JP2009169675A - Document processing apparatus, document processing method and document processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing apparatus, a document processing method and a document processing program that can automatically set document breaks in originals of various types of mixed documents without troubling users. <P>SOLUTION: The document processing apparatus includes a line area extraction part 21 for extracting line areas from document images stored in an image buffer part 13, a style feature detection part 22 for detecting a plurality of line attributes based on a plurality of predetermined attribute types and detecting a style feature indicating the combination pattern of the line attributes in each line area, a primary determination part 23 for determining primary style features of the document images from a plurality of detected style features, and a break position setting part 24 for setting break positions in the document images according to variations in the primary style features between pages. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a document processing apparatus, a document processing method, and a document processing program, and more particularly to a document processing apparatus, a document processing method, and a document processing program having a document reading function.

  From the viewpoint of resource saving and space saving, a document management system that converts and manages a document described on a paper manuscript or the like into an electronic document has been put into practical use. In such a document management system, a document image is generated by reading a document using a scanner device or the like, and an electronic document is generated from these document images.

  2. Description of the Related Art Conventionally, proposals have been made for automatically setting document separators when various documents are continuously input.

  For example, Patent Document 1 discloses that an electronic filing device performs character recognition of an image and sets a document break when the character recognition result matches a preset character string.

  Patent Document 2 discloses that the image processing apparatus sets document breaks based on the degree of difference between the layout of each page and the layout of a page adjacent to each page.

Patent Document 3 discloses that an electronic file device detects the orientation (vertical and horizontal) of an image and sets a document break when the detected orientation of the image is different from that of the immediately preceding document.
Japanese Patent Laid-Open No. 9-231309 JP 2006-72484 A JP 7-192109 A

  In Patent Document 1, in order to set a delimiter for a document, it is necessary to include a specific character string at the beginning or end of the document. However, the same type of document including a specific character string is limited.

  In Patent Document 2, a layout change is required between the beginning and end of a document. In a single type of document, there may be a regular change in layout due to document separation, but in the case where a plurality of documents are mixed, there are many cases where regularity does not occur in the change in layout. There are also types of documents whose layout does not change, or documents with various layouts.

  Furthermore, according to Patent Document 3, before a plurality of documents are scanned, the user needs to change the direction of each document to the direction of the immediately preceding document at a location where a separation is desired.

  The present invention has been made to solve the above-described problems, and an object of the present invention is to automatically set document separation without any user's effort from a manuscript in which various types of documents are mixed. An image processing apparatus, a document processing method, and a document processing program are provided.

  An image processing apparatus according to an aspect of the present invention is configured to extract a predetermined type of document area from a first storage unit for storing a document image and the document image stored in the first storage unit. Detecting means for detecting a plurality of area attributes based on each of a plurality of predetermined attribute types for each document area, and detecting a style feature representing a pattern of the combination of the area attributes; A plurality of the style features are classified for each pattern, a determination unit for determining one or more main style features for the document image based on the appearance frequency of the classified pattern, and a plurality of style features for each page Detect which of the main style features is present and set the document image separation position based on the amount of change of the main style features between pages And an order of the setting means.

  Preferably, for each of the style features, the determination unit includes a frequency calculation unit for calculating the number of pages in which the style feature appears as the appearance frequency, and a style feature in which the calculated number of pages is equal to or greater than a predetermined value. Means for determining as the main style feature.

  Preferably, the setting means includes means for determining the main style feature existing in each page as the page feature of the page, and for each page, the page feature of the page is derived from the page feature of the previous page. An amount calculating means for calculating the changed amount as the change amount; and a means for setting a break position between the pages when the calculated change amount is equal to or greater than a predetermined value.

  Preferably, when the same page feature is detected in the first and third pages other than the second page among the continuous first, second and third pages, the setting means The second page further includes correction means for correcting that the same page feature has been detected.

  Preferably, output means for dividing and outputting the document image based on the separation position set by the setting means is further provided.

  Preferably, when the document image is divided based on the separation position, a display control unit that generates a signal for displaying an index image of a first page in the plurality of divided document images, and the display Display means for performing output in accordance with a signal from the control means.

  Preferably, the apparatus further includes an instruction receiving unit for receiving an instruction from the user regarding the number of document image divisions by the setting unit.

  Preferably, in accordance with the received instruction, a changing unit that changes a predetermined parameter for setting a separation position by the setting unit, and after the change by the changing unit, the processing by the setting unit is executed again. And execution instruction means for instructing.

  Preferably, the image processing apparatus further includes a second setting unit for setting a break position of the document image based on a layout or a predetermined character string.

  Preferably, the plurality of predetermined attribute types include position, size, color in upper area, number of partial areas, position, height, color, distance between adjacent partial areas, character size, character modification , Character color, background color, and font type.

  Preferably, the predetermined type of document area corresponds to one of a column, a line, a character string, and a character.

  A document processing method according to still another aspect of the present invention is a document processing method executed in a document processing apparatus including a storage unit for storing a document image and an arithmetic processing unit, wherein the arithmetic processing unit includes: A step of extracting a predetermined type of document area from the document image stored in the storage unit; and the arithmetic processing unit includes a plurality of area attributes based on a plurality of predetermined attribute types for each of the document areas. Detecting and detecting a style feature representing a combination pattern of the region attributes, classifying the detected plurality of style features for each pattern, and based on the appearance frequency of the classified pattern, the document image Determining one or more primary style features of each of the plurality of primary style features, detecting which of the plurality of primary style features is present for each page; Based on the amount of change in the primary style features among di-, and a step of setting a sectioning position of the document image.

  An image processing program according to still another aspect of the present invention causes a computer to execute the document processing method described above.

  According to the present invention, it is possible to set a separation position without a user's effort even from an original in which various types of documents are mixed. In addition, since the main style feature is determined, the document image can be divided at an optimal position.

  Embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals and description thereof will not be repeated.

<About configuration>
(Overall system configuration)
FIG. 1 is a schematic configuration diagram of a system including a document processing apparatus according to an embodiment of the present invention. In the present embodiment, an MFP (Multi Function Peripheral) equipped with the document processing apparatus according to the present invention will be typically described. The document processing apparatus according to the present invention is
The present invention can be applied not only to the MFP but also to a copying machine, a facsimile apparatus, a scanner apparatus, and the like.

