JP2006301695A - Document processing device and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To gather descriptions in the range inferred as mutually relevant based on the postscript marks handwritten on a document and intelligibly present the contents to a user. <P>SOLUTION: A document processing device comprises an extracting means for analyzing a document image data obtained by computerizing a paper document and the postscript marks handwritten on the original document expressed by the document image data, an identifying means for identifying the image area corresponding to the extracted postscript marks respectively, a categorizing means for categorizing every postscript mark having the same or similar marks by analyzing the shape of each postscript mark when a plurality of the postscript marks are extracted, and an output means for outputting the image located in the identified image area corresponding to the postscript mark along a predetermined layout for each postscript mark categorized as having the same or similar shape. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a technique for extracting description contents of a region to which an additional mark is attached based on additional marks such as characters, symbols, and figures added by hand to a document.

Various comments may be added to the paper document by the reader. Some items added to a paper document, such as such comments, may contain important information for the reader, so there is a need to extract only such additional items from the paper document. Therefore, various techniques for enabling such a technique have been proposed in the past, and an example thereof is the technique disclosed in Patent Document 1. Patent Document 1 discloses a technique for classifying attributes of additional items on the basis of the context or the like to which each additional item is attached, and listing and outputting the additional items for each attribute.
Japanese Patent Laid-Open No. 11-219245

  By the way, when a reader of a paper document adds a specific character, symbol, figure, or the like indicating that to a chapter or paragraph that is judged to contain important information for the reader in addition to the comments as described above There is. Hereinafter, characters, symbols, figures, and the like added by hand to a paper document for such a purpose are referred to as “additional marks”. Since chapters and paragraphs marked with such additional marks contain important information for the reader, it is possible to extract and provide only the contents of the areas marked with additional marks. Convenient. In addition, when a reader writes a write-once mark on a paper document, it is common to give the same write-once mark to places where there is a description related to each other. It would be convenient if the description contents of the regions estimated to be related to each other such as the selected regions could be collected and presented to the user. However, since the technique disclosed in Patent Document 1 only lists and outputs additional items according to their attributes, this cannot be realized.

  The present invention collects description contents of regions that are presumed to be related to each other based on additional marks such as characters, symbols, and figures that are added by hand to a document and presents them to the user in an easily understandable manner. It aims to provide the technology that makes it possible.

  In order to solve the above problems, the present invention analyzes an input unit for inputting document image data obtained by digitizing a paper document, and analyzes the document image data input to the input unit. The first specifying means for specifying the additional mark added by hand writing to the original document to be represented, and the additional mark specified by the first specifying means are associated with the additional mark. When a plurality of additional marks are specified by the second specifying means for specifying the image area of the document image data and the first specifying means, the shape of each additional mark is analyzed, and the same or similar shape is analyzed. Classifying means for classifying each additional writing mark and each additional writing mark classified as having the same or similar shape by the classification means are associated with the additional writing mark. To provide a document processing apparatus and an output means for outputting the image disposed in the image area specified by the second specifying means arranged according to a predetermined layout.

  According to such a document processing apparatus, an image arranged in an image region associated with an additional mark having the same or similar shape is arranged and output in a predetermined layout. For this reason, for example, if a layout in which a plurality of images are arranged and arranged in a list format is adopted as the predetermined layout, in the image represented by the document image data, an image region associated with the same or similar additional mark is associated. The arranged images are output in a list format. As described above, it is presumed that the images arranged in the image region associated with the same or similar additional mark are assumed to represent images of matters having relevance to each other. According to the processing apparatus, among the items described in the paper document, the items that are estimated to be related to each other are collected, and for example, the items that are related to each other are output in a list format. Can be presented in an easy-to-understand manner.

  In a more preferred aspect, the first specifying unit compares the document image data input to the input unit with original image data representing an original of a paper document represented by the document image data, and adds the additional mark. It is characterized by identification. In such an aspect, the postscript mark attached to the original is surely specified.

  In another preferred embodiment, the first specifying means is based on a difference between an image color represented by the document image data input to the input means and an original color of the paper document represented by the document image data. The additional mark is specified. In such an aspect, when the color of the additional mark attached to the original is different from the color used in the description of the original, the additional mark is reliably specified.

  In another preferred embodiment, the classifying unit analyzes the shape of the write-once mark and calculates a feature amount thereof, and the write-once marks having the same calculated feature amount are used as write-once marks having the same shape. On the other hand, it is characterized in that the recordable marks whose deviation of the calculated feature amount is within a predetermined range are classified as similar recordable marks. In such an aspect, the additional recording marks having the same or similar shapes are surely classified regardless of the arrangement mode such as the color of each additional recording mark and the presence / absence of rotation.

  Further, in order to solve the above-mentioned problems, the present invention analyzes document image data obtained by digitizing a paper document in a computer device, and is added by handwriting to the original document represented by the document image data. A first step of specifying a write-once mark and a second step of specifying an image area of the document image data associated with the write-once mark for each of the write-once marks specified in the first step And when a plurality of additional marks are identified in the first step, a third step of analyzing the shape of each additional mark and classifying each additional mark having the same or similar shape, If each additional recording mark classified as representing an additional recording mark having the same or similar shape in the third step is associated with the additional recording mark, the second scan is performed. Providing a program program for executing a fourth step of outputting the image disposed in the image region specified by arranging in accordance with a predetermined layout in-up.

  According to such a program, by installing this program in a general computer device and operating the computer device according to the program, the same function as that of the document processing device according to the present invention is given to the computer device. The In another aspect of the present invention, it is of course possible to provide the program by writing it in a computer-readable recording medium.

  According to the present invention, it is possible to collect the description contents of regions that are presumed to be related to each other and present them to the user in an easy-to-understand manner based on the postscript marks that are handwritten on the document. There is an effect.

The best mode for carrying out the present invention will be described below with reference to the drawings.
(A: Configuration)
FIG. 1 is a block diagram illustrating a configuration example of a document processing system 10 including a document processing apparatus 110 according to an embodiment of the present invention. An image reading device 120 in FIG. 1 is a scanner device having an automatic paper feeding mechanism such as an ADF (Auto Document Feeder), for example, and optically reads a paper document set in the ADF page by page, and reads the read image. The image data to be represented (hereinafter, document image data) is delivered to the document processing apparatus 110 via a communication line 130 such as a LAN (Local Area Network). In the present embodiment, the case where the communication line 130 is a LAN will be described, but it is needless to say that it may be a WAN (Wide Area Network), the Internet, or the like. In the present embodiment, the document processing apparatus 110 and the image reading apparatus 120 are described as separate hardware, but it is needless to say that both may be configured as integral hardware. In such an aspect, the communication line 130 is an internal bus that connects the document processing apparatus 110 and the image reading apparatus 120 within the hardware.

  In the document processing system 10 shown in FIG. 1, a paper document in which an additional mark is handwritten by a reader is set in the automatic paper feed mechanism of the image reading device 120, and document image data representing an image of the paper document is processed by the document processing. Sent to device 110. On the other hand, the document processing apparatus 110 stores in advance image data (hereinafter, “original image data”) representing an image of an original of the paper document (that is, a paper document that has not been added by handwriting). Then, the document processing apparatus 110 compares the document image data received from the image reading apparatus 120 with the original image data stored in advance in its own apparatus, identifies the additional mark added by the reader, and is identical or It has a function to collect descriptions of chapters and paragraphs with similar append marks and output them according to a predetermined layout. Hereinafter, the configuration and operation of the document processing apparatus 110 will be mainly described.

FIG. 2 is a diagram illustrating an example of a hardware configuration of the document processing apparatus 110.
As shown in FIG. 2, the document processing apparatus 110 includes a control unit 200, a communication interface (hereinafter referred to as IF) unit 210, a display unit 220, an operation unit 230, a storage unit 240, and each of these components. And a bus 250 that mediates data exchange between elements.

  The control unit 200 is, for example, a CPU (Central Processing Unit), and centrally controls each unit of the document processing apparatus 110 by executing various kinds of software stored in a storage unit 240 described later. The communication IF unit 210 is connected to the image reading device 120 via the communication line 130, receives the document image data sent from the image reading device 120 via the communication line 130, and delivers it to the control unit 200. It is. That is, the communication IF unit 210 functions as an input unit to which document image data sent from the image reading device 120 is input.

  The display unit 220 is, for example, a liquid crystal display and a drive circuit thereof, and displays an image corresponding to data delivered from the control unit 200. The operation unit 230 is, for example, a keyboard provided with a plurality of operators (not shown), and passes data (hereinafter referred to as operation content data) according to the operation contents of these operators to the control unit 200, so that the user can This is for transmitting the operation content of each of the above-mentioned operators to the control unit 200.

  As shown in FIG. 2, the storage unit 240 includes a volatile storage unit 240a and a nonvolatile storage unit 240b. The volatile storage unit 240a is, for example, a RAM (Random Access Memory), and is used as a work area by the control unit 200 operating according to various software described below. On the other hand, the non-volatile storage unit 240b is, for example, a hard disk. The nonvolatile storage unit 240b stores data and software for causing the control unit 200 to realize functions unique to the document processing apparatus 110 according to the present embodiment.

  As an example of the data stored in the nonvolatile storage unit 240b, the above-described original image data can be cited. On the other hand, examples of software stored in the nonvolatile storage unit 240b include OS software and editing software for causing the control unit 200 to implement an operating system (hereinafter referred to as “OS”). Here, the editing software extracts, for each region such as a chapter or a paragraph, a description portion to which the same or similar additional mark is given in the document represented by the document image data input from the image reading device 120. This is software for causing the control unit 200 to execute processing for displaying them on the display unit 220 according to a predetermined layout. Hereinafter, functions provided to the control unit 200 by executing these software will be described.

  When the power (not shown) of the document processing apparatus 110 is turned on, the control unit 200 first reads and executes the OS software from the nonvolatile storage unit 240b. The control unit 200 operating according to the OS software and realizing the OS reads out and executes functions for controlling each unit of the document processing apparatus 110 and other software from the nonvolatile storage unit 240b in accordance with a user instruction. Function is given. For example, when the execution of the editing software is instructed, the control unit 200 reads the editing software from the nonvolatile storage unit 240b and executes it. The control unit 200 operating according to the editing software is given the following four functions.

  First, the document image data received from the image reading device 120 via the communication IF unit 210 is analyzed, and the additional mark added by hand to the original document represented by the document image data is specified. It is a specific function. Specifically, the control unit 200 compares the document image data and the original image data, specifies an image representing the difference between the two as an additional image representing an additional item for the original, and sets each of the additional images. Image data to be represented (hereinafter referred to as additional image data) is generated. Since the additional image represented by the additional image data generated in this way includes the image of the additional recording mark described above, the additional recording mark is specified by generating the additional recording image data. .

  Secondly, for each additional mark specified by the first specifying function, a second specifying function for specifying an image area of the document image data associated with the additional mark. More specifically, the control unit 200 specifies the position in the image represented by the document image data with respect to the postscript image represented by each postscript image data generated by the first identifying function, and the original image data. Is subjected to layout analysis, and the arrangement position of each image region is specified. Then, an image area (for example, an image area whose distance from the additional image is equal to or less than a predetermined threshold) that is in a predetermined positional relationship with the additional image is defined as an image region that is associated with the additional mark represented by the additional image. Identify.

  Third, when a plurality of additional marks are specified by the first specifying function, the shape of each additional mark is analyzed and classified for each additional mark having the same or similar shape. More specifically, the control unit 200 analyzes the postscript image represented by each postscript image data, calculates the feature amount of the shape of the postscript mark represented by the postscript image, and the postscript marks having the same feature amount Are classified as the same additional recording marks, and the additional recording marks whose feature amounts are different from each other but within a predetermined range are classified as similar additional recording marks.

  And fourth, the image specified by the second specifying function when each of the additional marks classified as the additional mark having the same or similar shape by the classification function is associated with the additional mark. This is an output function for generating image data representing an image formed by arranging images arranged in a region according to a predetermined layout (hereinafter referred to as edited image data) and outputting the image data to the display unit 220. . In this embodiment, the case where the edited image data generated as described above is output to the display unit 220 and an image corresponding to the edited image data is displayed is described. Of course, the image may be transferred to an image forming apparatus such as a printer, and an image represented by the edited image data may be formed on a recording material such as printing paper or an OHP sheet.

  As described above, the hardware configuration of the document processing apparatus 110 according to the present embodiment is the same as the hardware configuration of a general computer apparatus, and various control software stored in the non-volatile storage unit 240b is controlled by the control unit. By executing the processing 200, functions unique to the document processing apparatus according to the present invention are realized. As described above, in the present embodiment, the case where the functions specific to the document processing apparatus according to the present invention are realized by software modules has been described. However, the present invention is based on a combination of hardware modules each having these functions. Of course, the document processing apparatus may be configured.

(B: Operation)
Next, of the operations performed by the document processing apparatus 110, operations that significantly show the features will be described with reference to the drawings. In the operation example described below, the control unit 200 of the document processing apparatus 110 operates according to the editing software, and is waiting for document image data to be sent from the image reading apparatus 120. .

  When a user sets a paper document in the ADF of the image reading device 120 and performs a predetermined operation (for example, pressing a start button provided in the operation unit of the image reading device 120), an image corresponding to the paper document Is read by the image reading device 120, and document image data corresponding to the image is sent from the image reading device 120 to the document processing device 110 via the communication line 130. In this operation example, the paper document shown in FIG. 3A is set in the ADF of the image reading apparatus 120, and document image data representing an image corresponding to the paper document is sent from the image reading apparatus 120 to the document processing apparatus 110. Shall. The non-volatile storage unit 240b of the document processing apparatus 110 stores only one original image data representing the original of the paper document (see FIG. 3B) shown in FIG. To do. As is clear from the comparison between FIG. 3A and FIG. 3B, in the paper document shown in FIG. 3A, the first paragraph (FIG. 3A: “B01”) is added. The mark M01 is assigned, and the third paragraph (FIG. 3 (a): “B02”) is provided with the additional mark M02, and the fourth paragraph (FIG. 3 (a): “B04”). Is provided with a postscript mark M03. As is clear from FIG. 3A, the additional recording mark M01 and the additional recording mark M03 are additional recording marks having the same shape.

  FIG. 4 is a flowchart showing the flow of editing processing performed by the control unit 200 in accordance with the editing software. As shown in FIG. 4, when the control unit 200 receives the document image data sent from the image reading device 120 via the communication line 130 by the communication IF unit 210 (step SA100), the control unit 200 and the document image data are stored in a nonvolatile manner. The original image data stored in the storage unit 240b is compared, and the additional mark attached to the original represented by the original image data is specified (step SA110). As is apparent from the comparison between FIG. 3A and FIG. 3B, in this operation example, three additional image data representing each of the additional recording marks M01, M02, and M03 are generated by the first specific function. Each additional recording mark is specified by these additional recording image data. In the present embodiment, the case where only one original image data representing the original of the paper document represented by the document image data is stored in advance in the nonvolatile storage unit 240b of the document processing apparatus 110 has been described. Of course, original image data representing each original of the paper document (that is, a plurality of original image data) may be stored in the nonvolatile storage unit 240b of the document processing apparatus 110. In such a case, prior to the execution of step SA110, the user may designate original image data representing the original of the paper document represented by the document image data.

  Next, the control unit 200 specifies an arrangement position in the image represented by the document image data for each additional mark specified in step SA110 (step SA120), and performs layout analysis on the image represented by the original image data. Then, for each block such as a chapter or paragraph in the original represented by the original image data, the arrangement position of the image area representing the block is specified (step SA130). Then, the control unit 200 identifies an image area whose distance from the additional image is equal to or less than a predetermined threshold as an image area associated with the additional mark represented by the additional image (step SA140). As shown in FIG. 3A, the additional mark M01 is located in the vicinity of the image area B01 representing the first paragraph of the document to be processed. It is specified that the region B01 is associated. Similarly, by the process of step SA130, it is specified that the additional recording mark M02 and the image area B02 are associated with each other, and it is specified that the additional recording mark M03 and the image area B04 are associated with each other. In the present embodiment, the case where layout analysis is performed on an image represented by original image data and an arrangement position of an image area representing the block is specified for each block such as a chapter or paragraph in the original has been described. The document image data delivered from the reading device 120 is subjected to layout analysis on the image data obtained by performing processing for removing the data representing the additional image, and each block such as a chapter or paragraph in the original is subjected to the block analysis. Of course, the arrangement position of the image area representing the position may be specified.

  Next, the control unit 200 determines whether or not a plurality of additional marks are specified in step SA110 (step SA150). If the determination result is “Yes”, the control unit 200 performs steps SA160 to SA170 described below. Execute the process. As described above, in this operation example, whether or not three additional marks are specified in step SA110, the determination result in step SA150 is “Yes”, and the processes in steps SA160 to SA170 are executed. Will be.

  In step SA160, which is subsequently executed when the determination result in step SA150 is “Yes”, the control unit 200 calculates a feature amount representing the shape of each additional mark, and the feature amount is the same. The recordable marks are classified as the same recordable marks, and the recordable marks whose divergence is within a predetermined range even if the feature amounts are different from each other are classified as similar recordable marks. By executing the processing of step SA160, in this operation example, the three additional recording marks identified in step SA110 include two sets of the additional recording mark M01 and the additional recording mark M03, and the additional recording mark M02. (See FIG. 3A).

In step SA170 executed subsequent to step SA160, control unit 200 associates each additional mark marked as having the same or similar shape in step SA160 with the additional mark. If so, image data representing an image obtained by arranging the image arranged in the image area specified in step SA130 according to the layout of the list format shown in FIG. 5A is generated and output to the display unit 220. To do.
The above is the editing process executed by the document processing apparatus 110 according to the present embodiment.

  As described above, according to the document processing apparatus 110 according to the present embodiment, the image shown in FIG. 5B is displayed on the display unit 220 of the document processing apparatus 110. In the display example shown in FIG. 5B, in the paper document to be processed, the description content of the region associated with the additional mark is displayed side by side for each additional mark having the same or similar shape. As described above, as described above, it is highly possible that the description content of the area to which the additional recording mark having the same or similar shape is attached is related. Therefore, the document according to this embodiment. According to the processing device 110, based on additional marks such as characters, symbols, and figures that are added by hand to a paper document, the description contents of the areas that are assumed to be related to each other are collected and easily understood by the user. There is an effect that it is possible to present.

(C: deformation)
Although one embodiment of the present invention has been described above, it is needless to say that the above-described embodiment may be modified as described below.
(C-1: Modification 1)
In the above-described embodiment, the document image data transferred from the image reading device 120 is compared with the original image data, whereby the additional image representing the item added to the original represented by the original image data is converted into the document processing apparatus. The case where 110 is extracted has been described. However, the document image data delivered from the image reading apparatus is analyzed by the document processing apparatus, and among the images represented by the document image data, a predetermined color is used as a color used when printing the original on a paper document. A part other than the image to be displayed may be extracted by the document processing apparatus as a postscript image. According to such an aspect, for example, the document processing apparatus can extract the additional information written in red for a paper document on which the original is printed in black and white without comparing the original with the original data representing the original. Is possible.

  Further, the document image data delivered from the image reading device is analyzed by the document processing device, and among the images represented by the document image data, an image representing a handwritten character or a handwritten figure is extracted as an additional image by the document processing device. May be. According to such an aspect, for example, the document processing apparatus can extract the items added by hand to a paper document printed in type without comparing with the original data representing the original. Is possible. In addition, if the paper used to print the original is Anoto Paper, and additional writing is performed with Anoto Pen, it is also possible to specify the additional writing position and the additional writing position based on the data output from the Anoto Pen. It is.

(C-2: Modification 2)
In the embodiment described above, the case where the paper document to be processed is composed of one page has been described. However, it is needless to say that a paper document composed of a plurality of pages may be processed by the document processing apparatus according to the present invention. In this way, when the paper document to be processed is composed of a plurality of pages, the processing in steps SA110 to SA140 described above may be executed for each piece of image data representing the image of each page. Further, in the above-described embodiment, the case where the area associated with each additional mark is an area representing an item described in the original of the paper document is described. If the image area where the image is placed (hereinafter referred to as the handwriting area) has a predetermined positional relationship with the additional mark, such as being located near the additional mark, the handwritten area becomes the additional mark. Of course, it may be specified that it is associated. For example, for a paper document composed of three pages as shown in FIG. 6 (a), an additional article is extracted by the document processing apparatus according to the present invention, and the extraction result is output to the document processing apparatus (for example, When the extraction result is displayed, the image shown in FIG. 6B is output.

  More specifically, in the paper document shown in FIG. 6A, the additional writing mark M11 is handwritten in the first paragraph B11 of the first page, and the additional writing mark M12 is added in the blank handwritten area C11. It is attached by hand. Further, a write-once mark M21 is handwritten in the margin handwritten region C21 on the second page, and a write-once mark M31 is handwritten in the marginal handwritten region C31 on the third page. As is clear from FIG. 6A, the additional recording mark M11 and the additional recording mark M31 are both additional recording marks representing the capital letter “A”, and the additional recording mark M12 and the additional recording mark M21 are uppercase letters. This is a postscript mark indicating “B”.

  As a result of performing the above-described steps SA110 to SA140 on the image data corresponding to each page of the paper document, the additional mark M11 and the additional mark M31 are the same for the paper document shown in FIG. Alternatively, the region is classified as a postscript mark having a similar shape and is associated with the postscript mark M11 (ie, the first page, first paragraph B11) and the region associated with the postscript mark M31 (ie, An image representing the description content of the third page margin handwritten area C31) is displayed side by side in association with the image of the additional mark. On the other hand, the additional recording mark M12 and the additional recording mark M21 are also classified as additional recording marks having the same or similar shape, and are associated with the additional recording mark M12 (ie, the handwritten region C11 in the first page margin). And an image representing the description content of the area associated with the additional mark M21 (that is, the handwritten area C21 in the second page margin) are displayed in association with the image representing the additional mark. As a result, the image shown in FIG. 6B is displayed.

(C-3: Modification 3)
In the embodiment described above, a case has been described in which an image arranged in an image region located in the vicinity of the additional recording mark is specified as the additional recording image. However, an image arranged in an image region located in the vicinity of the first additional recording mark may be specified as an image to be recorded with respect to the second additional recording mark positioned in the vicinity of the first additional recording mark. In this case, for example, as shown in FIG. 7, the second additional recording mark M42 located near the first additional recording mark M41 such as a lead line and the image positioned near the first additional recording mark M41. It is possible to associate the image arranged in the region B41.

(C-4: Modification 4)
In the above-described embodiment, the case has been described in which the software for causing the control unit 200 to realize functions unique to the document processing apparatus according to the present invention is stored in the nonvolatile storage unit 240b in advance. However, for example, the software is recorded on a computer-readable recording medium such as a CD-ROM (Compact Disk-Read Only Memory) or a DVD (Digital Versatile Disk), and is generally used with such a recording medium. Of course, the software may be installed in a simple computer device. If it does in this way, there exists an effect that it becomes possible to provide the same function as a document processing device concerning the present invention to a general computer device.

1 is a block diagram illustrating a configuration example of a document processing system 10 including a document processing apparatus 110 according to an embodiment of the present invention. 2 is a block diagram showing an example of a hardware configuration of the document processing apparatus 110. FIG. 2 is a diagram illustrating an example of a paper document represented by document image data input to the document processing apparatus 110 and an original document thereof. FIG. It is a flowchart which shows the flow of the edit process which the control part 200 performs according to edit software. 6 is a diagram illustrating an example of an editing result displayed on a display unit 220 of the document processing apparatus 110. FIG. It is a figure for demonstrating the edit process which concerns on the modification 2. FIG. It is a figure for demonstrating the edit process which concerns on the modification 3. FIG.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 ... Document processing system 110 ... Document processing apparatus 120 ... Image reading apparatus 130 ... Communication line 200 ... Control part 210 ... Communication IF part 220 ... Display part 230 ... Operation part 240 ... Storage part 240a ... volatile storage unit, 240b ... non-volatile storage unit, 250 ... bus.

Claims (5)

Input means for inputting document image data obtained by digitizing a paper document;
Analyzing the document image data input to the input means, and a first specifying means for specifying an additional mark added by hand writing on the original document represented by the document image data;
Second specifying means for specifying an image area of the document image data associated with the additional mark for each additional mark specified by the first specifying means;
When a plurality of additional marks are specified by the first specifying means, the shape of each additional mark is analyzed, and classification means for classifying each additional mark having the same or similar shape;
For each additional mark classified as having the same or similar shape by the classifying means, an image arranged in the image area specified by the second specifying means is associated with the additional mark. A document processing apparatus comprising: output means arranged and output according to a predetermined layout. The first specifying means includes:
2. The document according to claim 1, wherein the additional mark is specified by comparing the document image data input to the input means with original image data representing an original of a paper document represented by the document image data. Processing equipment. The first specifying means includes:
The additional mark is specified based on a difference between an image color represented by the document image data input to the input unit and an original color of the paper document represented by the document image data. The document processing apparatus described. The classification means includes
Analyzing the shape of the write-once mark and calculating its feature value, classifying the write-once marks that have the same calculated feature amount as write-once marks having the same shape, while the calculated feature amount has a predetermined divergence The document processing apparatus according to claim 1, wherein the recordable marks within the range are classified as similar recordable marks. Computer equipment,
A first step of analyzing document image data obtained by digitizing a paper document and identifying an additional mark added by hand to the original document represented by the document image data;
A second step of specifying an image area of the document image data associated with the additional mark for each additional mark specified in the first step;
When a plurality of additional marks are specified in the first step, a third step of analyzing the shape of each additional mark and classifying each additional mark having the same or similar shape;
The image area specified in the second step when each of the additional marks classified as representing the additional mark having the same or similar shape in the third step is associated with the additional mark. A program that executes a fourth step of arranging and outputting the image arranged in accordance with a predetermined layout.

Images