JP7201545B2 - FORM PROCESSING PROGRAM, FORM PROCESSING METHOD, AND FORM PROCESSING APPARATUS - Google Patents

Description

The present invention relates to a form processing program, a form processing method, and a form processing apparatus.

2. Description of the Related Art Conventionally, a system including a form processing apparatus is known as one of systems for handling forms. For example, the form processing apparatus performs character recognition on an optically read form image, and obtains (extracts) necessary information from the form image based on definition information registered in advance in a definition format. ).

As another system for handling forms, a system including a form registration support device is also known (see, for example, Japanese Unexamined Patent Application Publication No. 2002-100001).

JP 2003-208565 A

In a system including a form processing apparatus, it is necessary to register the definition information of the forms to be handled in advance in the definition body. For example, bank transfer request forms are created individually by receiving institutions (consignees), so there are many types of bank transfer request forms, and all types of definition information are registered in the definition body. It is not easy.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a technique capable of reducing the work of registering form definition information.

One aspect of the program is a form processing program that generates characteristic information of an image of a form that includes a character string without a corresponding It is determined whether or not definition information including feature information is registered in the definition body, and if it is determined that the definition information including the same or similar feature information is not registered in the definition body, the non-heading character Receiving input of a column, acquiring coordinates indicating an area of the accepted non-heading character string in the image of the form, generating the characteristic information, the accepted non-heading character string, and the acquired non-heading character When it is determined that the definition information including the coordinates indicating the column area is registered in the definition body as the definition information of the form, and the definition information including the same or similar feature information is registered in the definition body. (b) causing a computer to execute a process of obtaining a headline-less character string included in the definition information including the same or similar feature information, and the process of obtaining the headline-less character string is the same or similar When multiple definition information including feature information are registered in the definition body, for each definition information including the same or similar feature information, a character string without a heading included in the definition information and Determining whether or not the result of character recognition for the area of the image of the form corresponding to the coordinates indicating the area of the contained character string without heading matches, and acquiring the character string without heading when both match. do .

One aspect of the method is a form processing method in which feature information of an image of a form including a headline-less character string, which is a character string without a corresponding headline character string, is generated, and a character string identical or similar to the generated feature information is generated. It is determined whether or not definition information including feature information is registered in the definition body, and if it is determined that the definition information including the same or similar feature information is not registered in the definition body, the non-heading character Receiving input of a column, acquiring coordinates indicating an area of the accepted non-heading character string in the image of the form, generating the characteristic information, the accepted non-heading character string, and the acquired non-heading character When it is determined that the definition information including the coordinates indicating the column area is registered in the definition body as the definition information of the form, and the definition information including the same or similar feature information is registered in the definition body. (b) a headline-less character string included in the definition information containing the same or similar feature information; When a plurality of pieces of information are registered in the definition body, for each definition information containing the same or similar feature information, a non-heading character string included in the definition information and the non-heading character included in the definition information It is determined whether or not the result of character recognition for the area of the image of the form corresponding to the coordinates indicating the column area matches, and the headline-less character string is obtained when both match .

One aspect of the apparatus is a form processing apparatus, comprising: a generating unit for generating feature information of an image of a form including a character string without a corresponding heading character string; a determination unit for determining whether or not definition information including the same or similar feature information as the feature information is registered in the definition body, and the determination unit determines whether the definition information including the same or similar feature information is registered in the definition body. a coordinate acquisition unit that acquires coordinates indicating an area of the accepted non-heading character string in the image of the form when it is determined that the non-heading character string is not registered in the definition information including the feature information generated by the generation unit, the accepted character string without headings, and the coordinates indicating the area of the character string without headings obtained by the coordinate obtaining unit; a registration unit for registering information in the definition body; a headline-less character string acquisition unit that acquires a headline-less character string included in the headline-less character string , wherein the processing for acquiring the headline-less character string includes the definition information including the same or similar characteristic information that is obtained from the definition body. indicates, for each definition information containing the same or similar feature information, a non-heading character string included in the definition information and an area of the non-heading character string included in the definition information, when multiple registrations are made in It is determined whether or not the result of character recognition for the area of the image of the form corresponding to the coordinates matches, and the headline-less character string is acquired when both match .

According to the present invention, it is possible to reduce the work of registering the definition information of a form.

