JP6109688B2 - Form reader and program - Google Patents

Description

  Embodiments described herein relate generally to a form reading apparatus and a program.

  Forms for notifying health check results, for example, health check result notifications, have a column where the numerical values (item values) for each test item such as red blood cell count, cholesterol, blood sugar, etc. are written (printed). It has been. For the processing of such a form, a form reading apparatus that reads a form image using a scanner and recognizes characters is used.

  By the way, the health check result notification form employs a unique arrangement of items for each inspection institution, and even if the same items are used, the arrangement is different, so the form reading device reads each form in advance. It is necessary to define the reading information for (character recognition) for each inspection organization (for each form). The read information includes, for example, position information on a form in which recognition target characters for character recognition are recorded, types of recognition target characters (kanji, kana, katakana, numbers), and the number of characters.

  When the form reading apparatus is to read a new form, it is necessary to input and set the definition of the read information for character recognition for all items to be recognized. For this reason, much time and labor are required for defining the read information as an initial setting for reading the form.

Japanese Patent Laid-Open No. 9-305715

  As described above, in the case of the conventional form reading apparatus, it is necessary to perform the input setting of the reading information for the number of items for all the character recognition objects as the definition of the reading information.

  The problem to be solved by the present invention is to provide a form reading apparatus and program capable of easily defining the form reading information.

  The form reading apparatus according to the embodiment is a form reading apparatus that recognizes characters recorded in a form, and includes an image storage unit, an item name storage unit, a first definition unit, and a second definition unit. The image storage unit stores image information of a form in which a plurality of pairs of item names and character recognition areas corresponding to the item names are provided. The item name storage unit stores the item name and the reading information for recognizing the character recognition area corresponding to the item name in association with each other. The first definition unit character recognizes the first item name based on the position of the designated first item name and the position of the first character recognition area associated with the first item name, Based on the character recognition result, reading information associated with the item name recognized by referring to the item name storage unit is defined for the first character recognition area. The second definition unit includes a first character name associated with the position of the second character recognition area associated with the designated second item name, the position of the first item name, and the first item name. The second item name is character-recognized based on the position of the character recognition area, and the reading information associated with the item name recognized character by referring to the item name storage unit based on the character recognition result is used. Read information is defined for the second character recognition area.

It is a figure which shows the structure of the form reading system of 1st Embodiment. It is a figure which shows an example of the form of the definition object in 1st Embodiment. It is a flowchart which shows operation | movement of a form reading system. It is a figure which shows the other example of the form of the definition object in 1st Embodiment. It is a figure which shows the structure of the form reading system of 2nd Embodiment. It is a figure which shows an example of the form of the definition object in 2nd Embodiment.

  Hereinafter, embodiments will be described in detail with reference to the drawings. In the embodiment, a plurality of inspection fields created by a plurality of inspection organizations, each having a plurality of different arrangements of an item name field in which the name of the inspection item is described and a result field in which an item value as a result of the inspection item is described (printed) A case will be described as an example in which a health check result notification letter is recognized. In other words, all the examination items are common in the plurality of health check result notifications, but the arrangement of the item column and the result column is different. FIG. 1 is a block diagram showing a configuration of a form reading system according to the first embodiment.

(First embodiment)
As shown in FIG. 1, the form reading system according to the first embodiment includes an input device 1, a scanner 2, a computer 3 (hereinafter referred to as “PC3”), and a monitor 4 as a display device.

  The PC 3 includes, for example, a disk reproduction device as a reproduction device for reproducing a recording medium such as a CPU, a memory, a hard disk device, a CD-ROM, and a DVD-ROM. In the PC 3, the CPU reads out control software installed in the hard disk device from a recording medium set in the disk reproducing device onto the memory, and executes processing of the software, whereby the PC 3 functions as a form reading device that reads the form. .

  The PC 3 functioning as a form reading device includes a form image storage unit 31, an input / output interface 32 (hereinafter referred to as “input / output I / F 32”), an item name list storage unit 33, a definition information storage unit 34, and a first definition unit 35. The second definition unit 36 is provided.

