JPH07249098A - Device and method for information processing - Google Patents

Abstract

PURPOSE:To improve workability for an operator in correcting character recognition results. CONSTITUTION:This work station is equipped with an image file 4 which contains image data obtained by cutting image data on the whole slip obtained from an OCR 1, an image position file 5 which contains an image field for displaying code data and image data on a screen, and a control part 7 which recognizes characters on the basis of the image data and displays the code data at a display part 6, sets the image field of the image position file 5 on the display screen of the display part 6 according to the position of the code (input field) where a cursor is moved so as to correct the code data, and expands the image data corresponding to the code data in the image field.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information processing apparatus such as a workstation for processing image data obtained from forms and an information processing method using the apparatus.

[0002]

2. Description of the Related Art In recent years, although character recognition technology has improved in OCR, the number of errors in character recognition has decreased, but it is not perfect and human involvement is essential.

Generally, as shown in FIG. 8, a workstation (hereinafter referred to as WS) for reading the content described in forms such as a slip 80 with an optical character reader (hereinafter referred to as OCR) and character recognition processing is performed. Is
Since there are some errors in the character recognition results, the slip 8
The data (image data) of the image cut-out portion (dotted line portion) 0 of 0 and the result (code data) of character recognition thereof are simultaneously displayed on the display screen of the monitor, and the operator compares and confirms each, If there is a mistake in the character recognition result, it is corrected.

In this case, since it is better for the operator to place the code data and the image data close to each other, the code data 92 is displayed on the display screen 91 of the monitor as shown in FIG. The image data 93 are displayed side by side in the upper row or the like.

By the way, the number of characters that can be displayed on the display screen 91, particularly the "number of lines" here is limited. In particular, since the image data 93 and the like are enlarged and displayed, if two data (code data and image data) are displayed side by side only for confirmation of the character recognition result, the character recognition result will not fit on one screen Spans the screen. In the case of this example, the character recognition result of "telephone number" is displayed on the next screen 94.

Therefore, the operator must switch the display screen to correct the character recognition result, which is not good in workability.

[0007]

As described above, in the above-described conventional information processing apparatus, since the code data and the image data are displayed on the display screen only for confirming the character recognition result, one screen is displayed. There was a problem that the workability was not good because the operator had to change the screen when checking and correcting the character recognition result.

The present invention has been made to solve the above problems, and provides an information processing apparatus and an information processing method capable of improving workability in confirming and correcting a character recognition result. Has an aim.

[0009]

In order to achieve the above-mentioned object, an information processing apparatus according to claim 1 displays code data obtained by character recognition of image data of forms on a display screen. At this time, if there is code data that needs to be corrected, in the information processing device capable of moving the cursor by key operation and correcting the code data at the cursor position, a plurality of characters for character recognition can be obtained from the image data of the forms. A means for cutting out the partial image data, a data storage means for recognizing characters for each of the plurality of partial image data, and storing a plurality of code data obtained from each of the partial image data in association with each of the partial image data.
The plurality of code data stored by the data storage means are read out and displayed on the display screen in accordance with the format of the form, and the position of the first code data arbitrarily defined in the plurality of displayed code data. Means for displaying a cursor for indicating the correction target, and the partial image data corresponding to the code data for the correction target pointed by the cursor is read from the data storage means, and the desired image on the display screen is displayed. And a hop-up display means for displaying a hop-up at a position.

The information processing apparatus according to claim 2 is the information processing apparatus according to claim 1.
In the information processing apparatus described above, when a key operation for moving the cursor to another is made after correcting the first code data, means for moving the cursor to a display position of the next defined code data is provided. Further equipped.

An information processing apparatus according to claim 3 is the information processing apparatus according to claim 1.
In the information processing apparatus described in the above, when a desired position on the display screen where the partial image data is displayed by the hop-up display unit is designated by the cursor as code data to be corrected, a display field for the code data is displayed. An information processing apparatus, characterized in that it is within an image field capable of changing an area set at a position avoiding.

According to a fourth aspect of the information processing method, code data obtained by character recognition of image data of forms is displayed on the display screen, and if there is code data that needs correction at this time, a cursor is operated by a key operation. In the information processing method of moving the cursor and correcting the code data at the cursor position, when the code data to be corrected is designated by the cursor, the area can be changed on the display screen in correspondence with the code data. It is characterized in that a different image field is set, and the partial image data is expanded and displayed in the field.

