JPH1166232A - Document-defining method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable a user to define document information more easily by grouping process areas and defining the information, group by group as a time. SOLUTION: When a document image is inputted by an image input means 1 such as a scanner, an area coordinate setting part 2 sets the coordinates (area coordinate) of a processed image area. Areas with the coordinates set are grouped according to a grouping part 3 and further a document information setting part 4 sets document information on, for example, a recognition object character kind, a character string or the like. Then when the setting is completed by the operation performed so far, definition information is stored in a document definition information storage part 5, but if it is not completed, the respective processes are repeatedly performed in the order of the setting of the area coordinates until the completion of setting, and the definition information is saved in the document definition information storage part 5 last, thereby completing the definition of the document. Thus, the information defined in the document is grouped and defined at a time, so that the definition of the document which used to be very tedious and hard can be facilitated.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for recognizing a document image, and more particularly to a method for realizing a form processing system using document image recognition. Related to a form definition method for defining information of the form.

[0002]

2. Description of the Related Art With the advance of computers, OCR
The technology of document image recognition such as (optical character reading device) has been greatly advanced. As a system using this document recognition technology, a form processing system for automatically processing a fixed form such as an order form has been put to practical use. When using the form processing system, it is necessary to define in advance which area on the form is to be input with what information. Therefore, many methods have been devised so far for defining form information of a fixed form required when automatically processing the fixed form using a character recognition technique or the like. Defining the form information is a very troublesome operation, and the operation method is often difficult. Therefore, many of the methods devised are designed to make this operation easier.

For example, in a form format definition body creating apparatus described in Japanese Patent Laid-Open No. 6-96272, six digits (characters) are input in a date field and eight katakana areas are secured in a name field. By setting input information such as information on the form, the definition of the form information is simplified. However, in this method, there is a problem that it is difficult to set a complicated form, for example, when the entry column of one item extends over a plurality of lines, or when the entry column exists at a remote position.

In the screen form information definition body automatic generation processing method described in Japanese Patent Application Laid-Open No. 6-19695, when the same definition area is repeated several times, the definition is performed only by inputting that the definition area is repeated. I can do it. However, it is still not easy to define the form information even by using these methods. In the end, the form definition methods that have been devised up to now are not sufficiently effective, and the burden on the user is large. Not enough to facilitate the definition operation.

[0005]

SUMMARY OF THE INVENTION The present invention has been made in view of such circumstances, and has as its object to enable a user to more easily define form information in a form processing system.

An object of the present invention is to facilitate the definition of a form by grouping processing areas on the form in advance and defining form information collectively for each group.

A second object of the present invention is to reduce the amount of work for defining the form information by simultaneously setting the accompanying information when defining the form information. is there.

[0008] The object of the invention of claim 3 is that, in addition to the object of the invention of claim 1 or 2, the processing area setting is automated by using a table processing technique to reduce the work amount of form definition and It is to make it easier.

According to a fourth aspect of the present invention, in addition to any one of the first to third aspects of the present invention, the setting of the area for performing the grouping is automated by using an area identification technique. An object of the present invention is to reduce and facilitate the work amount of form information definition, and to realize full automation of area setting.

[0010]

According to a first aspect of the present invention, there is provided a fixed form processing system for automatically inputting form information to a fixed form, wherein a processing area of the form information is set on the form, A form definition method for defining information of each processing area on a form, comprising the steps of grouping areas and then defining and setting the form information collectively for each processing area group.

According to a second aspect of the present invention, in the form definition method according to the first aspect, when the form information is set, information associated with the information is set together with the defined information. .

According to a third aspect of the present invention, in the form definition method according to any one of the first and second aspects, a form cell and a frame are automatically extracted when the processing area of the form information is set. This is the definition method.

According to a fourth aspect of the present invention, in the form definition method according to any one of the first to third aspects, when the grouping is performed, a character area, a table area, a figure area, and the like are automatically converted from the form image. This is a form definition method for classifying and identifying information.

[0014]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG.
And 2 will be described. In FIG. 1, 1 is an image input unit, 2
Is a region coordinate setting unit, 3 is a group setting unit, 4 is a form information setting unit, 5 is a form definition information storage unit, and 6 is a form processing unit. The image input unit 1 is a unit for inputting a form image, and an image input device such as a scanner can be used.

The area coordinate setting section 2 sets an area to be processed with respect to the image input by the image input section 1. For example, when a form as shown in FIG. As in the upper left area of the address column shown in FIG. 7, the area coordinates, that is, the coordinate values of the upper left point and lower right point of the area ｛(x1, y
1)-(x2, y2)} may be set. Such an area setting is set for all areas to be processed on the form.

