JP2008040834A - Image processor and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor and an image processing program which can efficiently retrieve document data that shows paper document in which ruled lines and characters are included. <P>SOLUTION: An image data acquisition means reads a paper document in which ruled lines and characters are included and acquires information included in the paper document as image data. An extraction means extracts characteristic information and character information that shows characteristics of the ruled lines from the image data acquired by the image data acquisition means. A discrimination information imparting means imparts discrimination information which discriminates characteristic information extracted by the extraction means. A recording means records document information including discrimination information granted by the discrimination information imparting means, characteristic information, and character information. An acquisition means acquires character string information and discrimination information to retrieve desired document information from a plurality of document information recorded by the recording means. A retrieval means retrieves document information having discrimination information coinciding with discrimination information acquired by the acquisition means from a plurality of recorded document information, and retrieves character string information from the retrieved document information. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an image processing apparatus and an image processing program.

Conventionally, a paper document mainly composed of table ruled lines such as a form is scanned in an accounting operation or the like, converted into a structured document such as XML, and then registered in a database. In many cases, the converted document is registered in a database as it is. As a technique for registering such a document in a database, Patent Document 1 discloses a document creation apparatus that registers a document on a recording medium with a document name.
Japanese Patent Laid-Open No. 3-40065

  However, in the case of a database centered on a limited document such as a form with a ruled line, the contents of keywords used when a user searches are similar (for example, “product name”, “unit price”, As a result, many documents are often hit, and it is difficult to efficiently search for a desired form.

  In addition to search using keywords, there is a mechanism such as index (title) search, but this alone often results in erroneous search for documents with titles with high similarity.

  In view of the above problems, an object of the present invention is to provide an image processing apparatus and an image processing program that can efficiently search document data indicating a paper document in which ruled lines and characters are described.

  In order to achieve the above object, an image processing apparatus according to claim 1 reads a paper document in which ruled lines and characters are described, and acquires image data acquisition means for acquiring information described in the paper document as image data; Extraction means for extracting feature information indicating the feature of the ruled line and character information indicating the character from the image data acquired by the data acquisition means, and identification information for identifying the feature information extracted by the extraction means ID information providing means for providing ID information, recording means for recording document information including identification information given by the ID information giving means, the feature information, and the character information, and a plurality of paper documents by the recording means Acquisition means for acquiring character string information for searching for desired document information and the identification information from the plurality of document information recorded as a result, and the recording means The document information having the identification information that matches the identification information acquired by the acquisition unit is searched from the plurality of document information recorded by the acquisition unit, and the character string information is searched from the character information included in the searched document information. Search means.

  The present invention further includes ruled line image data generating means for generating ruled line image data indicating a ruled line image as a ruled line image described in the paper document from the image data, as in the invention of claim 2. The recording means further records the ruled line image data generated by the ruled line image data generating means as information included in the document information in association with the identification information given to the image data. May be.

  The present invention further includes input means for inputting the character string information and the identification information by a user as in the invention of claim 3, wherein the acquisition means is a character input by the input means. You may make it acquire column information and identification information.

  The present invention further includes ruled line image display means for displaying a plurality of ruled line images indicated by the plurality of ruled line image data, as in the invention of claim 4, wherein the input means includes the ruled line image display means. From the displayed ruled line image, the user can specify a ruled line image corresponding to the document information to be searched, and the acquisition unit can acquire identification information corresponding to the ruled line image data indicating the specified ruled line image. good.

  The present invention is recorded by the search information recording means for recording the information included in the document information searched for the character string information by the search means and the search information recording means, as in the invention of claim 5. Display means for displaying information included in the document information.

  In order to achieve the above object, an image processing program according to claim 6 reads an image data acquisition step of reading a paper document in which ruled lines and characters are described, and acquiring information described in the paper document as image data; An extraction step for extracting feature information indicating the feature of the ruled line and character information indicating the character from the image data acquired by the data acquisition step, and identification information for identifying the feature information extracted by the extraction step An identification information providing step for assigning a document, a recording step for recording document information including the identification information given by the identification information giving step, the feature information, and the character information, and a plurality of paper documents by the recording step. Character string information for searching for desired document information from the plurality of document information recorded as a result, and the identification A document information having an identification information that matches the identification information acquired by the acquisition means from the plurality of document information recorded by the acquisition step, and the document information searched A search step of searching for the character string information from the character information of the computer.

