JP2002298081A - Optical character recognition device and field definition method of document reading definition body - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an optical character recognition device and field definition method of a document reading definition body capable of efficiently and quickly performing a preparation work in preparing the document definition body for mixedly reading multiple documents. SOLUTION: A document definition tool 21 executed on a controller 12 starts in preparing a document reading definition body file 11, prepares a template to be stored in a field definition element template file 16, defines a field on a document reading definition body applying the template, and stores the prepared document reading definition body into the document definition body file 11.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] 1. Field of the Invention [0002] The present invention relates to an optical character recognition device having a form reading definition function, and a field definition method for a form reading definition body.

[0002]

2. Description of the Related Art An optical character recognition apparatus (OCR) includes a conventional form OCR, a so-called document reader type OCR for automatically analyzing a recognition target area from a reading target image and performing recognition. The format of a document that can be automatically recognized by the document reader type OCR is limited to a word processing document or the like, and the recognition rate including layout analysis cannot be said to be 100%, and requires correction by the user. On the other hand, in the conventional form OCR, it is necessary to read a large number of forms such as various application forms and slips at high speed and with high accuracy. A form reading definition body (FC: format control) is created, and at the time of reading, the form is read by referring to the corresponding form reading definition body. By using such a form reading definition body, the reading speed and accuracy of the form OCR are improved.
Note that the form reading definition body includes pre-processing to post-processing of recognition,
Information necessary for the modification process, the editing process, and the output process is described, and the definition is performed interactively by the operator.

[0003] In the above, a large number of small species are generated and the OCR
Is an effective method for processing forms designed for documents, but due to recent advances in OCR technology, forms that have not been read before (forms not created for OCR:
(Existing forms). This kind, existing forms are different from OCR forms,
It is characterized in that a small amount is generated. Although it is necessary to create a form reading definition body even when reading an existing form, it is necessary to simplify the definition because there are various types and small quantities. As one means,
Japanese Patent Application Laid-Open No. 6-96272 discloses a "form format definition body creating apparatus". This device creates a definition body creation form in which the types of characters and the like that should be entered there and the number thereof are written in each of the read area fields in the form, and optically reads this to form a definition body creation form. The definition body information including "form size", "reading area field position", "type and number of characters to be written in the reading area field" and the like is registered.

However, in this apparatus, with respect to a plurality of types of forms, each form except for a field in which all of "form size", "reading area field position", and "character type and number of characters" match. It is necessary to register the definition body information of various fields for each form. For this reason, the number of defined body information to be registered increases remarkably as the types of forms to be handled increase, and when trying to select and use the registered defined body information, an enormous number of defined body information One of the desired definition information must be selected from among them. Therefore, as the types of forms to be handled increase, the workability is significantly reduced, a large storage area is required, and the amount of data to be handled is increased. In addition, the processing load is significantly increased, and there is a difficulty in operability and practicality in a system configuration including a storage capacity.

[0005] As described above, in the above-described conventional apparatus, as the types of forms to be handled increase, the workability significantly decreases.
In addition, there is a problem that the load on the apparatus is significantly increased, and there is a useful apparatus that can efficiently and quickly perform the creation operation when creating a form definition body for reading a plurality of forms in a mixed manner. Did not.

[0006]

As described above, in the related art, when a form definition body for reading a plurality of forms in a mixed manner is created, a useful and efficient operation can be performed quickly and efficiently. There is no device, and a lot of time and effort is required when creating a form definition body for reading a plurality of forms in a mixed manner.

[0007] The present invention has been made in view of the above circumstances,
An object of the present invention is to provide an optical character recognition device and a method for defining a field of a form reading definition body which can efficiently and quickly perform the creation operation when creating a form definition body for reading a plurality of forms in a mixed manner. Aim.