[0013]

In the information processing apparatus according to claim 1, a plurality of code data, which is a result of character recognition of image data of a form, is displayed on the display screen in accordance with the format of the form, and the plurality of displayed data are displayed. In the code data, a cursor for designating the correction target is displayed at the position of the arbitrarily defined first code data, and the partial image data corresponding to the code data of the correction target designated by the cursor is stored in the data storage means. Since it is read and displayed in a hop-up display at a desired position on the display screen, it becomes possible to display the character recognition result and the partial image data in one screen, and the operator can confirm and correct the character recognition result. Workability can be improved.

According to another aspect of the information processing apparatus of the present invention, when a key operation for moving the cursor to another is made after correcting the first code data, the cursor is moved to the next defined display position of the code data. It is moved, the partial image data corresponding to the code data at that position is read out from the data storage means, and hop-up is displayed at the desired position on the display screen. Therefore, the operator needs to perform an operation for hop-up display. Therefore, workability can be improved in checking and correcting the character recognition result.

In the information processing apparatus according to the third aspect, since the partial image data is displayed on the display screen at a position avoiding the display field of the code data by the hop-up display means, it is easy to confirm the character recognition result. .

In the information processing method according to claim 4, the code data obtained by character-recognizing the image data of the form is displayed on the display screen, and when the code data to be corrected is designated by the cursor, the display is performed. An image field whose area can be changed corresponding to the code data is set on the screen, and partial image data corresponding to the code data is expanded and displayed in the field, so that the display screen can be effectively used for displaying the code data. It can be used.

[0017]

Embodiments of the present invention will now be described in detail with reference to the drawings.

FIG. 1 is a diagram showing the construction of a workstation according to an embodiment of the present invention, FIG. 2 is a diagram showing a code field on the screen, and FIG. 3 is a diagram showing an image field on the screen.

In FIG. 1, reference numeral 1 is an optical character reader (hereinafter referred to as OCR), which reads an image of a form such as a slip as image data.
Reference numeral 2 is a field control file (hereinafter referred to as an FC file). Among the image data of the entire form obtained from OCR1, the field data for masking according to the form format and cutting out only the main part is included. It is stored. A code file 3 stores code data such as characters and symbols. An image file 4 is written with image data of the entire form obtained from the OCR 1 and image data cut out by masking. An image position file 5 is a file for storing image field data and code field data in which the display position is defined according to the format of the form for displaying the code data and the image data on the display screen. A display unit 6 displays a character recognition result, image data, and the like. 7
Is a control unit, which controls the OCR 1, the files 2 to 5, the display unit 6 and the like to execute data input processing, screen layout processing, data correction processing, and the like. A code input unit 8 such as a keyboard is used to input code data for correcting the character recognition result. The movement keys on the keyboard move the cursor displayed on the display screen up, down, left and right. Image position file 5 above
As shown in FIG. 2, the data in the code field 22 to which the reception numbers “1” to “4” and the like are assigned in advance corresponding to the display screen 21 is stored therein.

Further, in the image position file 5, as shown in FIG. 3, the data of the image field 23 to which the input field numbers are assigned in advance corresponding to the display screen 21 is stored.

As shown in FIG. 4, each data of the code file 3, the image file 4 and the image position file 5 is associated with the control section 7 by the reception number or the input field number assigned to each data. The management table 40 is set.

Next, the operation of this workstation will be described with reference to FIGS.

In this workstation, as shown in FIG. 8, the OCR 1 scans a slip in which handwritten characters or printed characters are described in each column of postal code (postal code), address, name and telephone number, and the like. Image
When the data is read, the control unit 7 first reads the image data of the entire slip from the OCR 1 as a data input process, and temporarily stores the image data in the image file 4
Write in.

Subsequently, the control section 7 starts a screen layout process.

In this case, the control section 7 takes out the masking field data (area data excluding the area within the dotted line in the form format of FIG. 8) from the FC file 2,
The image data outside the dotted line is masked by superimposing it on the image data of the entire form of the image file 4, only the image data existing in the area within the dotted line is cut out, and each image is given a receipt number and written in the image file 4.

That is, the reception number "1" is in the image data in the postal code column on the left end, the reception number is "2" in the image data in the address column, the reception number is "3" in the image data in the name column, and the telephone number is A reception number "4" or the like is given to the image data in the column.

Then, the control unit 7 controls the input field numbers of the preset image fields 23a to 23c in the image position file 5 shown in FIG.
Is taken out and the respective image data in the image file 4 are made to correspond in the order of the acceptance numbers “1” to “4” with reference to the management table 40 of FIG. In the case of this embodiment,
Since it is easier for the operator to confirm the image data of the postal code and the address at the same time, the input field number is made to correspond to the image data of the reception number “1” and the reception number “2”. For this reason, the numbers are shifted so that the input field number corresponds to the image data of the reception number "3" and the input field number corresponds to the image data of the reception number "4".

