JP2020107330A - Ledger registration device and ledger registration program - Google Patents

Abstract

To enhance security at the time of electronizing and registering information recorded in a ledger.SOLUTION: A ledger registration device is adapted to include: a ledger image acquisition unit for acquiring ledger image data by imaging each of a plurality of sheets of a ledger; an image division unit for dividing each of the ledger image data for each preset entry area of a ledger and creating a plurality of divided image data; a divided image shuffling unit for shuffling a plurality of divided image data of different entry areas so that the entry areas become irregular; a divided image transmission unit for transmitting the plurality of the shuffled divided image data to character recognition means; a divided text receiving unit for receiving divided text data that are results of character recognition of each of the divided image data; and a text integrating unit for integrating a plurality of the divided text data based on common ledger image data.SELECTED DRAWING: Figure 8

Description

The present invention relates to a form registration device used for converting information entered in a form into text and registering the program, and a program used for this device.

For example, as a system for digitizing and registering information entered in forms such as moving notices and consultation forms, as shown in Patent Document 1, the completed form is imaged and the image data is recognized by characters. There is a configuration in which a character is recognized by a means and the text data obtained by this is registered.

In such a system, when the side that registers the text data outsources the character recognition to the outside, if the image data of the form is sent to the outside as it is, personal information will be leaked.

Therefore, in the system shown in Patent Document 1, the image data of a plurality of forms is divided into items such as names and telephone numbers, and among the divided image data items having common items are shuffled in random order, The personal information is protected by transmitting it to the character recognition means.

However, even if the divided image data having common items is shuffled in this way, it is relatively easy to guess which item the transmitted divided image data belongs to. Not expensive.

JP, 2006-244315, A

Therefore, the present invention has been made to solve the above-mentioned problems, and its main problem is to strengthen the security of the information entered in the form in an electronic form and registered.

That is, the form registration apparatus according to the present invention includes a form image storage unit for storing a plurality of form image data in which a plurality of completed forms are imaged, and each of the form image data for each preset entry region of the form. An image division unit that divides the image data into a plurality of divided image data, and a divided image shuffle unit that shuffles a plurality of divided image data including divided image data in different writing areas so that at least the writing areas are out of order. Common form image data, a divided image transmission unit that transmits a plurality of shuffled divided image data to a character recognition unit, a divided text reception unit that receives divided text data that is a result of character recognition of each of the divided image data. And a text integration unit that creates a text integrated data by integrating a plurality of the divided text data based on the above.

According to the form registration apparatus configured in this way, for example, if "surname" and "first name" are set as different entry areas, the divided image data obtained by dividing the names of a plurality of persons into their surnames and given names is shuffled. It is almost impossible to guess the name of a specific person from the divided image data.
Also, for example, if you divide a telephone number or postal code into less than the actual number of digits and set them in different entry areas, those divided image data will no longer represent simple numbers, but the number of any item. I can't even guess.
As described above, according to the form registration device of the present invention, a plurality of divided image data including divided image data of different entry areas are shuffled so that at least the entry areas are out of order, and are transmitted to the character recognition means. Security can be strengthened far more than before.

The image division unit sets the file name of the divided image data to a character string including at least a unique key generated for each of the writing areas, and the divided image shuffle unit sets the divided images by the divided image transmission unit. It is preferable that the transmission order of data is determined according to a predetermined rule regarding the file name.
With such a configuration, since the unique key unique to the file name of the divided image data is included, if it is decided to transmit the divided image data in alphabetical order or numerical order of the file name, for example, a plurality of divided images can be obtained. Image data can be shuffled easily.

There is a trade-off relationship between the security enhancement and the data processing time. For example, the more shredded divided image data is, the stronger the security is. On the other hand, the time required for the data processing becomes longer.
Therefore, it is preferable that the number of forms as a source of the plurality of divided image data shuffled by the divided image shuffle unit is preset and the set number can be changed.
With such a configuration, the user can change the set number in consideration of the desired security and the desired data processing time, which is more convenient for the user.

Depending on the user, some of the items entered in the form may be arranged as not to be transmitted to the outside.
In order to make this device usable even in such a case, of the writing areas set in the form, the writing areas excluded from the transmission target of the divided image transmitting unit are accepted and the writing area is set as the non-transmission area. It is preferable to further include a non-transmission area setting unit configured as.
With such a configuration, by setting an item that cannot be transmitted to the outside as a non-transmission area, the device according to the present invention can be used for the remaining items that can be transmitted.