  Referring to FIG. 1, MFP 1 according to the present embodiment is configured to include an image reading unit 104 for reading a document 300 and a printing unit 106 for performing a printing process on a paper medium or the like. MFP 1 according to the present embodiment obtains a document image by reading document 300 by image reading unit 104 and generates an electronic document including the document image. In addition, the MFP 1 outputs the read document image to the printing unit 106.

  In particular, the MFP 1 can set the separation position of the document image based on the style characteristics of the document image having a plurality of pages. The delimiter position is set for each page.

  The MFP 1 divides the document image according to the set delimiter positions, and generates a plurality of electronic documents corresponding to the plurality of divided document images. These electronic documents 400 typically employ a format such as PDF (Portable Document Format).

  The MFP 1 stores the generated electronic document 400 in its own storage unit (not shown in FIG. 1). In addition, the stored electronic document 400 is transmitted to personal computers PC1, PC2 and PC3 (hereinafter also collectively referred to as “personal computer PC”) via a network. As a typical usage pattern, the MFP 1 sends an electronic document 400 to the personal computers PC1 and PC2 connected to a local area network (LAN) that is a network laid in the same office where the MFP 1 is installed. Is sent directly. On the other hand, a server SRV is provided at a connection point between a LAN and a WAN (Wide Area Network). A personal computer PC3 or the like in an office remote from the MFP 1 is connected from the MFP 1 via the server SRV. An electronic document 400 is transmitted. Here, the server SRV typically includes a mail server, an FTP (File Transfer Protocol) server, a Web server, an SMB server, and the like.

  The image reading unit 104 includes a loading table for setting a document, a document table glass, a conveyance unit that automatically conveys the documents set on the loading table one by one to the document table glass, and a scanned document. And a discharge stand for discharging (both not shown). As a result, one or a plurality of electronic documents can be generated by continuously reading a plurality of documents.

  The print unit 106 has a sort function. The MFP 1 divides the document image according to the set separation position, and outputs each of the divided document images to the printing unit 106 by changing the sorting method. Thereby, it is possible to sort and output the originals read at one time.

(Schematic configuration of MFP 1)
FIG. 2 is a block diagram showing a schematic hardware configuration in MFP 1 according to the embodiment of the present invention.

  Referring to FIG. 2, the functional configuration of MFP 1 includes a control unit 100, a memory unit 102, an image reading unit 104, a printing unit 106, a communication interface unit 108, an operation panel unit 110, and a storage unit 112. Including.

  The control unit 100 is typically composed of an arithmetic device such as a CPU (Central Processing Unit), and implements document processing according to the present embodiment by executing a program. The memory unit 102 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory), and holds a program executed by the control unit 100, data necessary for executing the program, and the like. The communication interface unit 108 is typically a part for transmitting and receiving data to and from the personal computer PC (FIG. 1) via a network (for example, the LAN shown in FIG. 1). Including driver software to control The print unit 106 is a part for performing print processing, and includes a control device for controlling the operation of each unit in addition to the hardware configuration related to print processing.

  The storage unit 112 is typically a nonvolatile storage device such as a hard disk device or a flash memory, and stores a program for the operation of the control unit 100, the electronic document 400 generated by the control unit 100, and the like.

  In the present embodiment, it is assumed that the document image divided based on the set separation position is output to any one of the communication interface unit 108, the storage unit 112, and the print unit 106.

  An example of the appearance of the operation panel unit 110 is shown in FIG. FIG. 3 is a diagram showing an example of the appearance of the operation panel unit of MFP 1 according to the embodiment of the present invention.

  Referring to FIG. 3, operation panel unit 110 includes a display panel 110a including a liquid crystal display device, a touch panel, and the like, a stop button 110b, a start button 110c, and an operation button 110d including alphanumeric keys. ing.

  The MFP 1 includes the operation panel unit 110 having both a display function and an instruction input function. Alternatively, the MFP 1 may include both a display unit and an input unit including hardware buttons. Good.

(Configuration of personal computer)
FIG. 4 is a schematic diagram showing a schematic hardware configuration of personal computer PC according to the embodiment of the present invention.

  Referring to FIG. 4, personal computer PC temporarily stores a CPU (Central Processing Unit) 201 that executes various programs including an operating system (OS) and data necessary for the CPU 201 to execute the program. A memory unit 213 that stores data and a hard disk unit (HDD: Hard Disk Drive) 211 that stores programs executed by the CPU 201 in a nonvolatile manner are included. The hard disk unit 211 stores a browsing application for displaying the electronic document 400 generated by the MFP 1, and such a program is stored in the flexible disk 217 a by the FDD drive 217 or the CD-ROM drive 215, respectively. Alternatively, it is read from a CD-ROM (Compact Disk-Read Only Memory) 215a or the like.

  The CPU 201 receives an instruction from the user via the input unit 209 including a keyboard and a mouse, and outputs a screen output generated by executing the program to the display unit 205. Further, the CPU 201 acquires the electronic document 400 from the MFP 1 or server SRV (FIG. 1) connected to the LAN or WAN via the communication interface unit 207 including a LAN card and stores the electronic document 400 in the hard disk unit 211 or the like. Further, the above-described units exchange data with each other via the internal bus 203.

(Functional configuration of MFP)
FIG. 5 is a functional block diagram showing a functional configuration when MFP 1 according to the embodiment of the present invention generates an electronic document.

  Referring to FIG. 5, the control unit 100 of the MFP 1 includes an image buffer unit 13, an electronic document generation unit 15, an image analysis unit 16, a transmission processing unit 17, a display control unit 25, and an instruction reception unit 26. A parameter changing unit 27.

  The above-described image reading unit 104 reads the document 300 and acquires a document image. More specifically, RGB digital image data is acquired by optically reading a paper-like document 300 and converting it to digital data. The image reading unit 104 outputs the acquired document image (digital image data) to the image buffer unit 13.

  In the present embodiment, the document image read by the image reading unit 104 is described as being output to the image buffer unit 13, but the image data 310 received by the communication interface unit 108 functioning as the receiving unit 12. May be output to the image buffer unit 13. The receiving unit 12 may receive the image data 310 via a network such as a LAN, or may receive the image data 310 stored in a portable small memory (not shown), for example. The receiving unit 12 outputs the image data 310 after matching the data format.

