JP2005044256A - Slip field attribute preparation system, method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a system by which attribute information on an input field in an OCR (Optical Character Reader) slip is almost automatically prepared without undergoing complicate work. <P>SOLUTION: An original slip showing a contrast between an item name by character information and the field and its recording is prepared. A scanner 11 inputs the character information recorded on the original slip and an image corresponding to the field. An OCR device 1 displays a slip image corresponding to the original slip based on the inputted image on a display picture. Upon indicating a region corresponding to the field of the displayed slip image by using a pointing device, an OCR slip preparation/editing device 2 prepares the attribute information on the field item based on image data in the region or a neighborhood region. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a form field attribute creation apparatus and method, and a program, and more specifically, automatically creates attribute information of each field constituting a form based on image data in the field area or a predetermined area nearby. The present invention relates to a form field creation device and method, and a program.

  2. Description of the Related Art Conventionally, a personal computer that recognizes character information entered on a form by using an optical character reader (hereinafter referred to as an OCR device) and executes various data processing using the recognition result. A small-scale information processing system is provided as the core. In this type of system, when the OCR device reads character information such as numbers entered in the field for each item provided in advance on the form, the system side pre-determines the form size and form on the form. It is necessary to recognize the position and size of the input field, and to define the data type (type) and the number of characters to be entered in this input field, that is, to create a form form definition body. .

However, since the data input when creating this form form definition was performed by the operator's keyboard operation, when there are a large number of input fields, the time required for the input work becomes long and input mistakes are likely to occur. Therefore, when the user indicates the location where the input field is displayed on the display screen that displays the image data captured from the OCR input form using a pointing device such as a mouse, Some can automatically create the position, size, and shape of the input field based on the data indicating the location (see, for example, Patent Document 1).
JP 9-34989 A

  However, the position, size, and shape of the field can be calculated from data indicating the location on the display screen specified by the pointing device, but other types of information, for example, the predetermined type required for the form form definition information The data format to be entered in the input field and the data of the maximum number of input digits, which are the information of, are still set in the input field setting dialog by the operator's keyboard operation. Therefore, the keyboard operation by the operator is still essential, and an input error has occurred in creating the form form definition body.

  In view of the above circumstances, attribute information other than the position / size / shape of the input field is automatically set by information included in the input field area designated by the mouse or the like from the image information of the form or in the vicinity area. SUMMARY OF THE INVENTION It is a problem to be solved by the present invention to provide a new form form definition setting device and method, and a program that can be used.

A form field attribute creation system according to one aspect of the present invention includes an input unit that optically scans a previously created original form and inputs a form image composed of a field image and a character image; and the image input unit Recognizing means for recognizing fields and characters from the form image inputted by the user and outputting the field area and character data, and display means for displaying the form image in which the field area outputted by the character recognizing means is compared with the character data. Designating means for designating a field area from the form image displayed by the display means, and creating means for creating attribute information of the field based on item definition data corresponding to the field designated by the field designating means The above-described problems are solved.
By doing this, it is possible to automatically create the attribute information of the field only by designating the field of the form image corresponding to the displayed original form.

In the above-described form field attribute system according to the present invention, the creating means includes an area extracting means for extracting a predetermined image area in the upward or left direction of the field area specified by the specifying means, and the extraction Search means for searching for an item label name consisting of one or more characters in the image area cut out by the means, and acquisition means for acquiring item type information corresponding to the item label name searched by the search means And can be further provided.
By doing this, the item label name corresponding to the item to which the field of the form image corresponding to the displayed original form belongs is automatically searched, so the item type information set in the item label is used as the item type information. It can be automatically created as attribute information.

In the above-described form field attribute system according to the present invention, the creating means determines whether there is a character frame in the input field specified by the field specifying means based on the image data. When the determining means determines that there is a character frame, the determining means counts the number of character frames in the field as the number of characters that can be input in the field, and the determining means determines that there is no character frame. A calculation means for calculating the number of characters that can be input in the field based on a field size, a character font size, and a margin between characters defined in advance for each field. it can.
By doing so, it is possible to automatically obtain the maximum number of characters according to the presence or absence of a character frame in the field area of the form image corresponding to the displayed original form.