[0008]

By using the form identification function in the existing form reading, forms of a plurality of formats can be mixed and read by the same reading execution.
At this time, a plurality of reading definitions are defined by one form definition body. The present invention, when defining this form, uses a format definition such as a field definition between a plurality of form definitions, and further allows a format definition to be diverted between a plurality of form definition bodies. Using the definition body creation tool, save and manage the field definition elements of the form definition body as a template, and when creating a new form definition body, display this template on the GUI and define the format on the template By dragging and dropping an element with a pointing device such as a mouse, a field definition can be easily performed. This makes it possible to easily use the field definitions between the form reading definition bodies in the work of creating the form reading definition bodies when the forms of a plurality of formats are mixed and read by the same reading execution.

The present invention is characterized in that an optical character recognition apparatus having a form reading definition function is provided with means for storing a field definition element of a form reading definition body as a template.

According to the present invention, in an optical character recognition apparatus, a template storage means for storing a field definition element of a form reading definition body as a template, and a field definition element of the template stored in the template storage means. Graphic user interface means for defining a field of a form reading definition body using the same.

According to the present invention, in an optical character recognition apparatus, a form reading definition file for storing a form reading definition, and a field definition element template file for storing a field definition element of the form reading definition as a template And the field definition element of the template stored in the field definition element template file is applied to a newly created form reading definition body or a field definition of a form reading definition body read from the form reading definition file. It is characterized by the following.

According to the present invention, in an optical character recognition apparatus, a form reading definition body storing means for storing a form reading definition body, and a form reading definition body which is to be stored by the form reading definition body storing means. A template storage means for storing the field definition element as a template, a template selection screen display means for displaying a list of templates stored in the template storage means in a selectable manner, and a method for creating a form reading definition body on the template selection screen. When a template to be used is selected, the definition element of the selected template is acquired from the template storage means, and a definition element setting screen display means for displaying each definition element so that setting can be changed, and applying the template Display method of form reading definition body creation screen that displays form reading definition body creation screen When a field to which the field definition element of the template stored in the template storage unit is applied is specified on the form reading definition body creating screen, the definition element of the definition element setting screen is added to the specified field. And a field definition element expanding means for reflecting the

According to the present invention, in a method for defining a field of a form reading definition in an optical character recognition apparatus, the field defining element of the form reading definition is stored as a template, and the stored template is stored. Is defined so as to be applicable to an arbitrary field definition when the form reading definition body is created.

Further, the present invention has a form reading definition file for storing a form reading definition, and a field definition element template file for storing a field definition element of the form reading definition as a template. The field definition method of the form read definition body that is applied to the field definition of the form read definition body in which the field definition element of the template saved in the file is newly created or the form read definition body read from the form read definition body file Displaying a form reading definition body creation screen for creating a new form reading definition body by using the form reading definition body stored in the form reading definition body file or newly; Of the template saved in the file Displaying a list in a window, and, when one of the templates displayed in the list is selected, obtaining the definition element of the selected template from the field definition element template file and displaying the window so that the setting can be changed. Reflecting the definition element of the template displayed in the window on the designated field on the form reading definition body creation screen and applying the definition to the field definition.

Further, the present invention is a recording medium for realizing a form definition body creation tool which can be read by a computer for realizing an optical character recognition device, wherein a template name is added to a field definition element of the form reading definition body. A program for realizing a function of creating a field definition element template file by saving a template in units of fields is recorded.

The present invention also relates to a recording medium for realizing a form definition body creation tool which can be read by a computer for realizing an optical character recognition device, wherein a field defining element of the form reading definition body is stored as a template. A function to create a definition element template file, and a form reading definition body that is newly created or changed using the field definition elements of the template saved in the above field definition element template file. A program for realizing the function to be applied to the definition of the field is recorded.

As described above, the present invention has a function of storing and applying field definition elements as a template, so that when a new form definition body is created, the field definition of the form definition body can be easily performed. Specifically, the stored template is displayed so as to be selectable on a GUI, and a format definition element on a desired template is dragged and dropped to an arbitrary field definition position using a pointing device such as a mouse. Thus, the field definition of the form definition body can be easily performed. This makes it possible to extremely easily and quickly create a form reading definition body when a plurality of forms are mixed and read by the same reading execution. In addition, by managing the field definition elements in the template, the field can be easily defined using the template at an arbitrary field position of the form reading definition body to be created, and input errors when setting the same field definition can be prevented. Can be eliminated. Furthermore, when applying the field definition element from the template, information as an instance of the field such as coordinates is not applied, so that the handling and management of the template are facilitated, and various types are efficiently used by using a small number of templates. It can be effectively applied to form field definitions.