  The image buffer unit 13 is a part for temporarily storing document image data, and holds the image data until an output request is received from the image analysis unit 16 and the electronic document generation unit 15. If there is an output request from the image analysis unit 16 and the electronic document generation unit 15, the corresponding image data is output. In the present embodiment, the image buffer unit 13 also holds management information for each image data. As described later, the management information includes a document ID.

  The image analysis unit 16 includes a line area extraction unit 21, a style feature detection unit 22, a main determination unit 23, and a break position setting unit 24.

  The line area extraction unit 21 extracts a line area from the document image output from the image buffer unit 13 as a predetermined type of document area. In the present embodiment, the “predetermined type of document area” may be an area included in the text area, and is not limited to the line area. For example, it may be other partial areas such as a character area, a character string, and a column divided by a certain margin or more. Alternatively, it may be an upper area such as a page or a column.

  The style feature detection unit 22 detects a style feature for each row region extracted by the row region extraction unit 21 based on a plurality of predetermined attribute types. More specifically, for each row region, a plurality of row attributes based on each of a plurality of predetermined attribute types are detected, and a combination pattern of the row attributes is detected as a style feature. “Predetermined multiple attribute types” are information used to identify the characteristics of a plurality of pages included in a document image. The position, size, color, number of partial areas, position, It includes at least two of height, color, distance between adjacent partial areas, character size, character modification, character color, background color, and font type. In addition, it may include the height of the upper character area. In the present embodiment, the predetermined plurality of attribute types include the height of a line (partial region), the line spacing (position) with an adjacent line, character color, background color, and character modification. In the present embodiment, “row attribute” refers to five types of attributes corresponding to each of the five attribute types for each row region.

The detected style feature for each row area is output to the main determination unit 23.
The main determining unit 23 determines a main style feature of the read document image among the detected plurality of style features. Specifically, a plurality of style features are classified for each pattern, and one or more main style features for the document image are determined based on the appearance frequency of the classified patterns. That is, for each style feature, the main determination unit 23 calculates (counts) the number of pages in which the style feature appears as the appearance frequency, and determines the style feature whose calculated number of pages is equal to or greater than a predetermined value as the main style. Judged as a feature (valid). In other words, the style feature having the number of pages less than the predetermined value is a local style feature, and is determined not to be a main style feature characterizing the document (invalid). The determined main style features are output to the break position setting unit 24.

  The delimiter position setting unit 24 sets the delimiter position of the read document image in units of pages based on the determined main style features. Specifically, for each page, it is detected which of a plurality of main style features is present, and the document image separation position is set based on the amount of change of the main style features between pages. . That is, the main style feature existing on the page is determined as the page feature of the page. Then, for each page, the amount of change of the page feature of the page from the page feature of the previous page is calculated as a change amount. The break position setting unit 24 sets a break position between the pages when the calculated change amount is equal to or greater than a certain value. Set the location as the break position. Further, the break position setting unit 24 assigns a document ID to the image data corresponding to each page based on the set break position. Information on the assigned document ID is output to the image buffer unit 13.

  Thus, the break position is automatically set based on the main style features in the document image. Therefore, it is possible to set a break at an optimum position without requiring the user's effort even from a manuscript in which various types of documents are mixed.

  Note that the break position setting unit 24 preferably performs correction processing after determining the page characteristics. That is, when the same page feature is detected in the first and third pages other than the second page among the first, second, and third pages that are continuous, the same applies to the second page. The correction is made assuming that the page feature is detected. Such correction is preferably performed only when the same page feature is not detected on all pages. When the same page feature is present in the preceding and following pages, the pages in between are generally the same page feature. For example, the case where the page in the meantime was a table | surface or a photograph is assumed. Even in such a case, the correction process as described above is performed in order to appropriately determine the page feature of each page from the appearance position of the main style feature. Thereby, it is possible to prevent a break from being set at a position that is not optimal as a break.

  The electronic document generation unit 15 inputs a document image and management information from the image buffer unit 13. The electronic document generation unit 15 performs image data compression processing and converts the compressed image data into a PDF format (generates an electronic document). At that time, the electronic document generation unit 15 generates a plurality of electronic documents based on the document ID included in the management information (that is, based on the set separation position). More specifically, an electronic document is generated for each assigned document ID. Then, the information of the generated electronic document is output to the display control unit 25. In addition, when the instruction receiving unit 26 receives a predetermined instruction, the generated electronic document is stored in the storage unit 112 or output to the transmission processing unit 17 according to the setting by the user. The degree of compression may be changed according to the size of the generated electronic document, the required resolution of the document image, and the like.

  The display control unit 25 generates a signal for displaying an index image for specifying each generated electronic document, for example, a preview image of the first page. The display control unit 25 outputs the generated signal to the operation panel unit 110. As a result, a plurality of preview images are displayed on the operation panel unit 110. Note that the index image is not limited to the preview image of the first page as long as it is possible to specify the document image separation position. Further, the image may not be an image as long as the document image separation position can be specified.

  The instruction receiving unit 26 receives an instruction regarding the number of generated electronic documents via the operation panel unit 110. Specifically, an instruction to increase the number of documents (hereinafter referred to as “increase instruction”), an instruction to decrease the number of documents (hereinafter referred to as “decrease instruction”), and an OK instruction (instruction to output with the current number of documents). Either of these is accepted. When receiving an increase instruction or a decrease instruction, the instruction receiving unit 26 outputs the instruction content to the parameter changing unit 27. When an OK instruction is accepted, a message to that effect is output to the electronic document generation unit 15.

  The parameter changing unit 27 changes a predetermined parameter for setting the break position based on the received correction instruction content. When the parameter is changed, execution of processing by the separation position setting unit 24 is instructed again. Thereby, the break position setting unit 24 executes the break position setting process again based on the changed parameter.

  As described above, in this embodiment, after the break position is automatically set, the user is made to confirm the break degree (number of divisions). Therefore, the user can instruct execution of the separation position setting process as many times as desired.

