JP2010128904A - Image processing apparatus, method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing apparatus that reduces the work for confirming the result of recognizing a paper document with a mark written thereon, when recognizing a portion written by a user from an image of the paper document written by the user and displaying the result of recognition, by overlapping an object to be displayed in the portion where the mark is recognized on the image recognized, and that facilitates an operator's correction work. <P>SOLUTION: A client computer 200 accepts settings of form definition information, such as a zone to be recognized (OMR (Optical Mark Reading) or OCRed (Optical Character Reading)) on an input original paper image. Based on the set form definition information, the zone on the image is recognized, and an object indicating the result of recognizing the zone subjected to the mark recognition is created. The object created is displayed on the zone. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, method, and program, and more particularly, to an image processing apparatus, method, and program that include a character recognition function for an input image and a correction function for a recognition result.

  2. Description of the Related Art Conventionally, a mechanism is known in which character recognition processing is performed on an image obtained by scanning an application form, a questionnaire sheet, and the like, and the recognition result is stored in a database and used for business.

  However, when character recognition processing is performed on an image obtained from a handwritten questionnaire or the like, a correct character recognition result is often not obtained. For this reason, in general, an operator confirms whether the character recognition result is correct and corrects (corrects) it.

For example, in order to easily and quickly correct the character recognition result by the operator, the character string image extracted from the input image and the image displaying the character recognition result corresponding to the image are associated in units of characters. A technique has been proposed in which correction screens arranged adjacent to each other are generated and the result of character recognition is displayed near an image subjected to character recognition processing (see Patent Document 1).
JP 2002-230480 A

  However, the health check questionnaire using both the mark (sheet) method and the description method has a plurality of places where a person who receives a medical check enters or marks a handwritten character. If the technology is used, for example, the recognition result is displayed with “checked”, “not checked”, or the presence / absence flag “0”, “1”. May not be mitigated.

  Also, in health checkup questionnaires, etc., it is necessary to visually check many places to be marked, such as marking multiple items that apply to the current lifestyle, or answering multiple questions. As a result, the business efficiency may be reduced. In addition, human error such as omission of correction may increase due to an increase in work time.

  Therefore, the present invention recognizes an object displayed at a location where a mark has been recognized when recognizing a location entered by the user from an image of a paper document entered by the user and displaying the recognized recognition result. To provide an image processing apparatus and method, and a program that can reduce the confirmation work of the recognition result of a paper document on which a mark has been written, and facilitate an operator's correction work, by displaying them in a superimposed manner. Objective.

  In order to achieve the above object, an image processing apparatus according to claim 1 is an image processing apparatus for recognizing an entry position with respect to an image obtained by reading a paper document entered by a user. A setting means for presetting an area for recognizing a written mark, and a mark recognition means for recognizing a mark for an area on an image to be recognized based on the area set by the setting means; A generating unit that generates an object indicating a recognition result for the region in which the mark is recognized by the mark recognizing unit; and the object generated by the generating unit corresponds to the region in which the mark is recognized by the mark recognizing unit. And a first display means for displaying the image superimposed on the position.

  In order to achieve the above object, an image processing method according to claim 9 is an image processing method of an image processing apparatus for recognizing an entry location with respect to an image obtained by reading a paper document entered by a user. Among the entries, a setting process for setting an area for recognizing the mark that has been entered in advance, and the recognition of the mark for the area on the image to be recognized based on the area set in the setting process A mark recognition step, a generation step for generating an object indicating a recognition result for the area where the mark has been recognized in the mark recognition step, and an object generated in the generation step for marking the object generated in the mark recognition step. And a display step of displaying the image superimposed on a position corresponding to the region where the recognition is performed.

  In order to achieve the above object, a program according to claim 10 executes an image processing method of an image processing apparatus for recognizing an entry position on an image obtained by reading a paper document entered by a user. A setting step for setting in advance a region for recognizing a written mark, and an image to be recognized based on the region set in the setting step. A mark recognition step for recognizing a mark on the upper region, a generation step for generating an object indicating a recognition result for the region where the mark has been recognized in the mark recognition step, and a generation step generated A display step for displaying an object in a superimposed manner at a position corresponding to the area where the mark has been recognized in the mark recognition step. Characterized in that it comprises and.

  According to the present invention, when recognizing a location entered by a user from an image of a paper document entered by the user and displaying the recognized recognition result, an object to be displayed at the location where the mark is recognized is recognized as the recognized image. By superimposing and displaying, the confirmation work of the recognition result of the paper document in which the mark is written can be reduced, and the correction work of the operator can be facilitated.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a diagram showing a schematic configuration of an image processing system including an image processing apparatus according to an embodiment of the present invention.

  In FIG. 1, the image processing system includes a management server 100, a plurality of scanners 300, and a plurality of client computers 200, which are communicably connected via a communication network 500 such as a LAN. The management server 100 receives image data of a document or form read by the scanner 300, stores it in a database (DB) 101, and collectively manages the image data. The client computer 200 is an information processing apparatus used by a user. On the management server 100 and the client computer 200, an OS and applications (not shown) are running. The DB 101 may be configured to be mounted on the client computer 200.

  A scanner 300 which is an image reading apparatus is connected to a communication network 500 directly or via a client computer 200 and can communicate with the client computer 200 and the management server 100. For example, the scanner 300 can continuously read a document or a form to which a barcode or a unique number is assigned, and transmit the obtained image data to the client computer 200 or the management server 100.

  In the illustrated image processing system, for example, when an image reading request from an operator is received on the client computer 200, the scanner 300 scans a form and transmits the obtained image data to the client computer 200. Yes. The client computer 200 is configured to transmit received image data to the management server 100 in response to an operator request, and is configured to store the image data received by the management server 100 in the DB 101. Note that the image data read by the scanner 300 may be transmitted to the management server 100 when an image reading request from the operator is received on the client computer 200. Further, the scanner 300 is not limited to this, and may be a copying machine or a multifunction machine as long as it has an image reading function.

  FIG. 2 is a block diagram showing an outline of hardware constituting the client computer 200 in FIG. Since the client computer 200 has substantially the same configuration as the management server 100, the client computer 200 will be described as a representative.

  The client computer 200 includes a CPU 201, a RAM 202, a ROM 203, a LAN adapter 204, a video adapter 205, a keyboard 206, a mouse 207, a hard disk (HDD) 208, and a storage medium drive 209, which are a system. They are connected to each other via a bus 210.