1 is a diagram illustrating the configuration of a form processing system; FIG. 1 is a diagram illustrating a functional configuration of a form processing apparatus according to an embodiment; FIG. 6 is a flowchart illustrating form processing according to an embodiment; FIG. 10 is a diagram schematically showing an example of an image of a form acquired in the process of S1; FIG. 9 is a flowchart illustrating details of processing in S2. FIG. 10 is a diagram schematically showing a specific example of processing of S21 and S22; FIG. 10 is a flowchart illustrating details of the process of S25; FIG. It is a figure which shows typically the specific example of the process of S25. 9 is a flowchart illustrating details of processing in S5. FIG. 10 is a diagram schematically showing a specific example of processing in S52; It is a figure which illustrates the hardware constitutions of a computer.

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram illustrating the configuration of a form processing system.

A form processing system 1 illustrated in FIG. 1 is a system that handles a form including no-header character strings (character strings without corresponding headline character strings). The form processing system 1 includes a form processing device 2 , a scanner device 3 , an input device 4 , a display device 5 and a server device 6 .

The form processing device 2 performs character recognition on the form image, registers the definition information of the form in the definition body held by the server device 6, and extracts from the form image based on the registered definition information of the form. It is a device that acquires (extracts) necessary information. The form processing device 2 acquires the image of the form from the scanner device 3, for example. The scanner device 3 is a device that converts a paper medium such as a form into digital data (image).

The input device 4 is a device for inputting various information to the form processing device 2 . The input device 4 is, for example, a keyboard device. The display device 5 is a device for displaying various types of information such as the contents of the processing performed by the form processing device 2, the results of the processing, the information input by the input device 4, the image of the form, and the like. The display device 5 is, for example, a liquid crystal display.

The server device 6 is a device that holds a character recognition dictionary that the form processing device 2 refers to and a definition body that the form processing device 2 refers to or registers definition information. The server device 6 is communicably connected to the form processing device 2 via the network 7 .

FIG. 2 is a diagram illustrating the functional configuration of the form processing apparatus according to one embodiment.
As illustrated in FIG. 2, the form processing apparatus 2 includes a scanner control unit 210, a character recognition unit 220, a characteristic information generation unit 230, a determination unit 240, a no-index character string acquisition unit 250, and a coordinate acquisition unit. 260 , a registration unit 270 , a display control unit 280 and a main control unit 290 . The form processing device 2 also includes a storage unit (not shown).

The scanner control unit 210 controls processing for obtaining an image of a form from the scanner device 3 .
The character recognition unit 220 refers to the character recognition dictionary 610 held by the server device 6 to recognize characters included in the image of the form. The character recognition unit 220 also recognizes characters included in the form image based on definition information registered in the definition body 620 held by the server device 6 .

The feature information generation unit 230 generates feature information of the image of the form. For example, as the feature information, information indicating the feature of distribution of line segments in the image of the form is generated. The generation of information indicating the distribution characteristics of such line segments is performed, for example, using the technique described in the patent application of Japanese Patent Application No. 2018-138117 filed by the applicant of the present application.

The determination unit 240 determines whether definition information including feature information identical or similar to the feature information generated by the feature information generation unit 230 is registered in the definition body 620 held by the server device 6 .

When the determination unit 240 determines that definition information including feature information identical or similar to the feature information generated by the feature information generation unit 230 is registered in the definition body 620, the headline-less character string acquisition unit 250 , to get the heading-less character string included in the definition information. However, if a plurality of definition information including feature information identical or similar to the feature information generated by the feature information generation unit 230 are registered in the definition body 620, each definition information has a headline included in the definition information. Determines whether or not the non-heading character string matches the result of character recognition for the area of the image of the form corresponding to the coordinates indicating the area of the non-heading character string included in the definition information, and if both match. Get the no-header string. Note that character recognition at this time is performed by the character recognition unit 220 .

The coordinate acquisition unit 260 acquires the coordinates indicating the character string area in the form image. For example, the coordinate acquisition unit 260 determines by the determination unit 240 that definition information including feature information identical or similar to the feature information generated by the feature information generation unit 230 is not registered in the definition body 620, and the input device 4 When a character string without heading is input by , the coordinates indicating the area of the character string without heading in the image of the form are obtained.