  The transmission processing unit 17 performs processing for transmitting the electronic document 400 to a destination designated by the user according to various communication protocols. As the protocol, for example, SMB (Server Message Block), FTP (File Transfer Protocol), HTTP (Hyper Text Transfer Protocol), SMTP (Simple Mail Transfer Protocol) or the like can be selected. In the present embodiment, when a plurality of electronic documents 400 having different document IDs are generated, the transmission processing unit 17 assigns a different file name to each electronic document 400. For example, “Doc” + “Document ID” + “. Pdf” is given as the file name. Further, the transmission processing unit 17 sets a destination of the electronic document 400 based on an instruction from the user. Examples of these specific processes will be described later. The transmission processing unit 17 outputs the electronic document 400 and the file name and destination for each electronic document 400 to the transmission unit 18.

  The transmission unit 18 is realized by the communication interface unit 108, and transmits the plurality of electronic documents 400 generated by the electronic document generation unit 15 to a personal computer PC (FIG. 1) or the like via a network such as a LAN. The transmission unit 18 can be mounted with, for example, a portable small memory (not shown), and the electronic document 400 may be output to such a removable memory.

  The operation of each block included in the control unit 100 may be realized, for example, by executing software stored in the storage unit 112, and at least one of these blocks is implemented by hardware. It may be realized.

<About operation>
(Electronic document generation processing)
The electronic document generation process executed by the MFP 1 according to the embodiment of the present invention will be specifically described below with reference to the flowcharts of FIGS. 6 to 8 and FIGS.

  FIG. 6 is a flowchart showing an electronic document generation process in the embodiment of the present invention. The processing shown in the flowchart of FIG. 6 is stored in advance in the storage unit 112 as a program, and the function of the electronic document generation processing is realized by the control unit 100 reading and executing this program. In this flowchart, it is assumed that the user has set transmission of an electronic document to a PC or the like via the Internet.

  With reference to FIG. 6, the line area extraction unit 21 first extracts a line area from the document image stored in the image buffer unit 13 (step S2). Specifically, a row area is extracted by the following procedure. FIG. 9 is a diagram for explaining row area extraction processing in the present embodiment. FIG. 9A shows an arbitrary page of the original document image.

  The row area extraction unit 21 binarizes the RGB image data of each page. For example, the luminance value of the RGB image is converted and compared with the average luminance value of each page. Accordingly, “0” is temporarily recorded in the bright area and “1” is recorded in the dark area in the memory unit 102, for example. Next, the pixels of the binary image whose value is “1” are scanned eight times. When there is connection, a black connected region is generated by giving the same label value to the pixel, and a circumscribed rectangle is obtained. FIG. 9B is a diagram illustrating a result of obtaining a circumscribed rectangle.

  Next, for each circumscribed rectangle, a region close to a certain distance in the left-right direction is detected, and the detected regions are integrated into one region. FIG. 9C shows a region where the circumscribed rectangles of FIG. 9B are integrated. The line area extraction unit 21 outputs the integrated area as a line area. An example of a row area extracted for a document including a plurality of pages is shown in FIG. Note that the process for extracting the row region is not limited to the process described above.

  When the process of step S2 ends, the style feature detection unit 22 detects the style feature for each extracted row region based on a plurality of predetermined attribute types (step S4). Specifically, line height, line spacing with adjacent lines, character color, background color, and character modification are used as a plurality of attribute types. Therefore, the style feature detection unit 22 detects a style feature based on these attribute types for each row region.

  The “row height” is obtained by calculating the height of the row area. “Inter-row spacing” detects the adjacent row regions in the vertical direction and calculates the distance to each adjacent row region. Then, the value having the smaller distance is obtained as “the space between adjacent rows”. “Character color” and “background color” generate a color histogram of each row region. Then, the most frequent color is obtained as “background color” and the next frequency color is obtained as “character color”. “Character modification” generates a run-length histogram of the line area. That is, a continuous length histogram of black pixels in the vertical and horizontal directions of the row region is generated. Then, based on the generated run length histogram, character modification such as “thick character” and “italic” is determined, and the most frequent character modification is obtained as “character modification”. The method for detecting each row attribute is not limited to the method described above.

The style feature detection unit 22 records each detected row attribute in the row area list.
FIG. 11 is a diagram illustrating an example of a list of row areas included in the document image. Referring to FIG. 11, the row area list has mainly four items, that is, a page, a page ID, a row ID, and an attribute type, and these items are associated with each other. In the page item, the first page, the second page,..., The sixth page are recorded in the page order of the document image. In the page ID item, identification information (ID) for uniquely specifying each page is recorded. In the row ID item, identification information (ID) for uniquely specifying each row in each page is recorded. In the attribute type item, style characteristics based on the above five attribute types are recorded for each row ID. “Style feature” refers to a feature based on a combination of five row attributes in the present embodiment. That is, for example, in the row with the row ID 1 on the first page, the row height “4”, the line spacing “20” with the adjacent row, the character color “black”, the background color “white”, and the character modification “thick character”. Each is a row attribute of this row. A combination of these row attributes is a style feature of this row.

  When the process of step S4 ends, the style feature detection unit 22 generates a style feature list based on the style features detected for each row region (step S6). The style feature list is a list of unique style features.

FIG. 12 is a diagram illustrating an example of a style feature list.
Referring to FIG. 12, the style feature list has six items, that is, a style ID, a line height, a space between adjacent lines, a character color, a background color, and a character modification item, and each item corresponds to each other. It is attached. The style ID is identification information (ID) for uniquely specifying a unique style feature.

  When the process of step S6 ends, the main determination unit 23 calculates the frequency for each style feature (step S8). More specifically, the number of appearing lines and the number of pages are calculated for each style ID in the style feature list. Thus, the appearance frequency (existence ratio) in the document image is calculated for each style feature specified by each style ID. Since it is necessary to extract the style features for each page, only the number of pages may be calculated.

  FIG. 13 is a diagram illustrating an example of a table indicating a frequency calculation result for each style feature (hereinafter referred to as “calculation result table”). Referring to FIG. 13, the calculation result table column includes seven items corresponding to the seven style IDs, and the row of the table includes six items corresponding to the six page IDs, and An item indicating the number of lines and an item indicating the number of pages are provided. In addition, the item of the effectiveness included in the row of the calculation result table records the result of the subsequent determination process.

  In the calculation result table, the number of lines in which the style feature specified by each style ID appears is recorded in the page ID column. Then, the main determination unit 23 calculates the number of lines and the number of pages for each style ID based on the recorded information on the number of lines.

