JP2013182459A - Information processing apparatus, information processing method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique capable of reducing time and labor for preparing definition data of a form.SOLUTION: An information processing device according to one aspect of the present invention includes: an acquisition part for acquiring image data of a first form, and image data of a second form which is the same type kind of form as the first form and includes information not existing in the first form; an extracting part for extracting an area in the second form including the information from a difference between the image data of the first form and the image data of the second form; and a definition preparing part for preparing definition data used for reading processing for the same kind of form as the first form and the second form, in which a position of the extracted area in the second form is set as a position for reading information.

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program technique.

  Patent Document 1 discloses a technique for extracting handwritten image information, which is information on a handwritten portion, from a paper document having handwritten writing information in which a form is defined in advance.

JP-A-2005-346459

  Conventionally, a user manually creates definition data used for form recognition processing. In order to create the definition data, the user has to acquire knowledge about the definition data creation. Therefore, the conventional technique has a problem that it takes time to create definition data of the form.

  In one aspect, the present invention has been made in consideration of such a problem, and an object thereof is to reduce the trouble of creating form definition data.

  An information processing apparatus according to an aspect of the present invention provides a second form that is an image data of a first form and a form that is the same type of form as the first form and includes information that does not exist in the first form. An acquisition unit for acquiring the image data, an extraction unit for extracting an area where the information exists in the second form from a difference between the image data of the first form and the image data of the second form, A definition creating unit configured to create definition data used for reading the same form as the first form and the second form, in which the position of the extracted area in the second form is set as an information reading position.

  According to the information processing apparatus according to one aspect of the present invention, information obtained from the difference between the first form and the second form is used for recognition processing of the same type of form as the first form and the second form. Definition data is created.

  Therefore, the user does not need to manually create definition data used for the form recognition process. Further, in order to create definition data, the user only needs to prepare image data of the first form and the second form. Therefore, the user can create definition data without knowledge about creation of definition data. As a result, according to the information processing apparatus according to one aspect of the present invention, it is possible to reduce the trouble of creating definition data for the form.

  Further, as another form of the information processing apparatus, the definition creating unit obtains an attribute of information existing in the extracted area obtained by applying a predetermined recognition process to the extracted area. The definition data may be set as an attribute relating to the extracted area.

As another form of each of the information processing apparatuses, the extraction unit specifies a print area in which characters are printed in the vicinity of the extracted area in the first form or the second form. The definition creating unit may set a name indicated by characters acquired from the print area in the definition data as an item name of the extracted area.

  As another form of the information processing apparatus, the definition creation unit refers to dictionary data in which names used as item names of areas included in the form are registered, and uses characters acquired from the print area. If the indicated name is not registered in the referenced dictionary data, the name indicated by the character acquired from the print area is indicated by the character acquired from the print area among the registered names. It may be modified to a name similar to the name and set in the definition data as the item name of the extracted area.

  As another form of each of the information processing apparatuses, the acquisition unit is a form of the same type as the first form and the second form, and there is information that does not exist in the first form and the second form. Further, image data of a third form, which is an existing form, is further acquired, and the extraction unit calculates the first form in the third form from the difference between the image data of the first form and the image data of the third form. And an area where information that does not exist in the second form is further extracted, and the definition creating unit extracts an area extracted from the image data of the third form from the image data of the second form The information reading position set by the area extracted from the image data of the second form, the area extracted from the image data of the second form and the third form It may be modified to a position of a region including.

  In addition, as another aspect of each said information processing apparatus, the information processing method which implement | achieves each said structure may be sufficient, a program may be sufficient, and the computer other apparatus and machine which recorded such a program May be a readable storage medium. Here, the computer-readable recording medium is a medium that stores information such as programs by electrical, magnetic, optical, mechanical, or chemical action.

  According to the present invention, it is possible to reduce the trouble of creating form definition data.

FIG. 1 illustrates a creation scene of definition data according to the embodiment. FIG. 2 illustrates an information processing apparatus according to the embodiment. FIG. 3 is a flowchart illustrating the processing procedure of the information processing apparatus according to the embodiment. FIG. 4 is a flowchart illustrating definition data creation processing by the information processing apparatus according to the embodiment. FIG. 5 is a flowchart illustrating a coordinate acquisition process performed by the information processing apparatus according to the embodiment. FIG. 6 is a flowchart illustrating an item name acquisition process by the information processing apparatus according to the embodiment. FIG. 7 is a flowchart illustrating definition data correction processing by the information processing apparatus according to the embodiment. FIG. 8 illustrates a definition data display screen created by the information processing apparatus according to the embodiment. FIG. 9 is a flowchart illustrating definition data storage processing by the information processing apparatus according to the embodiment. FIG. 10 illustrates an example of a definition data correction scene according to the embodiment. FIG. 11 is a flowchart illustrating the processing procedure of the information processing apparatus according to the embodiment. FIG. 12 is a flowchart illustrating the definition data correction process based on the extracted difference by the information processing apparatus according to the embodiment.

  Hereinafter, an embodiment according to an aspect of the present invention (hereinafter, also referred to as “this embodiment”) will be described with reference to the drawings. However, the present embodiment described below is merely an example of the present invention in all points, and is not intended to limit the scope thereof. It goes without saying that various improvements and modifications can be made without departing from the scope of the present invention. That is, in implementing the present invention, a specific configuration according to the present embodiment may be employed as appropriate.

  Although data appearing in the present embodiment is described in a natural language, more specifically, it is specified by a pseudo language, a command, a parameter, a machine language, or the like that can be recognized by a computer.

§1 Information processing apparatus FIG. 1 illustrates a creation scene of definition data according to the embodiment. The information processing apparatus according to the present embodiment acquires the image data of the first form 50 and the image data of the second form 60 from an apparatus such as a scanner. The second form 60 is the same type of form as the first form 50, and is a form in which information that does not exist in the first form 50 exists.

  Here, the information existing in the form is a character, symbol, figure, or the like that has been entered, stamped, printed, or pasted on the form. The information existing in the form is, for example, handwritten characters, printed bar codes, and the like. In the present embodiment, the number of characters is not limited. Hereinafter, the expression “character” includes a case of one character and a case of a plurality of characters.