The registration unit 270 registers the definition information of the form in the definition body 620 held by the server device 6 . For example, if the determination unit 240 determines that definition information including feature information that is the same as or similar to the feature information generated by the feature information generation unit 230 is not registered in the definition body 620, the registration unit 270 registers the feature information. Register definition information including the feature information generated by the information generation unit 230, the character string without index input by the input device 4, and the coordinates indicating the area of the character string without index obtained by the coordinate acquisition unit 260. .

The display control section 280 controls the display of the display device 5 . For example, the display control unit 280 generates screen data including the result of processing the image of the form, and causes the display device 5 to display the screen data.

The main control unit 290 includes the scanner control unit 210, the character recognition unit 220, the characteristic information generation unit 230, the determination unit 240, the no-index character string acquisition unit 250, the coordinate acquisition unit 260, the registration unit 270, and the display control unit 280. It controls a series of processes that work together.

FIG. 3 is a flowchart illustrating form processing according to one embodiment.
When starting the form processing, the form processing apparatus 2 first acquires an image of the form as illustrated in FIG. 3 (S1). The processing of S1 is performed by the scanner control unit 210 . Note that the image of the form acquired in the process of S1 is the image of the form in which necessary items have been entered or printed.

Next, the form processing device 2 performs recognition processing for recognizing (obtaining) necessary information from the image of the form, and causes the display device 5 to display the processing result (S2). The process of S2 is performed by the character recognition unit 220, the feature information generation unit 230, the determination unit 240, the headline-less character string acquisition unit 250, and the display control unit 280 in cooperation. Details of the processing of S2 will be described later with reference to FIG.

Next, the form processing device 2 receives the operator's correction input for the processing result displayed on the display device 5 (S3). The processing of S<b>3 is performed by the main control unit 290 via the input device 4 . The correction input by the operator is the input of only the headline-less character string, or the input of the coordinates indicating the area of the headline-less character string and the headline-less character string. Such correction input by the operator is performed when the coordinates indicating the area of the non-heading character string and the non-heading character string are not recognized (acquired) in the processing result displayed on the display device 5 by the processing of S2. done.

Next, the form processing apparatus 2 determines whether or not the operator has made a correction input (S4). The processing of S4 is performed by the main control unit 290 .

If the determination result in S4 is YES, the form processing device 2 registers the definition information including the input non-heading character string in the definition body 620 held by the server device 6 (S5), and ends the form processing. The processing of S5 is performed by the registration unit 270 . Details of the processing of S5 will be described later with reference to FIG.

On the other hand, if the determination result in S4 is NO, the form processing device 2 ends the form processing.
FIG. 4 is a diagram schematically showing an example of the image of the form acquired in the process of S1.

An image 8 of a form schematically shown in FIG. 4 is an image of an account transfer request form, and includes "Fujitsu Gas" as a character string indicating the name of the consignee. This is an image of a form that does not contain a headline character string (that is, an image of a form that contains a headline-less character string (“Fujitsu Gas”)). Note that the headline character string is also a character string indicating the item name.

FIG. 5 is a flowchart illustrating details of the processing of S2.
As exemplified in FIG. 5, when the process of S2 is started, first, the feature information generation unit 230 generates feature information of the image of the form described in Japanese Patent Application No. 2018-138117 filed by the applicant of the present application. information (hash value in the horizontal direction and hash value in the vertical direction) indicating the characteristics of the distribution of line segments in the form image is generated (S21).

Next, the determination unit 240 refers to the definition body 620 held by the server device 6, searches for definition information including a hash value that is the same as or similar to the generated hash value (S22). It is determined whether definition information including a hash value is registered in the definition body 620 (S23). Here, the similar hash value is, for example, a hash value in which the absolute values of digit-by-digit differences from the generated hash value are all equal to or less than a threshold.

If the determination result of S23 is YES, the determination unit 240 determines whether or not multiple pieces of definition information including the same or similar hash value are registered in the definition body 620 (S24). Note that even if the definition information of different types of forms has the same or similar characteristics of the distribution of line segments included in the forms, the definition information includes the same or similar hash values.

If the determination result in S24 is YES, the headline-less character string acquisition unit 250 narrows down the definition information including the same or similar hash value (S25). Details of the processing of S25 will be described later with reference to FIG.