Further, the control unit 7 takes out the image data from the image file 4 in the order of the acceptance number, executes the character recognition process, associates the code data with each image data, and accepts the acceptance number "1" of the image data. "4" is added to the code data.

The data correction processing operation will be described below with reference to the flowchart of FIG. In this case, the control unit 7 completes the character recognition process for all the image data even if there is a character that cannot be recognized, and once the character recognition processing is completed, the control unit 7 uses the reception numbers “1” to “4” as keys to generate the code file 3 The code data is read out and the character recognition result is displayed in the code field 22 on the display screen shown in FIG. 2 (step 501).

Then, the control unit 7 refers to the management table 40 and determines the input field number for correcting the code data based on the reception number "1" attached to the first code data (step 502). ), The control unit 7 displays a cursor at the position of the first character of the first code data displayed on the display screen. That is, as shown in FIG. 6, the cursor 61 is displayed at the position of “7” which is the first character of the first code data “700” displayed on the display screen 21.

Subsequently, the control unit 7 refers to the management table 40 from the input field number and selects the corresponding image field 23a in the image position file 5 (step 503).
The data a is taken out and the image field 23a is set on the actual display screen (step 504).

Then, the control section 7 reads the image data of the reception numbers "1" and "2" corresponding to the input field number from the image file 4 (step 505),
The read image data is expanded in the image field 23a on the display screen (step 506).

As a result, an image showing the postal code and the address is hop-up displayed in the image field 23a set on the display screen 21 of FIG.

If the operator finds erroneously recognized code data by comparing each image of the postal code and address displayed in a hop-up display with the code data corresponding to these images, the code input unit 8 When correct code data is input from (step 507), the control unit 7 corrects the zip code, address, etc. to the input code data (step 508).

When the cursor movement key on the keyboard is operated in the downward direction after the correction of the two fields of the zip code and the address, the control unit 7 causes the next code (input) field (as shown in FIG. 7). Display screen 21 with reception number "3")
The cursor 61 is moved to the position of the first character "Hold" in the upper name column (step 509). Then, the control unit 7 erases the image which is hop-up displayed on the display screen 21 (step 510). Then go back to step 502,
The input field number of the next moved code field (receipt number "3") is determined.

That is, since the position of the moved code (input) field is the name field, that is, the code field 22c shown in FIG. 2, the reception number "3" attached to the field data is changed to the management table 40. By collating and obtaining the corresponding input field number, the data of the image field 23b of that input field number is taken out from the image position file 5, and the image field 23b is set on the actual display screen 21 in the same manner as above, and within that field. The image data with the input field number is expanded to.

Then, in order to correct the erroneously recognized character in that column, correct code data is input from the code input section 8 in the same manner as above, and after correcting the code data, the cursor movement key of the keyboard is further operated downward. Then, the control unit 7 displays the cursor in the field of the telephone number, which is the next code input field (reception number "4"), and extracts the image field 23c from the image position file 5 based on the reception number "4". , Set an image field 23c on the display screen 21, and in the field,
The image data having the input field number corresponding to the image field 23c is expanded.

After correcting all the recognized character errors, the end key is operated to end the processing.

As described above, according to the workstation of this embodiment, the code data as the character recognition result and the image data thereof are not alternately displayed on the display screen from the beginning as in the prior art, but are displayed. While the code data of the entire character recognition result is displayed on the screen, the image fields 23a to 23c are set according to the display position of the cursor 61 for correcting the code data and the image data is expanded there, so that one screen is displayed. It becomes possible to display many character recognition results inside, and it becomes easy to correct each code data.

Further, in this embodiment, the image fields 23a to 23c are laid out so that the image data is hop-up displayed at the position where the code data to be corrected is not hidden. Since the hop-up display position (screen layout) of the image data can be changed by reading the data of No. 2 and changing the position and size of the image field, it is possible to perform display that meets the needs of the operator.

Further, when the character recognition result is displayed within the limit of one screen, the display position of the image data can be freely set as described above, so that the code data to be corrected is hidden by the hop-up display. Is eliminated, making it easier to correct the character recognition result.

Further, when correcting the character recognition result, if the cursor is moved to the start position of the code data to be corrected, the image data corresponding to the code data is displayed in a hop-up display, and the operator performs screen switching work one by one. This makes it easier to check and correct the character recognition result.