  The state in which information that does not exist in the first form 50 exists in the second form 60 is, for example, a state in which characters or barcodes that are not entered in the first form 50 exist in the second form 60, The first form 50 and the second form 60 are in a state where different characters are entered in the corresponding areas.

  A specific example of a state in which information that does not exist in the first form 50 exists in the second form 60 will be described with reference to FIG. The second form 60 shown in FIG. 1 is the same type of form as the first form 50, which is named “XX book”. The fields 61 and 62 of the second form 60 correspond to the fields 51 and 52 of the first form 50, respectively.

  In the column 51 and the column 61, for example, characters (“A item” in the figure) indicating the item names of information entered in the column 52 and the column 62 are printed. In the columns 52 and 62, for example, information indicated by item names printed in the columns 51 and 61 is entered by handwriting or the like. In FIG. 1, nothing is entered in the column 52, and the characters “AAAA” are entered in the area 63 of the column 62.

  In the example shown in FIG. 1, a bar code not printed on the first form 50 is printed in the area 64 of the second form 60. In the present embodiment, the type of barcode printed on the form is not limited. For example, it is assumed that an NW-7 standard barcode indicating a 12-digit numerical value is printed in the area 64 of the second form 60.

  In FIG. 1, the information that does not exist in the first form 50 but exists in the second form 60 is specifically the characters “AAAA” that exist in the area 63 and the barcode that exists in the area 64. . For example, even if a character different from “AAAA” is entered in the column 52, in this embodiment, the character “AAAA” present in the area 63 does not exist in the first form 50 but is in the second form 60. Is considered to be present information.

  When such information that does not exist in the first form 50 exists in the second form 60, the information such as the area 63 and the area 64 exists from the difference between the first form 50 and the second form 60, for example. The area to be performed can be specified. The information processing apparatus according to the present embodiment uses a difference between the image data of the first form 50 and the image data of the second form 60, such as an area 63 and an area 64 in which the information exists in the second form 60. To extract. This extracted area is presumed to be an area where information is entered (area where information exists) in the same type of form as the first form 50 and the second form 60. That is, it is estimated that the information can be obtained by applying a predetermined recognition process to this area.

  Therefore, the information processing apparatus according to the present embodiment uses the same type of form as the first form 50 and the second form 60 in which the positions of the area 63 and the area 64 extracted in the second form 60 are set as information reading positions. Create definition data to be used for reading process. That is, according to the information processing apparatus according to the present embodiment, information obtained from the difference between the first form 50 and the second form 60 is used, and the same type of form as the first form 50 and the second form 60 is used. Definition data used for recognition processing is created. In the present embodiment, the position of the area is expressed as coordinates on the image data. However, the method of expressing the position of the region is not limited and is appropriately selected.

  Since the definition data is created in this way, according to the information processing apparatus according to the present embodiment, the user does not need to manually create definition data used for form recognition processing. Further, in order to create the definition data, the user only needs to prepare at least two image data of the same type of form having a relationship such as the first form 50 and the second form 60. Therefore, the user can create definition data without knowledge about creation of definition data. As a result, according to the present embodiment, it is possible to reduce the trouble of creating form definition data.

  In the present embodiment, the type of form for which definition data is to be created is not limited. The image data of the form may be data obtained by digitizing the form by a scanner or the like, or may be data such as a document or an image created on a computer.

  Further, the image data of the first form 50 and the image data of the second form 60 may be image data acquired from one form (paper). For example, the user can acquire the image data of the first form 50 by causing the scanner to read the form before entry. Then, the user obtains the image data of the second form 60 by entering the characters in the form column (for example, the field 52) used for obtaining the image data of the first form 50 and causing the scanner to read the characters. can do.

  The information processing apparatus according to the present embodiment extracts the difference between the first form 50 and the second form 60, so that the definition data used for recognition processing of the same form as the first form 50 and the second form 60 is obtained. create. Therefore, it is preferable that the difference between the first form 50 and the second form 60 is clear. That is, it is preferable that the first form 50 is, for example, an unfilled form in which no information is entered in a column for entering information.

  In addition, the information processing apparatus according to the present embodiment specifies a print area in which characters are printed that exist around the position of the area extracted based on the difference in the first form 50 or the second form 60. Also good. Then, the information processing apparatus according to the present embodiment may set the name indicated by the characters acquired from the print area in the definition data as the item name of the extracted area.

  For example, the information processing apparatus according to the present embodiment searches the periphery of the position of the area corresponding to the area 63 in the first form 50 or the position of the area 63 in the second form 60, and characters are printed. A print area may be specified. In this case, for example, the area of the column 51 is specified as the print area in the first form 50, and the area of the column 61 is specified as the print area in the second form 60.

The information processing apparatus according to the present embodiment may recognize the character “A item” by executing, for example, OCR (Optical Character Recognition) processing in the print area. Then, the information processing apparatus may set the recognized character “A item” as the item name of the reading area of the form set based on the area 63.

  In this case, the information processing apparatus may refer to dictionary data in which names used as item names of areas included in the form are registered. When the name indicated by the character acquired from the print area is not registered in the referenced dictionary data, the information processing apparatus registers the name indicated by the character acquired from the print area in the dictionary data. You may correct based on the name. Thereby, the information processing apparatus may set the corrected name in the definition data as the item name of the area extracted from the difference between the first form 50 and the second form 60.

  In addition, the information processing apparatus according to the present embodiment searches for a character that satisfies a predetermined condition in at least one of the first form 50 and the second form 60, and thus is the same type as the first form 50 and the second form 60. The name of the form (form name) may be acquired.

  For example, the information processing apparatus according to the present embodiment may search the first form 50 for the character having the largest font size and acquire the name indicated by the character that satisfies the condition as the form name. Since the second form 60 is the same type of form as the first form 50, there is a character indicating the form name at a position on the second form 60 corresponding to the position where the form name is acquired in the first form 50. Should do. Therefore, the information processing apparatus according to the present embodiment determines whether or not a character indicating the form name exists at a position on the second form 60 corresponding to the position at which the form name is acquired in the first form 50. By determining, it may be determined whether or not the form name acquired from the first form 50 is a truly correct form name. Through such processing, for example, in the example illustrated in FIG. 1, the information processing apparatus may acquire the name “XX book” as the form name.