  The CPU 201 sequentially reads programs stored in the ROM 203 or HDD 208 and the storage medium drive 209 (internal CD-ROM or the like) into the RAM 202 and executes various control processes described later. The RAM 202 is loaded with a part of an operating system (OS) and application programs, and temporarily stores various data including arrays and variables used when executing the application programs under the control of the CPU 201. It is memory. The ROM 203 stores a control program (so-called BIOS) for each hardware. Note that the ROM 203 can also store a part of the OS.

  A LAN adapter (network interface card) 204 is a communication interface for connecting to a network such as the communication network 500. The client computer 200 inputs an image from the scanner 300 or the like via the LAN adapter 204 as an image input unit. The video adapter 205 is a so-called video graphic adapter (VGA) to which various displays such as a liquid crystal display (not shown) are connected.

  The HDD 208 stores various application programs including an OS and screen information (information for displaying a screen on a display described in itml, CGI, or the like). Further, the HDD 208 stores image data, management information for managing the image data, a transmission / reception (including transfer) program of the image data, and the like. Furthermore, an application program for realizing the steps of the flowchart described later is stored. The storage medium drive 209 is a drive device that can read data and programs from a storage medium such as a CD-ROM or a DVD-ROM. In the case of the management server 100, the DB 101 may be set in the HDD 208 or in an external storage device (not shown).

  FIG. 3 is a block diagram showing an outline of hardware constituting the scanner 300 in FIG.

  The scanner 300 includes a CPU 301, a RAM 302, a ROM 303, a LAN adapter 304, a liquid crystal panel & I / F 305, a communication line I / F 306, a scan engine 307, and a hard disk (HDD) 308, which are system buses. They are connected to each other via 310.

  The CPU 201 sequentially reads programs stored in the ROM 303 or the HDD 308 to the RAM 302 and executes various control processes. A RAM 302 is a memory for temporarily storing various data used by the CPU 301. Various control programs are stored in the ROM 303.

  The LAN adapter 304 is a communication interface for connecting to the client computer 200 and the management server 100 via a network such as the communication network 500. The liquid crystal panel & I / F 305 includes a touch panel and has a display function and a data input function. The communication I / F 306 manages an interface such as USB and can connect to the client computer 200.

  The scan engine 307 optically reads an image of a document or a form and converts it into image data. In addition to the system program, the HDD 308 stores a transfer program for transferring image data to the client computer 200 and the management server 100 via the communication I / F 306 and the LAN adapter 304.

  FIG. 4 is a flowchart showing the overall flow of the form recognition process executed by the client computer 200.

  The form recognition process in this embodiment is divided into a form information registration process (step S400) and a scanning process (steps S401 to S405). The forms to be recognized include health check questionnaires and answer sheets that use both the mark sheet method (mark recognition processing) and the description method (character recognition processing).

  In the form information registration processing, the timing mark position information is acquired from the base paper image 1900 of the form (form) as shown in FIG. 19 and the written form image (recognition target image) 2000 as shown in FIG. Information necessary for OCR processing / OMR processing is generated (defined). OMR is a technology for recognizing a user's pre-determined position (entry location), but not limited to this, it recognizes a user's hand-written check mark in the entry location. You may use the technique to do. That is, as long as it is a recognizable symbol (a mark such as a fill symbol or a check symbol), the symbol written in any form may be recognized.

  In the scanning process, first, a form recognition process is performed on an image to be recognized, and a recognition pattern (also referred to as an OCR pattern) is determined (step S401). Next, recognition processing (OMR (Optical Mark Reader) processing (mark recognition processing) and OCR (Optical Character Reader) processing (character recognition processing))) is performed according to the form information (definition) corresponding to the determined recognition pattern (steps). S402). Next, a recognition result display process is performed from the result of the recognition process obtained in step S402 (step S403). Subsequently, recognition result correction processing (step S404) and registration processing (step S405) are sequentially performed. Details of these processes will be described later.

  FIG. 5 is a flowchart showing details of the form information registration process in step S400 of FIG. This process is a process executed by the CPU 201 based on a program read from the HDD 208 or the storage medium drive 209. Note that an image (base paper image) that is a form read by the scanner 300 or an image (base paper image) obtained by imaging a form generated by a form creation application is stored as image data in the storage medium drive 209 (or HDD 208). It shall be.

  In FIG. 5, the CPU 201 acquires a base paper image of the form from the storage medium drive 209 (or HDD 208), and displays a form definition screen 1100 as shown in FIG. 14 on a liquid crystal display (not shown) (step S501).

  The form definition screen 1100 includes a display unit 1110 on which a base paper image of a form as shown in FIG. 19 is displayed, a zone ID setting field 1200 for inputting a zone ID, and a zone name setting for inputting a zone name. A column 1201, a zone reading attribute setting column 1202, an overlay setting column 1203, a list display setting column 1204, a list content setting column 1205, a cancel button 1120, a registration button 1121, and a completion button 1122 are arranged. ing. Here, the zone (area) means an area that is a target of recognition processing (OCR processing (character recognition processing) / OMR processing (mark recognition processing)) in the base paper image of the form, and the base paper displayed on the display unit 1110. Designated by the user on the image.

  In the zone ID setting field 1200, an arbitrary ID can be input as the identification information of the zone designated by the user on the base paper image. If no ID is entered in the zone ID setting field 1200, the CPU 201 automatically assigns a zone ID. In the zone name setting field 1201, an arbitrary name for the zone designated by the user can be input. In the zone reading attribute setting field 1202, “OCR” or “OMR” can be selected as processing to be executed for the zone designated by the user. Here, when “OCR” is selected, the zone is subjected to OCR processing, and when “OMR” is selected, the zone is subjected to OMR processing. In the overlay setting field 1203, it is possible to set “ON” or “OFF” whether or not to display the zone designated by the user and the recognition result subjected to the OMR or OCR process. When “ON” is set, the recognition result of the zone is displayed superimposed on the position corresponding to the zone of the base paper image.

  In the list display setting column 1204, “ON” or “OFF” of the list display can be set. However, when “OMR” is selected in the zone reading attribute setting column 1202, the list display is automatically set to “ON”. " The list display can be set to “OFF” when “OCR” is selected in the zone reading attribute setting field 1202. Note that the list display setting field 1204 is configured such that it cannot be input to the list content setting field 1205 when the list display is set to “OFF”.