In the above embodiment, two code fields (postal code and address) are associated with one image field or one-to-one, but all code fields are associated with one. It may correspond to the image field on a line-by-line basis, that is, on a line-by-line basis. Also, regardless of the unit of "line", one line of code field may be further set to multiple fields, and the range on the image field side may be increased or decreased. You may spread it to the left and right and make it a block unit.

Further, the present invention can be applied to an actual form with OC.
The definition format of R utilizes the fact that the positions of the code field and the image field are defined, but the positions of the fields are set interactively in advance in the screen layout, such as setting of rows and columns. After being operated, it is stored in each file as each field data. Further, when setting rows and columns in a conversational form, fine adjustment of the screen layout (area change of each field, etc.) can be performed by further inputting coordinate data.

[0045]

As described above, according to the information processing apparatus of the first aspect, a plurality of code data, which are the result of character recognition of image data of a form, are displayed on the display screen according to the format of the form. Since the partial image data corresponding to the code data to be corrected can be displayed in a hop-up display as desired, many character recognition results and partial image data can be displayed in one screen, and the operator can recognize the character. Workability can be improved in checking and correcting the results.

According to the information processing apparatus of the second aspect, after the first code data is corrected, the partial image data corresponding to the code data at the display position of the cursor moved to a desired position on the display screen. Since the hop-up display is performed, it is not necessary for the operator to perform an operation for the hop-up display, and it is possible to improve workability when the operator confirms and corrects the character recognition result.

According to the information processing apparatus of the third aspect, since the partial image data is displayed at a position avoiding the display field of the code data displayed on the display screen, the operator can easily confirm the character recognition result. Become.

According to the information processing method of claim 4, when the code data obtained by character recognition of the image data of the form is displayed on the display screen and the code data to be corrected is designated by the cursor, An image field whose area can be changed corresponding to the code data is set on the display screen, and partial image data corresponding to the code data is expanded and displayed in the field, so that the display screen is used for displaying the code data. You can use it effectively.

[Brief description of drawings]

FIG. 1 is a diagram showing a configuration of a workstation according to an exemplary embodiment of the present invention.

FIG. 2 is a diagram showing a code field of an image position file in this workstation.

FIG. 3 is a diagram showing an image field of an image position file in this workstation.

FIG. 4 is a diagram showing a management table of a control unit in this workstation.

FIG. 5 is a flowchart showing the operation of this workstation.

FIG. 6 is a diagram showing a display example of image data in this workstation.

FIG. 7 is a diagram showing a display example when a cursor is moved from the display state of FIG.

FIG. 8 is a diagram showing the contents of an OCR input slip.

FIG. 9 is a diagram showing a conventional workstation.

[Explanation of symbols]

1 ... OCR, 2 ... FC file, 3 ... code file,
4 ... Image file, 5 ... Image position file, 6 ... Display unit, 7 ... Control unit, 8 ... Code input unit.

Claims (4)

[Claims] 1. Code data obtained by character recognition of image data of forms are displayed on a display screen. If there is code data that needs correction at this time, the cursor is moved by key operation and the cursor position is changed. In an information processing device capable of correcting the code data of, a means for cutting out a plurality of partial image data for character recognition from the image data of the form, and character recognition for each of the plurality of partial image data, Data storage means for storing a plurality of code data obtained from each partial image data in association with each partial image data, and reading out the plurality of code data stored by the data storage means according to the format of the form. The first code that is arbitrarily defined in the displayed multiple code data while being displayed on the display screen. Means for displaying a cursor for indicating a correction target at a data position; and the partial image data corresponding to the code data for the correction target pointed by the cursor, read from the data storage means, and displayed on the display screen. And a hop-up display means for displaying a hop-up at a desired position of the information processing apparatus. 2. The information processing apparatus according to claim 1, wherein after a key operation for moving the cursor to another is made after modifying the first code data, the cursor is moved to the next defined code data. An information processing apparatus further comprising means for moving to the display position of. 3. The information processing apparatus according to claim 1, wherein the desired position on the display screen where the partial image data is displayed by the hop-up display means, and the code data to be corrected is designated by the cursor. At this time, the information processing apparatus is in an image field capable of changing the area set at a position avoiding the display field of the code data. 4. Code data obtained by character recognition of image data of forms are displayed on a display screen. If there is code data that needs correction at this time, the cursor is moved by key operation and the cursor position is changed. In the information processing method for correcting the code data of, when the code data to be corrected is designated by the cursor, an image field capable of changing the area corresponding to the code data is set on the display screen, An information processing method comprising expanding and displaying the partial image data in a field.