A data output section for outputting a plurality of text integrated data created by the text integrating section, and text extracting data for receiving the text integrated data excluded from the output target of the data output section and setting the text integrated data as non-output data It is preferable to further include a part.
With such a configuration, it is possible to extract the text integrated data that needs to be reconfirmed, for example, so that it will not be output as it is, and reconfirm it later. be able to.

Further, the form registration program according to the present invention includes a form image storage unit for storing a plurality of form image data in which a plurality of completed forms are imaged, and each of the form image data sets a preset entry area for the form. An image dividing unit that divides each image to create multiple divided image data, and a divided image shuffle unit that shuffles multiple divided image data containing divided image data in different writing areas so that at least the writing areas are in random order. A common form image; a divided image transmission unit that transmits the shuffled plurality of divided image data to a character recognition unit; a divided text reception unit that receives the divided text data that is the result of character recognition of each of the divided image data; It is characterized in that the computer is caused to exert a function as a text integration unit that creates a text integrated data by integrating a plurality of the divided text data based on the data.
The form registration program thus configured can also achieve the same effects as the form registration device described above.

According to the present invention configured as described above, the security at the time of digitizing and registering the information entered in the form can be greatly strengthened as compared with the related art.

The schematic diagram which shows the usage example of the form registration apparatus which concerns on this embodiment. The schematic diagram of the form in the same embodiment. The functional block diagram which shows the function of the form registration apparatus in the embodiment. The flowchart figure for demonstrating operation|movement of the form registration apparatus in the same embodiment. The figure explaining the template file in the embodiment. The figure explaining the reference table in the same embodiment. The figure explaining the function of the image division part in the embodiment. The figure explaining the function of the division image shuffle part in the same embodiment. The functional block diagram which shows the function of the form registration apparatus in other embodiment.

A form registration device according to an embodiment of the present invention will be described with reference to the drawings.

The form registration device 1 of the present embodiment is used to digitize and register the information entered in the form P, and as shown in FIG. 1, image recognition means 2 such as a scanner or character recognition such as OCR. The form registration system X is constructed together with the means 3.

First, the form P will be briefly described with reference to FIG.
The form P is an entry sheet provided with entry fields P1 for each of a plurality of entry items. The entry items are “name”, “date of birth”, “address”, “telephone number”, “sex” and the like. The entry field P1 is surrounded by a frame line here. For example, like the entry field P1 for the entry item "sex", one entry area P2 is provided, or the entry field P1 is called "name". Some of them are subdivided into a plurality of entry areas P2, such as a "surname" entry area P2 and a "first name" entry area P2 for entry items. That is, in the entry field P1, one or a plurality of entry areas P2 are set in advance.

Next, the form registration device 1 will be described.
The form registration device 1 is a dedicated or general-purpose computer including a CPU, a memory, an input/output interface, etc., and causes a CPU and other peripheral devices to cooperate in accordance with a form registration program stored in the memory. Thus, as shown in FIG. 3, the template storage unit 11, the form image storage unit 12, the file name changing unit 13, the reference table creating unit 15, the image dividing unit 16, the divided image shuffle unit 18, the divided image transmitting unit 20, and the dividing unit. The text reception unit 21 and the text integration unit 23 are configured to perform their functions.

Hereinafter, the operations up to the registration of information by the form registration system X using the form registration apparatus 1 will be described with reference to the functional block diagram of FIG. 3 and the flowchart of FIG. The various image data described below may be image data or data obtained by converting the image data into a character string.

First, as shown in FIG. 5, the user creates a template file including a position of the entry area P2 provided in the form P and a plurality of template information in which at least item names for the entry area P2 are linked ( S1).

Specifically, the entry area P2 set in the form P is selected using an input means such as a mouse, a keyboard, or a touch panel, and the item name for the entry area P2 is entered. As a result, the coordinates indicating the position of the entry area P2 and the item name are linked as template information, and the template information is stored in the template storage unit 11 set in a predetermined area of the hard disk of the apparatus 1. As the template information, in addition to the coordinates and item names of the writing area P2, for example, the type of characters (for example, numbers, alphabets, etc.) written in the writing area P2, the number of lines in the writing area P2, and the like regarding the writing area P2 are added. You may combine information. The template storage unit 11 may be set in an auxiliary storage device such as SSD.