  The scanner 2 optically reads a form to be read, for example, a form image (form image) of the form 20 (see FIG. 2), and stores the read form image in the form image storage unit 31 of the PC 3.

  The form 20 shown in FIG. 2 is a health check result notification. The form 20 is printed with a form name (health check result notification) at the top, an item name column in which item names are printed, and item values that are inspection results corresponding to the respective item names. And a result column. These fields are separated by ruled lines. This form 20 is an unused form on which the result of the inspection item is not printed.

  The form 20 is provided with a title column 21 on which a title “item” is printed. A plurality of item name fields are provided below the title field 21. In each item name column, the item names (red blood cells, white blood cells, hemoglobin, platelets, etc.) of the inspection items are printed. In the form 20, a title column 22 on which the title “result” is printed is provided in association with the right side of the title column 21. A plurality of result columns are provided below the title column 22. In each result column, a numerical value that is an inspection result corresponding to the inspection item printed in the item name column adjacent to the left is printed. The form image storage unit 31 stores a form image of a form optically read by the scanner 2.

  The input / output I / F 32 displays a screen for form definition setting on the monitor 4, reads out the form image to be defined from the form image storage unit 31, and displays it on the screen. The input / output I / F 32 can specify the position information of the item name column and the result column for the form image displayed on the screen by operating the input device 1.

  In the item name list storage unit 33, the item names of the inspection items common to the plurality of health check result notifications created by the plurality of inspection organizations and the items described (printed) in the result column associated with the inspection items The reading information related to the value is stored in association with each other.

  The item name is a name (text data) such as red blood cell, white blood cell, hemoglobin, and platelet. The read information includes the type of characters to be recognized (kanji, kana, katakana, numbers) and the number of characters. This read information does not include the position information of the result column.

  This is because the positions of the result columns associated with the examination items are not the same but different in the plurality of health check result notifications. In other words, it is assumed that the read information such as the type and number of characters to be recognized excluding position information is common in the plurality of health check result notifications.

  The definition information storage unit 34 stores read information including position information defined for each of the plurality of forms. When the position information (coordinate values) of the item name column 23 and the result column 24 in the form image read from the form image storage unit 31 is input from the input device 1 and specified, the first definition unit 35 specifies this position. Based on the image cut out from the form image area corresponding to the item name column 23, the item name printed in the item name column 23 is recognized.

  The first definition unit 35 refers to the item name list information storage unit 33 using the item name recognized as a character as a key, acquires read information associated with the item name, and reads this read information into the result column 24. Define as information. Based on the position information in the item name field 23 and the result field 24, the first definition unit 35 temporarily stores information on the relative positional relationship between them. The information on the relative positional relationship is, for example, the positional error (distance) between the positional information in the item name column 23 and the result column 24.

  When the position information of the result column 26 in which the reading information is to be defined next is input from the input device 1 and specified, the second definition unit 36 and the item provided from the first definition unit 35 Based on the information on the relative positional relationship between the name field 23 and the result field 24, the position of the area of the item name field 25 is specified, and the item is based on the image cut out from the area of the form image in which the position is specified. The item name printed in the name column 25 is recognized.

  The second definition unit 36 refers to the item name list information storage unit 33 using the item name that has been character-recognized as a key, acquires the read information associated with the item name, and assigns the read information to the result column 25. Define as read information.

Next, the operation of the form reading system according to the first embodiment will be described with reference to FIGS.
In the case of this form reading system, the input / output I / F 32 displays a form definition screen on the monitor 4, and performs an operation of capturing an image of the form to be processed on the screen, whereby the processing target set in the scanner 2 is displayed. 2, for example, the form 20 shown in FIG. 2 is optically read, and the form image of the read form 20 is stored in the form image storage unit 31 of the PC 3.

  Subsequently, the form image stored in the form image storage unit 31 is read out and displayed on the screen by performing an operation for reading out the form image to be defined on the screen (step S101 in FIG. 3).