  In the list content setting field 1205, for example, as shown in FIG. 16A, an item name 1221 corresponding to the designated zone 1209 can be input. The content input in the list content setting field 1205 is displayed, for example, in a list box on a recognition result correction screen 1700 shown in FIG. Specifically, in FIG. 16A, when the zones 1209 to 1211 are grouped and set as AAA groups, the item names 1221 to 1223 (“Eat every day”) entered in the list content setting field 1205. , “I eat sometimes” and “I rarely eat”) are displayed in a list in the list box 1505. If the recognition result is incorrect, the user can select a correction item from the list displayed in the list box. The list content setting field 1205 is arbitrarily input by the user, but may be configured so that the result of character recognition can be input.

  Returning to FIG. 5, in step S <b> 501, the CPU 201 temporarily saves in the RAM 202 the form ID, form name, and form image storage information (save destination path of the base paper image) for the base paper image of the form acquired in step S <b> 501. The form ID is automatically given or entered by the user. The form name is input by the user. The form ID, form name, and form image storage information temporarily stored in the RAM 202 are stored in the form definition table tb01 shown in FIG. The form definition table tb01 is table information stored (registered) in the DB 101.

  Next, in step S502, the CPU 201 reads the timing mark position on the base paper image and temporarily stores it in the RAM 202 as timing mark position information (X-axis coordinates, Y-axis coordinates). The timing mark is used as a reference value for specifying the position of a zone to be subjected to OCR / OMR processing, and indicates, for example, the timing mark 1901 on the base paper image shown in FIG. The timing mark position information temporarily stored in the RAM 202 is stored in the form definition table tb01 shown in FIG. 12A in step S515 described later. It should be noted that, as in the illustrated example, a plurality of timing marks may be provided on the base paper of the form, and the position of the zone may be specified from these. Further, the X-axis coordinate is the vertical direction of the base paper image, and the Y-axis coordinate is the horizontal direction of the base paper image.

  In step S503, the CPU 201 receives from the user designation of a zone to be subjected to OCR / OMR processing on the base paper image displayed on the display unit 1110 on the form definition screen 1100. The zone is designated by the user using the mouse 207 or the like on the base paper image displayed on the display unit 1110. When the user designates a zone on the screen, for example, as shown in FIG. 16A, designated zones 1209 to 1220 are displayed by dotted lines.

  The CPU 201 specifies the position of the designated zone based on the timing mark 1901 and temporarily stores it in the RAM 202 as zone position information (X-axis coordinates, Y-axis coordinates). The zone position information is stored in the zone definition table tb03 shown in FIG. 12C in step S515 described later. The zone definition table tb03 is table information stored (registered) in the DB 101. Note that the zone position information is stored at the relative position from the timing mark 1901, so that the correction process during the scanning process can be performed.

  Next, in step S504, the CPU 201 sets the zone name setting field 1201, the zone reading attribute setting field 1202, the overlay setting field 1203, the list display setting field 1204, and the list for the zone designated by the user on the form definition screen 1100. The input (or setting) to the content setting column 1205 is accepted, and the zone setting information is temporarily stored in the RAM 202. The input (or set) contents are stored in the zone definition table tb03 shown in FIG. 12C in step S515 described later.

  In step S505, the CPU 201 determines whether or not all of the zone designation and zone setting information settings on the base paper image displayed on the display unit 1110 on the form definition screen 1100 have been completed. Here, when the completion button 1122 is pressed on the form definition screen 1100, the CPU 201 determines that the form information registration process has ended, and ends this process. When the cancel button 1120 is pressed, the CPU 201 closes the form definition screen 1100. When the registration button 1121 is pressed, the CPU 201 determines that the zone setting has been completed, displays the form definition screen 1500 shown in FIG. 15 on a liquid crystal display (not shown), etc., and proceeds to step S506.

  In FIG. 15, the form definition screen 1500 has a display portion 1110 on which a base paper image of the form is displayed, a group ID setting field 1400, a group name setting field 1401, a zone number setting field 1402, and a maximum selection. A number setting field 1403, an essential selection number setting field 1404, a cancel button 1520, a registration button 1521, and a completion button 1522 are arranged.

  In step S506, the CPU 201 receives from the user a designation for grouping the plurality of zones designated in step S503 on the base paper image displayed on the display unit 1110 on the form definition screen 1500. This is because, for example, it corresponds to a question having a plurality of answers in an inquiry form or the like. Regarding the designation of the group, the user designates a plurality of zones on the base paper image displayed on the display unit 1110 by using the mouse 207 or the like. For example, as shown in FIG. 16B, the set groups 1_1406 and 2_1407 are displayed with dotted lines.

  Next, the CPU 201 determines whether or not there is a group designation (step S507). Here, the user groups a plurality of zones on the form definition screen 1500 to determine whether or not a group is designated. If the group is not designated, the process proceeds to step S511. If the group is designated, the CPU 201 determines that the group is designated and proceeds to step S508.

  In step S508, the CPU 201 sets a group ID setting field 1400 for inputting an ID for a group designated by the user on the form definition screen 1500, a group name setting field 1401 for inputting a group name, and setting the number of zones in the group. The input (or setting) to the column 1402, the maximum selectable number setting column 1403 and the essential selection number setting column 1404 is accepted, and the group setting information is temporarily stored in the RAM 202.

  In the group ID setting field 1400, an arbitrary ID can be input as the identification information of the group designated on the base paper image by the user. When no ID is input in the group ID setting field 1400, the CPU 201 automatically assigns a group ID. In the group name setting field 1401, an arbitrary name for the group designated by the user can be input.

  In the in-group zone number setting column 1402, the number of zones in one group is displayed. The CPU 201 may be configured to detect the number of zones in the group and display the value in the in-group zone number setting field 1402 of the group, or may be configured to be input by the user himself / herself. In the maximum selectable number setting column 1403, the maximum number of selectable items in the group (the number that can be selected (marked) by the user) can be input. For example, if “multiple answers allowed, up to 3” is set in the questionnaire shown in FIG. 19, “3” is entered in the maximum selectable number setting column 1403. In the required selection number setting field 1404, the number of items that are necessarily selected (marked) in the group is input. For example, “1” is input to a question that selects any one of a plurality of answers. The values (maximum selectable number and required selection number) in the maximum selectable number setting field 1403 and the required selection number setting field 1404 are used as reference values in setting information consistency check (consistency determination) in step S509 described later. The

  If no input is made to the group ID setting field 1400 to the required selection number setting field 1404 on the form definition screen 1500, no value is stored in the group definition table tb02 shown in FIG. . If no value is stored in the group definition table tb02, it is determined that there is no group setting in step S712 in FIG.