On the other hand, the plurality of completed forms P are imaged by using the image pickup means 2 such as a scanner (S2). Then, the image data of the form is input to the apparatus 1, and the form image data for a plurality of sheets is stored in the form image storage unit 12 set in a predetermined area of the hard disk of the apparatus 1. The form image storage unit 12 may be set in an auxiliary storage device such as SSD.

Next, the file name changing unit 13 makes the file names of the form image data stored in the form image storage unit 12 unique to different unique file names (S3).

Specifically, the file name changing unit 13 sequentially acquires the form image data from the form image storage unit 12 and generates a first unique key composed of a plurality of character strings and different for each form image data. To do. The file name after uniqueness is obtained by adding the generated first unique key to the front of the file name when the form image data is acquired. For example, if the file name of the acquired form image data is abc and the first unique key generated for this form image data is 3f2504E0, the file name after uniqueization will be 3f2504E0.abc. The form image data having the unique file name is stored in the unique file storage unit 14 set in a predetermined area of the hard disk of the apparatus 1. The unique file storage unit 14 may be set in an auxiliary storage device such as SSD.
Note that the method of making the file name unique is not limited to the one described above, and for example, the file name obtained when the form image data is acquired is replaced with the generated first unique key, and the file name after making unique is used. , May be changed as appropriate.

Subsequently, the reference table creation unit 15 associates the file name after uniqueization, the item name included in the template information, and the second unique key generated for each item name, as shown in FIG. A reference table is created (S4). The reference table creation unit 15 is a function exerted by the on-memory. However, the function as the reference table creation unit 15 may be exhibited by a technique such as an on-memory database or a virtual drive.

Specifically, the reference table creation unit 15 refers to a plurality of item names stored in the template storage unit 11 as template information, and includes a plurality of character strings for each of the item names, which are different from each other. Generate a unique key for.

A file name after one form image data is made unique, that is, a file name including the first unique key, a plurality of item names, and a second unique key generated for each item name. Tie together. The reference table may be further linked with the additional information included in the template information.

The reference table creating unit 15 sequentially performs the above-described operation on the form image data for a preset number of sheets. As a result, the reference table creation unit 15 creates the first reference table by the number of item names stored in the template storage unit 11 (the number of items) when creating a single reference table. Will generate 2 unique keys.
The set number can be changed. Specifically, when the user inputs the set number using an input means such as a keyboard, the set number changing unit (not shown) accepts the input value and the set number is changed. It

After that, the image dividing unit 16 acquires the form image data from the unique file storage unit 14, and divides the form image data into the entry areas P2 to create divided image data as shown in FIG. 7 (S5). .. The image division unit 16 has a function to be exerted by an on-memory. However, the function as the image dividing unit 16 may be exhibited by a technique such as an on-memory database or a virtual drive.

Specifically, the image division unit 16 refers to the template storage unit 11, acquires the coordinates of the writing area P2 corresponding to each item name, and divides the form image data for each writing area P2 represented by those coordinates. To do.

Then, the image dividing unit 16 refers to the reference table and, as shown in FIG. 7, sets the second unique key associated with each item name as the file name of each divided image data. It should be noted that the file name of the divided data does not necessarily have to include only the second unique key. For example, if the file name includes at least the second unique key, another character string is added after the second unique key. May be added.

The image dividing unit 16 divides the form image data into the set number of form image data. As a result, the number of pieces of divided image data is generated by multiplying the above-mentioned set number by the number of item names (the number of items) stored in the template storage unit 11. Then, these file names include the second unique keys different from each other, and all have different unique file names.

Then, these divided image data include a plurality of divided image data of the writing areas P2 different from each other.
More specifically, for example, when the template file described above is created, if the “surname” and “first name” of the form P are set as different entry areas P2, a plurality of divided image data created by the image dividing unit 16 will be described. In this case, the divided image data of the "surname" written in the set number of forms P and the divided image data of the "first name" written in the set number of forms P are mixed.
Although different from FIG. 7, if each digit of the postal code or each digit of the telephone number is set as a different writing area P2, for example, a plurality of divided image data created by the image dividing unit 16 will be displayed. The divided image data of each digit of the postal code and each digit of the telephone number written in the set number of sheets P are mixed in the inside.
However, the setting method of the entry area P2 is not limited to the above-described mode, and the user may change it appropriately.