After S25, the non-heading character string acquisition unit 250 acquires the non-heading character string and the coordinates indicating the area of the non-heading character string, which are included in the narrowed down definition information, and the character recognition unit 220 acquires the Acquire the coordinates indicating the area of the content of each item in the form, and recognize the characters included in the area of the image of the form corresponding to the coordinates, and the character indicating the content of each item. The columns are acquired, and the display control unit 280 causes the display device 5 to display the acquired results (S26). As a result, the display device 5 displays a character string without heading, the coordinates indicating the area of the character string without heading, the character string indicating the content of each item, and the coordinates indicating the area of the character string indicating the content of each item (each item (coordinates indicating the area of the contents of the

On the other hand, if the determination result in S24 is NO, the same processing as in S26 described above is performed based on the definition information including the hash value that is the same as or similar to the generated hash value.

If the determination result in S23 is NO, the character recognition unit 220 performs keyword recognition on the image of the form, acquires a keyword (character string) indicating the item name, and obtains a character string indicating the content of the keyword. , the coordinate acquisition unit 260 acquires the coordinates indicating the area of the character string indicating the content of the keyword, and the display control unit 280 causes the display device 5 to display the acquisition results (S27). As a result, the display device 5 displays the character string indicating the contents of the keyword indicating the item name, the coordinates indicating the area of the character string, and the like.

In the process of S27, it is not possible to obtain a character string without a headline by keyword recognition, so it is not possible to obtain the coordinates indicating the area of the character string without a headline. Therefore, the display of the coordinates indicating the area of the non-heading character string and the non-heading character string is not performed. Therefore, in the subsequent processing of S3, it is necessary for the operator to input a headline-less character string or to input a coordinate indicating an area of the headline-less character string and the headline-less character string by corrective input by the operator.

In the process of S27, the character recognition unit 220 performs keyword recognition by referring to the character recognition dictionary 610 held by the server device 6, for example. In this case, the character recognition dictionary 610 includes, for example, a keyword dictionary in which character strings that can be keywords indicating item names are registered. Keyword recognition is performed, for example, using existing technology.

FIG. 6 is a diagram schematically showing a specific example of the processing of S21 and S22.
In the specific example schematically shown in FIG. 6, it is assumed that the form image 8 schematically shown in FIG. 4 has been acquired as the form image.

In this case, in the processing of S21, for example, as schematically shown in FIG. A hash value of the direction ("1235") is generated. Note that in this example, each digit of the hash value is represented by a hexadecimal number. Further, in the process of S22, for example, as schematically shown in FIG. is searched for.

In (b) of FIG. 6, each definition information registered in the definition body 620 includes an index (“Index”), a horizontal hash value (“Hash”), a vertical hash value (“Hash (vertical)”), “consignor name”, “consignor name coordinates”, item names (not shown), and information on the coordinates indicating the area of the character string indicating the contents of the item names. In this example, the "consignor name coordinates" are displayed by the coordinates of the two diagonal points of the rectangular area containing the character string indicating the "consignor name".

In this specific example, if the similar hash value is a hash value in which the absolute value of the difference in each digit from the generated hash value is all 1 or less, the definition information with the indexes "1" and "2" is The definition information includes a hash value that is the same as or similar to the generated hash value.

The reason why not only the definition information containing the same hash value as the generated hash value, but also the definition information containing a similar hash value is searched is that noise (dirt, dust, etc.) on the form, written characters, etc. This is because the same type of forms may not have the same hash value. Therefore, even definition information including a hash value in such a case can be searched without omission by allowing a certain amount of error in the search.

FIG. 7 is a flowchart illustrating details of the processing of S25.
As exemplified in FIG. 7, when the process of S25 is started, each definition information containing a hash value that is the same as or similar to the generated hash value registered in the definition body 620 held by the server device 6 , S251 to S253 are repeated.

Specifically, first, the headline-less character string acquisition unit 250 selects one of the non-processing definition information (definition information including a hash value that is the same as or similar to the generated hash value) as a processing target, The headline-less character string and the coordinates indicating the region of the headline-less character string are obtained from the definition information (S251).

Next, the character recognition unit 220 recognizes characters included in the area of the form image corresponding to the acquired coordinates indicating the area of the character string without heading (S252).

Next, the headline-less character string acquisition unit 250 determines whether or not the acquired headline-less character string matches the recognition result of the character recognition unit 220 (S253).