  Next, in step S509, the CPU 201 checks (determines) the consistency of the group setting information received in step S508. Specifically, the CPU 201 determines whether or not the value input in the maximum selectable number setting column 1403 is equal to or less than the value input in the in-group zone number setting column 1402, and the required selection number setting column It is checked whether the value entered in 1404 is less than or equal to the value entered in the in-group zone number setting field 1402 and less than or equal to the value entered in the maximum selectable number setting field 1403. As a result, if it is determined that there is no consistency (NG), the error content is displayed and then the process returns to step S508. If there is consistency (OK), the process proceeds to step S510.

  In step S510, it is determined whether or not all group designation and group setting information settings on the base paper image displayed on the display unit 1110 on the form definition screen 1500 have been completed. Here, when the registration button 1521 or the completion button 1522 is pressed on the form definition screen 1500, the process proceeds to step S511. When a cancel button 1520 is pressed, the CPU 201 closes the form definition screen 1100.

  In step S511, the CPU 201 stores (registers) the form base paper image, the value input (or set) on the form definition screens 1100 and 1500 and the value temporarily stored in the RAM 202 in the DB 101 as form definition information. This process is terminated. The form definition information is stored in the form definition table tb01 shown in FIG. 12A, the group definition table tb02 shown in FIG. 12B, the zone definition table tb03 shown in FIG. 12C, and FIG. It is assumed that a list definition table tb04 shown is included.

  Next, a form recognition process for an image to be recognized will be described.

  FIG. 6 is a flowchart showing details of the form recognition process in step S401 of FIG. This process is a process executed by the CPU 201 based on a program read from the HDD 208 or the storage medium drive 209. It is assumed that an image to be recognized read by the scanner 300 as shown in FIG. 20 is stored as image data in the storage medium drive 209 (or HDD 208).

  First, in step S <b> 601, the CPU 201 acquires a recognition target image from the storage medium drive 209 and acquires a form base paper image (form image data) from the DB 101.

  Next, in steps S <b> 602 and S <b> 603, the CPU 201 performs matching (comparison) between the acquired recognition target image and form image data, and checks whether there is form image data that matches the recognition target image. If there is no matching form image data, the form recognition error process (step S605) is performed, and then this process ends.

  On the other hand, if there is form image data that matches the image to be recognized in step S603, the CPU 201 selects from a plurality of recognition patterns (templates for performing character recognition or the like with OCR or OMR settings). A recognition pattern of the matched form image data is determined (step S604). The recognition pattern is the form definition information stored (registered) in the DB 101 in the above-described form information registration process, and includes the form definition table tb01 shown in FIG. 12A to the list definition table tb04 shown in FIG. Information. The form image data and the recognition pattern have a one-to-one correspondence. Therefore, if there is form image data that matches the image to be recognized, the recognition pattern is automatically determined.

  In step S603, the recognition target image is stored in a storage location designated in advance (for example, a temporary storage area in the HDD 208). In addition, a recognition pattern of the form image that matches the image to be recognized is held on the RAM 202. The recognition pattern held in the RAM 202 is used in the recognition result display process described later.

  The form recognition process described above can be realized by using an existing general technique. In this form recognition processing, for example, ruled lines are extracted from the acquired form image data and the recognition target image, the positional relationship between the ruled lines is regarded as a feature of the form, and the ruled line structure of the form image data and the recognition target image is determined. Match forms to identify them. Then, recognition processing described later is performed using the recognition pattern corresponding to the form.

  FIG. 7 is a flowchart showing details of the recognition processing in step S402 of FIG. This process is a process executed by the CPU 201 based on a program read from the HDD 208 or the storage medium drive 209.

  In FIG. 7, in step S701, the CPU 201 extracts an OCR / OMR target zone based on the recognition pattern determined in the form recognition process. The extraction of the OCR / OMR target zone is performed by extracting zone position information (values stored in the zone position information (X axis) 1312 and zone position information (Y axis) 1313 of the zone definition table tb03) from the recognition pattern and the zone size ( Values stored in the zone size (width) 1314 and zone size (height) 1315 of the zone definition table tb03 and timing mark position information (timing mark position information (X axis) 1302 of the form definition table tb01), timing mark position Information (values stored in the Y-axis) 1303), the image of the recognition target area is specified from the recognition target image, and the image is acquired.

  Next, the CPU 201 sets “1” to the error flag set on the RAM 202 (step S702), and then acquires the zone reading attribute (the value of the zone reading attribute 1311 of the zone definition table tb03) from the recognition pattern, It is determined whether it is OCR or OMR (step S703). The error flag is a flag for determining whether or not the result of the OCR process or the OMR process is valid based on the contents defined in advance. If the error flag is “1”, the recognition result is displayed. When an error is displayed. As a result of the determination in step S703, if the zone reading attribute is OCR, the process proceeds to step S706, and if it is OMR, the process proceeds to step S704.

  In step S704, the CPU 201 performs OMR processing on the OMR target zone extracted in step S701, and determines whether or not there is a mark (check mark) in the zone. When it is determined that there is a mark, a flag with a mark is temporarily stored in the RAM 202 as a recognition result. On the other hand, when it is determined that there is no mark, a flag with no mark is temporarily stored in the RAM 202 as a recognition result.

  In step S706, the CPU 201 performs OCR processing on the OCR target zone extracted in step S701, acquires a character string existing in the zone as an OCR result, and temporarily stores it in the RAM 202. In step S708, the CPU 201 checks the validity of the acquired recognition result. In this validity check, it is assumed that a numerical item does not include a recognition result other than a numerical value, and an alphabet item includes a recognition result other than an alphabet. That is, when the zone reading attribute is OCR, the symbol attribute (for example, numerical value, alphabet, kana, etc.) as a result to be acquired is also stored in the RAM 202. This attribute is defined when the zone is set in the form information registration process of FIG.

  If the result of the validity check in step S708 is OK, the CPU 201 sets “0” in the error flag and sets the consistency check result 1322 in the recognition result table tb05 shown in FIG. “0” is set.

  In step S710, the CPU 201 stores the recognition result obtained by the OMR process or the OCR process in the recognition result 1321 in the recognition result table tb05. In addition, about the OMR result, you may preserve | save the presence or absence of a mark using a flag. Next, in step S711, the CPU 201 determines whether or not the OMR / OMR processing has been completed for all the OCR / OMR target zones based on the recognition pattern. As a result of the determination, when the OMR / OCR processing for all the OCR / OMR target zones is completed, the process proceeds to step S717.