  For the form image displayed on the screen, first, the user specifies the position information in the result column 24 by operating the input device 1 such as a mouse (Yes in step S102). The position information is specified by a method of specifying two points (a combination of the upper left corner and the lower right corner, or a combination of the upper right corner and the lower left corner) located on the diagonal line of the result column 24, or the result column 24. This is done by specifying the range of the entire area.

  Subsequently, when the position information in the item name column 23 is designated (Yes in step S103), the first definition unit 35 recognizes the item name printed in the item name column 23 as characters.

  Then, the first definition unit 35 refers to the item name list information storage unit 33 using the item name recognized as a character as a key, acquires read information associated with the item name, and stores the read information in the result column 24. Is defined as read information for.

  As a result, the read information for recognizing characters in the area of the result column 24 in which the test result of the item name “red blood cell” is printed is defined. Based on the position information in the item name column 23 and the result column 24, the first definition unit 35 temporarily stores information on the relative positional relationship between the two (step S104).

  Next, when the user designates the position information of the result column 26 where the reading information is to be defined next by the operation of the mouse (Yes in step S105), the second definition unit 36 determines the position information and the first definition of the result column 26. The position of the area of the item name column 25 corresponding to the result column 26 is specified based on the information on the relative positional relationship between the item name column 23 and the result column 24 provided from the unit 35, and this position is specified. The item name printed in the item name column 25 is recognized based on the image cut out from the form image area (step S106).

  The second definition unit 36 refers to the item name list information storage unit 33 using the item name that has been character-recognized as a key, acquires the read information associated with the item name, and assigns the read information to the result column 25. It is defined as read information (step S107). As a result, the read information for recognizing the area of the result column 26 where the test result of the item name “white blood cell” is printed is defined.

  Similarly, when the position information of the result column in which the read information is to be defined is designated, the read information for recognizing the character of the region of the result column is defined. When the definition ending operation is performed (Yes in step S108), the second definition unit 36 stores the definition information of the form 20 together with the form name, form ID, and the like in the definition information storage unit 34 (step S109).

  As described above, according to the first embodiment, when the position information of the item name field 23 associated with the result field 24 and the result field 24 in which the reading information of the form 20 is to be defined is specified, the information is printed in the item name field 23. The character of the item name is recognized, and the reading information associated with the item name is defined as the reading information for the result column 24. Next, when the position information of the result column 26 in which the read information is to be defined is specified, the item name column 25 is based on the position information of the result column 26 and the information on the relative positional relationship between the item name column 23 and the result column 24. , The character recognition of the item name printed in the item name column 25 in which the position is specified, and the definition of the read information for the result column 26 are performed. Thereafter, the user can define the reading information for the result column only by specifying the position information of the result column.

  As a result, it is possible to easily define the read information for a plurality of forms having the same item name and different arrangements of the columns to be recognized that are associated with the item name.

  In the above embodiment, the definition of read information for a form 20 in which an item name field and a result field are directly adjacent to each other on the left and right and separated by a ruled line, and a plurality of pairs of item name fields and result fields are arranged in the vertical direction. explained. However, the form is not limited to such a form 20.

  That is, the present invention can also be applied to a form in which the item name column and the result column are directly adjacent to each other in the vertical direction and separated by a ruled line, and a plurality of pairs of the item name column and the result column are arranged in the horizontal direction. Furthermore, although the item name field and the result field are separated by a ruled line, the present invention can also be applied to a form in which the item name field and the result field are arranged correspondingly without being directly adjacent to each other. In this case, any of a form in which a plurality of pairs of item name fields and result fields are arranged in the horizontal direction and a form in which a plurality of pairs of item name fields and result fields are arranged in the vertical direction may be used.

  Furthermore, the present invention can be applied to a form in which the item name column and the result column are not separated by ruled lines. FIG. 4 shows a form 27 in which the item name field and the result field are not separated by ruled lines. When reading information is defined for this form 27, a used form is used as shown in FIG.

  Since the form 27 has no ruled line, the item name field and the result field do not exist, but the position information of the area corresponding to the item name field and the result field is designated based on the print result. The designation of position information in this case is performed by designating the position of the area corresponding to each column with a mouse or the like as indicated by the dotted line in FIG. In addition, since there is no ruled line in this range specification, it is impossible to specify the position of the accurate range, but it is sufficient if a rough range in which characters to be recognized exist can be specified.