  Further, the form field attribute creation method according to another aspect of the present invention optically scans a previously created original form, inputs a form image composed of a field image and a character image, and inputs the input The field and character data are recognized from the generated form image, the field area and the character data are output, the form image is compared with the output field area and the character data, and the field is displayed from the displayed form image. The above-described problem is solved by designating an area and creating attribute information of the field based on the item definition data corresponding to the designated field.

According to this method, the same operation and effect as the above-described form field attribute creation system according to the present invention can be obtained.
Further, even if the program causes a computer to perform the process corresponding to the above-described form field attribute creation method according to the present invention, the form field attribute according to the present invention described above can be executed by causing the computer to read and execute the program. The same operation and effect as the creation system can be obtained, and the above-described problems can be solved.

  The present invention displays a form image corresponding to the original form on the display screen based on image data input from an original form in which item names and fields based on character information prepared in advance are recorded by comparison. When an area corresponding to the input field of the displayed form image is specified using a pointing device, the field attribute table is used on the screen to define the attributes related to the input field by using the area or nearby image data. can do.

  By doing so, there is an effect that the OCR form field attribute information can be created almost automatically without going through a complicated work process.

Embodiments of the present invention will be described below with reference to the drawings.
FIG. 1 is a block diagram showing an example of a configuration for implementing an OCR system according to the present invention.
This system comprises a normal OCR device 1 and an OCR form creation / editing device 2 related to the present invention. The OCR device 1 includes a scanner unit 11 that is an image input, an image memory 12, a field detection unit 13, a recognition processing unit 14, a result storage unit 16, a display screen generation unit 17, a display memory 18, and a display unit 19.

  The scanner unit 11 scans a field and character information recorded in an OCR form designed and created in advance, converts it into image data, and inputs it. The image memory 12 temporarily stores the input image data.

  The field detection unit 13 detects a field position to be read from the image memory 12 according to the form format information registered in the form information storage unit 15 and outputs the field image.

The recognition processing unit 14 performs character information recognition processing based on the output image data.
The result storage unit 16 temporarily stores the recognition result of the recognition processing unit 14.

Connected to the output side of the image memory 12 and the result storage unit 16 is a display screen generation unit 17 for generating form screen information of recognition results.
A display memory 18 for storing form screen information is connected to the output side of the display screen generating unit 17, and the form screen information stored in the display memory 18 is displayed on the display unit 19.

  The OCR form design / creation unit 2 has a function of generating OCR control information from an OCR form designed and created in advance, and includes an input unit 21, a form format generation unit 22 including form control information, an attribute information generation unit 23 and the digit reference table 24 are constituent elements.

The input unit 21 is an input device and includes a keyboard and a mouse.
The OCR form definition management unit 22 executes a process for defining a form based on input data from the input unit 21 and a process for registering form definition information in the form information storage unit 15 of the OCR device 1.

  As shown in FIG. 2, the form information storage unit 15 has a form definition information and a header part definition information as long as the form to be read is a slip form as shown in FIG. 3, for example. And detail part definition information are stored. In the header part definition information and the detail part definition information, attribute control information is stored for each input field item included in the header area and the detail area in the form.

  When the input field is designated by the input unit 21 from the form image input to the OCR device 1 and displayed on the display unit 19, the attribute information generation unit 23 is stored in the form information storage unit 15 corresponding to the designated field. The recognition processing unit 14 recognizes an image in a predetermined area searched by the field detection unit 13 according to the item definition information, and obtains the data type corresponding to the recognition result from the type reference table 24 and designates it. The maximum number of recognized characters is calculated from the number of character frames in the field.

  As shown in FIG. 4, the structure of the type reference table 24 is stored in advance in association with data types such as item names, numerical values, characters, and dates.

The OCR system is configured as described above.
Hereinafter, a procedure of processing performed in the OCR system will be described.

FIG. 5 is a flowchart showing the contents of the field attribute setting process performed in the OCR system.
For the sake of simplicity, in the following description, the form information storage unit 15 stores each input field (character input) of a form to be read, for example, an invoice (deduction) slip as shown in FIG. It is assumed that the type of data type and the maximum number of recognized characters are not set among the item definition elements corresponding to each possible field), and all other elements are set.