  In step S717, the CPU 201 reads the recognition result of the zone whose read attribute is OMR from the recognition result table tb05. In step S712, the CPU 201 determines whether there is group setting information in the recognition pattern. Here, it is determined whether or not a value is stored in the group definition table tb02. If the value is stored in the group definition table tb02 as a result of this determination, after obtaining the OMR processing result of each zone in the group (step S713), the maximum selectable number and the necessary selection number in the group setting information are obtained. Based on this, the consistency of the OMR processing result is checked (determined) (step S714). Specifically, the CPU 201 calculates the number of zones in which the recognition result 1321 of the zone in the group is checked, and based on the group setting information, the OMR process recognition result (the number of zones that are checked). Check if is less than the maximum selectable number or more than the required number. As a result, if it is determined that there is consistency (OK), the error flag is set to “0” (step S715).

  In step S716, the CPU 201 stores the consistency check result temporarily stored in the RAM 202 in the recognition result table tb05. If there is a plurality of group setting information, steps S712 to S716 are repeated for the number of group setting information.

  If a group is designated, data is stored in the group definition table tb02. If the group setting information is present in step S712 (YES in step S712), the zone reading attribute is “OMR”, and if it is “OCR”, there is no group setting information. In addition, the above-described OCR / OMR processing can be performed using an existing general technique.

  8a and 8b are flowcharts showing details of the recognition result display process in step S403 of FIG. This process is a process executed by the CPU 201 based on a program read from the HDD 208 or the storage medium drive 209.

  First, in step S801, the CPU 201 refers to the values of the zone ID 1309 to the list display presence / absence 1318 stored in the zone definition table tb03 shown in FIG. 12C in order from the top (for example, the smaller zone ID). Next, in step S802, the CPU 201 determines the value (ON or OFF) of the list display presence / absence 1318 of the referenced zone definition table tb03. As a result of the determination, if the value of the list display presence / absence 1318 is “ON”, the CPU 201 sets the list box according to the contents of the list definition table tb04 (step S804). On the other hand, if the value of the list display presence / absence 1318 is “OFF” in step S802, the CPU 201 sets a text box (step S804).

  The above processing is repeated from the first column to the last column in the zone definition table tb03 (step S805). Thereby, for example, when the OCR is set in the zone reading attribute 1311 of the zone in the range 1207 on the display unit 1110 shown in FIG. 14, the recognition result of the zone is displayed in the text box format. On the other hand, if the zone reading attribute 1311 of the zone in the range 1420 on the display unit 1110 is set to OMR, the recognition result of the zone is displayed in a list box format.

  Next, in step S806, the CPU 201 refers to the values of the form ID 1300 to the correction flag 1323 stored in the recognition result table tb05 shown in FIG. 13E in order from the top (for example, the smaller form ID). Next, in step S807, the CPU 201 determines whether or not the recognition result 1321 of the recognition result table tb05 is empty. If nothing is stored in the recognition result 1321 as a result of this determination and it is empty (YES in step S807), there is nothing to display as the recognition result, so the next column (zone) in the recognition result table tb05 (Step S811).

  On the other hand, if the recognition result 1321 is not empty in step S807 (NO in step S807), the value of the error flag set in the RAM 202, that is, the value of the consistency check result 1322 of the recognition result table tb05 is determined (step S808). . If the value of the consistency check result 1322 is “0” as a result of this determination, the recognition result is displayed in the corresponding list box or text box (step S809). The recognition result displayed here is acquired from the recognition result 1321 of the recognition result table tb05. The text box means a box for storing the value of the recognition result 1321 of the recognition result table tb05 when the value of the list display presence / absence 1318 of the zone definition table tb03 is “OFF”. (Location according to zone position information and size in the zone definition table tb03).

  If the value of the consistency check result 1322 is “1” in step S808, a recognition result error is displayed (step S810). For the recognition result error displayed here, for example, a character string indicating a predetermined error is displayed.

  The above process is repeated from the first column to the last column in the recognition result table tb05 (step S811).

  In FIG. 8B, in step S812, the CPU 201 searches all columns for the value of the overlap presence / absence 1316 in the zone definition table tb03, and determines the number of overlap “ON”. If the result of this determination is that the number of overlays “ON” is “0” (that is, there is no overlay setting), the recognition target image saved in the form recognition process is displayed (step S813), and this process ends. .

  If the number of overlays “ON” is “1 or more” in step S812, the CPU 201 determines the timing mark position from the timing mark position coordinates (X axis) 1302 and the timing mark position information (Y axis) 1303 of the form definition table tb01. Information is acquired (step S814). Subsequently, in steps S815 and S816, a recognition result drawing offset value and recognition result drawing font information defined in advance are acquired. The recognition result drawing offset value here is a value for calculating the start position for drawing the recognition result. The result of adding the offset values specified in the zone position information (X axis) 1312 and the zone position information (Y axis) 1313 of the zone definition table tb03 is set as a start position for actually drawing the recognition result. The font information is a character font used when drawing the recognition result text.

  Next, in step S817, the CPU 201 refers to the values of the zone ID 1309 to the list display presence / absence 1318 stored in the zone definition table tb03 in order from the top (for example, the smaller zone ID). Next, in step S818, the CPU 201 determines the value (ON or OFF) of the overlapping presence / absence 1316 of the referenced zone definition table tb03. As a result of this determination, if the value of overlay presence / absence 1316 is “OFF”, the process moves to the next column (zone) in the zone definition table tb03, and the processing from step S817 onward is repeated.

  On the other hand, if the value of the overlay presence / absence 1316 is “ON” in step S818, the CPU 201 reads zone position information (X axis, Y axis) 1312 and 1313, zone size (width) 1314, zone size from the zone definition table tb03. The value of (height) 1315 is acquired (step S819). Subsequently, the CPU 201 adds the offset value acquired in step S815 to the acquired zone position information (X axis, Y axis) (step S820). This offset value is applied only when the value of the zone reading attribute 1311 is “OCR”.

  Next, in step S821, the CPU 201 determines the value of the zone read attribute 1311 of the zone definition table tb03. If the value of the zone reading attribute 1311 is “OMR” as a result of this determination, the value of the consistency check result 1322 of the recognition result table tb05 is determined (step S822), and the original image (the image to be recognized (entered by the user) The recognition result is drawn on the image of the paper document)) (step S823 or step S824). FIG. 18B shows an enlarged view of the groups 1406 and 1407 in FIG. 17 as an example of drawing the recognition result on the original image.