  When the process of step S8 ends, the main determination unit 23 determines main style characteristics (step S10). Specifically, for example, a style feature having a predetermined number of pages or more is determined as a main style feature. Here, the “predetermined number” is preferably a value calculated in advance based on the number of pages of the document image. For example, it is a value obtained by multiplying the number of pages by a certain ratio (for example, 1/3). Therefore, in the example of the document image shown in FIG. 10, the style feature having two or more pages is determined as the main style feature.

  The main determination unit 23 records “present” indicating validity in a style ID column corresponding to a style feature having two or more pages in the validity column of the calculation result table, and a style having less than two pages. “None” indicating invalidity is recorded in the style ID column corresponding to the feature. In other words, “Yes” is recorded for the main style feature. FIG. 13 shows that style features with style IDs 2, 3, 5, and 6 are main style features.

  Here, the main style features are determined based only on the number of pages, but determination may be made in consideration of the number of lines. For example, a case where the number of pages is 2 or more and the number of lines is a predetermined number or more may be determined as the main style feature. The “predetermined number” in this case may be a value calculated in advance based on the total number of rows, or may be a value calculated in advance based on the number of pages. In this way, by making a determination in consideration of the number of lines, it is possible to prevent a style feature having a low appearance ratio in the page from being determined as a main style feature. Alternatively, the occupation area of each style feature in a page may be calculated, and the number of pages may be counted only when the ratio is equal to or greater than a certain value.

  When the process of step S10 ends, the main determination unit 23 generates a table (hereinafter, “main area feature table”) of style features determined to be main style features (step S12). FIG. 14 is a diagram illustrating an example of the main area feature table.

  Referring to FIG. 14, the main area feature table includes only items corresponding to the style ID in which “present” is recorded in the validity column in the calculation result table shown in FIG. 13. In other words, the main area feature table includes the number of appearing lines, the total number of lines, and the number of appearing pages (and validity) for each page for the style feature determined as the main style feature.

  When the process of step S12 ends, the break position setting unit 24 executes a break position setting process (step S14). The delimiter position setting process will be described in detail with reference to the flowchart of the subroutine of FIG.

  FIG. 7 is a flowchart showing a delimiter position setting process according to the embodiment of the present invention.

  The delimiter position setting unit 24 determines the page feature of each page (step S102). Based on the main area feature table of FIG. 14, the page feature of page 1 is a style feature with a style ID of 2 and 3, and the page feature of page 2 is a style feature with a style ID of 3. The page features of page 3 are style features with style IDs 2 and 3, and the page features of pages 4 and 5 are style features with style IDs 5 and 6, respectively. The page feature of page 6 is a style feature with a style ID of 6.

  Next, the break position setting unit 24 executes correction processing (step S104). Specifically, when there is a style ID that does not exist only in the pages between three consecutive pages, the page is corrected as having the style ID. In the example of FIG. 14, the style feature (page feature) specified by the style ID “2” exists on pages 1 and 3 but does not exist on page 2 as indicated by a surrounding line 51. Therefore, the break position setting unit 24 rewrites the page 2 field corresponding to the style ID “2” from “0” to “1”. The corrected result is shown in FIG. FIG. 15 is a diagram showing a main area feature table after the correction processing according to the embodiment of the present invention is performed. As shown in FIG. 15, the number of rows and the number of pages of the row with the style ID “2” are incremented by 1 along with the rewriting. As a result of such correction processing, a page feature determination result item 61 is added to the column of the main area feature table. Referring to the line of the item 61, it is indicated that the page features of pages 1 to 3 are style IDs 2 and 3, the page features of pages 4 and 5 are style IDs 5 and 6, and the page feature of page 6 is style ID 6.

  Note that the correction processing here is executed if at least one row having the same style feature exists in the previous and subsequent pages (first and third pages). However, for example, the correction process may be executed only when there is a predetermined number of lines according to the total number of pages.

  The correction process is executed only when the “variable i” for specifying whether or not to perform the correction process is 1, and the variable i is initially set to 1.

Note that such correction processing does not necessarily have to be executed.
When the process of step S104 is completed, the break position setting unit 24 calculates a page feature change amount between pages (step S106). The delimiter position setting unit 24 further adds a page feature change amount item 62 to the column of the main area feature table shown in FIG. Referring to the row of the item 62, since the page features of the pages 1 to 3 are the same, the change amount from the page 1 to the page 2 and the change amount from the page 2 to the page 3 are both “0”. Is recorded. Since page 4 has neither of style IDs 2 and 3 which are page features in page 3, the change amount from page 3 to page 4 is recorded as “2”. Since page 4 and page 5 have the same page characteristics, the amount of change from page 4 to page 5 is “0”. Since the page 6 does not have the style ID 5 that is the page feature of the page 5, the change amount from the page 5 to the page 6 is “1”.

  When the process of step S106 is completed, the break position setting unit 24 sets a break position (step S108). Specifically, the break position setting unit 24 sets a break position between pages whose change amount is “variable j” or more. “Variable j” is a value (amount of change) that serves as a reference when setting the delimiter position, and initially, variable j is set to 1. That is, the separation position is set immediately before the page in which a numerical value of 1 or more is recorded in the item 62 column. Therefore, in this example, a separation position is set between page 3 and page 4 and between page 5 and page 6.

  Referring to FIG. 6 again, the break position setting unit 24 assigns a document ID based on the break position (step S16). In other words, the break position setting unit 24 updates the document ID at the location determined as the break position. Specifically, the break position setting unit 24 adds a document ID item 63 to the column of the main area feature table shown in FIG. Referring to the row of item 63, “1” is recorded as the document ID in the columns of pages 1 to 3, and “2” is recorded as the document ID in the columns of pages 4 and 5. In the page 6 column, “3” is recorded as the document ID. Thus, “1” is assigned as the document ID to the first page, and the document ID is incremented by 1 at the break position.

  The delimiter position setting unit 24 outputs the document ID information to the image buffer unit 13. As a result, the management information including the document ID is stored in the image buffer unit 13 together with the document image. FIG. 16 shows an example of the data structure of management information including a document ID. In the management information, a page ID, a document ID, and a pointer to each image data (page) are stored in association with each other. The image buffer unit 13 outputs document image data and management information to the electronic document generation unit 15.

  The electronic document generation unit 15 generates a plurality of electronic documents based on the document ID information included in the management information (step S18). That is, the electronic document generation unit 15 generates electronic documents for the number of document IDs. FIG. 17 shows an example in which three documents are generated for the document image of FIG. Referring to FIG. 17, PDF data 1 serving as a first electronic document corresponds to document ID 1, and the electronic document includes page 1 to page 3 document images. The PDF data 2 serving as the second electronic document corresponds to the document ID 2, and the electronic document includes the document images of pages 4 and 5. The PDF data 3 serving as the third electronic document corresponds to the document ID 3, and the electronic document includes the document image of page 6.

  Next, the display control unit 25 displays a document confirmation screen on the display panel 110a of the operation panel unit 110 (step S20). FIG. 18 is a diagram illustrating an example of a document confirmation screen, and FIG. 18A illustrates an example of a screen displayed in step S20 of FIG. Referring to FIG. 18A, a preview image of the first page of each electronic document is displayed on the document confirmation screen, and a message “Three documents have been read. Are you sure you want to send them?” Is displayed. Is displayed. In addition, four buttons (an OK button, a correction (increase) button, a correction (decrease) button, and a cancel button) for receiving an instruction from the user are displayed on the screen.

  The instruction receiving unit 26 determines whether or not an OK instruction is input via the operation panel unit 110 (step S22). When the correction button is selected (NO in step S24), the parameter changing unit 27 executes a parameter changing process (step S26). When the cancel button is selected, all processing is interrupted and the original state (state where no separation position is set) is returned.

  The parameter change process will be described with reference to a subroutine flowchart shown in FIG.

  FIG. 8 is a flowchart showing parameter change processing in the embodiment of the present invention. Referring to FIG. 8, parameter changing unit 27 determines whether an increase instruction is input from the user (step S202). When it is determined that an increase instruction has been input, that is, when the correction (increase) button is selected (YES in step S202), parameter changing unit 27 sets variable i described above to 0 (step S204). That is, it sets so that the above-mentioned correction processing (Step S104) may not be performed.

  When it is determined that the instruction is not an increase instruction, that is, when the correction (decrease) button is selected (NO in step S202), the parameter changing unit 27 sets the above-described variable j (when setting the separation position). For example, the reference is incremented by 1 (step S206).

  When the parameter changing process ends, the process returns to step S14, and the delimiter position setting process is executed again based on the changed parameter.

  In the above example, first, the variable i is 1 (correction processing is performed), and the variable j is also 1 (reference value is 1). When an increase instruction is input, the variable i is set to 0 (no correction process is performed). FIG. 19 is a diagram showing a main area feature table when the delimiter position setting process is executed again after the increase instruction is input. Referring to FIG. 19, since the correction process is not executed, the style feature specified by style ID 2 does not exist in page 2. Therefore, referring to the row of the page feature determination result item 61A in this state, the page features of pages 1 and 3 are style IDs 2 and 3, the page feature of page 2 is style ID 3, and the page features of pages 4 and 5 are styles. It is indicated that the page features of IDs 5 and 6 and page 6 are style ID6. Then, referring to the page feature change amount item 62A, it is recorded that the change amount from page 1 to page 2 and the change amount from page 2 to page 3 are both “1”. The column of change amount on pages 3 to 6 is the same as that in FIG. Accordingly, referring to the row of the document ID item 63A, the document ID is updated at a location where the amount of change is 1 or more, so “1” is recorded as the document ID in the page 1 column, and the page 2 column. "2" is recorded as the document ID. Further, “3” is recorded as the document ID in the column of page 3, and “4” is recorded as the document ID in the columns of pages 4 and 5. In the page 6 column, “5” is recorded as the document ID. Thus, when an increase instruction is input, the number of divisions is increased from three to five.

  FIG. 18B shows an example of the document screen confirmation screen displayed in the second step S20 when the correction (increase) button is selected on the document confirmation screen shown in FIG. It is.

  On the other hand, when a reduction instruction is input, the variable j (change amount reference value) is set to 2. FIG. 20 is a diagram illustrating a main area feature table when the delimiter position setting process is executed again after the reduction instruction is input. Referring to FIG. 20, since the page feature determination result is the same as that in the first separation position setting process, the rows of items 61 and 62 are the same as those in FIG. Referring to the row of the document ID item 63B, since the document ID is updated at a location where the amount of change is 2 or more, “1” is recorded as the document ID in the columns of pages 1 to 3, and pages 4 and 5 In this column, “2” is recorded as the document ID. Since the amount of change from page 5 to page 6 is less than the reference value (2), “2” is also recorded as the document ID in the page 6 column. Thus, when the reduction instruction is input, the number of divisions is reduced from three to two.

  FIG. 18C shows an example of the document confirmation screen displayed in the second step S20 when the correction (decrease) button is selected on the document confirmation screen shown in FIG. .

  In the screens shown in FIGS. 18B and 18C, each time a correction button is selected, the parameter (variables i, j) is changed and the delimiter position setting process is repeated.

  If an OK instruction is input in step S22, that is, if the OK button is selected (YES in step S22), the transmission processing unit 17 generates a file name for each document image and sends it to the operation panel unit 110. A destination setting screen is displayed (step S24).

  FIG. 21 is a diagram illustrating an example of a destination setting screen. Referring to FIG. 21, the name and destination of each electronic document are displayed on the destination setting screen, and a message “Send to below” is displayed. On this screen, buttons (OK button, cancel, change button) for accepting input of instructions from the user are displayed. The change button is a button for accepting an instruction to change the name and destination of each electronic document, and is provided for each electronic document. FIG. 21 shows an example of a screen after the transmission destination is set by the user. The delivery destination may be set for each electronic document, for example, when the user manually inputs a mail address. Such an input may be accepted by the operation panel unit 110.

  When the OK button is selected on the transmission destination setting screen, the transmission processing unit 17 transmits the electronic document to the transmission destination set for each electronic document via the transmission unit 18 (step S28). This completes the document image generation process.

  Note that although the case where the generated electronic document is output to the transmission unit 18 has been described, the same processing as described above is executed when the generated electronic document is output to the storage unit 112. In that case, instead of the processes of steps S24 and S28, a process of storing a plurality of electronic documents in the storage unit 112 may be executed.