In the group setting section 3, the area coordinate setting section 2
For example, when a form as shown in FIG. 6 is input, as shown in FIG. 8, the areas in the address column are grouped as one group. As a grouping setting method, the grouping may be performed so as to include all the regions to be grouped.

For example, when a form as shown in FIG. 6 is input, only a numeral is entered in the number field at the lower right of the form, and the form information setting unit 4 recognizes the form when the form is read by the OCR. Set the character type to number. In addition, since the character strings to be entered are limited in the address, name, and article fields, character strings that may be input are held as a knowledge dictionary, and the type of the entry field is set. Good to put. At this time, when setting the information of the area grouped by the group setting unit 3, the same setting is made for the entire area grouped into the group. The form definition information storage unit 5 stores area definition information such as the recognition designation character type set by the form information setting unit 4.

The form processing unit 6 includes a form definition information storage unit 5
Is automatically processed using OCR or the like, based on the form definition information stored in step (1). However, since the form processing unit 6 is not necessary for specifying the present invention, it is not included in the present invention.

Next, an embodiment of the present invention will be described with reference to a flowchart of the operation shown in FIG. When a form image is input by an image input unit such as a scanner (S101), the area coordinate setting unit 2 sets the coordinates (area coordinates) of an image area to be processed (S102), and sets the area where the coordinates are set to a group setting. The group information is grouped in the section 3 (S103), and the form information setting section 4 sets form information such as a character type to be recognized and a character string (S10).
4) If the setting has been completed by the operation up to this point, the definition information is saved (S106), and if not, the above steps are repeated from the setting of the area coordinates until the setting is completed. It executes (S105), and finally saves the definition information (S106), and ends the form definition.

FIG. 3 is a flowchart for explaining an embodiment of the second aspect of the present invention, and the embodiment of the second aspect of the present invention will be described with reference to FIG. When the form image is input by an image input unit such as a scanner (S201),
The area coordinate setting unit 2 sets the coordinates (area coordinates) of the area of the image to be processed (S202), and the areas for which the coordinates are set are grouped by the group setting unit 3 (S20).
4) Further, the form information setting unit 4 sets the form information such as the character type to be recognized and the character string (S204), and sets the additional information (S205). If the setting has been completed by the operation up to this point, the form definition information is saved (S207), and if not, the above-described steps are repeatedly executed sequentially from the setting of the area coordinates until the setting is completed. (S206), and finally save the definition information (S2
07) Terminate the form definition.

The form information definition unit for implementing the embodiment of the second aspect of the invention may use the form information definition unit shown in FIG. That is, an image input unit 1, an area coordinate setting unit 2, a group setting unit 3, a form information setting unit 4, a form definition information storage unit 5, and a form processing unit 6 are used. Here, the form information setting unit 4 sets detailed information for each of the areas set by the area coordinate setting unit 2 and the group setting unit 3 and the group area. Based on the information to be performed, information accompanying the information can be set at the same time. For example, if there is a postal code entry column in the form, if the column is grouped and specified as a postal code column, the recognition designation character type is automatically set to a number or the number of recognized characters Can be set to 3 or 5.

Next, a third embodiment of the present invention will be described. FIG. 4 is a flowchart for explaining an example of the embodiment of the third aspect of the invention, and the embodiment of the third aspect of the invention will be described with reference to FIG. When the form image is input by image input means such as a scanner (S
301), a table process for automatically extracting cells and frames in the table is performed (S302), and the area coordinate setting unit 2 sets the coordinates (area coordinates) of the area of the image to be processed (S30).
3) The areas where the coordinates are set are grouped in the group setting unit 3 (S304), and the form information setting unit 4 sets the form information such as the type of character to be recognized and the character string (S305). If the setting has been completed by the above operation, the definition information is saved (S307),
If the setting is not completed, the above steps are repeated and executed sequentially from the table processing step until the setting is completed (S30).
6) Finally, the definition information is stored (S307), and the form definition is completed.

The form definition unit for implementing the embodiment of the third aspect of the present invention uses the form definition unit shown in FIG. That is, a form definition unit including an image input unit 1, an area coordinate setting unit 2, a group setting unit 3, a form information setting unit 4, a form definition information storage unit 5, and a form processing unit 6 is used. However, here, when the area coordinate setting unit 2 sets an area to be processed with respect to the image input by the image input unit 1, a table processing technique for automatically extracting cells and frames in the table is used. For example, when the form shown in FIG. 6 is input, if a table area is designated as shown in FIG. 9, the cells in the table are automatically extracted as the gray-filled area in the figure. Therefore, the area can be set as it is as a form processing area.