  In addition, the information processing apparatus according to the present embodiment may apply a predetermined recognition process to an area extracted based on the difference between the first form 50 and the second form 60. The predetermined recognition process is, for example, an OCR process, a barcode recognition process, or the like. The information processing apparatus may set the attribute of information existing in the extracted area obtained by applying the predetermined recognition process in the definition data as an attribute related to the extracted area.

  For example, in the example shown in FIG. 1, the information processing apparatus according to the present embodiment applies the OCR process to the area 63 to thereby enter the type of characters entered in the area 63 (column 52 and column 62). And an attribute (number of characters) related to the number of characters. In addition, the information processing apparatus applies the barcode recognition process to the area 64 to print the attribute related to the type of barcode (barcode type) and the number of characters indicated by the barcode. Attributes (number of characters). Note that the information processing apparatus may apply a plurality of recognition processes to each area without specifying the recognition process to be applied to each area. In this case, the information processing apparatus may specify the attribute value of each area based on the result of the recognition process in which no error has occurred.

In addition, the information processing apparatus according to the present embodiment may use image data of three or more forms in order to create definition data.

  For example, the information processing apparatus may create definition data based on the image data of three or more forms by treating that there are a plurality of second forms 60. In this case, the information processing apparatus creates definition data based on the difference between the first form 50 and each second form 60.

  Further, for example, the information processing apparatus is the same form as the first form 50 and the second form 60, and the third form is a form in which information that does not exist in the first form 50 and the second form 60 exists. The image data may be acquired. In this case, the information processing apparatus determines, from the difference between the image data of the first form 50 and the image data of the third form, an area where information that does not exist in the first form 50 and the second form 60 exists in the third form. May be further extracted. The information processing apparatus sets the area extracted from the image data of the second form 60 when the area extracted from the image data of the third form overlaps the area extracted from the image data of the second form 60. The information reading position may be corrected to the position of the area including the area extracted from the image data of the second form 60 and the third form (FIGS. 10 to 12 described later).

  In the following, the information processing apparatus 1 according to the present embodiment, based on the difference between the first form 50 and the second form 60, the information reading position (coordinates), information attributes (character type, number of characters, etc.), item name An example of creating definition data in which a form name is set is shown.

[Configuration example]
FIG. 2 illustrates the information processing apparatus 1 according to the present embodiment. As illustrated in FIG. 2, the information processing apparatus 1 includes a storage unit 11, a control unit 12, an input / output unit 14, a communication unit 15, and the like that are connected to the bus 13 as a hardware configuration.

  The storage unit 11 stores various data and programs used in processing executed by the control unit 12 (not shown). The storage unit 11 is realized by a storage device such as a hard disk or a flash memory, for example.

  The storage unit 11 stores dictionary data 21. In the dictionary data, names that may be used as item names of areas included in the form are registered. For example, the dictionary data 21 is a list of names that may be used as item names of areas included in the form.

  The dictionary data may not be held in the information processing apparatus 1 as in the present embodiment. For example, the dictionary data 21 may be held in another information processing apparatus accessible by the information processing apparatus 1. Further, when an item name correction process based on dictionary data, which will be described later, is not performed, the information processing apparatus 1 may not hold the dictionary data 21 and may not access the dictionary data 21.

The control unit 12 includes one or more processors such as a microprocessor or a CPU (Central Processing Unit), and peripheral circuits (ROM (Read Only Memory), RAM (Random Access Memory) used for processing of the one or more processors. ), An interface circuit, and the like. The control unit 12 implements the processing of the information processing apparatus 1 in the present embodiment by executing various data and programs stored in the storage unit 11. ROM, RAM, and the like may be referred to as a main storage device in the sense that they are arranged in an address space handled by a processor in the control unit 12.

As shown in FIG. 2, the control unit 12 includes an acquisition unit 31, an extraction unit 32, and a definition creation unit 33. For example, the acquisition unit 31, the extraction unit 32, and the definition creation unit 33 are expanded by a program stored in the storage unit 11 in a RAM that is a peripheral circuit of the control unit 12 and executed by the processor of the control unit 12. It is realized by doing.

  The acquisition unit 31 acquires the image data of the first form and the image data of the second form, which is a form of the same type as the first form and includes information that does not exist in the first form. .

  Based on the difference between the image data of the first form and the image data of the second form, the extraction unit 32 extracts an area where information that does not exist in the first form exists from the second form.

  The definition creating unit 33 creates definition data used for the reading process of the same form as the first form and the second form, in which the position of the area extracted in the second form is set as the information reading position.

  Note that the definition creation unit 33 relates the attribute of the information existing in the extracted area obtained by applying a predetermined recognition process to the area extracted in the second form, regarding the extracted area. It may be set in the definition data as an attribute. Here, the predetermined recognition process is a process for recognizing information existing in the region by image analysis, such as an OCR process or a barcode recognition process.

  When the information existing in the area is expressed by characters, the definition creating unit 33 can acquire the information existing in the area without error by applying the OCR process to the area. At this time, the definition creation unit 33 may set the type (alphabet, number, etc.) of the characters (acquired information) read without error, the number of characters read, and the like as the attributes related to the area in the definition data. .

  On the other hand, when the information existing in the area is expressed by a barcode, the definition creating unit 33 can acquire the information existing in the area without error by applying the barcode recognition process to the area. At this time, the definition creating unit 33 may set the type of the barcode (acquired information) read without error, the number of characters indicated by the read barcode, and the like as the attributes related to the area in the definition data. .

  In addition, the extraction unit 32 may specify a print area in which characters are printed that exist around the position of the extracted area in the first form or the second form. In this case, the definition creation unit 33 may set the name indicated by the characters acquired from the print area in the definition data as the item name of the extracted area.

  Further, in this case, the definition creation unit 33 refers to the dictionary data 21, and if the name indicated by the character acquired from the print area is not registered in the referenced dictionary data 21, the definition creation unit 33 acquires the print data from the print area. The name indicated by the character is corrected to a name similar to the name indicated by the character acquired from the print area among the registered names, and set in the definition data as the item name of the extracted area May be.

Further, the acquisition unit 31 further obtains image data of a third form, which is a form of the same type as the first form and the second form and includes information that does not exist in the first form and the second form. You may get it. The extraction unit 32 further extracts, from the difference between the image data of the first form and the image data of the third form, an area in the third form where information that does not exist in the first form and the second form exists. May be. When the area extracted from the image data of the third form overlaps with the area extracted from the image data of the second form, the definition creation unit 33 is set by the area extracted from the image data of the second form The information reading position may be corrected to the position of the area including the area extracted from the image data of the second form and the third form.