  According to the present invention, it is possible to provide an image processing apparatus and an image processing program that can efficiently search document data indicating a paper document in which ruled lines and characters are described.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In this embodiment, the image processing apparatus of the present invention is applied to a combination of a personal computer and a scanner.

  First, the image processing apparatus will be described with reference to FIG. FIG. 1 shows a personal computer 10 and a scanner 34 connected via a LAN or USB.

  Among these, the scanner 34 reads a paper document in which ruled lines and characters are described, and acquires information described in the paper document as image data. The scanner 34 transmits the acquired image data to the personal computer 10.

  The personal computer 10 extracts feature information indicating the characteristics of the ruled lines and character information indicating the characters from the image data, and gives identification information for identifying the extracted feature information. Document information including feature information and the character information is recorded.

  Further, the personal computer 10 acquires character string information for searching for desired document information and the identification information from a plurality of recorded document information, and acquires the identification information acquired from the plurality of recorded document information. Document information having identification information that matches the information is retrieved, and character string information is retrieved from character information included in the retrieved document information.

  Details of the processing of the personal computer 10 described above will be described later. Next, the configuration of the personal computer 10 will be described with reference to FIG. The personal computer 10 includes a CPU (Central Processing Unit) 18, an HDD (Hard Disk Drive) 20, a RAM 22, a network I / F (interface) unit 24, a ROM 26, a display unit 28, an operation input unit 30, and the like. And a bus 32 for connecting the two.

  The CPU 18 governs the overall operation of the personal computer 10, and a flowchart showing a processing flow of the personal computer 10 described later is executed by the CPU 18. The HDD 20 is a non-volatile storage device that records each database, various programs, an OS, and the like. The RAM 22 is a volatile storage device in which the OS, programs, data, and the like are expanded.

  The network I / F unit 24 is for connecting to a network, and includes a NIC for connecting to a LAN, its driver, or a USB device. The ROM 26 is a non-volatile storage device that stores a boot program that operates when the personal computer 10 is activated. The display unit 28 displays various information to the user. The operation input unit 30 is used when a user inputs an operation instruction or various information of the personal computer 10. The bus 32 is used when information is exchanged between the above units.

  The HDD 20 described above stores an image processing program (to be described later) executed by the CPU 18 and data used by the program. This program is not necessarily a program recorded in the HDD 20. Specific examples of the recording medium other than the HDD 20 include a program recorded on a portable recording medium. In this case, the personal computer 10 is provided with a reading device for reading a portable recording medium, and the portable recording medium causes a change state of energy such as magnetism, light, electricity, etc. to the reading device and responds to it. The contents of the program description can be transmitted to the reading device in the form of a signal.

  Examples of portable recording media include magneto-optical disks, optical disks (including CDs and DVDs), magnetic disks, memories (including IC cards and memory cards), and the like.

  The above is the configuration of the image processing apparatus in this embodiment. Document information is recorded in the HDD 20 of the personal computer 10 as a document information database (hereinafter referred to as DB). This document information will be described with reference to FIG. The figure shows a data structure of document information corresponding to one image data. The structure of the document information includes a serial number, ID, feature information, thumbnail data, and character information as shown in FIG.

  The reference number is a unique value for identifying the document information, and is usually given in the registered order. The ID is a value for identifying feature information, and document information having the same feature information has the same ID.

  The feature information is information indicating the feature of the ruled line extracted from the image data acquired by the scanner 34. The thumbnail data is image data indicating an outline of ruled lines described in a paper document. The character information is information indicating characters extracted from the image data acquired by the scanner 34.

  The document information described above is provided in a number corresponding to the number of read image data.

  Hereinafter, the details of the above-described feature information, thumbnail data, and character information will be described in order. FIG. 4 is a diagram showing feature information. FIG. 5 is a diagram showing how feature information is extracted. FIG. 5A shows an example of ruled lines, and FIG. 5B shows projection distribution patterns in the vertical and horizontal directions of the ruled lines. Specifically, FIG. 5 (b) extracts a ruled line from the image data by extracting black dots, and displays a histogram indicating the number of extracted black dots for each vertical axis and horizontal axis in coordinates with the upper left as a vertex. It is shown in.