  If the value of the consistency check result 1322 is “0” (OK) as a result of the determination in step S822, the CPU 201 sets a rectangle (object) having the same size as the zone recognized by the OMR processing in advance by the user. A color is generated, and as a recognition result, a rectangle (object) is superimposed and drawn at a position corresponding to the zone on the original image (image to be recognized) (step S823). A drawing example is shown in a zone 1209 in FIG. In the illustrated example, a normal color is indicated by a downward sloping diagonal line. Transparency is set for the generated rectangle (object). By setting the transparency, it is possible to confirm the contents actually checked in the original image after the rectangle is overlapped. In particular, when a noise is picked up and misrecognized during OMR processing, the operator can easily grasp the misrecognition.

  In step S823, in the case of the group 1703 (CCC group) in FIG. 17, normal color rectangles (objects) are superimposed on the zones 1513, 1514, and 1515 in the group 1703 as shown in FIG. 18C. Drawn.

  In step S823, the list stored in the list content 1320 of the list definition table tb04 can be displayed, for example, in a list box 1505 (AAA group) on the recognition result correction screen 1700. When displaying the recognition results of the grouped zones in the list, it is possible to display all of the list contents of the zones in the list box.

  On the other hand, in step S822, when the value of the consistency check result 1322 is “1” (NG), the CPU 201 sets a rectangle (object) having the same size as the zone recognized by the OMR process to an abnormal color preset by the user. As a recognition result, a rectangle (object) is superimposed and drawn on the zone on the original image (image to be recognized) (step S824). A drawing example is shown in a zone 1214 in FIG. In the illustrated example, the abnormal color is indicated by a diagonally slanting left-down line. For the generated rectangle (object), transparency setting is performed as in step S823. This makes it possible for the operator to easily grasp misrecognition.

  In step S824, for example, if the number of zones selected in the group 1703 (CCC group) in FIG. 17 exceeds the maximum possible selection number, all the selected zones are displayed in abnormal colors. That is, in the case of abnormality, the CPU 201 changes the display format of the generated rectangle (object) so that it is different from the normal display format. The normal color and the abnormal color are different from each other, and a color with good visibility is preferable.

  In step S824, the list stored in the list contents 1320 of the list definition table tb04 can be displayed in, for example, the list box 1506 (BBB group) on the recognition result correction screen 1700. When the value of the consistency check result 1322 is “1”, the list box 1506 is displayed in an abnormal color as shown in FIG.

  As many rectangles (objects) are generated as the number of zones in which the value of the zone read attribute 1311 of the zone definition table tb03 is “OMR”. Among them, the above-described color display is performed for those for which the recognition result 1321 is not empty. Note that a rectangle (object) drawn overlapping the zone does not have to be a rectangle, and when a circular object is recognized, an object that matches the shape may be generated. In addition, when drawing a rectangle (object), in addition to placing the rectangle (object) on the original image (image to be recognized), an image in which the rectangle (object) is arranged is generated, and this generated The image and the original image (the image to be recognized) may be combined and drawn.

  In step S821, when the value of the zone reading attribute 1311 is “OCR”, the value of the consistency check result 1322 of the recognition result table tb05 is determined (step S825), and the original is displayed as in the recognition result correction screen 1700 shown in FIG. The recognition result is displayed on the image (step S826 or step S827). FIG. 18A shows an enlarged view of zones 1503 and 1504 in FIG. 17 as a display example of the recognition result on the original image.

  As a result of the determination in step S825, when the value of the consistency check result 1322 is “0” (OK), the CPU 201 uses the original OCR recognition result (recognized character) stored in the recognition result 1321 of the recognition result table tb05. A normal color is displayed in the vicinity (proximity) of the zone on the image (step S826). For example, as shown in FIG. 18A, the recognized character “12345” is displayed in the vicinity of the zone 1503 as 1510, and the zone 1503 is displayed in a normal color. Then, on the recognition result correction screen 1700 shown in FIG. 17, zone names (for example, city codes, consultation numbers, etc.) of the zones targeted for OCR and text boxes 1511 and 1512 are displayed, and the recognition results are displayed in those text boxes. Is displayed.

  On the other hand, if the value of the consistency check result 1322 is “1” in step S825, the CPU 201 displays the zone on the original image in an abnormal color so that the OCR processing result can be identified as a recognition error (step S827). ). For example, when a character string cannot be acquired as a recognition result, the character string of the recognition result is not displayed as in the zone 1504 in FIG.

  The above process is repeated from the first column to the last column in the zone definition table tb03 (step S828), and then this process ends. Note that the display position and format of the recognition result (rectangle (object) or text) to be drawn (or displayed) can be defined in advance by the user. The size of the recognition result (rectangle (object) or text) is automatically set based on the width and height of the zone size stored in the zone definition table tb03.

  With respect to a part where a mark or a check is determined using OMR by the above processing, whether or not there is a check is superimposed (displayed on the recognized part) and displayed on the image, and a character string is displayed using OCR. The part to be acquired is displayed without overlapping the character string on the recognized part. That is, the display is switched depending on the recognition method.

  As described above, since the display method can be switched depending on the OCR processing area and the OMR processing area, the operator who confirms or corrects the recognition result can easily grasp the recognition result of the OCR or OMR.

  FIG. 9 is a flowchart showing details of the recognition result correction process in step S404 of FIG.

  First, in step S <b> 901, the CPU 201 copies the recognition result displayed on the recognition result correction screen 1700 of FIG. 17 to a save area set on the RAM 202 or HDD 208. The table layout of the save area has the same format as the recognition result table tb05.

  Regarding correction of the recognition result, a list box or text box that needs correction is selected on the recognition result correction screen 1700 to correct the recognition result. For example, in the group 1407 (group BBB) shown in FIG. 18B, the recognition result is “almost all” like the list box 1506 in FIG. If “not eaten”, the user clicks “▽” in the list box 1506 to display the list contents set in the group BBB, and the correction item (here, “eating almost every day”). Select. If correction is required for the character string displayed in the text box, enter it directly in the text box. The text box 1511 corresponds to the zone 1503, and the text box 1512 displays the recognition result corresponding to the zone 1504. If it is corrected, the corresponding recognition result copied to the save area is discarded.

  In step S902, the CPU 201 determines whether or not the recognition result has been corrected on the recognition result correction screen 1700. As a result of this determination, when it is determined that the recognition result is corrected, the process proceeds to a correction process (step S907) described later.

  In step S903, the CPU 201 determines whether the reset button 1507 has been pressed on the recognition result correction screen 1700. When the reset button 1507 is pressed, the CPU 201 copies the contents copied to the save area to the OCR recognition result area set on the RAM 202 or the HDD 208, and redisplays the screen according to the contents of the OCR recognition result area. This is performed (step S908).