  The input / output unit 14 is one or a plurality of interfaces for transmitting / receiving data to / from a device existing outside the information processing device 1. The input / output unit 14 is, for example, an interface for connecting to a user interface such as an input device and an output device, an interface for connecting to a device such as a USB (Universal Serial Bus) memory, or these interfaces. It is a combination. For example, the input / output unit 14 may be connected to a user interface (not shown) (input / output devices such as a touch panel, a numeric keypad, a keyboard, a mouse, and a display). The input / output unit 14 may be connected to the scanner 2. In this case, the information processing apparatus 1 acquires data from the scanner 2 via the input / output unit 14.

  The communication unit 15 is one or a plurality of interfaces for performing data communication with other devices via a network. When the information processing apparatus 1 and the scanner 2 are connected via a network, the information processing apparatus 1 acquires data from the scanner 2 via the communication unit 15.

  The information processing apparatus 1 according to the present embodiment is an apparatus having these configurations. The information processing apparatus 1 is, for example, a general-purpose computer such as a PC or a virtual environment computer.

§2 Operation Example Next, an operation example of the information processing apparatus 1 according to the present embodiment will be described with reference to FIGS. Note that the operation example described below is merely an example of information processing of the information processing apparatus 1 according to the present embodiment, and each process uses a dependency relationship such as the result of the process executed before each process. They may be replaced as much as possible.

  FIG. 3 shows an example of a processing procedure of the information processing apparatus 1 according to the present embodiment. In FIG. 3, the step is abbreviated as “S”. Similar abbreviations are used in FIGS. 4 to 7 and 9 and FIGS. 11 and 12 described later.

  First, for example, a program stored in the storage unit 11 is expanded in the RAM or the like of the control unit 12 in accordance with a user operation. Then, the program developed in the RAM or the like of the control unit 12 is executed by the processor of the control unit 12. In this way, the information processing apparatus 1 starts processing.

  In step 100, the image data of the form is acquired by the acquisition unit 31. For example, the acquisition unit 31 receives an operation of selecting image data used to create form definition data among the image data stored in the storage unit 11 or the like. Alternatively, the acquisition unit 31 accepts reading of a form in the scanner 2 connected to the information processing apparatus 1. In the present embodiment, the acquisition unit 31 thereby acquires the image data of the first form 50 and the image data of the second form 60.

  In step 200, the first form 50 and the second form 60 are compared, the difference is extracted, and based on the extracted difference, the definition data of the same type of form as the first form 50 and the second form 60 is obtained. Created. Specific examples of the definition data creation processing are shown in FIGS.

FIG. 4 is a flowchart illustrating definition data creation processing by the information processing apparatus 1 according to this embodiment. In this operation example, the first form 50 in the second form 60 is stored in the second form 60 based on the difference between the image data of the first form 50 and the image data of the second form 60 acquired in step 100 by the extraction unit 32. A region where information that does not exist is extracted. Then, based on the extraction result, the definition creation unit 33 creates definition data related to the same type of form as the first form 50 and the second form 60. Specifically, the process is executed as follows.

  In step 210, the extraction unit 32 acquires the coordinates of an area in the second form 60 where information that does not exist in the first form 50 exists. A specific example of the coordinate acquisition process is shown in FIG.

  FIG. 5 is a flowchart illustrating the coordinate acquisition process by the information processing apparatus 1 according to this embodiment. In this operation example, the difference area between the first form 50 and the second form 60 is extracted based on the layout-related information (layout information) acquired from the first form 50, and the coordinates of the extracted area are acquired. The Specifically, the process is executed as follows.

  In step 211, the layout information of the first form 50 is acquired. For example, the extraction unit 32 analyzes the image data of the first form 50, satisfies the specific conditions such as ruled line information, information for specifying the area (pre-printed area) on which characters and the like are printed, and a circle. Layout information including information for specifying a graphic area is acquired. The method for specifying the ruled line, the pre-printing area, and the area of the graphic that satisfies the specific condition is not particularly limited and is appropriately selected. For example, the ruled line is expressed by the coordinates of the start point, the length (height) in the vertical direction, the length (width) in the horizontal direction, the thickness, and the like. In addition, the pre-printing area and the graphic area satisfying the specific condition are expressed by the coordinates of the upper left corner and the coordinates of the lower right corner of a rectangle including characters, graphics, and the like, respectively. The expression method of the ruled line, the pre-printing area, and the graphic area that satisfies the specific condition is not particularly limited, and is appropriately selected.

  In step 212, the form name is acquired from the pre-print area of the first form 50. For example, the definition creation unit 33 acquires, as a form name, the name indicated by the character in the pre-print area in which the character having the largest font size is printed out of the pre-print areas. For example, the definition creation unit 33 acquires the name indicated by the characters in the pre-print area existing at a predetermined position as the form name. In the example shown in FIG. 1, the definition creation unit 33 acquires the name “XX book” as the form name.

  Note that the definition creating unit 33 acquires information on characters printed in the pre-printing area by applying OCR processing to the pre-printing area, for example. The definition creation unit 33 uses the acquired form name, for example, as a file name of definition data to be created.

  In step 213, the layout information of the first form 50 is used, and the collation operation between the first form 50 and the second form 60 is executed. For example, the extraction unit 32 collates the first form 50 and the second form 60 using the layout information of the first form 50 acquired in step 211. At this time, for example, the extraction unit 32 may determine that the first form 50 and the second form 60 do not match as the layout of the first form 50 and the second form 60 differ. In addition, the extraction unit 32 may determine that the first form 50 and the second form 60 do not match, for example, as the description that does not exist in the first form 50 exists in the second form.

  Here, the extraction unit 32 uses a result obtained by comparing the first form 50 and the second form 60 as a form matching rate, and a numerical value indicating that there is no match from a numerical value indicating that they are completely matched. It may be expressed by a numerical value included in the range. Then, when the matching rate of the form exceeds the threshold for determining that the first form 50 and the second form 60 are the same image data, the extraction unit 32 selects the two images to be processed. The data may be determined to be the same data. In this case, the control unit 12 may display an error message on a display device (not shown) connected to the information processing device 1 to notify that the same data is a processing target.