  Information on the points on the horizontal axis and the vertical axis (points indicated by arrows in FIG. 5B) where the number of black dots extracted in this way is equal to or greater than a predetermined threshold is shown in FIG. It is.

  In addition to using the above-described histogram, run lengths of peaks and valleys of the projection distribution may be used as the feature information. Alternatively, the image data itself may be used as feature information.

  Next, the thumbnail data will be described using the user interface (UI) shown in FIG. The UI shown in the figure is displayed on the display unit 28 and shows a screen on which character string information and the identification information are input by the user.

  This UI includes a keyword input field 52, radio buttons 56, and thumbnail images 54, as shown in FIG. These pieces of information are acquired by the DB described in FIG. 3 and reflected in the UI.

  The keyword input field 52 is a field for the user to input character string information. The thumbnail image 54 is an image indicated by the thumbnail data. As shown in the figure, the UI displays thumbnail data corresponding to the document information to be searched by displaying a plurality of thumbnail images indicated by the plurality of thumbnail data. , The radio button 56 is used to allow the user to specify.

  Note that the thumbnail data described above is created when image data is transmitted from the scanner 34. Further, it is possible to make it possible to input a document title, a term, a date, and the like in the UI, and to reflect the input information in the search processing.

  Next, character information will be described with reference to FIGS. These figures show a paper document and character information extracted from the paper document using image processing such as OCR processing. The character information extracted from the paper document shown in FIG. 7 corresponds to the character information shown in FIG. 8, and the character information extracted from the paper document shown in FIG. 9 corresponds to the character information shown in FIG. is doing.

  As shown in FIGS. 8 and 10, the character information is information described in XML, and the characters described in the paper document are extracted. Specifically, in the paper document shown in FIG. 7, the characters “Establishment of quotes made by Kou Soft Co., Ltd. TOOL Ver.1.0” and “2” are described. In FIG. 8 showing the character information extracted from this paper document, the tag “PRODUCT” indicates “Established Quote Form TOOL Ver.1.0”, and the tag “QUANTITY” indicates the number. “2” is shown.

  Further, in the paper document shown in FIG. 9, “Taro Yamada” and characters “110,000” are described as the unit price. In FIG. 10 showing the character information extracted from this paper document, “Taro Yamada” is indicated by the tag “WRITER”, and “110,000” which is the unit price is indicated by the tag “UNITOFPRICE”.

  As described above, character information is extracted from the paper document as an XML document. Note that, as shown in the XML document described above, in the extraction processing according to the present embodiment, advanced processing is performed for extracting to an appropriate tag in consideration of items described in the paper document. A process of simply extracting characters described in a paper document may be performed without performing such advanced processing. Further, the document is not limited to paper, but may be another recording medium such as a plastic on which characters and ruled lines are described.

  Next, processing executed by the CPU 18 of the personal computer 10 will be described. FIG. 11 is a flowchart showing a processing flow from reading a paper document to recording document information in the DB.

  First, in step 100, the CPU 18 instructs the scanner 34 to read a paper document in which ruled lines and characters are described, and to acquire information described in the estimate as image data. Next, in step 101, the CPU 18 determines whether or not image data has been acquired from the scanner 34. If acquired, the process proceeds to step 102.

  Next, the CPU 18 executes a feature information extraction process described later in step 102, and subsequently executes a character information extraction process described later in step 103.

  Thereafter, in step 104, the CPU 18 records document information (ID, feature information, character information, thumbnail data) together with the reference number in the DB.

  Next, the flow of the feature information extraction process will be described with reference to the flowchart shown in FIG. In step 200, the CPU 18 binarizes the image data, and in step 201, a ruled line is extracted. Next, in step 202, the CPU 18 generates thumbnail data.

  In step 203, the CPU 18 calculates vertical and horizontal projection distributions from the extracted ruled lines and extracts feature information. This feature information extraction processing is as described in FIG. When the feature information is extracted, the CPU 18 searches the feature information in the DB in step 204, and determines whether or not the feature information exists in step 205.

  If the CPU 18 makes a negative determination in step 205, since it is new feature information, a new ID is assigned in step 206. On the other hand, if the CPU 18 makes an affirmative determination in step 205, the feature information already exists in step 207 is assigned because the feature information already exists.