FIG. 5 is a flow chart for explaining an example of the embodiment of the invention of claim 4, and the embodiment of the invention of claim 4 will be described with reference to FIG. When a form image is input by an image input unit such as a scanner (S401), table processing for automatically extracting cells and frames in the table is performed (S402), and the area coordinate setting unit 2 determines the area of the image to be processed. Coordinates (area coordinates) are set (S4
03), the area where the coordinates are set is identified (S40).
4), grouped by the group setting unit 3 (S4
05) Further, the form information setting unit 4 sets the form information such as the type of character to be recognized and the character string (S406). If the setting has been completed by the above operation, the definition information is saved (S408). If not, the steps from the table processing to the above steps are repeatedly and sequentially executed until the setting is completed (S408). (S407) Finally, the definition information is saved (S408), and the definition of the form ends.

A form definition unit for carrying out the embodiment of the fourth aspect of the present invention is as shown in FIG. That is, a form definition unit including an image input unit 1, an area coordinate setting unit 2, a group setting unit 3, a form information setting unit 4, a form definition information storage unit 5, and a form processing unit 6 shown in FIG. 1 is used. However, in this case, the group setting unit 3 employs an area identification technique for automatically classifying / identifying a character area, a table area, a figure area, and the like from an image when grouping the areas set by the area coordinate setting unit 2. Used. For example, when the form shown in FIG. 6 is input,
When the area identification technique is used, the area can be automatically classified into a character area, a table area, and an enclosing area as shown in FIG. 10, so that the table area and the enclosing frame area can be used as a grouping area.

The method of the present invention can also be realized by software. When the present invention is implemented by software, as shown in FIG. 11, a CPU, a memory, a display device, a hard disk, a keyboard, a CD-R
A computer system including an OM drive, a scanner, and the like is prepared. On a computer-readable recording medium such as a CD-ROM, a program for realizing a form definition function such as setting of image area coordinates, grouping, and setting of form information of the present invention is recorded. The form image input from the image input unit such as a scanner is temporarily stored in a hard disk or the like. When the program is started, the temporarily stored form image data is read, the form definition is executed, and the processing result is output to a display or the like.

[0027]

【The invention's effect】

Effect corresponding to claim 1: Since the information defined in the form is grouped in advance and defined collectively, it is possible to easily define the form which is very troublesome and difficult. Effect corresponding to claim 2: In addition to the effect corresponding to claim 1, when defining the form information, the accompanying information is set at the same time as the information, so that the work amount of the form definition can be reduced. Effect corresponding to claim 3: In addition to the effect corresponding to claim 1 or 2, by using a table processing technique,
Since the setting of the processing area can be automated, the workload of the form definition can be reduced, and the form definition can be facilitated. Effect corresponding to claim 4: In addition to the effect corresponding to any one of claims 1, 2 and 3, since the setting of the grouping area can be automated by using the area identification technology, the work amount of the form information definition is reduced. It can be reduced and the form information definition becomes easy. Further, in the invention of claim 3, by implementing the invention of claim 4, it is possible to realize full automation of the area setting.

[Brief description of the drawings]

FIG. 1 is a block diagram for explaining a form definition unit and a form processing unit that implement the present invention.

FIG. 2 is a flowchart for explaining an embodiment of the invention of claim 1;

FIG. 3 is a flowchart for explaining an embodiment of the invention of claim 2;

FIG. 4 is a flowchart for explaining an example of an embodiment of the invention of claim 3;

FIG. 5 is a flowchart for explaining an example of the embodiment of the invention according to claim 4;

FIG. 6 is a diagram showing an example of a form processed according to the embodiment of the present invention.

FIG. 7 is a diagram for describing setting of a processing area of a form according to the embodiment of the present invention.

FIG. 8 is a diagram for explaining grouping of the processing areas according to the embodiment of the present invention.

FIG. 9 is a diagram for explaining automatic extraction of cells and frames in a table according to an embodiment of the present invention.

FIG. 10 is a diagram illustrating region identification according to an embodiment of the present invention.

FIG. 11 is a diagram illustrating an example of a computer system used when the present invention is implemented by software.

[Description of Signs] 1 ... image input unit, 2 ... region coordinate setting unit, 3 ... group setting unit, 4 ... form information setting unit, 5 ... form definition information storage unit,
6… Book mark processing unit.

Claims (4)

[Claims] In a fixed form processing system for automatically inputting form information to a fixed form, a processing area of the form information is set on a form, the processing areas are grouped, and then the form information is stored in the form. A form definition method for defining information of each processing area on a form, comprising a step of collectively defining and setting each processing area group. 2. The form definition method according to claim 1, wherein, when the form information is set, information accompanying the information is set together with the defined information. 3. The form definition method according to claim 1, wherein a cell and a frame of a table are automatically extracted when the processing area of the form information is set. Definition method. 4. The form definition method according to claim 1, wherein when performing the grouping, a character area, a table area, a figure area, and the like are automatically classified and identified from the form image. Form definition method characterized by performing.