If the determination result in S253 is YES, although illustration is omitted, the headline-less character string acquisition unit 250 determines the definition information to be processed as the narrowed down definition information. Note that if the determination result of S253 is YES, the processing of S25 ends even if definition information that is not to be processed remains.

On the other hand, if the determination result of S253 is NO, the processing from S251 onwards is started again only when definition information that is not subject to processing remains.

FIG. 8 is a diagram schematically showing a specific example of the process of S25.
In the specific example schematically shown in FIG. 8, the definition information including the hash value identical or similar to the generated hash value has the index "1 ” and “2”.

In this case, first, as schematically shown in FIG. 8A, the definition information with the index "1" is processed, and the processing of S251 to S253 is performed. character string (“Fujitsu Electric”) indicating the name of the consignor, and the coordinates of the consignor name (“(x1, y1, x2, y2)”), which are the coordinates indicating the area of the character string without headings. The recognition result ("-" in this case because the character was not recognized) does not match.

Next, as schematically shown in (b) of FIG. 8, the definition information with the index "2" is processed, and the processing of S251 to S253 is performed. Character recognition result ( "Fujitsu Gas") is a match.

Therefore, in the case of this specific example, the definition information with the index "2" is determined as the narrowed down definition information.

FIG. 9 is a flowchart illustrating details of the processing of S5.
As exemplified in FIG. 9, when the process of S5 is started, the main control unit 290 first determines whether or not the operator's correction input was input of only a character string without headings (S51).

If the determination result in S51 is YES, the character recognition unit 220 recognizes characters included in the image of the form, and the coordinate acquisition unit 260 searches for the input non-heading character string in the recognition result to obtains the coordinates indicating the region of the indexless character string in the image of (S52).

After S52, the registration unit 270 registers the generated horizontal and vertical hash values, the input non-heading character string, the acquired coordinates indicating the region of the non-heading character string, and the is registered in the definition body 620 held by the server device 6 (S53).

On the other hand, if the determination result in S51 is NO, the registration unit 270 stores the generated horizontal and vertical hash values, the non-heading character string input by the operator's correction input, and the region of the non-heading character string. The definition information including the indicated coordinates and the result obtained in the process of S27 is registered in the definition body 620 held by the server device 6 (S53).

FIG. 10 is a diagram schematically showing a specific example of the process of S52.
In the specific example schematically shown in FIG. 10, it is assumed that the form image 8 schematically shown in FIG. 4 has been acquired as the form image. It is also assumed that the correction input by the operator is only a character string ("Fujitsu gas") indicating the consignee's name, which is a character string without headings.

In this case, in the process of S52, as schematically shown in FIG. 10, the characters included in the image 8 of the form are recognized, and in the recognition result, the input "Fujitsu Gas" is searched, and the form The coordinates (“(x3, y3, x4, y4)”) indicating the region of “Fujitsu Gas” in the image 8 of are acquired.

As described above, according to the form processing performed by the form processing apparatus 2, when the definition information including the same or similar feature information as the feature information of the image of the form including the character string without heading is not registered in the definition body 620 is corrected by the operator and the definition information of the form is registered in the definition body 620 . The operator's correction input is not limited to the input of the non-heading character string and the coordinates indicating the area of the non-heading character string. By doing so, it is possible to reduce the operator's work involved in registering the definition information in the definition body 620 .

Note that the functional configuration of the form processing device 2 is not limited to the configuration illustrated in FIG. 2, and can be changed as appropriate. For example, one or both of the character recognition dictionary 610 and the definition body 620 held by the server device 6 may be stored in a storage unit (not shown) provided in the form processing device 2 . Further, the form processing apparatus 2 may acquire an image of a form provided via a portable recording medium such as a memory card or an optical disc, or a network, and perform the above-described form processing.

In addition, the form processing device 2 can be realized by a computer and a program executed by the computer. The form processing apparatus 2 implemented by a computer and a program will be described below with reference to FIG.

FIG. 11 is a diagram illustrating the hardware configuration of a computer;
As illustrated in FIG. 11 , the computer 9 includes a CPU (Central Processing Unit) 901 , a memory 902 , an auxiliary storage device 903 , an input device 904 and a display device 905 . The computer 9 also includes an input/output interface 906 , a communication control device 907 and a media drive device 908 . These elements 901 to 908 in the computer 9 are interconnected by a bus 909 so that data can be exchanged between the elements.

