JP5604814B2 - Information processing apparatus, information processing method, and program - Google Patents

Description

The present invention relates to an information processing apparatus, an information processing method, and a program, particularly to a technique for generating a recognition template that is used in the recognition process.

Conventionally, a form or the like is created by overlaying data such as variables (data not fixed to a template such as characters and numerical values) on a certain format (template). In addition, software for creating template data used to create a form or the like in this way has been developed.

The template data (template data) is specifically form data (form data) such as a form having a certain format. Using this software, form forms can be created, output areas that output data such as variables in some areas of the forms, and print areas that allow users to input (describe) characters, etc. Template data is created by setting. The template data created in this way is overlaid with the variables and the like, and the target form is output.

In addition, conventionally, after a form is output in this way, OCR processing (character recognition) is performed on the form in order to read variables output to the form output area or characters written in the print area by the user. Process). In order to efficiently perform OCR processing, an OCR template that is defined as an OCR processing area is generated for a part of the form (such as an output area or a printing area) in accordance with a user instruction, and OCR template is generated according to the OCR template. Processing is being executed.

For example, Patent Document 1 discloses that an image of a form read from a scanner is displayed, and field item attribute information of an area designated by a user is created from the displayed image.
Japanese Patent Laid-Open No. 2005-044256

  However, in the above prior art, when creating the template data of a form, an object such as a form output area is set, and a character font (typeface such as Gothic or Mincho) or font is set for the object. Set the attribute information such as the size, the character / numeric attribute indicating whether the output data is characters or numbers, the number of digits such as the output characters or numbers, and then perform the OCR processing. , Attribute information such as a dictionary used in OCR processing must be set in the target area. That is, the user has to set attribute information when creating template data and performing OCR processing, which is complicated.

An object of the present invention is to accept setting of an object for the form form data by a user operation via a display screen displayed when creating the form form data, and for each object set in the form form data. the attribute information relating to the object that contains the type of the object, and receives setting information indicating whether to perform recognition processing for the object, attribute information relating to the object for each of the respective object is set When creating form form data and creating the form form data, for each object set in the form form data, it is determined whether or not the setting information of the object indicates recognition processing. accepts the determined setting information to indicate that performing the processing According to a type of the object, when determining the recognition type of the object that indicates the recognition method of the object, the setting information is determined not to indicate that performs recognition processing, generates the recognition attribute information of the object without, when the setting information is determined to indicate that performs recognition processing in accordance with attribute information relating to the object, attribute information relating to the recognition processing of the object containing the recognition type of the determined the object generating a recognition attribute information indicating an area of the object recognition attribute information generated as information indicating the attribute information relating to the recognition processing of the object is set, the recognition processing by the recognition method shown in recognized type of the object by generating a set recognized template as an area to perform, the user It is to reduce typing of 識属 information.

The present invention relates to an information processing apparatus for generating a recognition template used in a recognition process in which an object area set in the form form data is set as an area for performing a recognition process of a reading target. via the display screen displayed when creating, by the operation of the user, accepts a setting of an object with respect to the continuous form data, for each said object to be set to the slip form data, the including the type of the object attribute information relating to the object, and a receiving means for receiving setting of setting information indicating whether to perform a recognition process for the object, and against each of the objects of accepting the setting of the attribute information by said receiving means, said Attribute information related to the object received by the receiving means A continuous form data creating means but to create a set form form data, when creating the continuous form data, for each object that has been set for the document form data by said receiving means, with respect to the object It is determined whether or not the setting information received by the receiving unit indicates that the recognition process is to be performed, and the setting information determined to indicate that the recognition process is to be performed is included in the attribute information related to the object received by the receiving unit. In accordance with the type of the object included, a determination unit that determines a recognition type of the object indicating a recognition method of the object, and when the form form data is created, the reception unit sets the form form data. created by the continuous form data creation means an object was Results setting information accepted by the accepting means for the continuous form data to the set object is determined whether indicates that performs recognition processing, is set for the document form data by said receiving means For each object, if it is determined that the setting information received by the receiving unit for the object does not indicate that recognition processing is performed, the object information is received according to the attribute information related to the object received by the receiving unit. without generating a recognition attribute information indicating attribute information relating to recognition of an object, whereas, if the setting information accepted by the accepting means with respect to the object is determined to indicate that performs recognition processing, the Attribute information related to the object received by the receiving means, the form form data Recognition indicating attribute information related to the object recognition processing including the recognition type of the object determined by the determining means according to the attribute information related to the object set in the form data created by the data creating means an attribute information generating means for generating attribute information, when creating the continuous form data, the recognition attribute information generated as information indicating the attribute information relating to the recognition processing of the object by the attribute information generation unit is set Using the recognition attribute information, generate a recognition template for the form form data, which is set as an area to be recognized by the recognition method indicated by the recognition type of the object included in the recognition attribute information. Template generating means for performing the template generation Stage, when the recognition type included in the recognition attribute information generated as information indicating the attribute information relating to the recognition processing of the object by the attribute information generating means indicating the character recognition, the in which the recognition attribute information is set A recognition template for the form form data, in which an object area is set as an area for character recognition processing, is generated.

The present invention is an information processing method in an information processing apparatus for generating a recognition template used in a recognition process in which an object area set in form form data is set as an area for performing recognition processing of a reading target, receiving unit, via a display screen displayed when creating the continuous form data by operating the user accepts the setting of the object with respect to the continuous form data, for each said object to be set to the slip form data , attribute information relating to the object that contains the type of the object, and a reception step of receiving a setting of setting information indicating whether to perform a recognition process for the object, the continuous form data creating means, the attribute by the receiving step each of the object, which has received a set of information In contrast, a continuous form data creating step of creating continuous form data attribute information is set according to the object that has been received in the receiving step, the determining means, when creating the continuous form data, by said receiving step For each object set for the form data, it is determined whether the setting information received by the receiving step indicates that the object is to be recognized, and indicates that the recognition process is to be performed. and according to type of the object included in the attribute information of the determined setting information to the object received by the receiving step, a determination step of determining a recognition type of the object that indicates the recognition method of the object, the attribute information generating means the but when creating the continuous form data, by said receiving step It indicates that the setting information accepted by the accepting step for the object set in a continuous form data created by an object set for vote form data by said continuous form data producing step performs recognition processing As a result of determining whether or not, for each object set for the form form data by the receiving process, the setting information received by the receiving process for the object does not indicate that recognition processing is performed. If it is determined, according to the attribute information related to the object received in the receiving step, the recognition attribute information indicating the attribute information related to the object recognition process is not generated. It was determined that the received setting information indicates that recognition processing is to be performed . In this case, it is determined by the determining step according to the attribute information related to the object received by the receiving step and set in the form form data created by the form form data creating step. The attribute information generating step for generating the character recognition attribute information indicating the attribute information related to the recognition processing of the object, including the recognition type of the object, and the template generating means, when the form form data is generated, the attribute the region of the object recognition attribute information generated as information indicating the attribute information relating to recognition of objects by the information generating step is set, by using the recognition attribute information, of the object included in the recognition attribute information An area where recognition processing is performed using the recognition method indicated in the recognition type. Set, and a template generation step of generating a recognition template for the continuous form data, the template generation process is recognized generated as information indicating the attribute information relating to the recognition processing of the object by the attribute information generation step If the recognition type included in the attribute information indicates character recognition, an area of the object to which the recognition attribute information is set, is set as an area to perform character recognition processing, generates a recognition template for the continuous form data It is characterized by

The present invention is a program that can be read and executed by an information processing apparatus that generates a recognition template used for recognition processing in which an object region set in form form data is set as a region for performing recognition processing of a reading target. , the information processing apparatus, the through display screen displayed when creating the continuous form data, by a user operation, which accepts a setting of an object with respect to the continuous form data, are set on the document form data for each object, attribute information relating to the object that contains the type of the object, and a receiving means for receiving setting of setting information indicating whether to perform a recognition process for the object, the setting of the attribute information by said receiving means for each of the objects accepted, the A continuous form data generating means for generating a continuous form data attribute information is set according to the object which is received by the urging means, when creating the form form data, set for the document form data by said receiving means For each object, it is determined whether or not the setting information received by the receiving unit for the object indicates that recognition processing is performed, and the setting information determined to indicate that the recognition processing is performed is In accordance with the type of the object included in the attribute information related to the object received by the receiving unit, the determining unit that determines the recognition type of the object indicating the recognition method of the object, and the reception when creating the form form data Object set for the form data by means Result of determining whether indicating the setting information accepted by the accepting means for the object set in a continuous form data to be created to perform the recognition process by the continuous form data creating means comprising at said reception For each object set for the form data by the means, if it is determined that the setting information received by the receiving means for the object does not indicate that recognition processing is to be performed, the receiving means According to the received attribute information related to the object, the recognition attribute information indicating the attribute information related to the object recognition process is not generated, while the setting information received by the receiving unit performs the recognition process for the object. If it is determined to show the the of accepted by the accepting means The object information including the recognition type of the object determined by the determining unit according to the attribute information related to the object set in the form form data generated by the form form data generating unit. Information generating means for generating recognition attribute information indicating the attribute information related to the recognition processing of the object , and when generating the form data, the attribute information generating means generates information indicating the attribute information related to the object recognition processing. the region of the object recognition attribute information is set which is, by using the recognition attribute information, is set as an area to perform the recognition process by the recognition method shown in recognized type of the object included in the recognition attribute information , A template for generating a recognition template for the form data To function as a rate generator, the template generating unit, when recognizing type included in the recognition attribute information generated as information indicating the attribute information relating to the recognition processing of the object by the attribute information generating means indicates a character recognition , an area of the object to which the recognition attribute information is set, is set as an area to perform character recognition processing, and generates a recognition template for the continuous form data.

According to the present invention, setting of an object for the form form data is accepted by a user operation via a display screen displayed when creating the form form data, and each object set in the form form data is received. the attribute information relating to the object that contains the type of the object, and receives setting information indicating whether to perform recognition processing for the object, attribute information relating to the object against each of the respective object is set When creating form form data and creating the form form data, for each object set in the form form data, it is determined whether or not the setting information of the object indicates recognition processing. accepts the determined setting information to indicate that performing the processing According to a type of the object, when determining the recognition type of the object that indicates the recognition method of the object, the setting information is determined not to indicate that performs recognition processing, generates the recognition attribute information of the object without, when the setting information is determined to indicate that performs recognition processing in accordance with attribute information relating to the object, attribute information relating to the recognition processing of the object containing the recognition type of the determined the object generating a recognition attribute information indicating an area of the object recognition attribute information generated as information indicating the attribute information relating to the recognition processing of the object is set, the recognition processing by the recognition method shown in recognized type of the object by generating a set recognized template as an area to perform, the user It is possible to reduce the input work of 識属 information.

FIG. 1 is a diagram illustrating a configuration example of a system according to the present embodiment. FIG. 2 is a block diagram showing a hardware configuration of the information processing apparatuses 100 and 200 shown in FIG. FIG. 3 is a block diagram illustrating an example of a software configuration of the information processing apparatus illustrated in FIG. FIG. 4 is an example of the form editor screen 400. FIG. 5 is an example of a form form property screen 500 for inputting form attribute information. FIG. 6 is an example of a property screen for inputting object attributes (definitions). FIG. 7 is an example of a form definition table in which data for defining a form is stored. FIG. 8 is an example of an object definition table that stores data for defining (attributes) objects. FIG. 9 is a diagram illustrating an example of an OCR definition table of a form. FIG. 10 is a diagram illustrating an example of an OCR definition table of objects. FIG. 11 is a diagram illustrating an example of output data. FIG. 12 is a diagram showing an example of a display screen showing a region to be subjected to OCR processing of a form (template). FIG. 13 is a diagram illustrating an example of a display screen that shows an OCR processing target area of a form described by a user, read by the multifunction device 300. FIG. 14 is a flowchart showing an example of a first control processing procedure in the system of the present invention. FIG. 15 is a flowchart illustrating an example of detailed processing in step S1404 illustrated in FIG. FIG. 16 is a flowchart showing an example of detailed processing in step S1508 shown in FIG. FIG. 17 is an example of a dictionary table. FIG. 18 is a flowchart showing an example of detailed processing of step S1602 in FIG. 16, step S1902 in FIG. 19, step S2002 in FIG. 20, and step S2102 in FIG. FIG. 19 is a flowchart showing an example of detailed processing of step S1509 in FIG. FIG. 20 is a flowchart illustrating an example of detailed processing of step S1510 of FIG. FIG. 21 is a flowchart showing an example of detailed processing of the processing in step S1511 of FIG. FIG. 21 is a flowchart showing an example of a second control processing procedure in the system of the present invention. FIG. 23 is a conceptual diagram for explaining the relationship among an object placement area 2301, an OCR process area (OCR process target area 2302), and a clear area 2303.

Hereinafter, the present invention will be described in detail according to preferred embodiments with reference to the accompanying drawings.
<Description of FIG. 1>
FIG. 1 is a diagram illustrating a configuration example of a system according to the present embodiment.
As illustrated in FIG. 1, the information processing apparatus 100, the information processing apparatus 200, and the multifunction peripheral (image processing apparatus) 300 are connected to each other via a network 400 so that they can communicate with each other.

The multifunction machine 300 is an image processing apparatus such as a so-called MFP (Multifunction Peripheral) having a scanner function, a printing function, and the like, and executes a printing process in response to a request from the information processing apparatus or forms (paper). It is possible to transmit digitized data (electronic data) generated by reading (scanning) or the like to the information processing apparatus.

The information processing apparatus can make a print request for a form or the like to the multifunction device 300 via the network 400. The information processing apparatus also has a function for creating and editing templates (form data) such as forms, and form attribute information (form definition that is data in the form definition table (FIG. 7)) that is input when creating a template. Information) and attribute information of the object (object definition information which is data in the object definition table (FIG. 8)) and a function for generating OCR definition information (data in FIG. 10) set for OCR. Yes.

Also, it has a function of displaying electronic data of a form described by the user transmitted from the multifunction device. FIG. 13 is a diagram illustrating an example of a display screen that shows an OCR processing target area of a form described by a user, read by the multifunction device 300. As illustrated in FIG. 13, areas 1302, 1303, 1304, 1305, 1306, 1307, and 1308 indicate areas that are subject to OCR processing.

<Description of FIG. 2> Hereinafter, the hardware configuration of the information processing apparatuses 100 and 200 illustrated in FIG. 1 will be described with reference to FIG.

FIG. 2 is a block diagram showing a hardware configuration of the information processing apparatuses 100 and 200 shown in FIG.

In FIG. 2, reference numeral 201 denotes a CPU that comprehensively controls each device and controller connected to the system bus 204. Further, the ROM 202 or the external memory 211 has a BIOS (Basic Input / Output System) or an operating system program (hereinafter referred to as OS), which is a control program of the CPU 201, and functions executed by each server or each PC (information processing apparatus). Various programs and the like to be described later necessary for the realization are stored.

A RAM 203 functions as a main memory, work area, and the like for the CPU 201. The CPU 201 implements various operations by loading a program or the like necessary for execution of processing from the ROM 202 or the external memory 211 into the RAM 203 and executing the loaded program.

An input controller 205 controls input from a keyboard (KB) 209 or a pointing device such as a mouse (not shown). A video controller 206 controls display on a display (display unit) such as a CRT display (CRT) 210. In FIG. 2, although described as CRT 210, the display device is not limited to the CRT, but may be another display device such as a liquid crystal display. These are used by the administrator as needed.

A memory controller 207 is provided in an external storage device (hard disk (HD)), flexible disk (FD), or PCMCIA card slot for storing a boot program, various applications, font data, user files, editing files, various data, and the like. Controls access to an external memory 211 such as a compact flash (registered trademark) memory connected via an adapter.

A communication I / F controller 208 connects and communicates with an external device via the network 400, and executes communication control processing on the network. For example, communication using TCP / IP is possible.

Note that the CPU 201 enables display on the CRT 210 by executing outline font rasterization processing on a display information area in the RAM 203, for example. In addition, the CPU 201 enables a user instruction with a mouse cursor (not shown) on the CRT 210.

Various programs to be described later for realizing the present invention are recorded in the external memory 211 and executed by the CPU 201 by being loaded into the RAM 203 as necessary. Further, files and various tables used when executing the program are also stored in the external memory 211.

<Description of FIG. 3> FIG. 3 is a block diagram illustrating an example of a software configuration of the information processing apparatus illustrated in FIG. 1.

The external memory 211 includes a form editor software program 301, an OCR software program 318, a form definition table (FIG. 7), an object definition table (FIG. 8), draft image data 312 and a form OCR definition table. (FIG. 9), an OCR definition table of objects (FIG. 10), a dictionary table (FIG. 17), various dictionaries (316) used for OCR processing, and an output result in which a recognition processing result by the OCR engine is output 317 and output data (FIG. 11) are stored.

A form editor software program 301 (hereinafter also referred to as form editor software) is software used to create or edit a form template such as a form.

The form editor software 301 is arranged in the template with a form data / attribute input unit 302 (FIG. 5) for inputting form template data such as a form and various attribute information of the template in accordance with an instruction from the user. OCR definition information (FIG. 10) is generated using the object data input / attribute input unit 303 (FIG. 6) for inputting various object data and various attribute information of the object (FIG. 6), and the data input in 302 and 303. Set the OCR definition information generated by the OCR definition information generation unit 304, the image data generation unit 305 that generates image data (data to be overlaid with the template) as the draft of the template, and the OCR definition information generated by the OCR definition information generation unit 304 in the OCR engine. Where the OCR software reads to And OCR definition information setting unit 306 for storing the OCR definition information in a storage area of, and the output unit 307 for outputting OCR processing (character recognition processing) a result of executing the (recognition result), and a. Note that the image data generated by the image data generation unit 305 is stored in the storage unit 308.

Here, the data of the template (form) input in 302 and various attribute information of the template are stored in the form definition table (FIG. 7) 310, and the data of various objects input in 303 and the various attributes of the object. The information is stored in an object definition table (FIG. 8) 311. The data in the form definition table 310 and the object definition table 311 is data 309 for configuring (defining) a form (style) serving as a template.

The OCR definition information generation unit 304 generates OCR definition information from the data in the form definition table (FIG. 7) and the object definition table (FIG. 8) stored in the storage unit 308 as described above.

Then, the OCR definition information setting unit 306 stores the generated OCR definition information in the object OCR definition table 315 stored in the storage unit 308.

These form OCR definition table 314 and object OCR definition table 315 are data 313 used to execute OCR processing (character recognition processing).

The storage unit 308 is a storage unit such as the external memory 211 and stores various dictionaries 316 used in OCR processing.

The OCR software program 318 (also referred to as OCR software) is read by the reading unit 319 and the reading unit 319 for reading the OCR definition table 314 of the form stored in the storage unit 308 and the OCR definition information in the object OCR definition table 315. A character recognition processing unit 320 (OCR engine) that performs character recognition processing using data (OCR definition information), and an output unit 321 that outputs a result recognized by the character recognition processing unit 320 to be stored in the storage unit 308. I have.

Here, the output unit 321 can output the recognition result of the character recognition processing unit 320 for display on a display unit such as the CRT 210, or can output the result of printing on the multi-function device 300. .

<Description of FIG. 14> Next, processing executed by the form editor software 301 will be described with reference to the flowchart of FIG.

FIG. 14 is a flowchart showing an example of a first control processing procedure in the system of the present invention, and corresponds to the processing by the form editor software 301 shown in FIG. That is, it is realized by the CPU 201 of the information processing apparatus 100 executing a program read from the ROM 202 or the external memory 211 to the RAM 203. In the figure, S1401 to S1406 indicate each step.

First, when executing the form editor software program, the CPU 201 of the information processing apparatus 100 displays the form editor screen 400 shown in FIG. FIG. 4 is an example of the form editor screen 400.

Next, the CPU 201 of the information processing apparatus 100 receives an input of a form such as a form from the user. Specifically, when the CPU 201 of the information processing apparatus 100 detects that the setting button has been pressed by the user, the form form property screen shown in FIG. 5 is displayed.

FIG. 5 is an example of a form form property screen 500 for inputting form attribute information.

A form form property screen 500 shown in FIG. 5 includes a unit 501 for inputting a form name (name) of a form, a unit 503 for inputting the size (size) of output paper, and a unit 507 for inputting a printing direction. A grid interval unit 509, a margin input unit 512, a layout unit input unit 517, and an OCR process input unit 518. Each information input in each part of the form form property screen 500 will be described as attribute information of the form (template).

Here, the form form property screen 500 will be described in detail.

Reference numeral 502 denotes a text box that accepts input of the form name (name) of the form by the user.

Reference numeral 504 denotes a pull-down menu capable of selecting a paper size (A4 or the like), reference numeral 505 denotes a text box in which a paper width can be input, and reference numeral 506 denotes a paper height. It is a text box that can. Reference numeral 508 denotes a pull-down menu in which the print direction (vertical or horizontal) can be input.

Reference numeral 510 denotes a grid box (height), and reference numeral 511 denotes a text box in which the grid gap (horizontal) can be entered. Reference numerals 513, 514, 515, and 516 denote text boxes for inputting the margins of the template, and the upper, lower, left, and right margins of the template can be input, respectively.

Reference numeral 517 denotes a pull-down for inputting a layout unit. For example, millimeters (mm) can be input.

Reference numeral 519 denotes a check box that can input a setting for executing the OCR process for the form displayed in FIG. 4. If the check box is checked here, a setting for executing the OCR process is input. The Rukoto. Reference numeral 520 denotes a check box capable of inputting a setting for not executing the OCR processing for the form displayed in FIG. When this is checked, a setting for not executing the OCR process is input.

The attribute information input to each part of the form form property screen 500 described here is data for defining the form, such as grid intervals and margins.

When the user inputs attribute information in each part of the form form property screen 500 and presses the OK button 521, the CPU 201 of the information processing apparatus 100 stores the input attribute information in the form definition table (FIG. 7). (Step S1401). When the cancel 522 button is pressed, the form form property screen 500 is closed. FIG. 7 is an example of a form definition table in which data for defining a form is stored.

Next, the CPU 201 of the information processing apparatus 100 arranges and displays objects on a template (form) 401 displayed on the form editor screen 400 in accordance with a user instruction.

Specifically, when the display button 416 is pressed by the user, the field list screen 417 is displayed.

On this screen, objects for arranging objects such as a fixed field 418 and a variable field 419 are displayed.

Here, the fixed field is an area for outputting fixed (no change) data, and the variable field is an area for outputting variable data. When the user drags and drops the fixed field 418 and arranges it on the template 401, an output area such as 413 can be set on the template. Similarly to the fixed field, the variable field can be set on the template by dragging and dropping the variable field 419 and placing it on the template 401.

The OLE field 420 of the field list screen 417 is an object that can set the output of a two-dimensional code such as a QR code. Like the variable field, the OLE field 420 is arranged on the template 401 by dragging and dropping the OLE field 420. The For example, an output area such as 414 can be set on the template. Here, reference numeral 414 denotes an example set as an area for outputting a QR code.

In addition, the user can directly input a character on the template 401 by pressing the object 421 and inputting the character from the KB 209. For example, characters 403, 404, 406, 407, 408, 409, 410, and 411 are input in this way.

Reference numeral 405 denotes an input of a check box object. In step 405, when the object 422 is pressed by the user and the template 401 is designated, the CPU 201 of the information processing apparatus 100 inputs 405 on the template 401. The “ladder frame” object shown at 412 can be input in the same manner.

Next, the CPU 201 of the information processing apparatus 100 selects the input object according to the user's instruction, and displays the property screen 600 (FIG. 6) of the selected object according to the user's instruction. For example, when the user selects an object and right-clicks in the selected state and selects “Property” (not shown), the property screen 600 (FIG. 6) of the selected object is displayed. Is done.

Then, from the displayed property screen 600 (FIG. 6), data indicating the definition of the object can be input to the object in accordance with a user instruction.

FIG. 6 is an example of a property screen for inputting object attributes (definitions).

The object property screen 600 shown in FIG. 6 includes a unit 601 for inputting the name of the object and its type, a unit 604 for inputting whether to perform OCR processing, and a unit for inputting the arrangement position and size of the object. 607, 619, a line attribute input unit 610, a character attribute input unit 614, and an output definition for inputting whether a character (column) is combined horizontally or vertically, and whether a character is full-width or half-width A section 620 and a section 623 for inputting the number of lines and the number of digits of the character frame when a character frame is set.

Here, the object property screen 600 will be described in detail.

Reference numeral 602 denotes a text box for inputting a field graphic name (name), and reference numeral 603 denotes a pull-down for selecting and inputting the type. Here, as the type, for example, a figure (square), a character, a figure (check box), a character (circle), a figure (ladder frame), an output area (character), an output area (QR code), or the like is selected. be able to.

The figure (square) is an object in which a template is surrounded by a square figure (line) as shown by 402 in FIG. The character is, for example, a character object input in 403, 404, 406, 408, 410, 411 in FIG. The figure (check box) is an object used as a check box, for example, as indicated by reference numeral 405 in FIG. The character (circled) is an object circled by the user, for example, as indicated by reference numerals 407 and 409 in FIG. The figure (ladder frame) is an object in which characters or the like are input (filled in) by the user, for example, as shown at 412 in FIG.

The output area (character) is an object to which a character is output, for example, as indicated by 413 in FIG. The characters output to this object are stored in advance as output data (FIG. 11), for example, in accordance with a user instruction.

FIG. 11 is a diagram illustrating an example of output data.

In FIG. 11, as data to be output to the area 413 (character area) in FIG. 4, the text data “* Please access the electronic coupon from here” and the area 414 in FIG. 4 (to output the QR code) QR code data “ABC... Jpee3dw” is shown as data to be output to the area (1).

When the template of FIG. 4 is printed, the data of the output data (FIG. 11) is output to the areas 413 and 414 for printing. The printed result is shown in FIG.

FIG. 12 is an example of a display screen of the OCR area of the template.

Returning to the description of the object property screen 600. The output area (QR code) is an object for outputting a two-dimensional code as indicated by 414 in FIG. 4, for example.

Reference numeral 605 denotes a check box in which a setting for executing an OCR process on a selected object can be input. When this box is checked, a setting for executing an OCR process on a selected object is set. Will be entered. Reference numeral 606 denotes a check box capable of inputting a setting for not executing the OCR process on the selected object. When this is checked, a setting for not executing the OCR process on the selected object is input.

Reference numeral 608 denotes a text box that can input a distance from the leftmost side of the template as a reference position of the arrangement position of the object. Reference numeral 609 denotes a text box that can input a distance from the uppermost side of the template.

Reference numeral 611 denotes a pull-down menu that can select a line type such as a solid line or a dotted line of the object. Reference numeral 612 denotes a pull-down menu for selecting and inputting the line width of the object. Reference numeral 613 denotes a pull-down menu that can select and input the line color of the object.

Reference numeral 615 denotes a pull-down menu that can input a font of an object character (such as Gothic or Mincho). Reference numeral 616 denotes a pull-down menu that can input the character style of the object (thin characters, standard characters, bold characters, etc.). Reference numeral 617 denotes a pull-down menu in which the character size (points) of the object can be input. Reference numeral 618 denotes a pull-down menu capable of inputting the character color of the object.

Reference numeral 619 denotes a text box in which an object size (size) can be input. Here, it is possible to input the width and height of the object.

Reference numeral 621 denotes a pull-down menu that can selectively input the direction of the character set of the object. Reference numeral 622 denotes a pull-down menu that can selectively input the output size (full-width, half-width, etc.) of the character of the object. Reference numerals 624 and 625 are pull-downs for selecting and inputting the number of lines and the number of digits of the character frame, respectively.

When data indicating the definition of the object is input via the property screen 600 (FIG. 6) and the OK button is pressed by the user, the CPU 201 of the information processing apparatus 100 displays the data indicating the definition of the input object. This is stored in the object definition table shown in FIG. The user performs this operation on each object.

As described above, in step S1402, the CPU 201 of the information processing apparatus 100 inputs data indicating the definition of an object for each object from the displayed property screen 600 (FIG. 6) according to a user instruction. Accept. Then, the input data is stored in the object definition table (FIG. 8). FIG. 8 is an example of an object definition table in which data for defining (attributes) (field attribute information) of objects (fields) is stored.

The object definition table shown in FIG. 8 includes “object number”, “type”, “sequential number within type”, “name”, “OCR usage classification”, “left”, “top”, “width”, “height”. ”,“ Number of lines ”,“ Number of digits ”,“ Line type ”,“ Line width ”,“ Line color ”,“ Font ”,“ Style ”,“ Size ”,“ Color ”,“ Composition direction ”,“ Text ” It consists of the item “Output Size”.

“Object number” is a number for identifying an object, and corresponds to the number indicated in parentheses in the reference numerals of FIG. That is, the object number <1> indicates a frame 402 in FIG. “Type” is information indicating the type (type) of the object. The “in-type serial number” is a consecutive number assigned to identify objects of the same type. “Name” is the name of the object. The “OCR usage classification” stores information indicating whether or not to use OCR. In the case of an object that performs OCR, “Yes” is stored, and in the case of an object that does not perform OCR, “No” is stored. Further, “left” stores information indicating the reference position of the object arrangement position and indicating the position from the leftmost side of the template. Further, “upper” stores information indicating the position from the top of the template that specifies the reference position of the object arrangement position. Further, the “width” stores the width of the object. In “height”, the height of the object is stored. The “number of lines” is the number of lines in a character input area such as a ladder frame. “Number of digits” is the number of digits in a character input area such as a ladder frame. The “line type” is information such as a solid line or a dotted line. The “line width” is a line width. The “line color” is a line color. The “font” is a font of characters. The “style” is a character style. “Size” is the size of a character. The “color” is the color of the character. The “set direction” is a set direction of characters (rows). The “character output size” is a character output size such as full-width or half-width.

Next, the CPU 201 of the information processing apparatus 100 determines whether or not “use OCR” in the form definition table (FIG. 7) input and stored in step S1401 is “Yes” (step S1403).

That is, it is determined whether or not 519 of the form property screen 500 is checked. If 519 is checked (when “Use OCR” in the form definition table (FIG. 7) is “Yes”) (step S1403: YES), the object definition table stored in the storage unit is used to execute the OCR process. OCR definition information is generated (step S1404). On the other hand, when 519 is not checked and 520 is checked (when “Use OCR” in the form definition table (FIG. 7) is “No”) (step S1403: NO), OCR definition information is not generated. The process ends.

Detailed processing in step S1404 will be described later with reference to FIG.

Next, when the CPU 201 of the information processing apparatus 100 generates the OCR definition information in step S1404, the CPU 201 acquires the scan resolution (dpi), the print orientation, and the like of the form OCR definition table (FIG. 9) stored in advance. For example, using the following formula, the size of the image data (upper left X coordinate: 0, upper left Y coordinate: 0, lower right X coordinate: value calculated by the following formula, lower right Y coordinate: The image data to be a draft of the template is generated (step S1405). By using the image data generated here as a draft of the OCR definition information, it is possible to specify which area in the template is to be the OCR process area.

FIG. 12 is a diagram showing an example of the display screen 1200 showing the OCR processing target area of the form (template) specified as described above. FIG. 12 is a screen in which an OCR processing target area is displayed on a form in which output data (FIG. 11) is output to the output area. In FIG. 12, 1202, 1203, 1204, 1205, 1206, 1207, and 1208 are defined as OCR processing target areas. Note that the size of the OCR processing target area can be corrected according to a user instruction.

(Expression)-Lower right X coordinate = Size (width) (mm) x Scanning resolution (dpi) ÷ 25.4 (mm)-Lower right Y coordinate = Size (height) (mm) x Scanning Resolution (dpi) ÷ 25.4 (mm)

For example, if the printing resolution is 300 dpi when scanning a vertical A4 sheet (width 210 mm and height 297 mm), and substituting these values into the above equation, the lower right X coordinate is 210 (mm) × 300 (dpi) ÷ 25.4 (mm) = 24800.349... And a value of about 2480. Also, if the lower right Y coordinate is substituted in the same manner, 297 (mm) × 300 (dpi) /25.4 (mm) = 3507.87..., Which is about 3507.

In this way, the size of the image data generated here is determined, and image data (image) of that size is generated (step S1405).

Next, the CPU 201 of the information processing apparatus 100 sets the OCR definition information in the OCR software by storing the OCR definition information generated in step S1404 in a storage unit that is read by the OCR software (step S1406).

Here, FIG. 9 will be described. FIG. 9 is a diagram illustrating an example of an OCR definition table of a form.

The form OCR definition table includes “form form name”, “OCR use”, “printing resolution”, “scanning resolution”, “image file name”, and “clear area initial value”.

The “form form name” is data corresponding to the “form form name” in the form definition table (FIG. 7), and is stored (generated) by being copied by the OCR definition information generating unit 304.

“OCR use” is data corresponding to “OCR use” in the form definition table (FIG. 7), and is stored (generated) by being copied by the OCR definition information generating unit 304.

“Resolution at printing” is a value stored in advance in response to a user instruction, and defines a resolution at which printing is performed at the time of printing. Accordingly, the form data generated by the form editor software 301 is instructed to be printed at the resolution set here.

The “scanning resolution” is a value stored in advance according to a user instruction, and defines which resolution is read at the time of scanning. Therefore, the form data generated by the form editor software 301 is read at the resolution set here.

“Image file name” is the file name of the image data generated in step S1405, and is generated by copying the form name of the form definition table (FIG. 9) when the image data is generated.

The “clear area initial value” is a value stored in advance in response to a user instruction, and is a length 2303 of a width from an object arrangement area 2301 to an area 2302 for performing OCR processing, as shown in FIG. .

FIG. 23 is a conceptual diagram for explaining the relationship among an object placement area 2301, an OCR process area (OCR process target area 2302), and a clear area 2303.

<Description of FIG. 15> Next, processing executed by the form editor software 301 will be described with reference to the flowchart of FIG.

FIG. 15 is a flowchart showing an example of detailed processing in step S1404 shown in FIG. 14, and corresponds to the processing by the form editor software 301 shown in FIG. That is, it is realized by the CPU 201 of the information processing apparatus 100 executing a program read from the ROM 202 or the external memory 211 to the RAM 203. In the figure, S1501 to S1511 indicate steps.

The CPU 201 of the information processing apparatus 100 repeatedly executes processing from step S1502 to step S1511 described later for all object definition information stored in the object definition table (FIG. 8). Here, the object definition information (form field attribute information) indicates the data of the record information shown in FIG.

First, the CPU 201 of the information processing apparatus 100 reads the object definition information in the object definition table (FIG. 8) (step S1502). For example, here, object definition information whose object number is <1> is read.

Then, the CPU 201 of the information processing apparatus 100 determines whether or not the “OCR usage classification” is defined as “Yes” (step S1503). That is, it is determined whether 605 in the object property screen (FIG. 6) is checked or 606 is checked.

Here, in the object definition table (FIG. 8), when 605 is checked, “OCR usage category” is stored as “Yes”, and when 606 is checked, “OCR usage category” is set as “No”. It is remembered.

If the CPU 201 of the information processing apparatus 100 determines that the “OCR usage classification” is defined as “Yes” in step S1503 (step S1503: YES), the process proceeds to step S1504. If it is determined that “classification” is defined as “no” (step S1503: NO), the processing target is set to the next record in the object definition table, and the process returns to step S1502. At this time, the process is executed for all the object definition information, and the process ends when there is no processing target.

Next, when the CPU 201 of the information processing apparatus 100 determines that the “OCR usage classification” is defined as “Yes” (step S1503: YES), the type of the object included in the object definition information is “character”. ”Or“ graphic (ladder frame) ”or“ output area (character) ”(step S1504).

If the CPU 201 of the information processing apparatus 100 determines that the object type is “character”, “figure (ladder frame)”, or “output area (character)” (step S1504: YES), step S1508 is performed. The process is shifted to and the character recognition setting process (FIG. 16) is executed. On the other hand, when it is determined that the object type is not “character”, “graphic (ladder frame)”, or “output area (character)” (step S1504: NO), the object type is “graphic (check box)”. Is determined (step S1505).

If the CPU 201 of the information processing apparatus 100 determines that the object type is “figure (check box)” (step S1505: YES), the process proceeds to step S1509 and the check box recognition setting process (FIG. 19) is executed. On the other hand, if it is determined that the object type is not “figure (check box)” (step S1505: NO), it is determined whether the object type is “character (circled)” (step S1506). ).

If the CPU 201 of the information processing apparatus 100 determines that the type of the object is “character (circled)” (step S1506: YES), the process proceeds to step S1510, and the circled number recognition setting process is performed. (FIG. 20) is executed. On the other hand, if it is determined that the object type is not “character (circled)” (step S1506: NO), it is determined whether the object type is “output area (QR code)” (step S1507). ).

If the CPU 201 of the information processing apparatus 100 determines that the type of the object is “output area (QR code)” (step S1507: YES), the process proceeds to step S1511 and the QR code recognition setting process ( 21) is executed.

When the CPU 201 of the information processing apparatus 100 determines in step S1507 that the object type is not “output area (QR code)”, and after executing the processing of step S1508, step S1509, step S1510, and step S1511, As in the case where NO is determined in step S1503, the processing target is set to the next record in the object definition table, and the process returns to step S1502. At this time, the process is executed for all the object definition information, and the process ends when there is no processing target.

In this way, the processing from step S1502 to step S1511 is executed for all object definition information stored in the object definition table.

<Description of FIG. 16> Next, processing executed by the form editor software 301 will be described with reference to the flowchart of FIG.

FIG. 16 is a flowchart showing an example of detailed processing in step S1508 shown in FIG. 15, and corresponds to the processing by the form editor software 301 shown in FIG. That is, it is realized by the CPU 201 of the information processing apparatus 100 executing a program read from the ROM 202 or the external memory 211 to the RAM 203. In the figure, S1601 to S1615 indicate the respective steps.

First, the CPU 201 of the information processing apparatus 100 generates data (here, “OCR”) indicating that a character recognition process for recognizing a character is executed as a type (type) to be recognized (step S1601). The data generated here is stored in the OCR definition table (OCR template) of the object shown in FIG. Here, the OCR template is a set of OCR definition information of each object shown in FIG.

FIG. 10 is a diagram illustrating an example of an OCR definition table of objects. Various data used for OCR is stored in the OCR definition table.

The object OCR definition table shown in FIG. 10 stores “No”, “area name (name)”, “object number”, “recognition type”, and the X coordinate of the upper left coordinate of the object placement area (recognition area). “X”, “Y” in which the Y coordinate of the upper left coordinate of the object arrangement area (recognition area) is stored, “X” in which the X coordinate of the lower right coordinate of the object arrangement area (recognition area) is stored, "Y", "Use dictionary", "Composition direction", "Character frame", "Number of digits", "Number of lines", "Character" where the Y coordinate of the lower right coordinate of the object placement area (recognition area) is stored "Output size" etc.

“No” is a number for identifying a record, and part or all of the information in this record is referred to as OCR definition information. The “area name (name)” is the name (area name) of an object (OCR target object) to be subjected to OCR. The “object number” is a number corresponding to the object number in the object definition table of FIG. The “recognition type” is a type (type) of recognition processing performed by the OCR software 318. The “use dictionary” indicates a dictionary used in recognition processing performed by the OCR software 318. The “set direction” indicates whether the character (row) is in the vertical direction or the horizontal direction. “Character frame” indicates what kind of frame a character frame such as a ladder frame is. “Number of digits” indicates the number of digits in the character frame. “Number of lines” indicates the number of lines in the character frame. “Character output size” indicates half-width or full-width.

Next, the CPU 201 of the information processing apparatus 100 executes the common information generation process (step S1602), and from the object definition information, the OCR target object (such as the object area name) in the object OCR definition information table and the recognition area. (Pixel) (object placement position (coordinates)) is generated. The generated OCR target object (object area name, etc.) and recognition area (Pixel) (object placement position (coordinates)) are stored in the object OCR definition table. Detailed processing in step S1602 will be described later with reference to FIG.

Next, after executing the common information generation process, the CPU 201 of the information processing apparatus 100 determines whether a font name is stored in “font” of the object definition information (step S1603). If it is determined that the font name is stored (step S1603: YES), a dictionary corresponding to the font is searched from the dictionary table (FIG. 17) (step S1604).

FIG. 17 is an example of a dictionary table. FIG. 17 shows that a dictionary suitable for OCR is stored for character fonts. The dictionary table is stored in the storage unit.

Next, the CPU 201 of the information processing apparatus 100 determines whether or not a dictionary corresponding to the font has been searched in step S1604 (step S1605). If it is determined that a dictionary corresponding to the font has been searched (step S1605: YES), “use dictionary” in the OCR definition table (FIG. 10) of the object is used to set the dictionary to use the searched dictionary. ”Is stored (generated). On the other hand, if it is determined that the dictionary corresponding to the font has not been searched (step S1605: NO), the object's OCR definition table (FIG. The dictionary name of the default dictionary is stored (generated) in the “use dictionary” of 10) (step S1607).

If it is determined in step S1603 that no font name is stored in the “font” of the object definition information, that is, if there is no font information, the process of step S1607 is executed. That is, the dictionary name of the default dictionary is stored (generated) in the “use dictionary” of the object OCR definition table (FIG. 10).

Next, after executing the processing of step S1607 or step S1606, the CPU 201 of the information processing apparatus 100 indicates “composition direction” of one record (object definition information) of the object definition table to be processed (FIG. 8). “Character output size” is stored (generated) in “Composition direction” and “Character output size” of the OCR definition table (FIG. 10) of the object.

Then, the CPU 201 of the information processing apparatus 100 determines whether or not it is a character frame object by determining whether or not a numerical value is currently set in the “frame” of the object definition information to be processed ( Step S1609). If the CPU 201 of the information processing apparatus 100 determines that the object is a character frame object (step S1609: YES), the CPU 201 determines whether the character frame is divided into a plurality of pieces (step S1610). That is, by determining whether or not the value (at least one of the number of lines and the number of digits) set in the “frame” of the object definition information to be processed is a numerical value of 2 or more, "Or" field frame "is determined (step S1610).

Then, when it is determined that the frame is a “ladder frame” (when it is determined that at least one of the number of lines and the number of digits set in the “frame” is a numerical value of 2 or more) (step S1610). : YES), “ladder” is stored (generated) as data indicating a ladder frame in the “character frame” of the object OCR definition table (FIG. 10) (step S1611). On the other hand, when it is determined that it is a “field frame” (when it is determined that both the number of lines and the number of digits set in the “frame” are numerical values of 1) (step S1610: NO), “Field” is stored (generated) in the “character frame” of the object OCR definition table (FIG. 10) as data indicating a field frame (step S1613).

If it is determined in step S1609 that a numerical value is not currently set in the “frame” of the object definition information to be processed (determined that the object is not a character frame object) (step S1609: NO), the object OCR “-” Is stored (generated) as data indicating that there is no frame in the “character frame” of the definition table (FIG. 10) (step S1604).

Next, the CPU 201 of the information processing apparatus 100 sets the values of “number of lines” and “number of digits” of the “frame” in the object definition table (FIG. 8) as the maximum number of characters to be recognized as the object. Are stored (generated) in “number of rows” and “number of digits” in the OCR definition table (FIG. 10) (step S1612).

Further, after executing the processing of step S1604 or step S1613, the CPU 201 of the information processing apparatus 100 sets “0 (zero)” as setting information that causes the OCR software to automatically recognize the number of characters to be recognized. Then, it is stored (generated) in “number of rows” and “number of digits” in the OCR definition table of the object (FIG. 10) (step S1615).

As described above, when the process of step S1615 or step S1612 is executed, the character recognition setting process shown in step S1508 ends, and the definition information of the next object to be processed is read in step S1502.

<Description of FIG. 18> Next, processing executed by the form editor software 301 will be described with reference to the flowchart of FIG.

FIG. 18 is a flowchart showing an example of detailed processing of step S1602 in FIG. 16, step S1902 in FIG. 19, step S2002 in FIG. 20, and step S2102 in FIG. 18 corresponds to the processing by the form editor software 301 shown in FIG.

That is, it is realized by the CPU 201 of the information processing apparatus 100 executing a program read from the ROM 202 or the external memory 211 to the RAM 203. In the figure, S1801 to S1804 indicate each step.

The CPU 201 of the information processing apparatus 100 generates a name (area name) of the OCR target object (step S1801).

Specifically, when the name of an object is input in “Name” of the object definition table (FIG. 8), the name is used as the name of the OCR target object (area name) (FIG. 10). ) In (area name (name)). If the name of the object is not entered in “Name” of the object definition table (FIG. 8), the name (area name) of the OCR target object is generated from the “type” of the object and the “sequential number within type”. Then, it is stored (generated) in “area name (name)” of the object OCR definition table (FIG. 10).

For example, since the object with the object number <4> is a check box, the area name (name) is connected to “CHK” indicating a check box and “001” of “in-type serial number”, and is an OCR target “CHK001”. An object name (area name) is generated and stored in “area name (name)” of the object OCR definition table (FIG. 10).

Next, the CPU 201 of the information processing apparatus 100 calculates the coordinates of the recognition area from the “placement” information in the object definition table (FIG. 8), and calculates the result in the “recognition area (pixel)” of the object OCR definition table. Is stored (generated) (step S1802). Specifically, for example, the upper left coordinates and the lower right coordinates of the recognition area can be calculated using the following equations.

(Expression) • “X coordinate at upper left of recognition area” = (reference position (left) −initial value of clear area) × scanning resolution (dpi) ÷ 25.4 (mm) • “Y coordinate at upper left of recognition area “= (Reference position (upper) −initial value of clear area) × scanning resolution (dpi) ÷ 25.4 (mm) ·“ lower right X coordinate of recognition area ”= (reference position (left) + size ( (Width) + Clear area initial value) x Scanning resolution (dpi) ÷ 25.4 (mm) · "Y coordinate at the bottom right of the recognition area" = (Reference position (Up) + Size (Height) + Clear area Initial value) x scanning resolution (dpi) ÷ 25.4 (mm)

Here, as shown in FIG. 23, the clear area is the length 2303 of the width from the object arrangement area 2301 to the area 2302 where the OCR processing is performed, and is set in advance by a user instruction and stored in the storage unit. Yes. Here, the value of the clear area set in advance by the user's instruction is described as the initial value of the clear area.

The scan resolution is set in advance by a user instruction and stored in the OCR definition table (FIG. 9) in the form of the storage unit. The reference position (left), reference position (top), size (width), and size (height) are the items “left”, “top”, “width”, “size” of the object definition table (FIG. 8), respectively. This is the value stored in “Height”.

In step S1802, the coordinates of the recognition area can be calculated by acquiring these pieces of information and substituting them into the above-described formula.

Next, the CPU 201 of the information processing apparatus 100 determines whether or not the recognition area determined by the coordinates calculated in step S1802 falls within the area of the template (form) (step S1803).

Specifically, it is determined whether the coordinates of the recognition area obtained by calculation in step S1802 exceed the coordinates of the size of the image data determined when generating the image data in step S1405.

Then, the recognition area falls within the template area (the coordinates of the recognition area obtained by calculation in step S1802 do not exceed the coordinates of the size of the image data determined when generating the image data in step S1405). 18 is finished, the process shown in FIG. 18 is terminated, while the image does not fit (the recognition area coordinates obtained by calculation in step S1802 are determined when the image data is generated in step S1405). If it is determined that it exceeds the coordinates of the size of the image data), each coordinate of the recognition area is corrected so as to be within the area of the template (step S1804).

Specifically, the coordinates of the recognition area determined by calculating in step S1802 that is determined to be exceeded are set to the coordinates of the size of the image data determined when generating the image data in step S1405. This can be corrected.

<Description of FIG. 19> Next, processing executed by the form editor software 301 will be described with reference to the flowchart of FIG.

FIG. 19 is a flowchart showing an example of detailed processing of step S1509 in FIG. FIG. 19 corresponds to the processing by the form editor software 301 shown in FIG.

That is, it is realized by the CPU 201 of the information processing apparatus 100 executing a program read from the ROM 202 or the external memory 211 to the RAM 203. In the figure, S1901 to S1902 indicate each step.

First, the CPU 201 of the information processing apparatus 100 generates data (here, “check box”) indicating that a character recognition process for recognizing a check box is executed as a type to be recognized (type) (step S1901). The data generated here is stored in the OCR definition table of the object shown in FIG.

Next, the CPU 201 of the information processing apparatus 100 executes the common information generation process shown in FIG. 18 (step S1902), and ends the process of step S1509.

<Description of FIG. 20> Next, processing executed by the form editor software 301 will be described with reference to the flowchart of FIG.

FIG. 20 is a flowchart illustrating an example of detailed processing of step S1510 of FIG. 20 corresponds to the processing by the form editor software 301 shown in FIG.

That is, it is realized by the CPU 201 of the information processing apparatus 100 executing a program read from the ROM 202 or the external memory 211 to the RAM 203. In the figure, S2001 to S2002 indicate each step.

First, the CPU 201 of the information processing apparatus 100 generates data (here, “circle”) indicating that a character recognition process for recognizing a circled character is executed as a type (type) to be recognized (step S2001). The data generated here is stored in the OCR definition table of the object shown in FIG. Next, the CPU 201 of the information processing apparatus 100 executes the common information generation process shown in FIG. 18 (step S2002), and ends the process of step S1510.

<Description of FIG. 21> Next, processing executed by the form editor software 301 will be described with reference to the flowchart of FIG.

FIG. 21 is a flowchart showing an example of detailed processing of the processing in step S1511 of FIG. FIG. 21 corresponds to the processing by the form editor software 301 shown in FIG.

That is, it is realized by the CPU 201 of the information processing apparatus 100 executing a program read from the ROM 202 or the external memory 211 to the RAM 203. In the figure, S2101 to S2102 indicate each step.

First, the CPU 201 of the information processing apparatus 100 generates data (here, “QR code”) indicating that character recognition processing for recognizing a two-dimensional code is executed as a type to be recognized (type) (step S2101). The data generated here is stored in the OCR definition table of the object shown in FIG. Next, the CPU 201 of the information processing apparatus 100 executes the common information generation process shown in FIG. 18 (step S2102), and ends the process of step S1511.

<Description of FIG. 22> Next, processing executed by the OCR software 315 will be described with reference to the flowchart of FIG.

FIG. 21 is a flowchart showing an example of the second control processing procedure in the system of the present invention, and corresponds to the processing by the OCR software 315 shown in FIG. That is, it is realized by the CPU 201 of the information processing apparatus 100 executing a program read from the ROM 202 or the external memory 211 to the RAM 203. In the figure, S2201 to S2204 indicate steps.

The CPU 201 of the information processing apparatus 100 reads the form OCR definition table (FIG. 9) and the object OCR definition table (FIG. 10) from the storage unit 308 (step S2201), and reads the form OCR definition table (FIG. 9). And the data in the object OCR definition table (FIG. 10) are set for OCR (step S2202).

Then, OCR is executed using the data set in step S2202 (step S2203), the recognition result is output to be stored in the storage unit (step S2204), and the process is terminated. The form editor software reads and outputs (displays, prints, etc.) the stored recognition result.

As described above, according to the present embodiment, the attribute information by the user is generated by generating the attribute information for the target area for executing the OCR process according to the attribute information of the object input to create the template data. Information input work can be reduced.

Although one embodiment of the present invention has been described in detail above, the present invention can take an embodiment as, for example, a system, an apparatus, a method, a program, or a storage medium. You may apply to the system comprised from an apparatus, and may apply to the apparatus which consists of one apparatus.

Another object of the present invention is to supply a storage medium storing software program codes for realizing the functions of the above-described embodiments to a system or apparatus, and the computer (or CPU or MPU) of the system or apparatus stores the storage medium. Needless to say, this can also be achieved by reading and executing the program code stored in.

In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the program code itself and the storage medium storing the program code constitute the present invention.

As a storage medium for supplying the program code, for example, a flexible disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a magnetic tape, a nonvolatile memory card, a ROM, or the like can be used.

Further, by executing the program code read by the computer, not only the functions of the above-described embodiments are realized, but also an OS (basic system or operating system) running on the computer based on the instruction of the program code. Needless to say, a case where the function of the above-described embodiment is realized by performing part or all of the actual processing and the processing is included.

Further, after the program code read from the storage medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer, the function is determined based on the instruction of the program code. It goes without saying that the CPU or the like provided in the expansion board or function expansion unit performs part or all of the actual processing and the functions of the above-described embodiments are realized by the processing.

DESCRIPTION OF SYMBOLS 100 Information processing apparatus 200 Information processing apparatus 300 Multifunction machine 400 Network

Claims (11)

An information processing apparatus for generating a recognition template used for a recognition process, in which an object area set in form form data is set as an area for performing recognition processing of a reading target,
Via the display screen displayed in creating the document form data by operating the user accepts the setting of the object with respect to the continuous form data, for each said object to be set to the slip form data of the object Accepting means for receiving attribute information relating to the object including the type, and setting information indicating whether or not to perform recognition processing on the object;
A continuous form data creating means for each of the objects of accepting the setting of the attribute information, to create a continuous form data attribute information relating to the object which is received is set by the receiving unit by the receiving unit,
Whether the setting information received by the receiving unit for the object indicates recognition processing for each object set for the form form data by the receiving unit when the form form data is created The object indicating the recognition method of the object according to the type of the object included in the attribute information related to the object received by the receiving unit with the setting information determined to indicate that the recognition process is to be performed Determining means for determining the recognition type of
When creating the continuous form data, for the receiving unit by an object set in a continuous form data created by an object set for the document form data the continuous form data creating means the As a result of determining whether or not the setting information received by the receiving unit indicates that recognition processing is to be performed, for each object set for the form form data by the receiving unit, the receiving unit for the object If it is determined that the received setting information does not indicate that the recognition process is to be performed, the recognition attribute information indicating the attribute information related to the object recognition process is set according to the attribute information related to the object received by the reception unit. without generating, while the receiving unit relative to the object If more setting information accepted is determined to indicate that performs recognition processing, the continuous form data created by said continuous form data creating means an attribute information relating to the object received by said receiving means Attribute information generating means for generating recognition attribute information indicating attribute information related to recognition processing of the object, including the recognition type of the object determined by the determining means, according to the attribute information related to the object to be set;
When creating the continuous form data, the attribute information area of the object recognition attribute information generated is set as information indicating the attribute information relating to recognition of an object by generating means, using the recognition attribute information A template generation unit configured to generate a recognition template for the form form data set as an area to be recognized by the recognition method indicated by the recognition type of the object included in the recognition attribute information;
With
The template generation unit sets the recognition attribute information when the recognition type included in the recognition attribute information generated as information indicating the attribute information related to the object recognition process by the attribute information generation unit indicates character recognition. the area of the object to be, is set as an area to perform character recognition processing, the information processing apparatus and generates a recognition template for the continuous form data. Using the generated recognized template by the template generating means, the area of the corresponding object recognition attribute information generated as information indicating the attribute information relating to recognition of an object by the attribute information generating means is set, the recognition The information processing apparatus according to claim 1, further comprising a recognition unit configured to perform a recognition process using a recognition method indicated by a recognition type of the object included in the attribute information. The template generating means, a predetermined distance area wider than the area of the object recognition attribute information generated as information indicating the attribute information relating to the recognition processing of the object is set by the attribute information generating means performs the recognition process The information processing apparatus according to claim 1, wherein a recognition template set as a region is generated. Or the attribute information generating means by said than the area of the object recognition attribute information generated as information indicating the attribute information relating to the recognition processing of the object is set a predetermined distance large area, more than an area of the continuous form data Determining means for determining
Correction means for correcting the wide area by the predetermined distance so as not to exceed the area of the form data when it is determined by the determination means to exceed
Further comprising
The information processing apparatus according to claim 3, wherein the template generation unit generates a recognition template in which a region wide by a predetermined distance corrected by the correction unit is set as a region for performing recognition processing. A character frame determination unit that determines whether or not the attribute information related to the object received by the reception unit includes character frame information indicating that the object is a character frame;
The attribute information generating means is provided on the condition that the character frame determining means determines that the attribute information relating to the object received by the receiving means includes character frame information indicating that the object is a character frame. Generating the recognition attribute information indicating the attribute information related to the recognition processing of the object in which the number of characters to be subjected to the character recognition processing is set from the number of character frames included in the attribute information, while the character frame determination means The number of characters to be recognized is recognized on the condition that it is determined that the attribute information related to the object received by the receiving means does not include character frame information indicating that the object is a character frame. Generating recognition attribute information indicating attribute information related to recognition processing of the object in which information for automatic recognition is set in the processing The information processing apparatus according to any one of claims 1 to 4, characterized. When the character frame determination unit determines that the attribute information related to the object received by the reception unit includes character frame information indicating that the object is a character frame, the character indicated in the character frame information A character frame number determining means for determining whether or not the frame is a frame for each character;
The attribute information generation unit recognizes the object in which the number of characters to be subjected to character recognition processing is set from the number of character frames when the character frame number determination unit determines that the character frame is a frame for each character. 6. The information processing apparatus according to claim 5, wherein recognition attribute information indicating attribute information related to processing is generated. The attribute information generating means, by the continuous form data said receiving means for the object set in a continuous form data created by said continuous form data creating means be an object set for by the reception means If it is determined that the received setting information does not indicate that the recognition process is to be performed , the attribute information related to the object received by the receiving unit and the form form data created by the form form data creating unit The control according to any one of claims 1 to 6, wherein control is performed so as not to generate recognition attribute information indicating attribute information related to character recognition of the object in accordance with the attribute information related to the object to be set. Information processing device. The accepting means further accepts a setting of template setting information indicating whether to generate a recognition template for the form data;
A template generation determination unit for determining whether to generate a recognition template for the form form data according to the template setting information received by the reception unit;
The template generation unit performs control so as not to generate a recognition template for the form form data when the template generation determination unit determines that a recognition template for the form form data is not generated. The information processing apparatus according to any one of claims 1 to 7.   The said template production | generation means produces | generates the recognition template with respect to the said form form data, when it determines with the said template production | generation determination means producing | generating the recognition template with respect to the said form form data. Information processing device. An information processing method in an information processing apparatus for generating a recognition template used for recognition processing, in which an object region set in form form data is set as a region for performing recognition processing of a reading target,
Receiving unit, via a display screen displayed when creating the continuous form data by operating the user accepts the setting of the object with respect to the continuous form data, for each said object to be set to the slip form data an accepting step of accepting attribute information relating to the object that contains the type of the object, and the setting of the setting information indicating whether to perform a recognition process for the object,
Form to be created continuous form data creating means, for each of the objects of accepting the setting of the attribute information by said receiving step, the continuous form data attribute information is set according to the object that has been received in said receiving step Form data creation process,
When the determination unit creates the form data, the setting information received by the receiving process is recognized for each object set for the form data by the receiving process. The method of recognizing the object according to the type of the object included in the attribute information related to the object received in the receiving step, the setting information determined to indicate that the recognition process is to be performed A determination step of determining the recognition type of the object indicating
When the attribute information generation unit creates the form data, the object is set to the form data that is set for the form data by the receiving process and is created by the form data creation process. results setting information accepted by the accepting step for the object is determined whether indicates that performs recognition processing for each object set for the document form data by said receiving step, to the object On the other hand, when it is determined that the setting information received by the receiving process does not indicate that the recognition process is to be performed, the attribute information related to the object recognition process according to the attribute information related to the object received by the receiving process. Recognition attribute information indicating When the setting information accepted by the accepting step for is determined to indicate that performs recognition processing is created by the continuous form data producing step a attribute information relating to the object received by the receiving step that according to the attribute information relating to the object set in the document form data, including recognition type of the object determined by the determining step, the attribute of generating character recognition attribute information indicating attribute information relating to the recognition processing of the object Information generation process;
Template generation means, when creating the continuous form data, the area of the object attribute information recognition attribute information generated as information indicating the attribute information relating to recognition of an object by generating process is set, the Using a recognition attribute information, a template generation step for generating a recognition template for the form form data set as an area for performing a recognition process by a recognition method indicated by the recognition type of the object included in the recognition attribute information;
With
The template generation step sets the recognition attribute information when the recognition type included in the recognition attribute information generated as information indicating the attribute information related to the object recognition processing by the attribute information generation step indicates character recognition. the area of the object to be, is set as an area to perform character recognition processing, the information processing method and generates a recognition template for the continuous form data. There is a program that can be read and executed by an information processing apparatus that generates a recognition template used for the recognition process, in which an object area set in the form data is set as a recognition target recognition process,
The information processing apparatus;
Via the display screen displayed in creating the document form data by operating the user accepts the setting of the object with respect to the continuous form data, for each said object to be set to the slip form data of the object Accepting means for receiving attribute information relating to the object including the type, and setting information indicating whether or not to perform recognition processing on the object;
A continuous form data creating means for each of the objects of accepting the setting of the attribute information, to create a continuous form data attribute information relating to the object which is received is set by the receiving unit by the receiving unit,
Whether the setting information received by the receiving unit for the object indicates recognition processing for each object set for the form form data by the receiving unit when the form form data is created The object indicating the recognition method of the object according to the type of the object included in the attribute information related to the object received by the receiving unit with the setting information determined to indicate that the recognition process is to be performed Determining means for determining the recognition type of
When creating the continuous form data, for the receiving unit by an object set in a continuous form data created by an object set for the document form data the continuous form data creating means the As a result of determining whether or not the setting information received by the receiving unit indicates that recognition processing is to be performed, for each object set for the form form data by the receiving unit, the receiving unit for the object If it is determined that the received setting information does not indicate that the recognition process is to be performed, the recognition attribute information indicating the attribute information related to the object recognition process is set according to the attribute information related to the object received by the reception unit. without generating, while the receiving unit relative to the object If more setting information accepted is determined to indicate that performs recognition processing, the continuous form data created by said continuous form data creating means an attribute information relating to the object received by said receiving means Attribute information generating means for generating recognition attribute information indicating attribute information related to recognition processing of the object, including the recognition type of the object determined by the determining means, according to the attribute information related to the object to be set;
When creating the continuous form data, the attribute information area of the object recognition attribute information generated is set as information indicating the attribute information relating to recognition of an object by generating means, using the recognition attribute information And functioning as a template generation means for generating a recognition template for the form form data set as an area for performing recognition processing by the recognition method indicated by the recognition type of the object included in the recognition attribute information,
The template generation unit sets the recognition attribute information when the recognition type included in the recognition attribute information generated as information indicating the attribute information related to the object recognition process by the attribute information generation unit indicates character recognition. the area of the object to be, is set as an area to perform character recognition processing, programs and generates a recognition template for the continuous form data.

Images