  In step 214, the collation operation between the first form 50 and the second form 60 is executed in more detail. For example, the extraction unit 32 divides the image data of the second form 60 into 8 × 8 pixel units. Then, the extraction unit 32 specifies ruled lines and areas corresponding to the ruled lines, the pre-printed areas, and the graphic areas that satisfy the specific conditions indicated by the layout information of the first form 50 in the image data of the second form 60. . As a result, the extraction unit 32 specifies the ruled lines and the coordinates of the areas on the second form 60 corresponding to the ruled lines, the pre-printed areas, and the graphic areas that satisfy the specific conditions included in the first form 50. The extraction unit 32 divides the second form 60 into 8 × 8 pixel units and collates it with the first form 50, so that a collation error due to local misalignment or the like in the second form 60 is possible. To prevent.

  In step 215, ruled lines corresponding to the ruled lines included in the first form 50 are erased from the image data of the second form 60 based on the result of the detailed collation performed in step 214 (standard erasure). For example, the extraction unit 32 erases the ruled line corresponding to the ruled line included in the first form 50 in each divided region of the image data of the second form 60 while specifying the thickness of the ruled line of the second form 60.

  In step 216, based on the result of the detailed collation performed in step 214, the image data of the second form 60 is converted into a graphic that satisfies a specific condition such as characters in the pre-print area included in the first form 50. Corresponding prints, graphics, etc. are erased (atypical erase). For example, in each divided area of the image data of the second form 60, the extraction unit 32 erases an image in an area corresponding to each of the pre-print area included in the first form 50 and the graphic area satisfying the specific condition. .

  In steps 215 and 216, those corresponding to the ruled lines, characters, graphics, etc. included in the image data of the first form 50 are deleted from the image data of the second form 60. Therefore, what remains in the image data of the second form 60 after these erasure processes are, for example, characters entered in the area 63 and bar codes printed in the area 64, which do not exist in the first form 50. It is. These correspond to the difference between the first form 50 and the second form 60 and correspond to information existing in the second form 60 that does not exist in the first form 50.

  In this operation example, it is assumed that there is no description in the area of the first form 50 corresponding to the area 63. However, as described above, in the area of the first form 50 corresponding to the area 63, characters different from “AAAA” written in the area 63 may be entered. In this case, in the present embodiment, the area of the first form 50 corresponding to the area 63 is treated as a pre-print area or a graphic area that satisfies a specific condition. Then, when the erasing process in step 216 is executed, “AAAA” entered in the area 63 may be erased even though the information does not exist in the first form 50.

  Whether the extraction unit 32 performs the erasure process before executing the erasure process of the area corresponding to the pre-print area of the first form 50 in the image data of the second form 60 in consideration of the possibility. Verification processing for determining whether or not may be performed.

  For example, as the verification process, the extraction unit 32 may obtain a coincidence rate indicating the degree of coincidence between the pre-print area of the first form 50 and the area of the second form 60 corresponding to the pre-print area. As the characters entered in the pre-print area etc. of the first form 50 and the characters entered in the area of the second form 60 corresponding to the pre-print area etc. differ, the matching rate becomes lower.

Therefore, in order to verify whether or not different characters are written in these areas, the extraction unit 32 may determine whether or not the matching rate of these areas is lower than a predetermined threshold. The threshold value is used to verify whether the characters entered in the pre-print area of the first form 50 and the characters entered in the area of the second form 60 corresponding to the pre-print area are different. Is set as appropriate.

  When the extraction unit 32 determines that the coincidence rate is lower than a predetermined threshold, different characters are present in the pre-print area of the first form 50 and the area of the second form 60 corresponding to the pre-print area. Judge that it is filled in. If it is determined in this way, the extraction unit 32 skips the execution of the erasure process in step 216 for the area of the second form 60 corresponding to the pre-print area or the like. Thereby, it is possible to prevent the above-mentioned possibility. This also applies to cases other than characters.

  In step 217, the coordinates of the area in which characters, barcodes, etc. that have not been erased by the erasure processing in steps 215 and 216 exist are obtained. As described above, characters, barcodes, and the like that have not been erased by the erasure processing in steps 215 and 216 are information that does not exist in the first form 50. The extraction unit 32 specifies an area where the information exists in the second form 60, and acquires the coordinates of the specified area.

  For example, the extraction unit 32 identifies a rectangular area that covers characters, barcodes, and the like that have not been erased by the erasure processing in steps 215 and 216. And the extraction part 32 acquires the coordinate expressing the said rectangular area. For example, the rectangular area is represented by the coordinates of the upper left corner and the coordinates of the lower right corner of the rectangle. As a result, the extraction unit 32 acquires the coordinates of an area where characters, barcodes, and the like that have not been erased by the erasure processing in steps 215 and 216 exist.

  In the present embodiment, the extraction unit 32 considers the distance between the respective areas when specifying a rectangular area that covers characters, barcodes, and the like that have not been erased by the erasure processing in steps 215 and 216. For example, the extraction unit 32 determines that those that are separated by a predetermined distance are included in different regions. Thereby, the extraction part 32 distinguishes and extracts the area | region 63 and the area | region 64 in the 2nd form 60, and acquires each coordinate.

  Through these processes, the coordinates of the area in the second form 60 where information that does not exist in the first form 50 exists are acquired. In the example illustrated in FIG. 1, coordinates representing each of the region 63 and the region 64 are acquired. Thereby, the coordinate acquisition process ends. Then, the process proceeds to step 220.

  In addition, when the extraction unit 32 extracts a region included in a column such as the region 63 (column 52, column 62), the coordinate representing the column including the extracted region is used instead of the coordinate representing the extracted region. May be obtained. For example, the extraction unit 32 refers to the ruled line information included in the layout information created in step 211 to identify the column including the extracted region.

  Returning to FIG. 4, in step 220, definition data used for reading the same type of form as the first form 50 and the second form 60 in which the coordinates of the area extracted in the second form 60 are set as the information reading position. Created. For example, the definition creating unit 33 prepares empty definition data, and sets the coordinates acquired in step 210 as the information reading position in the prepared definition data. In the example shown in FIG. 1, in the same type of form as the first form 50 and the second form 60, the information in the form is read by OCR processing, barcode recognition processing, etc. Definition data set as a position is created.