Then, these divided image data are stored in the divided image storage unit 17 set in a predetermined area of the hard disk of the apparatus 1. The divided image storage unit 17 may be set in an auxiliary storage device such as SSD.

Next, as shown in FIG. 8, the divided image shuffle unit 18 shuffles the plurality of divided image data stored in the divided image storage unit 17 so that at least the writing area P2 is out of order (S6).

Specifically, the divided image shuffle unit 18 determines the transmission order of the divided image data by the divided image transmission unit 20 described later according to a predetermined rule regarding the file name of the divided image data, so that the divided image data to be transmitted is The writing area P2 is irregular.

The predetermined rule may be, for example, an alphabetical order, a numerical order, or an order in which these are combined. The divided image shuffle unit 18 stores the divided image data in the divided image storage unit in this predetermined order. It acquires sequentially from 17 and arranges.

It should be noted that the divided image shuffle unit 18 here refers to the above-mentioned reference table and the additional information associated with the second unique key used in the file name of the divided image data acquired from the divided image storage unit 17. Is attached to the divided image data. As a result, the character recognition unit 3 described later can perform character recognition using this additional information.

Then, in this embodiment, in order to suppress the amount of data transmitted at one time by the divided image transmission unit 20 described later, the divided image shuffle unit 18 has a predetermined number of divided images continuously acquired from the divided image storage unit 17. The data is collected as one transmission data group.

After that, it is determined whether all the divided image data stored in the divided image storage unit 17, that is, all the divided image data of the number obtained by multiplying the set number of sheets by the number of items are acquired and shuffled by the divided image shuffle unit 18. It is determined (S7).

If all the divided image data stored in the divided image storage unit 17 have not been shuffled, the operation by the divided image shuffle unit 18 is repeated.
On the other hand, when all of the divided image data stored in the divided image storage unit 17 is shuffled, the reference table created by the reference table creation unit 15 described above is deleted from the on-memory, and the hard disk of the device 1 is predetermined. The data is stored in the reference table storage unit 19 set in the area (S8). The reference table storage unit 9 may be set in an auxiliary storage device such as SSD.

When the reference table is deleted from the on-memory, it is next determined whether the form image data stored in the form image storage unit 12 remains (S9).

When the form image data remains in the form image storage unit 12, the operations from S3 to S9 are repeated.
On the other hand, when the form image data stored in the form image storage unit 12 no longer exists, the divided image transmission unit 20 transmits the shuffled divided image data to the character recognition unit 3 here for each transmission data group. (S10). Since the character recognition means 3 is outside the device 1 and is operated by a person other than the user of the device 1, the divided image transmission unit 20 outputs the divided image data to the outside of the device 1. Will be done.

The character recognition unit 3 character-recognizes each of the divided image data transmitted by the divided image transmitting unit 20, and creates the divided text data which is the result obtained by this (S11). Here, the character recognition means 3 is configured to inherit the file name of the divided image data, that is, the second unique key as the file name of the divided text data, and the divided text data created in this way is It is input to the device 1 from the character recognition means 3.

The input fragment text data is accepted by the fragment text accepting unit 21 of the device 1 and stored in the fragment text storage unit 22 set in a predetermined area of the hard disk of the device 1 (S12). The divided text storage unit 22 may be set in an auxiliary storage device such as SSD.

After that, the text integration unit 23 integrates a plurality of pieces of divided text data based on common form image data among the plurality of pieces of divided text data to create text integrated data (S13).

Specifically, the text integration unit 23 refers to the reference table stored in the reference table storage unit 19 described above, and stores the form image data linked to the second unique key used in the file name of the divided text data. The file name (first unique key) is specified, and the divided text data having the common file name (first unique key) is specified as the one based on the common form image data.

Then, after all the divided text data based on the common form image data is specified, the reference table is referred to again, and the item name linked to the second unique key used for the file name of each divided text data. Is specified, and the character string indicated by each piece of divided text data is recognized as the character string entered as the specified item name.

Here, the text integration unit 23 creates the text integration data, and then displays the character string indicated by each piece of the divided text data forming the text integration data on the display.

Specifically, the text integration unit 23 acquires the form image data that is the source of the divided text data from the unique file storage unit 14, and can compare the image of the source form and the character string indicated by the divided text data. indicate.
Instead of obtaining the form image data from the unique file storage unit 14, or in addition to obtaining the form image data, the divided image data corresponding to the divided text data is obtained from the divided image storage unit 17, and the character string thereof is acquired. Alternatively, the divided images may be displayed in a comparable manner.

Here, the device 1 is configured to be able to modify the character string indicated by the fragment text data.
For example, when the character string displayed by the text integration unit 23 includes a character string created by the erroneous recognition of the character recognition unit 3, the character string is displayed by using an input unit such as a mouse, a keyboard, or a touch panel. The character string can be modified, and the modified character string is updated as the character string indicated by the fragment text data.

The text integrated data created by the text integrating unit 23 as described above can be output by the data output unit 24.

The data output unit 24 outputs the text integrated data in a predetermined output format. Here, for example, the text integrated data for a plurality of forms are collectively processed, for example, a character string indicated by the divided text data and the divided text data. The item name corresponding to is output in a table format or the like so as to be distinguishable (S14).

The device 1 receives the text integrated data excluded from the output target of the data output unit 24 among the plurality of text integrated data created by the text integrating unit 23, and sets the text integrated data as non-output data. The function as the unit 25 is further provided.

More specifically, for example, in the text integrated data displayed on the display by the text integration unit 23, reconfirmation is required when, for example, the written handwritten character itself cannot be read or gender is selected for both genders. With respect to the required text integrated data, the text integrated data can be selected by, for example, a mouse or a touch panel.

As a result, the selected text integrated data is accepted by the data extracting unit 25, set as non-output data, and excluded from the batch output target of the data output unit 24. Note that various comments such as the reason for reconfirmation may be entered on the set non-output data.

According to the form registration apparatus 1 configured as described above, for example, the divided image data obtained by dividing the names of a plurality of people into the surname and the given name is shuffled. Therefore, for example, the name of a specific person is inferred from the divided image data. It is almost impossible to do.
Also, for example, if you shuffle the divided image data obtained by dividing the telephone number or zip code into a smaller number of digits than the actual number of digits, those divided image data will no longer represent mere numbers, and the number of any item It's difficult to guess if there was any.
As described above, according to the form registration device 1 of the present invention, a plurality of pieces of divided image data in different entry areas P2 are shuffled so that the entry areas P2 are out of order, and are transmitted to the character recognition means 3. Can be strengthened much more than before.

Furthermore, since the second unique key is used for the file name of the divided image data, the divided image data can be easily arranged by arranging the divided image data so that the file names are in alphabetical order or numerical order. You can shuffle.

In addition, since the set number of sheets of the form P that is the source of the plurality of shuffled divided image data can be changed, the user can change the set number of sheets in consideration of the desired high security and the data processing time. This makes it easier for users to use.

In addition, since the text data extracting unit 25 sets as the text integrated data non-output data to be excluded from the output target of the data output unit 24, the text integrated data that needs to be reconfirmed, You can remove it so that it is not output as it is, and you can check it again later.

The present invention is not limited to the above embodiment.

For example, some users may have agreed that some of the items written on the form P should not be transmitted to the outside.

Therefore, as shown in FIG. 9, the form registration apparatus 1 accepts an entry region P2, which is excluded from the transmission target of the divided image transmission unit 20, among the entry regions P2 set in the form P, and sets the entry region P2 as the entry region P2. A non-transmission area setting unit 26 that is set as a non-transmission area may be further provided.

Specifically, for example, when an item name is input in a predetermined mode when creating a template file, the non-transmission area setting unit 26 sets the entry area P2 linked to the item name input in that mode in the non-transmission area. Set as. The predetermined mode may be, for example, a method of inputting a predetermined character before, after, or before and after the item name, and the like.
Further, as a method of setting the non-transmission area, a desired area can be selected from, for example, a check box or the like among various entry areas P2 included in the template file, and the entry area P2 selected by the user is not transmitted. It may be set as an area.

Then, the template file in which one or more entry areas P2 are set as non-transmission areas may be output from the template storage unit 11 to the text integration unit 23.
With such a configuration, the operator can input and add the character string of the non-transmission area to the text integrated data created by the text integrating unit 23.
As a result, the character strings entered in areas other than the non-send area are automatically included in the text integrated data, and the character strings entered in the non-send area are manually output to the text integrated data without being output to the outside. Can be included.

With such a configuration, by setting an item that cannot be transmitted to the outside as a non-transmission area, it is possible to use the form registration device 1 according to the present invention for the remaining items that can be transmitted while following the agreement. ..

In the above-described configuration, the image dividing unit 16 may or may not create the divided image data of the non-transmission area set by the non-transmission area setting unit 26. When the divided image data of the non-transmission area is created, the divided data shuffle unit may be configured not to acquire the divided image data of the non-transmission area from the divided image storage unit 17.

When the non-transmission area is set as described above, the text integration data created and displayed by the text integration unit 23 is set not only in the entry area P2 set in the non-transmission area but also in the non-transmission area. An unfilled entry area P2, which has not been entered, is also in a blank state.
Therefore, it is preferable that the text integration unit 23 displays the entry area P2 set as the non-transmission area so as to be distinguishable from the other entry areas P2. Specifically, the color of the entry area P2 is changed or the entry area P2 is changed. A display mode such as attaching an identification character to the inside or outside of P2 may be mentioned.

Further, the text integration unit 23 may be configured to filter the entry area P2 set as the non-transmission area and display and output it.
In this case, the user can input character strings one after another in the non-transmission area that is displayed after filtering, so that the work efficiency can be improved even in the configuration in which the non-transmission area is set.

In addition, the divided image transmission unit 20 of the above-described embodiment transmits the divided image data to the character recognition unit 3 in units of the transmission data group generated by the divided image shuffle unit 18, but the divided image data is sent one by one. It may be transmitted, or may be transmitted all at once.

In addition, various modifications and combinations of the embodiments may be made without departing from the spirit of the present invention.

X ... form registration system 2 ... imaging means 3 ... character recognition means 1 ... form registration device P ... form P1 ... entry field P2 ... entry area 11 ... template storage Part 12... form image storage part 13... file name changing part 14... unique file storage part 15... reference table creating part 16... image dividing part 17... divided image storing part 18 .. Split image shuffle unit 19... Reference table storage unit 20... Split image transmission unit 21... Split text reception unit 22... Split text storage unit 23... Text integration unit 24... Data Output unit 25 ・・・Data extraction unit 26 ・・・Non-transmission area setting unit

Claims (6)

A form image storage unit for storing a plurality of form image data in which a plurality of completed forms are imaged,
An image dividing unit that divides each of the form image data for each preset entry area of the form to create a plurality of divided image data,
A divided image shuffle section that shuffles a plurality of divided image data including divided image data of different entry areas so that at least the entry areas are in no particular order,
A divided image transmitting unit for transmitting the shuffled plurality of divided image data to the character recognition means,
A divided text receiving unit that receives the divided text data that is the result of character recognition of each of the divided image data,
A form registration device comprising: a text integration unit that creates a text integrated data by integrating a plurality of the divided text data based on common form image data. The image dividing unit sets the file name of the divided image data to a character string including at least a unique key generated for each of the writing areas,
The form registration apparatus according to claim 1, wherein the divided image shuffle unit determines the transmission order of the divided image data by the divided image transmission unit according to a predetermined rule regarding the file name. 3. The form according to claim 1 or 2, wherein the number of forms as a source of a plurality of divided image data shuffled by the divided image shuffle unit is set in advance, and the set number can be changed. Registration device. It further comprises a non-transmission area setting unit that accepts, from among the input areas set in the form, the input areas excluded from the transmission target of the divided image transmission unit and sets the input area as a non-transmission area. The form registration device according to any one of items 1 to 3. A data output unit for outputting a plurality of text integrated data created by the text integrating unit in a predetermined output format,
5. The data extracting unit that receives text integrated data to be excluded from the output target of the data output unit, and sets the text integrated data as non-output data. Form registration device described in. A form image storage unit for storing a plurality of form image data in which a plurality of completed forms are imaged,
An image dividing unit that divides each of the form image data for each preset entry area of the form to create a plurality of divided image data,
A divided image shuffle section that shuffles a plurality of divided image data including divided image data of different entry areas so that at least the entry areas are in no particular order,
A divided image transmitting unit for transmitting the shuffled plurality of divided image data to the character recognition means,
A divided text receiving unit that receives the divided text data that is the result of character recognition of each of the divided image data,
A program for registering a form, which causes a computer to exert a function as a text integration unit that creates a text integrated data by integrating a plurality of the divided text data based on common form image data.