[0018]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing a configuration of a main part of an optical character recognition device according to an embodiment of the present invention.

In the figure, reference numeral 11 denotes a form definition file for storing a form reading definition, 12 denotes a control device realized by the processing function of the CPU, and 13 denotes a main memory read / write-accessed by the control device 12. 14 is a GUI
An input device 15 including a pointing device such as a mouse for realizing the function, and 15 is a display device for realizing the GUI function.

Reference numeral 16 denotes a field definition for storing a field definition element template (hereinafter simply referred to as a template) in which a template name (definition name) is added to a definition element of the field in units of fields defined in the form reading definition body. Element template file. The field definition element template file 16 is constructed by the user, and is shown in FIG. 2 by the processing function of the form definition tool executed on the control device 12 in accordance with the user's operation instruction using the operation screen by the GUI. A field definition element (attribute set = attribute set) having such a template name (definition name) is registered and managed for each field.

Reference numeral 21 denotes a form definition tool executed on the control device 12, which is started when a form reading definition file is created, and creates and saves a template and stores the template in a procedure as shown in FIG. Processing such as field definition and storage on the applied form reading definition body is executed.

FIG. 2 shows an example of the configuration of a template registered in the field definition element template file 16 in the above embodiment. In this example, a field definition element (attribute set) having a template name (definition name) is shown. ) Is registered and managed on a field-by-field basis. In this example, dates, amounts, product names, product codes, and the like are registered as template names (definition names). For each template name (definition name), the character type, number of digits, font type, presence / absence of a frame, etc. A field definition element (attribute set) composed of a set of a plurality of attributes is provided.

FIG. 3 shows an example of a GUI screen at the time of creating a form reading definition body in the above-described embodiment. Reference numeral 30 denotes a form reading definition body creation screen main body, and 31 denotes reading of a form reading definition body and a template. Button, 32 is the same save button,
33 is the same correction button, 34 is a definition element selection screen 34, 3
Reference numeral 5 denotes a definition element setting screen. The form reading definition body creation screen body 30 displays a form reading definition body registered in the form definition file 11 or a newly created empty (field not defined) form reading definition body. The definition element selection screen 34 displays a list of template names defined in the field (definition name list). The definition element setting screen 35 displays a field definition element (attribute set) of the definition name selected on the definition element selection screen 34.

Here, an example is shown in which the definition element selection screen 34 and the definition element setting screen 35 are displayed in separate windows on the form reading definition body creation screen main body 30 on the display screen of the display device 15. Is shown.

The form reading definition body selected by the operation of selecting a form reading definition body by a GUI (not shown) is displayed in the form reading definition body file 30 in the form reading definition body file 11.
Is read from and displayed.

When a new form reading definition body is created without using a new form reading definition body registered in the new form definition body file 11, only a form image having no field defined is displayed. In the definition element selection screen 34, for example, when the mouse button is placed on the screen (the screen is active), for example, when the read button 31 is clicked, the field definition element template A field-based definition name list registered in the file 16 is sequentially displayed in the registered template order.

The definition element setting screen 35 displays a field definition element (attribute set) of the definition name selected on the definition element selection screen 34. The above definition element selection screen 3
4 and the field definition element (attribute set) displayed on the definition element setting screen 35, when the screen is active,
The correction can be made by clicking the correction button 33 and registered (new registration, change registration) in the field definition element template file 16 by clicking the save button 32.
Here, it is assumed that each time the template read button 31 is clicked, the templates stored in the field definition element template file 16 are displayed in the registration order. A function of selecting a predetermined template by a predetermined selection means and displaying it on the definition element selection screen 34 and the definition element setting screen 35, such as a function of calling a template or a function of calling a corresponding template by specifying a field name or the like on a list It may be.

FIG. 4 is a flow chart showing a procedure of field definition at the time of creating a form reading definition body in the above embodiment.
Is executed by being activated. Here, a process is performed until a template is created using the field definition elements of the fields defined in the form reading definition body registered in the form definition file 11 and registered (saved) in the field definition element template file 16 (S1). ~ S4)
And the field definition element template file 16
A processing procedure for creating a form reading definition body using the template registered in the form definition and linking and executing the processing (S5 to S8) until registration (save) in the form definition body file 11 is shown. I have.

The operation of the embodiment of the present invention will now be described with reference to the above-mentioned drawings.

First, a new template is created using the field definition elements of the fields defined in the form definition file registered in the form definition file 11 and registered (saved) in the field definition element template file 16.
The processing up to this point will be described.

On a GUI operation screen (not shown) by the input device 14 and the display device 15, it is instructed to create a template using a field defined in the form reading definition registered in the form definition file 11, or When an instruction is given to create a template by a new setting that does not use the fields defined in the form reading definition registered in the body file 11, the control device 12 activates the form definition tool 21 and executes the processing shown in FIG. ), The processing of the field definition at the time of creating the form reading definition body is started.

Here, when an instruction to create a template using the fields defined in the form definition file registered in the form definition file 11 is issued, the form stored in the form definition file 11 is used. The read definition body is developed on the main memory 13, and the registered form read definition body is placed under the control of the form definition tool 21 (step S4 in FIG. 4).
1) First, the form registration definition registered first is displayed on the display screen of the display device 15 (step S2 in FIG. 4).

When an instruction to create a new template is issued without using the fields of the registered form reading definition body, the processing in step S1 described above is omitted and an empty (field defined) The form reading definition body is developed on the main memory 13 and displayed on the form reading definition body creation screen main body 30.

When creating a template using the fields defined in the form reading definition body registered in the form definition file 11, each field displayed on the form reading definition body creation screen main body 30 in the active state is used. From
An arbitrary field having a field definition element to be registered is selected by the pointing device of the input device 14 and dragged and dropped on the definition element selection screen 34. As a result, the definition name list of the specified field is displayed on the definition element selection screen 34, and the definition element selection screen 34 is substituted for the form reading definition body creation screen main body 30.
Becomes active. Here, definition element selection screen 3
When an arbitrary definition name is selected by a click operation from the definition name list displayed in 4, the field definition element (attribute set) of the selected definition name is displayed on the definition element setting screen 3.
5, the definition element setting screen 35 is activated instead of the definition element selection screen 34. An arbitrary attribute is defined on the definition element setting screen 35 by using the modification button 33, a definition name is further set on the definition element selection screen 34 as necessary, and a read operation is performed by clicking the read button 31. A desired template including a field definition element (attribute set) set on the element setting screen 35 and a corresponding definition name list on the definition element selection screen 34 is registered (saved) in the field definition element template file 16 ( FIG. 4 steps S3, S4).

When a new template is created without using the fields defined in the registered form reading definition body, the form reading definition body with no fields defined is used as described above. With the display on the creation screen main body 30, the definition element selection screen 34 and the definition element setting screen 35 are activated to create a field definition element to be registered and a definition name list, and a form reading definition body creation screen main body if necessary. After confirming the field definition on the definition element 30 and clicking the read button 31 while the definition element setting screen 35 is active, the field definition element (attribute set) set on the definition element setting screen 35 and the definition are clicked. The desired template consisting of the corresponding definition name list on the element selection screen 34 is a field definition element template It is registered (saved) in the Airu 16.

Next, in the above-described template creation and registration processing, the field definition element template file 16
A process from creating a form reading definition body using the template registered in the form definition and registering (saving) it in the form definition body file 11 will be described.

In this case, the form reading definition body creation screen main body 3
0 is activated, and a read button 31 is clicked to display the form reading definition to be used on the form reading definition body creation screen main body 30. After that, the definition element selection screen 34 is activated, and the read button 31 is clicked. As a result, the template registered in the field definition element template file 16 is expanded on the main memory 13 (step S5 in FIG. 4), and a definition name list of the first registered template is first displayed on the definition element selection screen 34. You. Thereafter, each time the read button 31 is clicked, a list of template definition names according to the registration order is displayed on the definition element selection screen 34 (step S6 in FIG. 4).

With the definition name list of the desired template displayed on the definition element selection screen 34 by the click operation of the read button 31, from the definition name list,
By selecting one definition name (for example, date), the field definition element (attribute set) of that definition name (date)
Is displayed on the definition element setting screen 35, and the screen is activated. On the definition element setting screen 35, settings are made in accordance with the field conditions to be created. After that, the field definition elements (attribute sets) set on the definition element setting screen 35 are displayed on the form reading definition body creation screen main body 30. By dragging and dropping to an arbitrary field position by the pointing device of the input device 14, one field definition (date field definition) is completed (step S7 in FIG. 4).

Also, at the time of creating the form reading definition body, the user clicks the save button 32 while selecting and displaying an arbitrary field definition element (attribute set) on the definition element setting screen 35. As a result, the field definition element (attribute set) is registered (saved) in the field definition element template file 16. By clicking the correction button 33, the field definition element (attribute set) to be corrected can be corrected and re-registered on the definition element setting screen 35.

As described above, the field definition element to be defined is set on the definition element selection screen 34 and the definition element setting screen 35, and set to an arbitrary field definition position on the form reading definition body creation screen main body 30 by drag and drop. By doing so, a desired form reading definition body can be created.

At this time, the form reading definition body creation screen main body 30
Is activated, and the read button 31 is clicked to register (save) the form read definition defined in the fields on the form read definition body creation screen main body 30 in the form definition file 11 in a reusable manner. (Step S8 in FIG. 4).

As described above, by providing the function of storing and applying the field definition element as a template, the field definition of the form definition body can be easily defined when a new form definition body is created. In this embodiment, the stored template is displayed in a selectable manner on a GUI, and a desired format definition element on the template is dragged and dropped to an arbitrary field definition position with a pointing device such as a mouse, for example. Thus, the field definition of the form definition body can be performed extremely easily. As a result, when a plurality of forms are mixed and read by the same reading execution, the operation of creating the form reading definition body can be performed extremely simply and quickly. In addition, by managing the field definition elements with the template, the field can be easily defined using the template at an arbitrary field position of the form reading definition body to be created.
Input errors when setting similar field definitions can be eliminated. Furthermore, when applying the field definition element from the template, information as an instance of the field such as coordinates is not applied, so that the handling and management of the template are facilitated, and various types are efficiently used by using a small number of templates. It can be effectively applied to form field definitions.

In the GUI interface according to the above-described embodiment, the creation and registration of a field definition element template and the creation of a form reading definition body using the template are performed on a single GUI screen shown in FIG. And registration, which are shown so that the present invention can be easily understood. In the above embodiment, the GUI interface, the template configuration, the processing procedure, etc. It goes without saying that various modifications can be made without departing from the spirit of the present invention.

[0045]

As described above in detail, according to the present invention, when creating a form definition body for reading a plurality of forms in a mixed manner, the creation operation can be performed efficiently and quickly. In addition, by managing the field definition elements in the template, the field can be easily defined using the template at an arbitrary field position of the form reading definition body to be created, and input errors when setting the same field definition can be prevented. Can be eliminated. Furthermore, when applying the field definition element from the template, information as an instance of the field such as coordinates is not applied, so that the handling and management of the template are facilitated, and various types are efficiently used by using a small number of templates. It can be effectively applied to form field definitions.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a main part of an optical character recognition device according to an embodiment of the present invention.

FIG. 2 is a diagram showing a configuration example of a template in the embodiment.

FIG. 3 is a view showing an example of a GUI screen when a form reading definition body is created in the embodiment.

FIG. 4 is a flowchart showing a processing procedure of the embodiment.

[Explanation of symbols]

 11 ... Form Definition File 12 ... Control Device 13 ... Main Memory 14 ... Input Device 15 ... Display Device 16 ... Field Definition Element Template File 21 ... Form Definition Tool 30 ... Form Reading Definition Body Creation Screen Main Body 31 ... Read Button 32 ... Save Button 33: Modify button 34: Definition element selection screen 35: Definition element setting screen

Claims (12)

[Claims] 1. An optical character recognition device comprising means for storing a field definition element of a form reading definition body as a template. 2. A template storage means for storing a field definition element of a form reading definition body as a template, and a graphic user for defining a field of the form reading definition body using the field definition element of the template stored in the template storage means. An optical character recognition device comprising an interface means. 3. A form reading definition file for storing a form reading definition, and a field definition element template file for storing a field definition element of the form reading definition as a template, wherein the field reading definition file is stored in the field definition element template file. An optical character recognition device, wherein the field definition element of the template is applied to a newly created form reading definition body or a field definition of a form reading definition body read from the form reading definition file. 4. A form reading definition body storing means for storing a form reading definition body, and a template storing means for storing a field definition element of the form reading definition body which is a storage target of the form reading definition body storing as a template. A template selection screen display means for displaying a list of templates stored in the template storage means in a selectable manner; and when a template to be used when creating a form reading definition body is selected on the template selection screen, Means for displaying a definition element setting screen for acquiring the definition elements of the template from the template storage means and displaying each definition element in a setting changeable manner, and a form reading screen for displaying a screen for creating a form reading definition body to which the template is applied Means for displaying a definition body creation screen; and a form reading definition body creation screen. When a field to which the field definition element of the template stored in the template storage means is applied is specified, the field includes a field definition element expanding means for reflecting the definition element of the definition element setting screen in the specified field. An optical character recognition device characterized by the above-mentioned. 5. The template storage means stores a template in which a template name is added to a field definition element of a form reading definition body in units of fields, and stores the template based on the template name stored in the template storage means. 5. The optical character recognition device according to claim 4, wherein a selection screen is generated, and the definition element setting screen is generated based on the selection contents of the template selection screen and the field definition elements stored in the template storage unit. 6. The optical character recognition apparatus according to claim 4, further comprising means for storing the definition element set on the definition element setting screen as a new or updated template in the template storage means. 7. A display means for simultaneously displaying the template selection screen and the definition element setting screen applied to the field definition on the form reading definition body creation screen on the screen for creating the form reading definition body. Optical character recognition device. 8. A processing unit for storing a form reading definition created on the form reading definition creating screen as a new or updated form reading definition in the form reading definition storing unit, and the form reading. When an arbitrary form reading definition body is designated from the form reading definition bodies stored in the definition body storing means, the specified form reading definition body is used by the form reading definition body storing means for creating the form reading definition body. 5. The optical character recognition device according to claim 4, further comprising a processing means for calling on a screen. 9. A field definition element of a form reading definition body is stored as a template, and the stored template definition element is presented so as to be applicable to an arbitrary field definition when creating the form reading definition body. A field definition method of a form reading definition body in an optical character recognition device, characterized by: 10. A form reading definition file for storing a form reading definition, and a field definition element template file for storing a field definition element of the form reading definition as a template, wherein the file is stored in the field definition element file. A field definition method of a form reading definition body applied to a form reading definition body in which a field definition element of the template is newly created or a form reading definition body read from the form reading definition body file, Using a form reading definition body saved in the form reading definition file or displaying a form reading definition body creation screen for creating a new form reading definition body in a window; List of templates C) displaying, when one of the templates displayed in the list is selected, acquiring the definition element of the selected template from the field definition element template file and displaying the window so that the setting can be changed; Reflecting the definition element of the template displayed in the window on a designated field on the form reading definition body creation screen and applying the field definition to the field definition method. . 11. A recording medium that implements a form definition body creation tool that can be read by a computer that implements an optical character recognition device, wherein a template in which a template name is added to a field definition element of a form read definition body is used as a field. A machine-readable recording medium on which a program for realizing a function of creating a field definition element template file by saving the unit is recorded. 12. A recording medium for realizing a form definition body creation tool that can be read by a computer for realizing an optical character recognition device, wherein a field definition element template file storing field definition elements of the form reading definition body as a template. And the field definition element of the template saved in the field definition element template file to a newly created form reading definition body or to define an arbitrary field of a form reading definition body to be changed and used. A machine-readable recording medium on which a program for realizing a function to be applied is recorded.