  First, in S101, an OCR original form in which fields and the like are designed and prepared in advance is prepared. For example, the recorded contents of the OCR original form as shown in FIG. The data is stored in the memory 12.

  In S <b> 102, the slip image data stored in the image memory 12 is output to the screen of the display unit 19. Thus, the image of the OCR original form (form outline of the form, field frame line for character input, etc.) is generated by the display screen generation unit 17 and displayed on the screen.

  In S103, the form information management unit 22 determines whether or not the input field of the OCR original form image displayed on the screen of the display unit 19 is designated by the mouse of the input unit 21. If the determination result is Yes, the process proceeds to S104. If No, the determination is repeated until the determination result is Yes.

  In S104, a data type type setting process is performed in which the data entered in the designated field indicates a numerical value, a character, a date, or the like. Details of this processing will be described later.

In S105, the attribute information generation unit 23 determines whether or not there is a character number frame in the input field to be processed in the process of S104 described above. If this determination result is Yes, the process proceeds to S106, and if No, the process proceeds to S107.
In S106, processing for calculating the maximum number of characters that can be entered in the input field from the number of frames is performed. Details of this processing will be described later.

  In S107, whether or not there is an item definition in which the data type and the number of characters are not yet set in the form definition body in the form definition storage unit 15 corresponding to the OCR original form read by the processing of S101 described above. Is determined by the form information management unit 22. If the determination result is Yes, that is, all the input field attributes have been set, and the field attribute setting process ends. On the other hand, if the determination result is No, the process returns to S103 and the above-described process is repeated.

The process so far is the field attribute setting process.
Next, details of the data type setting determination process performed in the process of S104 in the field attribute setting process shown in FIG. 5 will be described. This process is a data type information setting process for generating a data type based on character information included in another image area among attributes for a field when setting an OCR form definition.

FIG. 6 is a flowchart showing the processing contents of the data type information setting processing input in the input field.
First, in S201, the item definition in the form information storage unit 15 corresponding to the field specified in the process of S101 described above is specified. For example, as shown in FIG. 7, when a field surrounded by a thick chain line is designated by the mouse, the form information storage stored corresponding to the detail part of the delivery slip (deduction) slip shown in FIG. It is specified from the item definition of the form detail part in the part 15.

  In S202, the form information management unit 22 acquires the search area range for examining the item label name of the designated field from the item definition designated by the processing of S201. As shown in FIG. 2, this search area range is item label search area range information in the item definition information that defines each of the input fields of the form. The area position coordinates and the size correspond to each of the set areas.

  In S203, the upward search area information in the acquired item name search area range information is provided to the field detection unit 13, and as shown in FIG. 8A, image data corresponding to the upward area from the designated field. Is extracted from the image memory 12 by the field detection unit 13 and output to the recognition processing unit 14.

In S204, character recognition is performed for each character from the output image data, and the recognition result is temporarily stored in a work memory (not shown).
In S205, whether or not the character is included in the area cut out by the processing of S203 described above and the character is correctly recognized is determined based on whether or not the character is stored in the work memory. If the determination result is Yes, the process proceeds to S209, and if No, the process proceeds to S206.

  In S206, the image data area corresponding to the left search area range information acquired in the process of S202 described above is given to the field detection unit 13, and the image data corresponding to the image area is cut out and output to the recognition processing unit 14. This is performed by the form information management unit 22.

  In S207, character recognition is performed for each character from the output image data, and the recognition result is temporarily stored in a work memory (not shown).

  In S208, discrimination processing similar to the processing in S205 described above is performed. If the discrimination result is Yes, the processing proceeds to S209, and if No, the processing proceeds to S212.

  In S209, the data type reference table 24 is searched for a character string consisting of one or more characters corresponding to the recognition result temporarily stored in the work memory, and the data associated with the corresponding character or character string is retrieved. Get the type. For example, if the recognition result in the work memory is “quantity” as shown in FIG. 8A, the data type “numeric” associated with “quantity” from the data type reference table 24 shown in FIG. Acquisition is performed.

  In S210, it is determined whether or not a data type has been acquired by the processing in S209 described above. If the determination result is Yes, that is, if the combination of the item label name corresponding to the recognition result and the type of the data type is in the data type reference table 24, the process proceeds to S211. If No, the process proceeds to S212.

  In S211, the type of data type acquired by the processing in S210 described above, for example, information indicating “numerical value” is set in the data type item of the item definition corresponding to the attribute setting target field.

In S212, when the determination result is No in the determination process of S208 described above, the message “item label name not found” is generated and displayed on the screen of the display unit 19. Further, when the determination result of the determination processing of S210 described above is No, a message “The data type of the item label name cannot be found” is generated and displayed on the screen of the display unit 19.
After the process of S211 or S212 is completed, the process returns to the original process.

The process so far is the data type setting process.
Next, details of the maximum character digit number setting process performed in the process of S106 in the field attribute setting process shown in FIG. 5 will be described. This process is a maximum character digit setting process for generating the maximum number of characters among the attributes for the field based on other field attribute information when setting the OCR form definition.

FIG. 9 is a flowchart showing the contents of the character digit number setting process.
First, in S301, item definition information corresponding to the field of the form image of the display unit 19 designated by the user by operating the mouse is selected in the form information storage unit 15.

  In S302, the field detection unit 13 cuts out image data corresponding to the field area based on the field coordinates and size information in the item definition information selected by the processing in S301.

  In S303, the recognition processing unit 14 determines whether or not a character frame is included in the image data cut out by the processing of S302 described above. And if a determination result is Yes, it will progress to the process of S304, and if No, it will progress to the process of S306.

In S304, ruled line recognition is performed from the field image cut out by the process of S302.
In S305, the recognition processing unit 14 detects the area frame surrounded by the ruled line recognized in the process of S304 described above, generates a detection signal every time the frame area is detected, and sends it to the attribute information generation unit 23. For example, as shown in FIG. 10, a digit counter (not shown) in the generation unit 23 is incremented by “+1” to calculate the number of frame regions.

  By the way, when the result of the determination process in S303 is No, that is, when there is no frame area in the field, the field size, character font, and inter-character space (pitch) as the field format are defined in advance in S306. Acquisition is performed by the form information management unit 22 from the formed form definition storage unit 15.

  In S307, as shown in FIG. 11, the number of characters CNmax is calculated based on the following calculation formula using the field width Fw, character font width FONTw, and character pitch width Pw acquired by the processing of S306 described above as variables. 23.

(Equation 1)
CNmax = Fw / (FONTw + Pw)

  In S308, the number of character digits or the number of characters calculated by the processing in S305 and S307 is temporarily stored in a maximum character digit number buffer (not shown) in the field attribute generation unit 23 as the maximum number of characters to be entered.

  In step S309, the number of characters stored by the above-described processing in step S308 is set as the maximum entry digit number item content in a field attribute setting dialog (not shown) for displaying a preview.

  In S310, the form information management unit 22 determines whether or not the confirm button has been pressed by the user arranged in the dialog in the state where the field attribute setting dialog is displayed by the process of S309. If this determination result is Yes, the process proceeds to S311, and if No, the process proceeds to S313.

  In S311, the form information management unit 22 performs registration definition by using the number of characters stored in the buffer by the process of S308 as the item content maximum character number item content corresponding to the field of the form definition information storage unit 15.

  If the determination process in S310 is No, it is determined in S313 whether or not the user has corrected the value of the number of characters displayed by the process in S309 described above. If the determination result is Yes, the process proceeds to S313. If No, the determination is repeated until the determination result in S310 becomes Yes.

In S313, the value of the number of characters corrected by the user is temporarily stored in a predetermined area in the work memory. When the process of S313 is completed, the process returns to S308.
When the process of S311 is completed, the process returns to the original process of S106 of FIG.

The above processing is the character digit number setting processing.
In the above embodiment, when the data type of the attribute creation target field is created based on the item label information, the item label information is searched from a predetermined area range in the upward or left direction set in advance. However, the field of the item label may be directly designated by the user using the pointing device.

  In the above embodiment, the number of characters is calculated based on the horizontal width size of the field in which the number of characters that can be input in the attribute creation target field is set in advance. However, when the vertical width size is larger than the horizontal width size. The number of characters may be calculated based on the vertical width size.

  A control program for causing a computer having a standard configuration to perform the various processes shown in FIGS. 5 to 11 described above is created, and the control program is read and executed by the computer. It is possible to cause such a computer to perform a function corresponding to the OCR form field attribute setting device in the embodiment described above. Further, by recording such a control program on a readable recording medium, causing the computer to read the program from the recording medium and executing the program, the function corresponding to the form data input device in this embodiment is provided in such a computer. It is also possible to do this.

As the recording medium here, for example, a storage device such as a ROM or a hard disk device provided as an internal or external accessory device in a computer, a flexible disk, an MO (magneto-optical disk), a CD-ROM, a DVD-ROM, or the like Such portable recording media can be used. The recording medium may be a recording device provided in a computer functioning as a program server connected to the computer via a network.
In this case, a transmission signal obtained by modulating a carrier wave with a data signal representing a control program is transmitted from a program server through a network as a transmission medium, and the computer demodulates the received transmission signal and controls the control program. The control program can be executed by playing back.

It is a figure which shows the structure of the OCR system which implements this invention. It is a figure which shows the structure of a form definition information storage part. It is a figure which shows an OCR original ledger sheet form. It is a figure which shows the structure of a data type reference table. It is a flowchart which shows the processing content of a field attribute setting process. It is a flowchart which shows the processing content of a data type setting process. It is a figure which shows the example of the state in which the field of the field attribute setting object was designated. It is a figure which shows the example of the state which represented the item label name search range in a pseudo manner, (a) shows the search area range of the setting object field area | region upward, (b) is the left direction of a setting object field area | region. Indicates the search area range. It is a flowchart which shows the process of a maximum character number setting process. It is a figure which shows the example of a state with a character frame in the setting object field area | region. It is a figure which shows the example of the state showing the format item content used when calculating the number of characters in a setting object field area | region.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 OCR apparatus 2 OCR form creation / editing apparatus 11 Scanner 12 Image memory 13 Field detection part 14 Recognition processing part 15 Form definition information storage part 16 Result storage part 17 Display screen generation part 18 Display memory 19 Display part 21 Input part 22 Form information Management unit 23 Attribute information generation unit 24 Data type reference table

Claims (5)

An input means for optically scanning a previously created original form and inputting a form image composed of a field image and a character image;
Recognizing means for recognizing fields and characters from the form image input by the image input means and outputting field areas and character data;
Display means for displaying a form image in which the field data output by the character recognition means and character data are contrasted;
Designation means for designating a field area from the form image displayed by the display means;
Creation means for creating attribute information of the field based on item definition data corresponding to the field designated by the field designation means;
A form field attribute creation system characterized by comprising: The creating means includes
Area cutout means for cutting out a predetermined image area in the upward or left direction of the field area designated by the designation means;
Search means for searching for an item label name consisting of one or more characters in the image area cut out by the cut-out means;
Acquisition means for acquiring item type information corresponding to the item label name searched by the search means;
The form field attribute creating system according to claim 1, further comprising: The creating means includes
Determining means for determining whether or not there is a character frame in the input field specified by the field specifying means based on the image data;
A counting unit that counts the number of character frames in the field as the number of characters that can be input in the field when the determination unit determines that there is a character frame;
If it is determined by the determining means that there is no character frame, the number of characters that can be entered in the field is determined based on the field size, the character font size, and the space between characters that are predefined for each field. A calculating means for calculating;
The form field attribute creating system according to claim 1, further comprising: Optically scan the original form created in advance, input the form image consisting of field image and character image,
Recognize the field and characters from the input form image and output the field area and character data,
Display the form image that contrasts the output field area and character data,
Specify the field area from the displayed form image,
Creating attribute information of the field based on the item definition data corresponding to the specified field;
A form field attribute creation method characterized by this. On the computer,
A process of optically scanning a previously created original form and inputting a form image consisting of a field image and a character image;
Processing for recognizing fields and characters from the input form image and outputting field areas and character data;
Processing to display a form image in which the output field region is compared with character data;
A process of designating a field area from the displayed form image;
A process of creating attribute information of the field based on the item definition data corresponding to the specified field;
A program that causes a computer to perform

Images