The definition creation unit 33 may set the layout information of the first form 50 created in step 211 as definition data to be created as layout information of the same form as the first form 50 and the second form 60. Good. In this case, the definition creation unit 33 may delete a part of the layout information of the first form 50 created in step 211 and then register the layout information from which the part has been deleted in the definition data. For example, the definition creation unit 33 deletes information for specifying a region of a character handwritten in the first form 50 in the layout information of the first form 50 created in step 211. As described above, the definition creation unit 33 may register the layout information in the definition data after omitting an area that may not exist in another form of the same type as the first form 50 as much as possible.

  In step 230, a predetermined recognition process is executed for the areas 63, 64, etc. extracted in the second form 60. The predetermined recognition process is an OCR process, a barcode recognition process, or the like. The definition creating unit 33 sequentially executes predetermined recognition processing such as OCR processing, barcode recognition processing, and the like for each of the regions 63 and 64 extracted in the second form 60.

  For example, when the information existing in the target area is expressed by characters, the barcode recognition process does not succeed (results in an error), but the OCR process succeeds. On the other hand, when the information existing in the target area is expressed by a barcode, the OCR process for character recognition is not successful, but the barcode recognition process is successful.

  In steps 240 and 250, when the predetermined recognition process executed in step 230 is successful by the definition creating unit 33 ("YES" in step 240), information existing in the target region obtained by the recognition process. Is set in the definition data as an attribute relating to the target area (step 250). On the other hand, when the predetermined recognition process executed in step 230 fails (“NO” in step 240), the process in step 250 is omitted.

  In the example shown in FIG. 1, the OCR process is successful in the area 63. The definition creation unit 33 can specify an attribute (character type) related to the type of characters entered in the area 63 and an attribute (number of characters) related to the number of characters by the OCR process. Specifically, the definition creation unit 33 acquires the attribute value “alphabet” of the character type and the attribute value “4” of the number of characters as a result of the OCR process for the region 63.

  In the area 64, the barcode recognition process is successful. The definition creation unit 33 specifies an attribute (barcode type) related to the type of barcode printed in the area 64 and an attribute (number of characters) related to the number of characters indicated by the barcode by the barcode recognition process. be able to. Specifically, the definition creation unit 33 acquires the attribute value “NW-7” of the barcode type and the attribute value “12” of the number of characters.

  In step 260, in the first form 50 or the second form 60, the print area around the area extracted in the second form 60 is searched, and the item name relating to the extracted area is acquired from the found print area. The A specific example of the item name acquisition process is shown in FIG.

  FIG. 6 is a flowchart illustrating an item name acquisition process by the information processing apparatus 1 according to this embodiment. In this operation example, with the area extracted from the second form 60 in step 210 as the target area, the print area is searched from the periphery of the target area, and the item name is acquired from the found print area. When a plurality of areas are extracted from the second form 60 in step 210, each of the plurality of areas is processed as a target area. Specifically, the process is executed as follows.

In step 261, in the first form 50 or the second form 60, a print area existing around the target area is searched. For example, the definition creating unit 33 refers to the layout information of the first form 50 and searches for a pre-print region that is within a predetermined distance around the target region. For example, the definition creation unit 33 searches the image data of the second form 60 for a print area within a predetermined distance around the target area.

  A print area in which an item name indicating the content of information existing in the target area is printed generally exists on the target area or adjacent to the left. Considering this point, the definition creating unit 33 may limit the search range to the upper side or the left side of the target area when searching for a pre-print area within a predetermined distance around the target area.

  In step 262, the definition creating unit 33 determines whether a print area exists around the target area. If one or more print areas exist around the target area, the process proceeds to step 263.

  In the example shown in FIG. 1, a pre-print area in which “Item A” is printed exists around the area 63. In this process, the definition creation unit 33 finds an area where “A item” is printed as a print area existing around the area 63.

  On the other hand, if there is no print area around the target area, the item name acquisition process ends. In this case, the definition creation unit 33 cannot acquire the item name from the periphery of the target area. At this time, the definition creation unit 33 may determine the item name by any method.

  In the example shown in FIG. 1, there is no area where the item name is printed around the area 64. Therefore, the definition creation unit 33 cannot acquire item names indicating information existing in the area 64 from the periphery of the area 64. In this case, the definition creation unit 33 may determine the item name, for example, “(name of object) _ (additional number)”. At this time, the definition creating unit 33 determines the item name indicating the information existing in the area 64 as “barcode_1”.

  In step 263, the definition creating unit 33 acquires a character string included in the print area around the target area as a candidate item name. The definition creation unit 33 acquires the character string included in the print area by applying the OCR process to the print area existing around the target area. If a plurality of print areas are found in the process of step 261, a plurality of character strings are acquired as item name candidates.

  In step 264, the definition creation unit 33 accesses the dictionary data 21 stored in the storage unit 11 in which names that may be used as item names are registered. When the dictionary data 21 is held in another device accessible by the information processing apparatus 1 via the network, the definition creation unit 33 accesses the dictionary data 21 held by the other device via the network. May be.

  In step 265, the dictionary data 21 is referred to, and it is determined whether a character string that completely matches the item name candidate acquired in step 263 is registered in the dictionary data 21. For item name candidates for which a completely matched character string is not registered in the dictionary data 21, the process of step 266 is applied ("NO" in step 265). On the other hand, the processing of step 266 is omitted for the item name candidates in which the character string that completely matches is registered in the dictionary data 21 (“YES” in step 265).

In step 266, the character string of the item name candidate is corrected based on the character string registered in the dictionary data 21. For example, the definition creation unit 33 corrects the character string of the item name candidate to a character string similar to the character string of the item name candidate among the character strings registered in the dictionary data 21. The character string similar to the item name candidate character string is, for example, the character string with the most characters matching the item name candidate character string, the character string matching the item name candidate character string, or the item name candidate character. For example, a character string that matches the sequence backward. The method for determining whether or not the item name candidate character string is similar is selected as appropriate.