  In step S904, the CPU 201 determines whether the cancel button 1508 has been pressed. When a cancel button 1508 is pressed, the CPU 201 clears the contents of the OCR recognition result area and the save area, and ends the form recognition process itself shown in FIG.

  In step S905, the CPU 201 determines whether the completion button 1509 has been pressed. When the completion button 1509 is pressed, the CPU 201 ends this process.

  FIG. 10 is a flowchart showing details of the correction processing in step S907 of FIG.

  In step S1001, the CPU 201 determines, for example, whether an image (for example, the zone 1209, 1214, etc.) on the recognition target image 2000 on the recognition result correction screen 1700 has been selected. As a result of the determination, if selected, the process proceeds to step S1002, while if not selected, the process proceeds to step S1003.

  In step S <b> 1003, the CPU 201 determines whether or not a text has been input in the text box on the recognition result correction screen 1700. As a result of this determination, if there is an input to the text box, the process proceeds to step S1007. If no input is performed, the process proceeds to step S1005.

  In step S1005, the CPU 201 determines whether the list box has been selected and corrected. If the result of this determination is that correction has not been made, the present process is terminated. If correction has been made, the process moves to step S1008.

  In step S1008, the CPU 201 acquires a display position on the original image corresponding to the selected list item. Specifically, the display position information of the zone corresponding to the selected list item is converted into zone position information (X axis) 1312, zone position information (Y axis) 1313, zone size (width) 1314 in the zone definition table tb03, Obtained from the zone (height) 1315. Subsequently, after drawing the correction result on the original image (step S1011) based on the acquired display position information of the zone, the correction content is stored in the RAM 202 (step S1013), and this processing is terminated.

  In step S1007, the CPU 201 converts the image display position information of the input text into zone position information (X axis) 1312, zone position information (Y axis) 1313, zone size (width) 1314, zone ( Height) is obtained from 1315. Subsequently, based on the acquired display position information of the zone, the text input content is displayed on the original image (step S1011), then the correction content is stored in the RAM 202 (step S1013), and this processing is terminated.

  In step S1002, the CPU 201 converts the display position information of the selected image into zone position information (X axis) 1312, zone position information (Y axis) 1313, zone size (width) 1314, zone (high) in the zone definition table tb03. C) Obtained from 1315. Subsequently, the CPU 201 determines whether or not a plurality of images (groups) have been selected (step S1004). Specifically, the CPU 201 obtains the determination by acquiring the zone number 1307, the maximum selectable number 1308, and the required selection number 1317 in the group definition table tb02 from the zone ID 1309 of the zone definition table tb03 acquired previously. Do.

  If a plurality of images are not selected as a result of the determination in step S1004, the correction result is drawn on the original image (step S1011) based on the information acquired in step 1002, and the correction content is stored in the RAM 202. (Step S1013) and the process is terminated.

  On the other hand, when a plurality of images are selected in step S1004, the CPU 201 determines whether or not a recognition result before correction is selected (step S1006). As a result of the determination, if the recognition result before correction is not selected, the process proceeds to step S1007. On the other hand, if the recognition result before correction is selected, the display of the selected original image is cleared (step S1009). After clearing the display of the corresponding list item (step S1012), the correction contents are stored in the RAM 202 (step S1013), and this process is terminated.

  In step S1007, the CPU 201 determines whether the corrected content is within the maximum selectable number. If the result of this determination is that the corrected content is within the maximum selectable number, after drawing the correction result on the original image (step S1011), the correction content is stored in the RAM 202 (step S1013), and this processing is performed. Exit. When the correction result is drawn on the original image, the display of the displayed object is switched from the abnormal color to the normal color (display switching). On the other hand, if the corrected content is larger than the maximum selectable number, it is determined that the group definition is inconsistent, an error message is displayed, and the processing ends without saving the corrected content.

  FIG. 11 is a flowchart showing details of the registration process in step S405 of FIG.

  In step S1101, the CPU 201 determines whether or not a recognition result before correction is output. The recognition result before correction is the value after the OCR processing (uncorrected value), and means the content (that is, the recognition result) copied to the save area on the RAM 202 in step S901 in FIG. The output of the recognition result before correction is not essential, and whether or not to output may be defined in advance in a setting file or the like.

  As a result of the determination in step S1101, if the pre-correction recognition result output is “Yes” (YES in step S1101), the content copied to the save area on the RAM 202 in step S901 in FIG. Registration or output to a local or network folder as a physical file (CSV or text format), and proceeds to step S1103. On the other hand, if the pre-correction recognition result output is “NO” in step S1101 (NO in step S1101), the process proceeds to step S1103.

  In step S1103, the CPU 201 registers the value of the recognition result 1321 of the recognition result table tb05 in the DB 101 or outputs it to a local or network folder as a physical file (CSV or text format). Next, in step S1104, the CPU 201 determines whether or not the raw paper image is stored. The base paper image is a recognition target image saved in step S401 in FIG. 4, and the setting of whether to save is defined in advance in a setting file or the like.

  If the result of the determination in step S1104 is that the base paper image is stored (YES in step S1104), the base paper image is output to a local or network folder (step S1105), and the process proceeds to step S1106. On the other hand, if the base paper image is not stored in step S1104, the process proceeds to step S1106.

  In step S1106, the CPU 201 clears the recognition result saving area on the RAM 202. Subsequently, the CPU 201 deletes the recognition result table tb05 from the DB 101 (step S1107), and ends this process.

  According to the embodiment, the setting of the form definition information of the zone (area) that is the target of recognition processing (OMR processing (mark recognition processing) or OCR processing (character recognition processing)) on the input raw paper image is accepted. Based on the set form definition information, a recognition process is performed on an area on the image to be recognized, and an object indicating a recognition result for the mark-recognized area is generated. Then, the generated object is displayed superimposed on the area. This reduces the confirmation work of the image recognition result for the paper document entered by the user with marks such as fill and check, and facilitates the operator's correction work. In addition, it is possible to easily correct the recognition result of a paper document in a format that is selectively entered by the user.

  In the above embodiment, the form recognition process in the client computer 200 has been described. However, the management server 100 may be configured to execute the above-described process. Further, the client computer 200 and the scanner 300 may be configured in the same casing, and may be configured to be executed by, for example, a multi-function peripheral in the same casing. In other words, in the above embodiment, the client computer 200 and the scanner 300 are configured as separate housings. Furthermore, the DB 101 in which the table information shown in FIGS. 12A to 13D is stored (registered) is set in the management server 100, but is not limited thereto, and is set in the client computer 200. May be.

