to the respective elements of the layout structure are converted to generate an output image, and a document image having a finally designated coloring image Generate In the printout module 15, the output image on the output image memory 151 is transferred onto paper using a laser beam printing technique and discharged.
In this embodiment, a laser beam printer capable of printing in full color is used.

The operation of the embodiment having the above configuration will be described with reference to a document having a layout as shown in FIG. A flowchart of the process is shown in FIG. Hereinafter, as shown in FIG. 3, in the coordinate system, the direction toward the right of the page is referred to as x coordinate, and the direction toward the bottom of the page is referred to as y direction. First,
The user places the document shown in FIG. 3 on a platen such as an image scanner, and selects a simple copy or a color copy on an operation panel as shown in FIG.

When the start button is pressed in a state where the color copying is selected, the image input module 11 starts scanning, and stores the image of the document in the input image memory 111. Next, the area dividing module 12 performs processing, and as a result, there is an area (character block area) in which the input image shown in FIG. 3 is arranged in the input image memory as shown in FIG. The image is divided into an area (line area), an area where the figure exists (graphic area), and the rest (margin) (step S42). The rectangle that represents the region has sides parallel to the x and y directions of the document image, and is the smallest rectangle that surrounds the target region. Data representing an area is basically represented by a set of “layout identifier, type, upper left point x coordinate, upper left point y coordinate, width, height”. The region division result is expressed in a table format as shown in FIG. 6, and the data, that is, the layout structure is represented by the color parameter determination module 13 and the output image generation module 1.
Pass to 4.

The color parameter determination module 13 extracts the color parameters stored in the color parameter table 131 on the ROM in advance according to the type of the area.
The color parameters corresponding to each layout identifier are sent to the output image generation module 14 (Step S43). As shown in FIG. 7, the individual color parameter table sent to the output image generation module 14 includes the hue, saturation, brightness, (effect) of the foreground color, the hue, saturation, brightness of the background color,
The coloring area margin and the like are managed in a table.
As shown in FIG. 8, the coloring area margin designates a range in which the area for coloring the background in the output image is extended outside the rectangular area obtained as a result of the area division. In this embodiment, the upper, lower, left, and right sides can be independently changed, but a common coloring area margin may be used.

The output image generation module 14 receives a layout structure and color parameters, and stores a partial image of the input document as specified by the parameters in the output image memory 1.
51 (step S44). In this embodiment, since full-color output is performed, it is assumed that the output image memory 151 holds gradation value information for four colors of cyan, magenta, yellow, and black for each pixel.

FIG. 9 shows a flowchart of the processing in the output image generation module 14. That is, first, the tone values for all four colors of all the pixels in the output image memory are initialized to 0 (step S91). Next, the elements are sequentially extracted from the layout structure (step S9).
3). In this example, an element whose layout identifier is "character block-1", which is the first element of the layout structure, is extracted. The color parameters of the extracted layout element are extracted (step S94). Further, a partial image corresponding to the area of the layout element is cut out from the input image (step S95). The area image mapping process is called using the layout structure element "character block-1", the color parameter corresponding to the element, and the partial image corresponding to the element on the input image as parameters (step S96).

In the area image mapping processing, first, a background color is given to an area corresponding to "character block-1". The “upper left point x coordinate, upper left point y coordinate, width, and height” of “character block-1” are extracted and defined as x1, y1, w1, and h1, respectively. Also, “coloring area margins (upper, lower, left, right)” in the color parameters are designated as margin_u, m, respectively.
argin_d, margin_l, margin_r
And Further, (x1-margin_l, y1-m
argin_u) as the upper left point, and (w1 + margin
_L + margin_r) as width, (h1 + margin
_U + margin_d) is set in the output image as the height. Then, the values of the pixels in the set area are set to the gradation value information of the four colors calculated by a known method from the hue, saturation, and brightness of the background color in the color parameters. Next, similarly, tone values of four colors are obtained from the hue, saturation, and brightness of the foreground color. Then, the pixels of the output image memory 151 at the positions corresponding to all the black pixels included in the partial image of the given input image are changed to the gradation value information corresponding to the foreground color. As a result of this processing, an output image is generated in which the content is written with the foreground color in the area colored with the background color according to the color parameter. This is the end of “character block-1”, and similar processing is repeated for “character block-2”, which is the next element in the table. In this way, it is determined whether or not the mapping of all the elements in the layout structure has been completed (step S92). The output image is scanned four times, the colors are visualized by superimposing the colors on plain paper by the laser beam printing technique from the gradation value information of each color, and output as shown in FIG.