  As described above, even when documents including various types of documents are read together, a plurality of automatically generated electronic documents can be transmitted to destinations set by the user. In addition, since the delimiter position is set based on the style characteristics of the acquired document image, the electronic document can be separated at the optimum position. In other words, according to the present embodiment, first, a style feature is detected for each row area, and a main style feature representing a style pattern that characterizes the document image is determined. Then, for each page, main style features existing on the page are detected as page features, and a document image separation position is set based on the amount of change in page features between pages. In this way, once the main style features in the entire document image are determined, the page features for each page are detected. Therefore, it is possible to set the delimiter position at an optimum position rather than simply setting the delimiter position based only on the style feature for each row area.

  As described above, in order to change the parameter, an input of an increase instruction or a decrease instruction is accepted, but the present invention is not limited to such a form as long as an instruction regarding the number of divisions is accepted from the user. For example, an input of the number of divisions may be received directly from the user. Alternatively, an input of the number of divisions may be received from the user before the separation position setting process is executed. In this case, the parameter is changed until the accepted division number (or a value close to the number) is reached, and the delimiter position setting process is executed. By doing so, the user can efficiently obtain a desired number of electronic documents.

  In addition, after the above-described separation position setting process is executed, the second separation position setting process may be executed using a conventional method. In the break position setting process in the present embodiment, the break position is set based on the style characteristics of the row area. Therefore, when a state where the amount of change in page feature is zero continues for a plurality of pages, no separation position is set between these pages. In such a case, since many pages are handled as one document, inconvenience may occur. Therefore, for example, the image analysis unit 16 may execute the second separation position setting process when a predetermined number of pages having the same document ID continue. Alternatively, the second delimiter position setting process may be executed when the change amount of the page feature is 0 continuously for a predetermined number of pages before assigning the document ID. As the second delimiter position setting process, for example, a process based on a layout or a specific character string (for example, a character string representing a page number) can be employed.

  The file name of each electronic document 400 is a combination of a fixed character string and a document ID, but the file name may be determined from the contents of each document. For example, a character string corresponding to the title of each divided document may be used as the file name. In that case, the image analysis unit 16 extracts the character string region having the maximum height from each document image in which the break position is set. Then, character recognition processing is performed on the area, and the result of the recognition processing is determined as a file name. By including the determined file name in the management information, the transmission processing unit 17 can give the file name of each electronic document 400 in the same manner as described above. By performing such processing, more useful file names can be assigned.

  In the above flowchart, once the electronic document is generated, an instruction to increase or decrease from the user is accepted. However, the present invention is not limited to such a procedure. For example, the display control unit 25 may first execute display processing based on the document ID, and the electronic document generation unit 15 may generate an electronic document when an OK instruction is input by the instruction reception unit 26. Good.

  In addition, the MFP 1 generates a plurality of electronic documents based on the set delimiter positions. However, the MFP 1 generates a single electronic document by inserting a specific page (for example, a blank page) at the delimiter positions. Also good.

  An example of the data structure of each electronic document 400 is shown in FIG. Referring to FIG. 22, each electronic document 400 includes a header part 402, a document image part 404, and a footer part 408. The header part 402 and the footer part 408 store information about the attributes of the electronic document 400, such as creation date / time / creator / copyright information. A document image corresponding to each page is stored in the document image unit 406. The document image may be stored in a compressed state as described above.

(Printing process)
The procedure for setting the delimiter position in the process of generating the electronic document from the document image has been described above. However, the delimiter position is also set in the process for executing the print process for the document image in the same manner as described above.

  FIG. 23 is a functional block diagram showing a functional configuration when MFP 1 according to the embodiment of the present invention executes print processing. FIG. 23 shows functions when the MFP 1 executes print processing. The same functions as those in FIG. 5 are denoted by the same reference numerals. Therefore, those descriptions will not be repeated.

  Referring to FIG. 23, an image processing unit 19 is added to the functional configuration of MFP 1 in place of electronic document generation unit 15 and transmission processing unit 17 in FIG. In addition, the printing unit 106 is added to the functional configuration of the MFP 1 instead of the transmission unit 18 and the storage unit 112. The image processing unit 19 converts the document image output from the image buffer unit 13 into an image suitable for a printing operation in the printing unit 106 according to a user operation. Typically, a document image defined by an RGB display system is converted into image data of a CMYK display system suitable for color printing. At this time, color adjustment according to the characteristics of the print unit 106 may be performed. The print unit 106 forms a print image from the CMYK image from the image processing unit 19 and performs a printing process on a paper medium or the like.

  When the MFP 1 executes the printing process, the electronic document generation process (step S18) in the flowchart of FIG. 6 is deleted. Further, image processing is executed in place of the destination setting screen display (step S24) and transmission processing (step S28). In the image processing, the image processing unit 19 performs the conversion processing as described above, and outputs the image data to the printing unit 106 by changing the sorting method for each document ID. As a result, the paper medium sorted by the printing unit 106 is output.

  Note that the print unit 106 does not necessarily have a sort function. In this case, for example, the image processing unit 19 may insert a specific page such as a blank page at the change of the document ID.

<Modification>
In the above-described embodiment, the case where the process according to the present invention is executed by the MFP 1 has been described. However, the above process may be executed by a computer having an image reading function for reading the document 300. In this case, it is also possible to provide a program for executing the processing function shown in FIG. 5 or FIG. 23 for causing the computer to function as a document processing apparatus. Such a program can be stored in an optical medium such as a CD-ROM (Compact Disk-Read Only Memory) or a computer-readable recording medium such as a memory card and provided as a program product. Alternatively, the program can be provided by being stored in a storage medium such as a hard disk built in the computer. A program can also be provided by downloading via a network.

  Further, the program in the storage unit 112 can be updated by reading, for example, an optical medium in which the program is recorded with a driving device (not shown) of the MFP 1.

  Alternatively, the image reading function may be realized by another device or computer, and the generated document image may be received and the separation position may be set according to the above processing.

  The program according to the present invention is a program module that is provided as a part of a computer operating system (OS) and calls necessary modules in a predetermined arrangement at a predetermined timing to execute processing. Also good. In that case, the program itself does not include the module, and the process is executed in cooperation with the OS. A program that does not include such a module can also be included in the program according to the present invention.

  The program according to the present invention may be provided by being incorporated in a part of another program. Even in this case, the program itself does not include the module included in the other program, and the process is executed in cooperation with the other program. Such a program incorporated in another program can also be included in the program according to the present invention.