  The object of the present invention can also be achieved by executing the following processing. That is, a storage medium in which a program code of software that realizes the functions of the above-described embodiments is supplied to a system or apparatus, and a computer (or CPU or MPU) of the system or apparatus is stored in the storage medium. This is the process of reading the code. In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the program code and the storage medium storing the program code constitute the present invention.

  Moreover, the following can be used as a storage medium for supplying the program code. For example, floppy (registered trademark) disk, hard disk, magneto-optical disk, CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW, magnetic tape, nonvolatile memory card, ROM or the like. Alternatively, the program code may be downloaded via a network.

  Further, the present invention includes a case where the function of the above embodiment is realized by executing the program code read by the computer. In addition, an OS (operating system) running on the computer performs part or all of the actual processing based on an instruction of the program code, and the functions of the above-described embodiments are realized by the processing. Is also included.

  Furthermore, a case where the functions of the above-described embodiment are realized by the following processing is also included in the present invention. That is, the program code read from the storage medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. Thereafter, based on the instruction of the program code, the CPU or the like provided in the function expansion board or function expansion unit performs part or all of the actual processing.

  Further, the present invention includes a case where the functions of the above-described embodiments are realized by executing the program code read by the computer. In addition, there is a case where the OS running on the computer performs part or all of the actual processing based on the instruction of the program code, and the functions of the above-described embodiments are realized by the processing. In this case, the program is supplied by downloading directly from a storage medium storing the program or from another computer or database (not shown) connected to the Internet, a commercial network, a local area network, or the like.

  The form of the program may be in the form of object code, program code executed by an interpreter, script data supplied to an OS (operating system), and the like.

1 is a diagram illustrating a schematic configuration of an image processing system including an image processing apparatus according to an embodiment of the present invention. It is a block diagram which shows the outline of the hardware which comprises the client computer in FIG. It is a block diagram which shows the outline of the hardware which comprises the scanner in FIG. It is a flowchart which shows the flow of the whole form recognition process performed with a client computer. It is a flowchart which shows the detail of the form information registration process in step S400 of FIG. It is a flowchart which shows the detail of the form recognition process in step S401 of FIG. It is a flowchart which shows the detail of the recognition process in FIG.4 S402. It is a flowchart which shows the detail of the recognition result display process in step S403 of FIG. It is a flowchart which shows the detail of the recognition result display process in step S403 of FIG. It is a flowchart which shows the detail of the recognition result correction process in step S404 of FIG. It is a flowchart which shows the detail of the correction process in FIG.9 S907. It is a flowchart which shows the detail of the registration process in FIG.4 S405. FIG. 5 is a diagram illustrating an example of table information used in the form recognition process of FIG. 4, (a) is a form definition table, (b) is a group definition table, (c) is a list definition table, and (d) is a list definition. It is a table. It is a figure which shows an example of the table information used by the form recognition process of FIG. 4, (e) is a recognition result table. It is a figure which shows an example of the form definition screen displayed when registering zone setting information. It is a figure which shows an example of the form definition screen displayed when registering group setting information. It is the elements on larger scale of a form definition screen, (a) is related with the setting of zone setting information, (b) is related with the setting of group setting information. It is a figure which shows an example of a recognition result correction screen. It is a partial enlarged view of the recognition result correction screen, (a) relates to the correction of the OCR zone, (b) relates to the correction of the group, (c), it is possible to select a plurality of zones within one group Is the case. It is a figure which shows an example of the base paper image of a form (form). It is a figure which shows an example of the image of the written form.

Explanation of symbols

100 Management Server 200 Client Computer 300 Scanner 201 CPU
202 RAM
208 HDD
tb01 Form definition table tb02 Group definition table tb03 Zone definition table tb04 List definition table tb05 Recognition result table

Claims (10)

An image processing apparatus for recognizing an entry location with respect to an image obtained by reading a paper document entered by a user,
A setting means for setting in advance an area for recognizing a written mark among the filled-in places,
Mark recognition means for recognizing a mark on an area on the image to be recognized based on the area set by the setting means;
Generating means for generating an object indicating a recognition result for the area where the mark is recognized by the mark recognition means;
An image processing apparatus comprising: a first display unit configured to superimpose and display an object generated by the generation unit at a position corresponding to an area where a mark has been recognized by the mark recognition unit.   The image processing apparatus according to claim 1, wherein the generation unit generates an object that transmits an image of the region. A consistency determination means for determining the consistency of the recognition result obtained by the recognition means;
The image processing apparatus according to claim 1, wherein the first display unit changes a display format of the object generated by the generation unit according to a determination result by the consistency determination unit. Correction means for correcting the recognition result obtained by the mark recognition means;
The image processing apparatus according to claim 1, further comprising a display switching unit that switches a display position of the object according to a correction result by the correction unit.   The display means deletes the object before correction in accordance with the switching by the display switching means, and displays the object newly generated by the generation means superimposed on the position corresponding to the corrected area. The image processing apparatus according to claim 4, wherein: The setting means presets an area for recognizing the entered characters,
6. The apparatus according to claim 1, further comprising a character recognizing unit configured to recognize characters in the region when a region for recognizing the character is set by the setting unit. The image processing apparatus described.   7. The image processing apparatus according to claim 6, further comprising second display means for displaying a recognition result recognized by the character recognition means at a position adjacent to a position corresponding to a character recognition area. .   The image processing apparatus according to claim 1, wherein the image processing apparatus is configured in a separate housing from the image reading apparatus that reads the paper document. An image processing method of an image processing apparatus for recognizing an entry location on an image obtained by reading a paper document entered by a user,
Of the entry points, a setting step for setting in advance a region for recognizing the entered mark;
A mark recognition step for recognizing a mark on a region on the image to be recognized based on the region set in the setting step;
A generation step of generating an object indicating a recognition result for the region where the mark is recognized in the mark recognition step;
An image processing method comprising: a display step of displaying the object generated in the generation step in a superimposed manner at a position corresponding to a region in which the mark is recognized in the mark recognition step. A program for causing an image processing apparatus to execute an image processing method of an image processing apparatus for recognizing an entry position on an image obtained by reading a paper document entered by a user,
A setting step for setting in advance an area for recognizing a mark that has been entered, among the entry points;
A mark recognition step for recognizing a mark on a region on the image to be recognized based on the region set in the setting step;
A generation step of generating an object indicating a recognition result for the area where the mark is recognized in the mark recognition step;
And a display step of displaying the object generated in the generation step in a superimposed manner at a position corresponding to the region in which the mark is recognized in the mark recognition step.

Images