  In step 267, the definition creation unit 33 identifies the item name of the target area from the item name candidates related to the target area. When there is one item name candidate character string related to the target area, the definition creating unit 33 identifies that character string as the item name of the target area. On the other hand, when there are a plurality of item name candidate character strings related to the target area, the definition creating unit 33 selects one character string from the plurality of character strings, and selects the selected character string as the item name of the target area. Is specified. For example, the definition creation unit 33 may accept selection of a character string to be set as the item name of the target area by presenting the item name candidate to the user. Further, the definition creation unit 33 may specify the item name of the target area after excluding the character string of the item name candidate that is not registered in the dictionary data.

  By these processes, the item name related to the area extracted from the second form 60 is acquired. In FIG. 1, for example, the name “A item” is acquired as the item name of the region 63. Thereby, the item name acquisition process ends. Then, the process proceeds to Step 270.

  Returning to FIG. 4, in step 270, the item name acquired in step 260 is set in the definition data as an item name indicating the content of the information existing in the target area.

  Through these processes, the definition of the same form as the first form 50 and the second form 60 in which the information reading position (coordinates), information attributes (character type, number of characters, etc.), item name, and form name are set. Data is created. Then, the definition data creation process ends. If no attribute is set in the definition data, the processes in steps 230 to 250 can be omitted. If no item name is set in the definition data, the processing in steps 260 and 270 can be omitted. When the definition data creation process ends, the process proceeds to step 300.

  Returning to FIG. 3, in step 300, definition data correction processing is executed by the control unit 12. Specific examples of the definition data correction process are shown in FIGS.

  FIG. 7 is a flowchart illustrating definition data correction processing by the information processing apparatus 1 according to this embodiment. In this operation example, the definition data created in step 200 is presented to the user. Then, the user manually corrects the created definition data based on the presented information. Specifically, the process is executed as follows.

  In step 301, the definition data created in step 200 is displayed on a display device (not shown) connected to the information processing apparatus 1. An example of the display screen is shown in FIG.

  FIG. 8 illustrates a display screen of definition data created by the information processing apparatus 1 according to the present embodiment. In the example shown in FIG. 8, a form used to create definition data is displayed on the right side of the screen. The displayed form may be either the first form 50 or the second form 60. For example, the control unit 12 adjusts the alpha value of each image data of the first form 50 and the second form 60 so that both the first form 50 and the second form 60 are displayed, and Image data may be superimposed and displayed.

On the left side of the screen, each parameter value of the definition data is displayed in a state that can be changed by a user operation. For example, the user operates the input device (not shown) connected to the information processing device 1 to input the parameter value or select the parameter value displayed in the pull-down list, thereby setting the definition data. Modify each parameter value that has been specified. The user operates the input device and presses the button 80 to end the correction operation.

  In step 302, the control unit 12 accepts such a user correction operation. In step 303, the control unit 12 determines whether or not to end the correction operation. When the button 80 is pressed, the control unit 12 determines to end the correction operation (“YES” in step 303), and ends the definition data correction process. When the definition data correction process ends, the process proceeds to step 400. On the other hand, when the button 80 is not pressed, the control unit 12 determines that the correction operation is not finished (“NO” in Step 303), and the correction operation is continuously accepted (Step 302).

  Returning to FIG. 3, in step 400, a definition data storage process is executed. A specific example of the definition data storage process is shown in FIG.

  FIG. 9 is a flowchart illustrating definition data storage processing by the information processing apparatus 1 according to this embodiment. In this operation example, it is determined whether or not an error has occurred in the created definition data. If no error has occurred, the created definition data is saved. Specifically, the process is executed as follows.

  In step 401, the control unit 12 determines whether there are a plurality of areas having the same item name. For example, the control unit 12 refers to the created definition data and determines whether or not the same parameter value (name) is set for the item name in a plurality of areas. When it is determined that the same parameter value is set for the item name in a plurality of areas (“YES” in step 401), the control unit 12 indicates that there are a plurality of areas having the same item name on the display device. An error message is output (step 404). On the other hand, when it is determined that the same parameter value is not set for the item name in the plurality of areas (“NO” in step 401), the control unit 12 advances the process to step 402.

  In step 402, the control unit 12 determines whether or not an abnormal parameter value is set in the created definition data. For example, when the set parameter values satisfy a predetermined condition, such as when a plurality of reading areas overlap, or when the area set as the reading area is outside the range of the image data, the control unit 12 Determines that there is an abnormal parameter value ("YES" in step 402). And the control part 12 outputs the error message which shows the reason determined to be the said abnormal value (step 404). On the other hand, when it is determined that there is no parameter value having an abnormal value (“NO” in step 402), the control unit 12 advances the process to step 403.

  In step 403, the created definition data is saved. For example, the control unit 12 stores the definition data created by the processes so far in the storage unit 11. Thereby, the definition data storage process ends. Then, the information processing apparatus 1 ends the process according to this operation example.

<Others>
Note that the information processing apparatus 1 according to the present embodiment may use a plurality of second forms 60 when creating definition data. When using a plurality of second forms 60, for example, the information processing apparatus 1 creates the definition data by applying the above process to each of the plurality of second forms 60.

In this case, for example, the same target area such as the column 52 may be acquired from the plurality of second forms 60. At this time, for example, when the areas acquired from the respective second forms 60 overlap, the extraction unit 32 may extract the areas as a single area including these areas. Thereby, the information processing apparatus 1 recognizes the areas extracted from the plurality of second forms 60 as the same target area as much as possible.

§3 Modification Note that the information processing apparatus 1 according to the present embodiment may further acquire a third form and modify the definition data using the third form. The definition data correction process based on the third form will be described with reference to FIGS.

  FIG. 10 illustrates a definition scene of definition data according to this embodiment. The third form 70 is the same type of form as the first form 50 and the second form 60, and is a form in which information that does not exist in the first form 50 and the second form 60 exists. Specifically, information that does not exist in the first form 50 and the second form 60 exists in the area 73 and the area 74 of the third form 70. In the area 73, characters “12345” are entered. Further, it is assumed that a bar code indicating the content different from that in the area 64 is printed in the area 74. For example, it is assumed that an NW-7 standard barcode indicating a 10-digit numerical value is printed in the area 74. The columns 71 and 72 of the third form 70 correspond to the columns 51 and 52 of the first form 50, respectively.

  FIG. 11 shows an example of definition data correction processing based on the third form 70 by the information processing apparatus 1 according to the present embodiment.

  In step 500, the image data of the third form 70 is acquired by the acquisition unit 31. The acquisition unit 31 acquires the image data of the third form 70 by the same method as in step 100.

  In step 600, the definition creation unit 33 identifies the definition data to be corrected among the definition data stored in the storage unit 11. For example, the definition creation unit 33 may accept designation of definition data to be modified. With this designation, the definition creation unit 33 may specify definition data to be modified. The definition creation unit 33 refers to the layout information of the form set in the definition data stored in the storage unit 11, and sets the layout information that most closely matches the third form 70 acquired in step 500. The defined definition data may be specified as a correction target.

  In step 700, the definition data specified in step 600 is corrected based on the difference between the first form 50 and the third form 70. A specific example of the definition data correction process based on the extracted difference is shown in FIG.

  FIG. 12 is a flowchart illustrating definition data correction processing based on the extracted difference by the information processing apparatus 1 according to this embodiment. Note that the processing in steps 710 to 770 corresponds to the processing in steps 210 to 270 described above by replacing the second form 60 with the third form 70. Therefore, detailed description of steps 710-770 is omitted.

  However, in steps 720, 750, and 770, the reading position (coordinates) of information set in the definition data, the attribute of information (character type, number of characters, etc.), and the parameter value of the item name are respectively in the third form. Based on the information extracted from 70, it is corrected as necessary.

  For example, with respect to the information reading position (coordinates), the definition creating unit 33 uses the area extracted from the second form 60 when the area extracted from the third form 70 overlaps with the area extracted from the second form 60. The set information reading position is corrected to the position of the area including the area extracted from the second form 60 and the third form 70. Accordingly, in the example illustrated in FIG. 10, for example, with respect to the reading region related to the column 52, the coordinates indicating the region 63 are corrected to the coordinates indicating the region including the region 63 and the region 73.

  Further, for example, for the information attribute (character type, number of characters, etc.), the definition creating unit 33 corrects the parameter value of the attribute so as to satisfy the attribute of the information existing in the area extracted from the third area 70. Accordingly, in the example illustrated in FIG. 10, for example, the definition creation unit 33 corrects the character type “alphabet” to “alphabet and number” and the number of characters “4” to “5” for the region 63 and the region 73. On the other hand, since the barcode existing in the area 74 is an NW-7 standard barcode indicating a 10-digit numerical value, the definition creating unit 33 creates a barcode type “NW-7” for the areas 64 and 74, It is not necessary to modify the parameter value while maintaining the number of characters “12”. Note that the definition creation unit 33 may also modify the item name in the same manner as the modification of the attribute.

  With these processes, the definition data specified in step 600 is corrected based on the difference between the first form 50 and the third form 70. Then, the process proceeds to Step 800.

  Returning to FIG. 11, in step 800, manual correction of definition data is accepted by the control unit 12. The process of step 800 can be described in substantially the same manner as the process of step 300. Therefore, detailed description of step 800 is omitted.

  In step 900, the control unit 12 executes a storage process for the corrected definition data. The process of step 900 can be described in substantially the same manner as the process of step 400 described above. Therefore, detailed description of step 900 is omitted. Thereby, the information processing apparatus 1 ends the processing according to this operation example.

1 ... information processing device, 2 ... scanner,
DESCRIPTION OF SYMBOLS 11 ... Memory | storage part, 12 ... Control part, 13 ... Bus, 14 ... Input / output part, 15 ... Communication part,
21 ... Dictionary data,
31 ... Acquisition unit, 32 ... Extraction unit, 33 ... Definition creation unit,
50 ... first form 51-52 ... column,
60 ... 2nd form, 61-62 ... column, 63-64 ... area,
70 ... 3rd form, 71 to 72 ... column, 73 to 74 ... area,

Claims (7)

An acquisition unit that acquires image data of a first form and image data of a second form that is a form of the same type as the first form and includes information that does not exist in the first form;
An extraction unit for extracting an area where the information exists in the second form from the difference between the image data of the first form and the image data of the second form;
A definition creating unit that creates definition data used for reading processing of the same form as the first form and the second form, in which the position of the extracted area in the second form is set as an information reading position;
An information processing apparatus comprising: The definition creation unit uses the attribute of information existing in the extracted area obtained by applying a predetermined recognition process to the extracted area as the attribute related to the extracted area. Set to
The information processing apparatus according to claim 1. The extraction unit specifies a print area in which characters are printed in the vicinity of the position of the extracted area in the first form or the second form,
The definition creation unit sets a name indicated by characters acquired from the print area in the definition data as an item name of the extracted area.
The information processing apparatus according to claim 1 or 2. The definition creation unit refers to dictionary data in which names used as item names of areas included in the form are registered, and names indicated by characters acquired from the print area are registered in the referenced dictionary data. If not, the name indicated by the character acquired from the print area is corrected to a name similar to the name indicated by the character acquired from the print area among the registered names, and the extraction is performed. Set in the definition data as the item name of the designated area,
The information processing apparatus according to claim 3. The acquisition unit further includes image data of a third form that is a form of the same type as the first form and the second form, and is a form in which information that does not exist in the first form and the second form exists. Acquired,
The extraction unit further includes an area in the third form in which information that does not exist in the first form and the second form exists based on a difference between the image data of the first form and the image data of the third form. Extract and
The definition creating unit is set by the area extracted from the image data of the second form when the area extracted from the image data of the third form overlaps with the area extracted from the image data of the second form. The information reading position is corrected to the position of the area including the area extracted from the image data of the second form and the third form.
The information processing apparatus according to any one of claims 1 to 4. Computer
Obtaining image data of a first form and image data of a second form, which is a form of the same type as the first form and has information that does not exist in the first form;
Extracting a region where the information exists in the second form from the difference between the image data of the first form and the image data of the second form;
Creating definition data used for reading processing of the same form as the first form and the second form, wherein the position of the extracted area in the second form is set as an information reading position;
Information processing method to execute. On the computer,
Obtaining image data of a first form and image data of a second form, which is a form of the same type as the first form and has information that does not exist in the first form;
Extracting a region where the information exists in the second form from the difference between the image data of the first form and the image data of the second form;
Creating definition data used for reading processing of the same form as the first form and the second form, wherein the position of the extracted area in the second form is set as an information reading position;
A program for running

Images