  In the feature information search process in step 204 described above, it is determined that the search is performed when the feature information to be registered matches the feature information recorded in the DB. However, in this process, even if the feature information is slightly different. The search may be determined. This is because when a paper document is read by a scanner, a slight error may occur even in the same paper document.

  The feature information, thumbnail data, and ID are obtained by the feature information extraction process described above.

  Next, the flow of the character information extraction process will be described with reference to the flowchart shown in FIG. In step 300, the CPU 18 recognizes characters in the image data by image processing such as OCR processing, extracts the recognized characters in step 301, and uses the characters extracted in step 302 to generate an XML document (FIG. 8, FIG. 10).

  Character information is obtained by the character information extraction process described above. Therefore, document information (ID, feature information, character information, thumbnail data) is obtained by this character information extraction process and the feature information extraction process.

  Next, the search process will be described. The flowchart shown in FIG. 14 shows the flow of search processing.

  First, in step 400, the CPU 18 displays a UI (see FIG. 6), and in step 401, waits for completion of input by the user. When the user completes the input, the CPU 18 acquires the search keyword and ID in step 402.

  Next, in step 403, the CPU 18 searches the DB for document information corresponding to the ID, and in step 404, determines whether there is document information corresponding to the ID. If the CPU 18 makes a negative determination in step 404, the process proceeds to step 409. If the CPU 18 makes an affirmative determination, in step 405, the keyword is further searched for in the document information.

  If the keyword does not exist in the document information as a result of the search, the process proceeds to step 408. If the keyword exists, in step 407, the CPU 18 stores the reference number of the document information for which the keyword is searched, for example, in the RAM 22.

  The next step 408 is a determination of whether or not all document information corresponding to the ID has been searched. If the CPU 18 makes a negative determination in step 408, the process of step 404 is executed again. On the other hand, if the CPU 18 makes an affirmative determination in step 408, the CPU 18 displays document information corresponding to the stored serial number in step 409. As the document information displayed here, all of the document information may be displayed, or a part of the document information (reference number or the like) may be displayed. At this time, if the reference number is not held, nothing has been searched, and in this case, the number of searches is displayed as 0.

  Here, the document information may be displayed on the display unit 28 or may be printed by connecting a printer. Alternatively, the retrieved document information may be distributed using electronic mail.

  As described above, in the present embodiment, an image data acquisition unit (step 101) that reads a paper document in which ruled lines and characters are described and acquires information described in the paper document as image data, and the image Extraction means (steps 102 and 103) for extracting feature information indicating the features of the ruled lines and character information indicating the characters from the image data acquired by the data acquisition means; and feature information extracted by the extraction means. Identification information adding means (steps 206 and 207) for giving identification information for identification, and recording means for recording the document information including the identification information given by the identification information giving means, the feature information, and the character information (Step 104) and the desired document information from the plurality of document information recorded corresponding to the plurality of paper documents by the recording means. It matches the identification information acquired by the acquisition means from the character string information for searching and the acquisition means (step 402) for acquiring the identification information and the plurality of document information recorded by the recording means. Searching means (step 403, step 405) for searching for document information having identification information and searching for the character string information from character information of the searched document information.

  The image data further includes ruled line image data generating means (step 202) for generating ruled line image data indicating a ruled line image which is a ruled line image described in the paper document, and the recording means includes the ruled line image data. The ruled line image data generated by the image data generating means is further recorded as information included in the document information in association with the identification information given to the image data.

  Further, the image processing apparatus further includes an input unit (step 401) for inputting the character string information and the identification information by a user, and the acquisition unit acquires the character string information and the identification information input by the input unit. .

  The image processing apparatus further includes ruled line image display means (step 400) for displaying a plurality of ruled line images indicated by the plurality of ruled line image data, wherein the input means searches from the ruled line image displayed by the ruled line image display means. The ruler image corresponding to the document information to be specified is specified by the user, and the acquisition unit acquires identification information corresponding to the ruled line image data indicating the specified ruled line image.

  Further, search information recording means (step 407) for recording information included in the document information searched for the character string information by the search means, and displaying information included in the document information recorded by the search information recording means. Display means (step 409).