(Second Embodiment)
Next, the second embodiment will be described with reference to FIGS. In the second embodiment, the same components as those in the first embodiment are denoted by the same reference numerals, and the description thereof is omitted.
As shown in FIG. 5, the form reading system according to the second embodiment includes a third definition unit 37. The third definition unit 37 collectively defines the next column using the definition information of the previous column.

  As shown in FIG. 6, in the case where the result column corresponding to each item name column is a health check result notification 60 provided in independent columns, such as a 2012 result and a 2013 result, In the first embodiment, it is necessary to repeat the definition work of the read information for each of the two columns of result columns.

  Therefore, in the second embodiment, after the first definition unit 35 finishes defining the read information in the last result column 28 in the first column, the user can use the position information and items in the first result column 29 in the second column. By specifying the position information in the name field 23, the third definition unit 37 based on the position information in the result field 29, the position information in the item name field 23, and the position information in all the result fields in the first column, Definitions of reading information for all the result columns in the second column are collectively defined.

  Thus, according to the second embodiment, the third definition unit 37 can collectively define the read information for all the result columns in the second column.

  Although the embodiment of the present invention has been described, the above embodiment is presented as an example, and is not intended to limit the scope of the invention. The novel embodiment can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. The above-described embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and equivalents thereof.

  Furthermore, in the above embodiment, each component is realized by a program installed in a storage such as a hard disk device of a computer. However, the above program is stored in a computer-readable electronic medium: electronic media, and the program is stored in the electronic medium. The computer may realize the functions of the present invention by causing the computer to read the information. Examples of the electronic medium include recording media such as CD-ROM and DVD-ROM, flash memory, removable media, and the like. Further, the configuration may be realized by distributing and storing components in different computers connected via a network, and communicating between computers in which the components are functioning.

  DESCRIPTION OF SYMBOLS 1 ... Input device, 2 ... Scanner, 3 ... Computer (PC), 4 ... Monitor, 20 ... Form, 24, 26, 28 ... Result column, 23, 25 ... Item name column, 31 ... Form image storage part, 32 ... Input / output interface (input / output I / F), 33 ... item name list storage section, 34 ... definition information storage section, 35 ... first definition section, 36 ... second definition section, 37 ... third definition section.

Claims (2)

In the form reading device that recognizes the characters recorded in the form,
An image storage unit for storing image information of a form in which a plurality of pairs of item names and character recognition areas corresponding to the item names are provided;
An item name storage unit for storing the item name and reading information for character recognition of the character recognition area corresponding to the item name;
Character recognition is performed on the first item name based on the position of the designated first item name and the position of the first character recognition area associated with the first item name. A first definition unit that defines read information for the first character recognition area using read information associated with the item name recognized by referring to the item name storage unit based on
The position of the second character recognition area associated with the designated second item name, the position of the first item name, and the first character recognition area associated with the first item name Character recognition of the second item name based on the position of the character, and using the reading information associated with the item name recognized character by referring to the item name storage unit based on the character recognition result A second definition unit that defines read information for the second character recognition area;
A form reading apparatus comprising: In a computer that recognizes characters recorded in a form,
The computer,
An image storage unit for storing image information of a form in which a plurality of pairs of item names and character recognition areas corresponding to the item names are provided;
An item name storage unit for storing the item name and reading information for character recognition of the character recognition area corresponding to the item name;
Character recognition is performed on the first item name based on the position of the designated first item name and the position of the first character recognition area associated with the first item name. A first definition unit that defines read information for the first character recognition area using read information associated with the item name recognized by referring to the item name storage unit based on
The position of the second character recognition area associated with the designated second item name, the position of the first item name, and the first character recognition area associated with the first item name Character recognition of the second item name based on the position of the character, and using the reading information associated with the item name recognized character by referring to the item name storage unit based on the character recognition result A program that functions as a second definition unit that defines read information for the second character recognition area.

Images