According to the document processing apparatus of the present embodiment, the document image is divided into regions by the region dividing module 12, and the coloring parameters are determined for each region by the color parameter determining module 13, and output based on the parameters. Since the document image colored by the image generation module 14 is generated and visualized by the printout module 15, the user does not need to perform any operation or instruction regarding the document coloring, and thus has the knowledge about the document coloring. Even if not, a good-looking document can be easily obtained based on an existing document written on paper or the like.

(Second Embodiment) FIG. 11 shows a second embodiment in which the present invention is applied to a copying machine. The device of this embodiment is
As shown in FIG. 11, the document image input module 111
, An area division module 112, a logical identifier assignment module 113, and a color parameter determination module 114
, An output image generation module 115, and a printout module 116.

The original image input module 111 and the area dividing module 112 are the same as those in the first embodiment, and the layout structure of the document output from the area dividing module 112 employs the same format.

The logical identifier assigning module 113 receives the layout structure of the document obtained in the area dividing module 112 as an input, and assigns a logical name such as “title”, “author”, or “text” as an identifier. Things. This is described in Japanese Patent Application No. 3-313186, previously filed by the present applicant (inventors Shoji Ozaki and Yusuke Ishida, "Apparatus and method for document logical structure recognition and document content recognition"). It is better to use technology. In this technique, a plurality of structural models expressing the correspondence between the layout structure and the logical structure to be recognized are registered in advance in the structural model storage unit 1131, and the matching processing unit 1132 performs a matching process between the region division result and the structural model. Is performed, and a name expressing a logical meaning is given to each of the elements of the layout structure by the logical structure determination unit 1133. At the same time, the type of the input document is estimated from information on which of the plurality of registered structural models has been matched.

The color parameter determination module 114 transfers color parameter data for each logical identifier corresponding to the type of the input document to the output image generation module 115 from the parameter table 1141 registered in advance. The color parameter table 1141 is classified into a type of an input document, an output paper size, and the like, and a ROM (Read On).
ly Memory). If the amount is large, it may be realized by a magnetic disk device or the like. The color parameter table 1141 is composed of two types of tables. One is a table of the type of the input document and the corresponding table number. The other is a table for each element having a logical identifier (for example, “title”). This is a table in which the foreground color, background color, and the like are shown. Here, the foreground color refers to the color of a character or figure line in an output document image (that is, a black pixel portion in a black and white image),
The background color refers to the color of the ground portion for each region in the output document image. These represent how each final document element must be colored. The parameter data stored in these tables is
It is determined in the same manner as in the first embodiment.

The output image generation module 115 receives color parameter data from the color parameter determination module 114, receives logical structure data from the logical identifier assignment module 113, and receives an input image from the document image input module 111. Then, the color parameter determination module 1
In accordance with the parameters received from 14, each of the partial images of the input document corresponding to each logical identifier is converted, an output image is generated, and finally a document image having the designated coloring image is generated. The same printout module as in the first embodiment is used.

The operation of the second embodiment will be specifically described based on the document example of FIG. 3 according to the first embodiment. A flowchart of the processing is shown in FIG. The image input module and the area division module perform the same processing as in the first embodiment (step S122).