  In this embodiment, an image data acquisition step (step 101) for reading a paper document in which ruled lines and characters are described and acquiring information described in the paper document as image data, and the image data acquisition step. An extraction step (steps 102 and 103) for extracting feature information indicating the feature of the ruled line and character information indicating the character from the acquired image data, and for identifying the feature information extracted by the extraction step An identification information adding step (steps 206 and 207) for assigning identification information, and a recording step (step 104) for recording the document information including the identification information given by the identification information giving step, the feature information, and the character information. And from the plurality of document information recorded corresponding to a plurality of paper documents by the recording step, The acquisition step (step 402) for acquiring the character string information for searching for desired document information and the identification information, and the acquisition means acquired from the plurality of document information recorded by the recording step. Document information having identification information that matches the identification information is searched, and a search step (step 403, step 405) for searching the character string information from the character information included in the searched document information is executed on the computer. Let

1 is an external view illustrating a configuration example of an image processing apparatus. It is a block diagram which shows the structural example of a personal computer. It is a figure which shows the data structure of document information. It is a figure which shows the characteristic information. It is a figure which shows a mode that feature information is extracted. It is a figure which shows a user interface. It is a figure which shows the paper document example (the 1). It is a figure which shows the character information example (the 1). It is a figure which shows the paper document example (the 2). It is a figure which shows the example of character information (the 2). It is a flowchart which shows the flow of a process from reading a paper document to recording document information in DB. It is a flowchart which shows the flow of a feature information extraction process. It is a flowchart which shows the flow of a character information extraction process. It is a flowchart which shows the flow of a search process.

Explanation of symbols

10 PC 18 CPU
20 HDD
22 RAM
34 Scanner

Claims (6)

Image data acquisition means for reading a paper document in which ruled lines and characters are described, and acquiring information described in the paper document as image data;
Extraction means for extracting feature information indicating the characteristics of the ruled lines and character information indicating the characters from the image data acquired by the image data acquisition means;
Identification information giving means for giving identification information for identifying the feature information extracted by the extraction means;
Recording means for recording document information including the identification information given by the identification information giving means, the feature information, and the character information;
Acquisition means for acquiring the character string information for searching for desired document information and the identification information from the plurality of document information recorded corresponding to the plurality of paper documents by the recording means;
Document information having identification information that matches the identification information acquired by the acquisition unit is searched from the plurality of document information recorded by the recording unit, and the character string is extracted from character information included in the searched document information. A search means for searching for information;
An image processing apparatus. The image data further comprises ruled line image data generating means for generating ruled line image data indicating a ruled line image which is a ruled line image described in the paper document,
The recording unit further records the ruled line image data generated by the ruled line image data generating unit as information included in the document information in association with the identification information given to the image data. The image processing apparatus described. The character string information and the identification information further include an input means for inputting by a user,
The image processing apparatus according to claim 2, wherein the acquisition unit acquires character string information and identification information input by the input unit. A ruled line image display means for displaying a plurality of ruled line images indicated by the plurality of ruled line image data;
The input unit causes the user to specify a ruled line image corresponding to the document information to be searched from the ruled line image displayed by the ruled line image display unit,
The image processing apparatus according to claim 3, wherein the acquisition unit acquires identification information corresponding to ruled line image data indicating a specified ruled line image. Search information recording means for recording information included in the document information searched for the character string information by the search means;
Display means for displaying information included in the document information recorded by the search information recording means;
The image processing apparatus according to any one of claims 1 to 4, further comprising: An image data acquisition step of reading a paper document in which ruled lines and characters are described, and acquiring information described in the paper document as image data;
An extraction step for extracting feature information indicating the feature of the ruled line and character information indicating the character from the image data acquired by the image data acquisition step;
An identification information providing step for providing identification information for identifying the feature information extracted by the extraction step;
A recording step for recording the document information including the identification information given by the identification information giving step, the feature information, and the character information;
An acquisition step of acquiring character string information for searching for desired document information and the identification information from a plurality of the document information recorded corresponding to a plurality of paper documents by the recording step;
Document information having identification information that matches the identification information acquired by the acquisition unit is searched from the plurality of document information recorded by the recording step, and the character string is extracted from character information included in the searched document information. A search step for searching for information;
An image processing program for causing a computer to execute a process including: