JP2010176267A - Information processor and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To create a business form whose recognition processing by a computer is made possible by changing the scale or position of a recognition region without imposing any burden on a business form creator, and to recognize a business form in which the scale or position of the recognition region has been changed. <P>SOLUTION: An information processor for executing the recognition processing of entry information entered in the entry column of an original, the entry column having an identification code for obtaining basic size information showing the basic size of the entry column, includes: an input means for inputting the image data of an original; an obtaining means for obtaining the basic size information on the basis of the identification code included in the input image data; a size change means for changing the size of a recognition object region by using the obtained basic size information; and a recognition means for executing the recognition processing to the recognition object region whose size has been changed. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an information processing apparatus and a program, and more particularly to a technique that is preferably applied to design and creation of a form and recognition processing of entry contents by a form writer.

  Conventionally, a method for designing a computer-readable form using dedicated form design software is known. For example, designating a form from scratch by specifying where to recognize characters and timing marks on the image of an existing form, or pasting a rectangle for entering characters and processing for that rectangle on the screen Etc. are known. In creating a form using such dedicated form design software, the form design is a complicated task, which increases the work load of the form creator, and the form design takes time to deviate from the actual form. There was a problem such as.

  The above problem also affects the recognition process for the information entered in the form. Normally, when the recognition process is performed, a form creator needs to set each form or each rectangle (recognition area). Specifically, the position and size of the recognition area, the processing method (which area is to be processed by which OCR (Optical Character Reader), etc.), the output of the recognition result (how to output the selected contents, etc.) For example, “1” is set to “male” and “2” is set to “female”)). As described above, according to the conventional method, the setting work by the form creator is complicated and the work burden on the creator is large, and when there is a deviation from the actual form, accurate and rapid form recognition processing is difficult.

  For example, Patent Document 1 discloses a table data input / output device intended to increase the speed and accuracy of table reading. This table data input / output device includes a bar code adding means for adding a bar code to the table data for designating the type of the table and the row direction and column direction position of each data in the table, and a bar code for reading the bar code A reader and classification / position recognition means for notifying the position in the table type, row direction and column direction from the read barcode are provided.

  For example, Patent Document 2 discloses an entry information extraction method for accurately extracting entry information such as characters and symbols from an image of a completed form input by an image scanner or the like. In this entry information extraction method, in addition to the completed form image, an unfilled form image (form image before filling) is prepared separately, and both images are aligned to reduce the effect of noise and reduce the form's effect. Extract entry details flexibly.

  When creating a form that can be recognized by a computer, the size and position of the recognition area can be changed freely and with less burden on the form creator. It leads to productivity improvement in form creation. Then, it is desirable to allow the form creator to recognize the form created by changing the size and position of the recognition area as described above without setting for processing each time.

  The invention of Patent Document 1 uses a bar code to increase the speed and accuracy of reading a table. For example, when the size or position of a table is changed, a bar that specifies the changed position each time is changed. It is necessary to add a code, and it is not possible to reduce the burden on the form creator and increase the flexibility of form creation. Further, although the invention of Patent Document 2 accurately extracts form entry information, a form creator sets a form created by changing the size and position of a recognition area for each process. It is not intended to be able to recognize without doing.

  Therefore, the present invention can create a form that can be recognized by a computer by changing the size and position of the recognition area without imposing a burden on the form creator, and the size and position of the recognition area can be changed. The purpose is to be able to recognize the generated form.

  In order to achieve the above object, the present invention provides an information processing apparatus for executing recognition processing of entry information entered in an entry column of a manuscript, wherein the entry column includes basic size information indicating a basic size of the entry column. An input unit that inputs image data of a document, an acquisition unit that acquires basic size information based on an identification code included in the input image data, and An information processing apparatus comprising size changing means for changing the size of a recognition target area using basic size information, and recognition means for executing recognition processing on the recognition target area whose size has been changed.

  The present invention also provides the above-described form recognition apparatus having ratio changing means for changing the identification code included in the input image data to a ratio at which the code necessary for obtaining the basic size information can be read. May be. Further, the ratio changing means may obtain a ratio of the thicknesses of the ruled lines constituting the entry column having the identification code, and change the ratio of the identification codes using the ruled line ratio.

  As another aspect, the present invention provides an information processing apparatus for creating a manuscript used for recognition processing of entry information entered in an entry column, and acquires basic size information indicating the entry column and the basic size of the entry column. An information processing apparatus comprising: an acquisition unit that acquires image data including an identification code for performing from a storage unit; and a generation unit that generates document data using the acquired image data.

  The present invention may also include an editing unit that changes the size of image data or additionally inputs character data in the form creation device.

  As another aspect, the present invention is a program for executing recognition processing of entry information entered in an entry column of a manuscript, and the entry column acquires basic size information indicating the basic size of the entry column. An acquisition function for acquiring basic size information on the basis of the identification code included in the input image data when the image data of the document is input, and the acquired basic This is a program for executing a size changing function for changing the size of a recognition target area using size information and a recognition function for executing a recognition process on the recognition target area whose size has been changed.

  In the above program, the computer causes the computer to execute a ratio changing function for changing the identification code included in the input image data to a ratio capable of reading the code necessary for obtaining the basic size information. There may be. Further, the ratio changing function may obtain the ratio of the thickness of the ruled lines constituting the entry field having the identification code, and change the ratio of the identification codes using the ruled line ratio.

  As another aspect, the present invention is a program for creating a manuscript used for recognition processing of entry information entered in an entry field, wherein the basic size indicating the entry field and the basic size of the entry field is displayed on a computer. A program for executing an acquisition function for acquiring image data including an identification code for acquiring information from a storage unit and a generation function for generating document data using the acquired image data.

  Further, in the above program, the present invention may cause the computer to execute an editing function for changing the size of image data or additionally inputting character data.

  According to the present invention, a form that can be recognized by a computer by changing the size and position of a recognition area without imposing a burden on the form creator is created, and the size and position of the recognition area are changed. Can be recognized.

It is the figure which showed the structure of the information processing apparatus to which this invention is applied. It is the figure which showed the structure of the information processing apparatus to which this invention is applied. It is a figure for demonstrating the operation | movement in the hardware constitutions of the client PC which concerns on embodiment of this invention, and the system containing this client PC. It is the flowchart which showed the flow of the form creation process in embodiment of this invention. It is the flowchart which showed the flow of the form recognition process in embodiment of this invention. It is the figure which showed the example of the parts data in embodiment of this invention. It is the figure which showed the example of the parts data in embodiment of this invention.

  FIG. 1 is a functional block diagram showing a configuration of an information processing apparatus to which the present invention is applied. The information processing apparatus 10 is a device that executes recognition processing, and includes an input unit 11, a ratio change unit 12, an acquisition unit 13, a size change unit 14, and a recognition unit 15. The input unit 11 inputs image data of a document used for recognition processing. The original entry field used for the recognition process includes an identification code for acquiring basic size information indicating the basic size of the entry area. Further, the image data in the entry column including the identification code is data (part data) that has been made into parts in a format that can be edited by word processing software, image editing software, or the like. The ratio changing unit 12 changes the identification code in the image data input by the input unit 11 to a code-readable ratio as necessary. The acquisition unit 13 acquires the basic size information by reading the identification code in the image data input by the input unit 11 or the identification code whose ratio has been changed by the ratio changing unit 12. The size changing unit 14 changes the size of the recognition target area using the basic size information acquired by the acquiring unit 13. The recognition unit 15 executes a recognition process on the recognition target area whose size has been changed by the size changing unit 14.

  FIG. 2 is a functional block diagram showing the configuration of the information processing apparatus to which the present invention is applied. The information processing apparatus 20 is an apparatus that creates a document such as a form used for recognition processing, and includes an acquisition unit 21, a creation unit 22, and an editing unit 23. The acquisition unit 21 acquires image data (part data) including an entry field and an identification code on the network or from the storage unit 40 of the own device. The part data is the same as that described in the form recognition device 10. The creation unit 22 generates document data using the image data acquired by the acquisition unit 21. The editing means 23 performs editing such as changing the size of the image data and adding input of text data.

  In the present invention, functions frequently used in a form are prepared as parts in one functional unit, and the parts are provided as image data in a format that can be used by word processing software or the like. Therefore, in the form creation process, the user can easily create a form simply by pasting a single part or a plurality of parts to a tool such as word processing software. In addition, the user can add information to a part within a predetermined range, or change the position and size. Each part includes a QR code or the like, and the QR code or the like is provided with a link to part design information and processing information. For this reason, in the form recognition process, when the form is read by the computer, the form design information and the processing information are accessed by following the link, and the form recognition process can be quickly performed using these pieces of information.

  In this way, the user does not design directly using dedicated form design software, but creates the form by pasting the parts together on word processing software, etc., so the form can be easily created for the user. , It can reduce the shift due to human hands. In addition, since the identification code for acquiring the design information and the processing information is given to the part, the entry information recognition process can be performed quickly and accurately without the user setting each time when recognizing the form.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. The embodiments described below are preferred embodiments of the present invention, and thus various technically preferable limitations are given. However, the scope of the present invention is particularly limited in the following description. Unless otherwise stated, the present invention is not limited to these embodiments.

  As an embodiment of the present invention, an information processing apparatus (client PC) that executes recognition processing and creates a form used for recognition processing will be described. FIG. 3 is a diagram for explaining a hardware configuration of the client PC according to the present embodiment and an operation in a system including the client PC.

  As shown in FIG. 3A, the client PC 100 of this embodiment includes a CPU 110, a ROM 120, a RAM 130, an HDD controller 140, an HDD 141, an external I / F 150, an input / output controller 160, a mouse 161, a KB (keyboard) 162, and a DSP. A (display) 163 is provided, and each device is connected to an internal bus. The ROM 120 stores a program for executing processing specific to the present embodiment, and the CPU 110 reads the program and performs processing specific to the present embodiment. That is, the CPU 110 reads each program in the ROM 120 to configure each means (ratio changing means 12, obtaining means 13, size changing means 14, and recognizing means 15) shown in FIG. The input unit 11 corresponds to an external I / F. Further, the CPU 110 reads the program in the ROM 120 to configure each unit (acquisition unit 21, generation unit 22, and editing unit 23) illustrated in FIG. 2 on the main memory.

  The operation in the system including the client PC will be described with reference to FIG. The client PC 100 is connected to an image reading device 400 such as a scanner and an image output device 300 such as a printer, and acquires data from the server 220 on the network and the storage area 210 of the own device. As described above, the client PC 100 performs a form recognition process by each means (input means 11, ratio change means 12, acquisition means 13, size change means 14, and recognition means 15) configured on the CPU 110. Similarly, a form creation process is performed by each means (acquiring means 21, generating means 22, editing means 13) configured on the CPU 110.

  An outline of the form creation process and the form recognition process in this embodiment will be described. First, in creating a form, the client PC 100 acquires the part data 1 from the storage area 210 of the own device or the server 220 on the network by the acquisition unit 21 ((1)). Then, the generation unit 22 generates form data by pasting the acquired part data 1 on word processor software or image editing software ((2)). At the stage of form data generation, the editing unit 23 edits the data as appropriate. Then, the client PC 100 sends the form data 2 to the image output device 300, and the image output device 300 outputs the image on a recording sheet or the like to create the form 3 ((3)). The form filler 500 fills in a blank form ((4)).

  Next, when recognizing the form, the image reading device 400 reads the completed form 4, acquires the completed form data 5 (image data of the completed form), and sends it to the client PC 100 ((5)). The client PC 100 inputs the completed form data 5 from the image reading device 400 by the input unit 11, reads the identification code in the completed form data 5 by the acquisition unit 13, and automatically acquires the processing information 6 necessary for the recognition process. Obtained from the storage area 210 of the device or the server 220 on the network ((6)). When reading the identification code, the ratio changing unit 12 changes the ratio of the identification code to a readable ratio as necessary. Then, the size changing means 14 uses the processing information 6 to change the size of the entry field (recognition target area) to a size that can be recognized, and the recognition means 15 uses the entry information in the entry field whose size has been changed. Then, recognition processing is performed ((7)).

  The form creation process and form recognition process in the present embodiment will be described in more detail. First, the form creation process will be described. FIG. 4 is a flowchart showing the flow of the form creation process in the present embodiment. The acquisition unit 21 of the client PC 100 loads part data from the local storage area 210 or the server 220 (step S101). Then, the part data is pasted on word processor software or image editing software (step S102). When pasting part data, the editing means 23 changes the size and the pasting position. Further, when part data is pasted (step S103 / YES), the above is repeated (step S101, step S102). When the design of the form is finished (step S103 / NO), the generation unit 22 finishes the pasting of the part data, and creates the form data by pasting the part data. Then, the generated form data is output to a recording sheet or the like (step S104).

  The part data is, for example, data as shown in FIG. 6 or FIG. 7 and is image data including a bitmap. The part data is a rectangle that is a target area for recognition processing, and is attached to the top (left end or upper left part) of the rectangle The QR code and the entry area (including previously entered characters and images) of the form writer in the rectangle are formed as a single package. In the QR code, the storage location of the part design information and processing information file is held as link information. If the capacity of the QR code permits, the file itself can be held instead of the file link information. Of course, a bar code can be used as the identification code, but in this case, the size becomes larger than the QR code. For part data, the pasting position can be freely changed, and the vertical and horizontal sizes can be freely changed. Further, as shown in FIG. 6, it is possible to add text data by inputting characters not only on the outside of the part data but also on the image data (region inside the rectangle).

  Next, the form recognition process will be described. FIG. 5 is a flowchart showing the flow of the form recognition process in the present embodiment. The client PC 100 acquires completed form data from the image reading device 400 by the input unit 11 (step S201). Next, the client PC 100 detects all rectangular image data from the completed form data (step S202). The following processing is repeated until there is no unprocessed rectangular image data (step S203 / YES).

  First, the client PC 100 determines whether the detected rectangular image data is part data (step S204). For example, whether or not the rectangular image data is part data may be determined based on the shape and size of white dots provided at the four corners of the rectangle (see FIG. 6A). Part data can be determined by various other methods. If the rectangular data is part data, the form recognition function 110 searches for a QR code attached to the rectangular image data (step S205). The search for the QR code is performed by scanning the mask pattern of the code in the area within the rectangle (pattern matching).

  Next, the ratio changing unit 12 determines whether or not the searched QR code is a readable ratio (step S206). For example, whether or not the QR code is a readable ratio refers to the ratio of rectangular ruled lines surrounding the QR code. That is, the vertical / horizontal ratio of the QR code when the thickness of the vertical ruled line and the thickness of the horizontal ruled line are the same is determined as a readable ratio. It is possible to determine whether the QR code ratio can be read by various other methods. If the retrieved QR code is not a readable ratio (step S206 / NO), the ratio changing unit 12 changes the ratio of the QR code to a readable ratio (step S207). Then, the acquisition unit 13 acquires the processing information by reading the QR code after the ratio change (step S208). If the QR code ratio is readable (step S206 / YES), the acquisition unit 13 reads the QR code as it is to acquire processing information (step S208).

  The processing information includes the position (coordinate value), size (vertical width and horizontal width), the processing method (information such as which OCR is to be processed), and the output result of the recognition result. (Information on how to output the entry contents) and the like. As described above, the QR code holds the link information of the file storage destination of the processing information, but it can be configured to hold the file itself if the data capacity permits.

  Subsequently, the size changing unit 14 extracts position information and size information from the acquired processing information, and determines whether the rectangle of the part data is a position and a size that can be recognized (step S209). If the position and size are not recognizable (step S209 / NO), the size changing unit 14 changes the size of the rectangular data based on the position and size of the processing information and adjusts the position of the rectangular data (step S210). . Then, the recognizing unit 15 performs a process of recognizing the image data represented as the entry content in the rectangle (step S211). If the rectangle has a position and size that can be recognized (step S209 / YES), the recognizing means 15 performs the process of recognizing the content as it is without adjusting the size or position (step S211).

  The above-described embodiment is a preferred embodiment of the present invention, and the scope of the present invention is not limited to the above-described embodiment alone, and various modifications are made without departing from the gist of the present invention. Implementation is possible.

  That is, the program executed on the client PC in the present embodiment includes the above-described units (ratio changing unit 12, acquiring unit 13, size changing unit 14, recognizing unit 15, acquiring unit 21, generating unit 22, editing unit). 23), and a specific means is realized by using actual hardware. That is, when the computer (CPU) reads a program from a predetermined recording medium and executes it, the above-mentioned means are loaded onto the main storage device and generated.

  The program executed on the client PC in the present embodiment may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Further, the program may be provided or distributed via a network such as the Internet.

  The program is a file in an installable or executable format, such as a floppy (registered trademark) disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD-R, DVD, nonvolatile memory card, or the like. It may be configured to be provided by being recorded on a computer-readable recording medium. Further, the program may be provided by being incorporated in advance in a ROM or the like.

  In this case, the program code itself read from the recording medium or loaded and executed through the communication line realizes the functions of the above-described embodiments. And the recording medium which recorded the program code comprises this invention.

DESCRIPTION OF SYMBOLS 10, 20 Information processing apparatus 11 Input means 12 Ratio change means 13 Acquisition means 14 Size change means 15 Recognition means 21 Acquisition means 22 Generation means 23 Editing means 40 Storage means 100 Client PC
110 CPU
120 ROM
130 RAM
140 HDD controller 141 HDD
150 External I / F
160 I / O controller 161 Mouse 162 KB
163 DSP
210 Client PC Storage Area 220 Server 300 Image Output Device 400 Image Reading Device 500 Form Filler

JP-A-5-342239 Japanese Patent No. 3614252

Claims (10)

An information processing apparatus for performing recognition processing of entry information entered in an entry column of a manuscript,
The entry field has an identification code for obtaining basic size information indicating the basic size of the entry field,
Input means for inputting image data of the original;
Obtaining means for obtaining the basic size information based on the identification code included in the input image data;
A size changing means for changing the size of the recognition target area using the acquired basic size information;
Recognition means for performing recognition processing on the recognition target area whose size has been changed;
An information processing apparatus comprising:   2. The information processing according to claim 1, further comprising: a ratio changing unit that changes the identification code included in the input image data to a ratio that enables reading of the code necessary for obtaining the basic size information. apparatus.   3. The ratio change unit obtains a ratio of thicknesses of ruled lines constituting the entry field having the identification code, and changes the ratio of the identification codes using the ruled line ratio. Information processing device. An information processing apparatus for creating a manuscript used for recognition processing of entry information entered in an entry field,
Acquisition means for acquiring image data including an identification code for acquiring the entry field and basic size information indicating the basic size of the entry field;
Generating means for generating document data using the acquired image data;
An information processing apparatus comprising:   The information processing apparatus according to claim 4, further comprising an editing unit that changes a size of the image data and additionally inputs character data. A program for executing recognition processing of information entered in the entry column of a manuscript,
The entry field has an identification code for acquiring basic size information indicating the basic size of the entry field, and when image data of the original is input,
On the computer,
An acquisition function for acquiring the basic size information based on the identification code included in the input image data;
A size changing function for changing the size of the recognition target area using the acquired basic size information;
A recognition function for performing recognition processing on the recognition target area whose size has been changed;
A program characterized by having executed.   7. The computer according to claim 6, wherein the computer executes a ratio changing function for changing the identification code included in the input image data to a ratio at which the code necessary for obtaining the basic size information can be read. Program.   8. The ratio changing function obtains a ratio of thicknesses of ruled lines constituting the entry column having the identification code, and changes the ratio of the identification codes using the ruled line ratio. Program. A program for creating a manuscript used for recognition processing of information entered in an entry field,
On the computer,
An acquisition function for acquiring from the storage means image data including an identification code for acquiring the entry size and basic size information indicating the basic size of the entry column;
A generation function for generating document data using the acquired image data;
A program characterized by having executed.   The program according to claim 9, causing the computer to execute an editing function for changing the size of the image data and additionally inputting character data.

Images