  The provided program product is installed in a program storage unit such as a hard disk and executed. Note that the program product includes the program itself and a storage medium in which the program is stored.

  The embodiment disclosed this time should be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the description above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

1 is a schematic configuration diagram of a system including a document processing device according to an embodiment of the present invention. FIG. 3 is a block diagram showing a schematic hardware configuration in an MFP according to an embodiment of the present invention. It is a diagram showing an example of an appearance of an operation panel unit of the MFP according to the embodiment of the present invention. It is a schematic diagram which shows the schematic hardware constitutions of the personal computer according to embodiment of this invention. 3 is a functional block diagram showing a functional configuration of the MFP when the MFP according to the embodiment of the present invention generates an electronic document. FIG. It is a flowchart which shows the electronic document production | generation process in embodiment of this invention. It is a flowchart which shows the division | segmentation position setting process in embodiment of this invention. It is a flowchart which shows the parameter change process in embodiment of this invention. (A)-(c) is a figure for demonstrating the row area | region extraction process in this Embodiment. It is a figure which shows the example of the line area | region extracted with respect to the document containing several pages. It is a figure which shows an example of the list | wrist of the line area | region contained in a document image. It is a figure which shows an example of a style feature list. It is a figure which shows an example of the calculation result table for every style feature. It is a figure which shows an example of a main area | region characteristic table. It is a figure which shows the main area | region characteristic table after the correction process in embodiment of this invention was performed. It is a figure which shows an example of the data structure of the management information memorize | stored in an image buffer part. It is a figure which shows the example by which three documents were produced | generated about the document image of FIG. (A)-(c) is a figure which shows an example of a document confirmation screen. It is a figure which shows the main area | region characteristic table when the division | segmentation position setting process is performed again after the increase instruction | indication is input. It is a figure which shows the main area | region characteristic table when the delimiter position setting process is performed again after the reduction instruction | indication is input. It is a figure which shows an example of a transmission destination setting screen. It is a figure which shows the data structure example of each electronic document. 3 is a functional block diagram showing a functional configuration of the MFP when the MFP according to the embodiment of the present invention executes a printing process. FIG.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 MFP, PC1, PC2, PC3 Personal computer, SRV server apparatus, 12 receiving part, 13 image buffer part, 15 electronic document production | generation part, 16 image analysis part, 17 transmission processing part, 18 transmission part, 19 image processing part, 21 Line area extraction unit, 22 style feature detection unit, 23 main determination unit, 24 position setting unit, 25 display control unit, 26 instruction reception unit, 27 parameter change unit, 100 control unit, 102 memory unit, 104 image reading unit, 106 Print unit, 108 communication interface unit, 110 operation panel unit, 112 storage unit, 201 CPU, 203 internal bus, 205 display unit, 207 communication interface unit, 209 input unit, 211 hard disk unit, 213 memory unit, 215 CD-ROM drive 215a CD- OM, 217 FDD drive, 217a flexible disk, 300 document, 310 image data, 400 an electronic document.

Claims (13)

First storage means for storing a document image;
Extraction means for extracting a predetermined type of document area from the document image stored in the first storage means;
Detecting means for detecting a plurality of region attributes based on each of a plurality of predetermined attribute types for each document region, and detecting a style feature representing a combination pattern of the region attributes;
Classification means for classifying the detected plurality of style features for each pattern, and determining one or more main style features for the document image based on the appearance frequency of the classified patterns;
Detecting, for each page, one of a plurality of the main style features, and setting a separation position of the document image based on a change amount of the main style features between pages. A document processing apparatus comprising setting means. The determination means includes
For each style feature, a frequency calculating means for calculating the number of pages in which the style feature appears as the appearance frequency;
The document processing apparatus according to claim 1, further comprising: a unit that determines a style feature whose calculated number of pages is a predetermined value or more as the main style feature. The setting means includes
Means for determining the primary style features present on each page as page features of the page;
For each page, an amount calculation means for calculating the amount of change of the page feature of the page from the page feature of the previous page as the amount of change;
The document processing apparatus according to claim 2, further comprising means for setting a break position between the pages when the calculated amount of change is equal to or greater than a predetermined value. The setting means includes
If the same page feature is detected in the first and third pages other than the second page among consecutive first, second and third pages, the second page is also displayed. The document processing apparatus according to claim 3, further comprising correction means for correcting that the same page feature is detected.   5. The document processing apparatus according to claim 1, further comprising an output unit configured to divide and output the document image based on a separation position set by the setting unit. Display control means for generating a signal for displaying an index image of the first page in a plurality of divided document images when the document image is divided based on the separation position;
The document processing apparatus according to claim 1, further comprising display means for performing output in accordance with a signal from the display control means.   The document processing apparatus according to claim 1, further comprising an instruction receiving unit configured to receive an instruction regarding the number of document image divisions by the setting unit from a user. A changing means for changing a predetermined parameter for setting a delimiter position by the setting means in accordance with the received instruction;
The document processing apparatus according to claim 7, further comprising an execution instructing unit for instructing execution of processing by the setting unit again after the change by the changing unit.   9. The document processing apparatus according to claim 1, further comprising: a second setting unit configured to set a break position of the document image based on a layout or a predetermined character string.   The plurality of predetermined attribute types include position, size, color in upper area, number of partial areas, position, height, color, distance between adjacent partial areas, character size, character modification, character color The document processing apparatus according to claim 1, wherein the document processing apparatus includes at least two of background color and font type.   The document processing apparatus according to claim 1, wherein the predetermined type of document area corresponds to any one of a stage, a line, a character string, and a character. A document processing method executed in a document processing apparatus including a storage unit for storing a document image and an arithmetic processing unit,
The arithmetic processing unit extracting a document area of a predetermined type from the document image stored in the storage unit;
The arithmetic processing unit detects a plurality of region attributes based on each of a plurality of predetermined attribute types for each document region, and detects a style feature representing a combination pattern of the region attributes;
Classifying the detected plurality of style features for each pattern, and determining one or more main style features for the document image based on the appearance frequency of the classified pattern;
Detecting which of the plurality of main style features is present for each page, and setting a separation position of the document image based on a change amount of the main style features between pages; A document processing method comprising:   A document processing program for causing a computer to execute the document processing method according to claim 12.

Images