In the logical identifier assigning module 113, the matching processing unit 1132 performs matching between the layout structure received from the area dividing module 112 and the structural model stored in the structural model storage unit 1131, and outputs the result of the matching. Based on the logical structure determination unit 1
133 gives, as an identifier, a logical name indicating what logical meaning each element of the layout structure has (step S123). The logical name is "title",
"Author", "Subtitle", "Body", "Footnote", "Footnote Rule", "Figure", "Graph", and the like. Usually, there are many fixed design documents such as "title" and "author" arranged vertically in a certain range. The structure model utilizes this property, and the structure model is a template for the design of a target document. The structural models serving as these templates are stored in a structural model storage unit 113 constituted by a ROM.
One is stored in advance in one. The structure model is shown in FIG.
As shown in the element's type (character block, character line,
Nodes with logical names corresponding to
It is represented by a graph structure in which the relative positional relationship between these elements is used as a link.

The matching processing of the matching processing unit 1132 in the logical identifier assignment module 113 is as follows.
That is, it is to determine whether or not it matches one registered structural model. The registered structural models are extracted one by one, and the matching processes are sequentially activated until the matching process is successful. If the matching with all the structural models fails, a message indicating that the input document is unrecognizable is displayed on the panel of the device, and a simple copy without coloring is performed and the processing is terminated.

If the matching with a certain structural model is successful, the correspondence between the elements in the layout structure and the nodes of the structural model can be known. Assign a logical name defined to the node. Data in which a logical name is assigned to an element of the layout structure in this manner is called a logical structure. Actual data representing a logical structure is represented by a row of pairs of a logical name and an identifier of a layout element corresponding to the logical name as shown in FIG. Also, it is possible to determine what kind of document the input document is based on the information on the number of the structural model and the success of the matching.

In the color parameter determination module 114,
According to the type of the input document estimated by the logical identifier assignment module 113 (that is, the number of the model that has been successfully matched), a corresponding one is selected from a plurality of color parameter tables that are classified and registered in the ROM in advance, and The color parameters stored in the color parameter table are extracted, and the color parameters corresponding to each logical name are sent to the output image generation module 115 (Step S)
124). As shown in FIG. 15, the individual color parameter table sent to the output image generation module 115 has the hue / saturation / brightness / (effect) of the foreground color, the hue / saturation / brightness of the background color, and the coloring area margin for each logical name. Are managed in a table.

The output image generation module 115 receives the logical structure and the color parameters, and stores a partial image of the input document as specified by the parameters in the output image memory 116.
1 (step S125). The output image memory 1161 holds gradation value information for four colors (cyan, magenta, yellow, and black) as in the first embodiment. A flowchart of the process in the output image generation module 115 is as shown in FIG. That is, the output image is initialized (step S161), and thereafter, parameters are extracted in the order of the elements of the individual color parameter table (step S163), and a region division result having the logical name is extracted (step S164). In this example, the title of the color parameter table is "Title".
The layout structure element having the name "Title" is extracted from the logical structure. Further, a partial image corresponding to the area of the layout structuring element is cut out from the input image (step S165). The area image mapping process is performed by using the layout structure element corresponding to the title, the color parameter of the title in the individual color parameter table, and the partial image corresponding to the layout structure element on the input image as parameters. (Step S16)
6). In the area image mapping processing, the same processing as in the first embodiment is performed. When the processing is completed for one element, it is determined whether there is an unprocessed element in the table (step S162), and if so, the above-described processing is performed for the next element. .

Further, the output result is visualized on paper as in the first embodiment, and a colored document as shown in FIG. 17 is output.

In the second embodiment described in detail above, similarly to the first embodiment, the user does not need to perform any operation or instruction regarding document coloring, and therefore, has a knowledge of document coloring. Even if not, a good-looking document can be easily obtained based on an existing document written on paper or the like. In the second embodiment, the logical identifier assigning module 11
3, the logical structure is identified, the type of the document is estimated, and each region can be further distinguished by the logical identifier even within the same type, so that a more varied coloring can be performed, and a document with a better appearance can be obtained. Can be obtained.