A CPU 901 controls the overall operation of the computer 9 by executing various programs including an operating system. For example, the CPU 901 executes a form processing program including each process described with reference to FIGS. 3 and 5 to 10. FIG.

The memory 902 includes ROM (Read Only Memory) and RAM (Random Access Memory), which are not shown. The ROM of the memory 902 prerecords, for example, a predetermined basic control program that is read by the CPU 901 when the computer 9 is started. The RAM of the memory 902 is used by the CPU 901 as a work storage area as necessary when executing various programs. The RAM of the memory 902 can be used for temporary storage of, for example, a form image, feature information of the form image, a character string without a heading, coordinates indicating an area of the character string without a heading, and the like.

The auxiliary storage device 903 is, for example, a magnetic disk such as an HDD (Hard Disk Drive) and a non-volatile memory such as a flash memory. Various programs executed by the CPU 901 and various data can be stored in the auxiliary storage device 903 . The auxiliary storage device 903 can be used to store, for example, the form processing program described above. Further, the auxiliary storage device 903 can be used to store, for example, images of forms, processing results of form processing, and the like.

The input device 904 is, for example, a keyboard device, a mouse device, a touch panel device, or the like. When the operator of the computer 9 performs a predetermined operation on the input device 904 , the input device 904 transmits input information associated with the content of the operation to the CPU 901 . The input device 904 corresponds to the input device 4 in the form processing system 1 of FIG.

The display device 905 is, for example, a liquid crystal display device. The display device 905 can be used to display, for example, the operating state of the computer 9, images of forms, processing results of form processing, and the like. A display device 905 corresponds to the display device 5 in the form processing system 1 in FIG.

The input/output interface 906 connects the computer 9 with electronic components and other electronic devices (for example, the scanner device 3). The input/output interface 906 can also be used, for example, to connect a flash memory having a USB (Universal Serial Bus) standard connector.

The communication control device 907 is a device that connects the computer 9 to a network and controls various communications between the computer 9 and other electronic devices via the network. The communication control device 907 can be used, for example, to refer to the character recognition dictionary and the definition form held by the server device 6 in the form processing system 1 of FIG. 1 and to register definition information in the definition form.

The medium drive device 908 reads programs and data recorded in the portable recording medium 10 and writes data stored in the auxiliary storage device 903 to the portable recording medium 10 . As the portable recording medium 10, for example, there is a Secure Digital (SD) standard memory card (flash memory). The portable recording medium 10 can be used to store the form processing program, the image of the form, the processing result of the form processing, and the like. Also, when the computer 9 is equipped with an optical disk drive that can be used as the medium drive device 908 , various optical disks that can be recognized by the optical disk drive can be used as the portable recording medium 10 . Optical discs that can be used as the portable recording medium 10 include, for example, Compact Discs (CDs), Digital Versatile Discs (DVDs), Blu-ray Discs (Blu-ray is a registered trademark), and the like.

When the operator operates the input device 904 to input a command to start the form processing program, the computer 9 causes the CPU 901 to read out the above-described form processing program from the auxiliary storage device 903 or the like and execute it. While executing the form processing program, the CPU 901 controls the character recognition unit 220, the feature information generation unit 230, the determination unit 240, the indexless character string acquisition unit 250, the coordinate acquisition unit 260 in the form processing apparatus 2 illustrated in FIG. , the registration unit 270 , and the display control unit 280 . When acquiring a form image from the scanner device 3, the CPU 901 and the input/output interface 906 function as the scanner control unit 210 in the form processing device 2 illustrated in FIG. Also, when the character recognition dictionary 610 held by the server device 6 or the like different from the computer 9 is referred to, the communication control device 907 takes part of the functions of the character recognition section 220 . Further, when the definition body 620 held by the server device 6 or the like different from the computer 9 is referred to, the communication control device 907 uses part of the functions of the character recognition unit 220 or the functions of the determination unit 240. Part of the functions and part of the functions of the headline-less character string acquisition unit 250 are provided. Furthermore, when registration is performed in the definition body 620 held by the server device 6 or the like different from the computer 9 , the communication control device 907 takes part of the functions of the registration unit 270 .

Note that the computer 9 operated as the form processing apparatus 2 does not need to include all of the elements 901 to 908 illustrated in FIG. 11, and it is possible to omit some of the elements depending on the application and conditions. For example, the computer 9 may omit the media drive device 908 and the communication control device 907 .

Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and various improvements and modifications are possible without departing from the gist of the present invention.

1 form processing system 2 form processing device 3 scanner device 4 input device 5 display device 6 server device 7 network 8 image 9 computer 10 portable recording medium 210 scanner control section 220 character recognition section 230 feature information generation section 240 determination section 250 no heading Character string acquisition unit 260 Coordinate acquisition unit 270 Registration unit 280 Display control unit 290 Main control unit 610 Character recognition dictionary 620 Definition body 901 CPU
902 Memory 903 Auxiliary Storage Device 904 Input Device 905 Display Device 906 Input/Output Interface 907 Communication Control Device 908 Media Drive Device 909 Bus

Claims (5)

Generating feature information of an image of a form including a character string without a heading, which is a character string without a corresponding heading character string,
Determining whether definition information including feature information identical or similar to the generated feature information is registered in the definition body,
when it is determined that the definition information including the same or similar feature information is not registered in the definition body, accepting the input of the headline-less character string;
obtaining coordinates indicating the area of the accepted non-heading character string in the image of the form;
registering definition information including the generated feature information, the accepted non-heading character string, and the coordinates indicating the area of the acquired non-heading character string in the definition body as definition information of the form ;
when it is determined that the definition information including the same or similar feature information is registered in the definition body, obtaining a non-heading character string included in the definition information including the same or similar feature information;
A form processing program characterized by causing a computer to execute processing ,
In the process of acquiring the non-heading character string, when a plurality of definition information containing the same or similar feature information are registered in the definition body, for each definition information containing the same or similar feature information, the Determining whether or not a character string without a heading included in the definition information matches a character recognition result for an area of the image of the form corresponding to the coordinates indicating the area of the character string without a heading included in the definition information and obtain the headline-less string when both match,
A form processing program characterized by: 2. The form processing program according to claim 1 , wherein the non-heading character string is a character string indicating a consignee name. The feature information is information indicating features of distribution of line segments,
The form processing program according to claim 1 or 2 , characterized by: Generating feature information of an image of a form including a character string without a heading, which is a character string without a corresponding heading character string,
Determining whether definition information including feature information identical or similar to the generated feature information is registered in the definition body,
when it is determined that the definition information including the same or similar feature information is not registered in the definition body, accepting the input of the headline-less character string;
obtaining coordinates indicating the area of the accepted non-heading character string in the image of the form;
registering definition information including the generated feature information, the accepted non-heading character string, and the coordinates indicating the area of the acquired non-heading character string in the definition body as definition information of the form ;
when it is determined that the definition information including the same or similar feature information is registered in the definition body, obtaining a non-heading character string included in the definition information including the same or similar feature information;
A form processing method characterized by
In the process of acquiring the non-heading character string, when a plurality of definition information containing the same or similar feature information are registered in the definition body, for each definition information containing the same or similar feature information, the Determining whether or not a character string without a heading included in the definition information matches a character recognition result for an area of the image of the form corresponding to the coordinates indicating the area of the character string without a heading included in the definition information and obtain the headline-less string when both match,
A form processing method characterized by: a generation unit that generates feature information of an image of a form including a character string without a heading, which is a character string without a corresponding heading character string;
a determination unit that determines whether or not definition information including feature information identical or similar to the feature information generated by the generation unit is registered in a definition body;
When the determination unit determines that the definition information including the same or similar characteristic information is not registered in the definition body and the input of the headline-less character string is accepted, a coordinate acquisition unit for acquiring coordinates indicating the area of the headline-less character string;
definition information including the feature information generated by the generation unit, the accepted character string without headings, and the coordinates indicating the area of the character string without headings obtained by the coordinate obtaining unit; a registration unit that registers information in the definition body ;
Heading-less character for acquiring a heading-less character string included in the definition information including the same or similar feature information when it is determined that the definition information including the same or similar feature information is registered in the definition body. a column acquisition unit;
A form processing device comprising :
In the process of acquiring the non-heading character string, when a plurality of definition information containing the same or similar feature information are registered in the definition body, for each definition information containing the same or similar feature information, the Determining whether or not a character string without a heading included in the definition information matches a character recognition result for an area of the image of the form corresponding to the coordinates indicating the area of the character string without a heading included in the definition information and obtain the headline-less string when both match,
A form processing device characterized by:

Images