Although the first and second embodiments described above use a laser beam printer that prints in full color in the printout module, printing in full color is possible. Instead of using a laser beam printer, the present invention can be implemented using a laser beam printer capable of performing “+1 color printing” by adding another color based on black. In this case, lower cost and higher printing speed can be expected. However, in this case, since the number of available colors is limited, it is necessary to change color parameters and the like. In this case, it is possible to compensate for the small number of colors by changing a decoration pattern such as shading.

(Third Embodiment) In a third embodiment, as a color parameter determination module, for example, IF-TH is used instead of referring to a table as in the first and second embodiments.
It utilizes a knowledge base written in EN rule format and an inference engine that performs forward and backward inference using the knowledge base. That is, as shown in FIG. 18, the color parameter determination module 184 stores information obtained from the logical identifier assigning module 183, the knowledge database 18 holding the color parameters and the knowledge defining their mutual relations.
42 and an inference mechanism 1841 (inference engine) that determines color parameters by performing some inference such as forward inference or backward inference while referring to the knowledge base 1842 based on information from the logical identifier assignment module 183. An example of the operation procedure of the inference mechanism will be described with reference to FIG. The color parameter determination module 185 is provided in FIG.
As shown in FIG. 9, when an instruction to start inference is received, the operation of the inference engine first causes the knowledge base 1842 to send the IF-
All the rules written in the THEN format are extracted and set as rules (step S191). Next, based on the data sent from the logical identifier assigning module 183, all rules where all the conditions written in the IF condition section are true are found, and these are set as Trues (step S193). Next, only one rule is selected from the rules, and the execution content of the rule written in the THEN execution unit is executed (step S193). The selection and execution of these rules are repeated until Trues becomes empty (determined in step S194) or an inference stop instruction is issued by the THEN execution unit (determined in step S192). Thereby, the color parameter determination module 185 determines an appropriate color parameter according to the layout structure. The color parameter determination module 184
The other components are the same as those of the second embodiment shown in FIG. According to the third embodiment, more sophisticated coloring suitable for each document can be performed.

In the first to third embodiments described above, the original image input module, the printout module and the like can be constituted by existing hardware technology. In addition, a part or all of the area division module, the logical identification module, the color parameter determination module, the image generation module, and the like are configured as software modules, and those software modules are stored in a ROM or other appropriate storage device,
They may be executed by a central processing unit, or they may be configured as hardware modules by a logic circuit in which individual logic elements are combined.

[0039]

As has been described in detail above, according to the present invention, a user can obtain a color based on an existing document written on paper or the like without having knowledge of the document coloring. Good looking documents can be easily created.

Further, according to the aspect of the present invention provided with the logical identifier assigning means, the type of the document can be estimated by identifying the logical structure, and each area can be further distinguished by the logical identifier within the same type. In addition, a variety of high-quality coloring can be performed, and a document with a better appearance can be obtained.

Further, according to the aspect of the present invention in which the knowledge base and the inference mechanism are used for the color parameter determining means, more advanced coloring suitable for each document can be performed.

[Brief description of the drawings]

FIG. 1 is a configuration diagram showing a first embodiment.

FIG. 2 shows an example of a coloring instruction input module.

FIG. 3 shows an example of an input document.

FIG. 4 is a flowchart of a process according to the first embodiment;

FIG. 5 is a diagram showing a processing result of a region dividing module according to an example of an input document;

FIG. 6 is a diagram showing a layout structure of a processing result of a region division module;

FIG. 7 is a diagram showing an example of a color parameter table according to the first invention.

FIG. 8 is a diagram showing an example of using a coloring margin in a color parameter table.

FIG. 9 is a flowchart of processing in the output image generation module of the first invention.

FIG. 10 is a diagram illustrating an example of an image output by the printout module according to the first embodiment;

FIG. 11 is a configuration diagram showing a second embodiment.

FIG. 12 is a flowchart of a process in the second embodiment.

FIG. 13 shows an example of a structural document model.

FIG. 14 is a diagram illustrating a matching result between an input document example and a structural document model example.

FIG. 15 is a diagram illustrating an example of a color parameter table according to the second embodiment.

FIG. 16 is a flowchart of processing in an output image generation module according to the second embodiment.

FIG. 17 is a diagram illustrating an example of an image output by the printout module according to the second embodiment.

FIG. 18 is a configuration diagram showing a third embodiment.

FIG. 19 is a flowchart of the inference processing in the third embodiment.

[Explanation of symbols]

11, 111: Original image input module, 12, 112
... Area division module, 13, 114 ... Color parameter determination module, 14, 115 ... Output image generation module, 15, 116 ... Printout module, 11
3 ... Logical identifier assigning module.

Continuation of the front page (56) References JP-A-1-315865 (JP, A) JP-A-4-160981 (JP, A) Yasuaki Nakano Outside, "A method of document understanding for automatic filing" Journal of the Society of Japan, 1988, Vol. J71-D, No. 10 P. 2050-2058

Claims (5)

(57) [Claims] 1. A document image holding unit for holding a document image, and a set of pixels on the document image held by the document image holding unit are divided into chunk regions each having a meaning as a document element. , Area type and area size for each area
Area information including the law and position and information indicating the relationship between the areas.
Area dividing means for outputting a layout structure including the table, and table means for storing correspondence between the type of the area and parameter values relating to coloring, and coloring the output document by referring to the table means based on an output result of the area dividing means. A color parameter determining unit that determines a parameter value related to each region, a region image for each region divided by the region dividing unit is cut out from a document image held in the document image holding unit, and the color parameter determining unit A document processing device comprising: an output image generation unit configured to process each area image according to the determined color parameter value for each area to generate an output image. 2. A document image holding unit for holding a document image, and a set of pixels on the document image held by the document image holding unit are divided into blocks each having a meaning as a document element. , Including area, area type, area dimensions, and position
Layout structure including information and information indicating relationship between regions
, A logical identifier assigning means for assigning an identifier representing the logical meaning of the document to each area on the document image divided by the area dividing means, and a logical identifier assigning means. A color parameter determining unit that determines a parameter value related to coloring of an output document for each logical identifier by referring to a result; and a logical image identifier assigned by the logical identifier assigning unit from a document image held in the document image holding unit. A document that cuts out each area image and processes each area image in accordance with the color parameter value for each logical identifier determined by the color parameter determination means to generate an output image. Processing equipment. 3. A document image storage for storing a document image.
Means and an image on the document image held by the document image holding means.
A collection of elements is defined as a set of
Area divided into areas, including area type, area dimensions, and position
Layout structure including information and information indicating relationship between regions
And a region on the document image divided by the region dividing means.
Identifiers that indicate the logical meaning of each document
Logical identifier assigning means, and an output document with reference to the result output by the logical identifier assigning means.
Determine the parameter value related to the coloring of each logical identifier
Color parameter determining means, and a document image stored in the document image storing means.
Each area for each logical identifier assigned by the logical identifier assigning means
Cut out the area image, and
According to the determined color parameter value for each logical identifier
An output image that generates an output image by processing each area image
A document processing apparatus comprising: a generation unit; wherein the logical identifier assigning unit is obtained by a structure model storage unit that stores a plurality of structural models representing a relationship between a layout structure and a logical structure; and a region division unit. A document comprising matching processing means for comparing the layout structure with the structural model; and logical structure determining means for assigning a logical identifier for each area based on the structural model that has been matched based on the result of the comparison. Processing equipment. 4. The color parameter determining means includes: a first table indicating a correspondence between a type of an input document and each corresponding table number; and a second table indicating a correspondence between a logical identifier and a parameter relating to coloring. 4. The document processing apparatus according to claim 3, further comprising a color parameter table having the following. 5. The color parameter determining means performs inference processing using a knowledge base storing knowledge information relating to coloring of a document and knowledge information stored in the knowledge base based on an output of the logical identifier providing means. claim 3, characterized in that by executing and a inference processing means for determining the parameter values for coloring documents output document
Document processing device as described.