JP2002279343A - Recognition result correction device and method, and recording medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a recognition result correction device in a character recognition device which improves the efficiency of a correcting work, when a large amount of documents are inputted. SOLUTION: This recognition result correction device inputs multiple documents, including one or more recognition items as image data. This device recognizes characters in the respective recognition items, in the respective documents of the inputted image and stores the recognition results of the characters included in the respective recognition items and sureness information in a result storage means 45, by making them correspond to the recognition items. The minimum value and/or an average value of the sureness information of the respective characters, stored in the result storage means 45, are calculated as representative values of the respective recognition items of the respective business forms, a priority order for correcting the recognition results of the respective items in the documents is regarded as the priority order of the sorting key, and the representative value of the recognition item is sorted, so as to determine the order of correcting the documents.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a recognition result correcting apparatus, a recognition result correcting method, and a recording medium for character recognition processing results.
The correction of the recognition result.

[0002]

2. Description of the Related Art Generally, when character recognition is performed on an image such as a document, some characters cannot be recognized or characters are erroneously recognized. Therefore, in the character recognition processing system,
It is possible to display the scanned image and the recognition result on a display device such as a display so that the user can work while checking the recognition result one by one. In such a case, if the recognition result is checked one by one every time the recognition is completed, the work efficiency is extremely low. Therefore, in that case, a method is adopted in which only recognition is performed first in batch processing, and the recognition result is collectively corrected later. As described above, when the recognition result is collectively corrected later, in order to improve work efficiency, the recognition result and the position (coordinate value) of the character on the image are associated with the image, and the character code unit of the recognition result is used. By adopting the method of storing, it is possible to easily find and correct erroneous characters when correcting the recognition result.

[0003]

In order to solve such a problem, in the technique disclosed in Japanese Patent Laid-Open No. 6-162253, the number of erroneously recognized or unrecognized characters is set in advance. It is determined whether the value is larger than the set value, and if the number of misrecognized or unrecognized characters is smaller than a preset value, the image of the misrecognized character or the unrecognizable character is displayed. The data is displayed and corrected. If the data is larger than the set value, the image data of the form in which the erroneously recognized or unrecognized character is entered is displayed to correct the recognition result. However, in such a correction method, it is necessary to check all input originals. For example, suppose a case where character recognition of a large number of forms (assuming N sheets) is processed,
Further, if erroneous recognition is included in the third sheet, the n-th sheet in the middle, and the last N-th sheet, the user does not know which recognition result includes the erroneous recognition. , 1
The recognition result is confirmed for the first to Nth sheets. Assuming that a recognition rate of 90% or more is obtained for each report, in this case, the remaining 90% of false recognitions are not included due to the recognition result including 10% of false recognitions scattered. The recognition result must be confirmed. Therefore, not knowing where the erroneous recognition is included makes the user anxious and lowers the work efficiency. The present invention is intended to solve such a problem, and in character recognition processing, when performing character recognition on a large amount of documents at once, a recognition result that improves the work efficiency of correcting the recognition result. It is an object to provide a correction device, a recognition result correction method, and a recording medium.

[0004]

In order to solve the above-mentioned problems, a first aspect of the present invention is to provide an image in which a plurality of forms including one or more recognition items are input as image data in each of the forms. In a character recognition device that obtains information on the recognition result and certainty of the character in each recognition item, a representative value calculation unit that obtains a representative value of each recognition item in each form from information on the certainty of the recognition result, Priority order instructing means for instructing a priority order for correcting the recognition result of each recognition item in the form; and, for each recognition item obtained by the representative value calculating means, according to the priority order instructed by the priority order instructing means. Correction order determining means for determining the order of a form for correcting the recognition result based on the representative value. According to a second aspect of the present invention, in the recognition result correcting apparatus according to the first aspect, the correction order determining means sets the priority of the recognition item designated by the priority designating means as the priority of the sort key, The order of the form to be corrected is determined by sorting the representative values of the recognition items.

According to a third aspect of the present invention, in the recognition result correcting apparatus according to the second aspect, when a plurality of representative values having the same value exist, the correction order determining means may determine that the form has the same representative value. Is characterized in that the order of the form to be corrected is determined by sorting by the representative value of the next priority recognition item. According to a fourth aspect of the present invention, in the recognition result correcting apparatus according to the second aspect, when there are a plurality of representative values having the same value, the correction order determining means determines whether a form having the same representative value has the same value. The order of the form to be corrected is determined by sorting by another representative value of the recognition item. Claim 5 of the present invention relates to claims 1 to 4
Wherein the representative value calculating means calculates a minimum value and / or an average value of certainty information of each character in the recognition item as a representative value. I do. Further, claim 6 of the present invention
A status display for displaying a relationship between a transition of a representative value of a recognition item to be corrected and a form currently being corrected in the recognition result correcting apparatus according to any one of claims 1 to 5. It is characterized by comprising means. According to a seventh aspect of the present invention, a plurality of forms including one or more recognition items are input as image data, and information of recognition results and certainty of characters in each of the recognition items in each of the forms in the form is obtained. In the character recognition method, a representative value of each recognition item in each form is obtained from information on the likelihood of the recognition result, and a priority order for correcting the recognition result of each recognition item in the form is indicated,
The designated priority is set as the priority of the sort key,
The order of the form to be corrected is determined by sorting the representative values of the recognition items. Further, according to claim 8 of the present invention, in the recognition result correcting method according to claim 7, when a plurality of representative values of the same value are present when sorting by the representative value, the form having the same representative value is determined as follows. The order of the forms to be corrected is determined by sorting by the representative values of the recognition items of the priority order.

According to a ninth aspect of the present invention, in the recognition result correcting apparatus according to the seventh aspect, when sorting by representative values,
When there are a plurality of representative values having the same value, the order of the forms to be corrected is determined by sorting the forms having the same representative value by other representative values of the recognition item. I do. Claim 10 of the present invention
Displays the relationship between the transition of the representative value of the recognition item to be corrected and the form currently being corrected, in the recognition result correcting method according to any one of claims 7 to 9,
The present correction state is displayed. An eleventh aspect of the present invention records a program for realizing the function of the recognition result correcting apparatus according to any one of the first to sixth aspects.

[0007]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The construction and operation of an embodiment of the present invention will be described below in detail with reference to the drawings. Embodiment (1) Configuration FIG. 1 is a block diagram showing a configuration of a character recognition device according to an embodiment of the present invention. The character recognition device of the embodiment is
Control means 10, item setting means 20, image input means 30,
It comprises a character recognition means 40, a representative value calculation means 50, a priority order instructing means 60, a correction order determining means 70, a status display means 80, an item setting storage means 25, and a result storage means 45. The control means 10 designates an area of a recognition item set in a document (form) and controls the entire functional means from input of a document image to correction of a character recognition result for the area. The item setting means 20 determines where a recognition item in a large number of documents (forms) to be read thereafter is set.
Read the form template with an image input device such as a scanner,
This is displayed on a display device such as a display, and the user is caused to specify the area with a mouse or the like. The designated area is registered in the item setting storage unit 25 for each recognition item.

As shown in FIG. 2, the item setting storage means 25 stores, for each recognition item set in the form of the form specified by the user, the recognition item name, the position coordinates of the area, the height,
Preserve breadth and priority. As other items, attributes of a region related to the item (input character type, font, color, security) can be considered. The image input unit 30 directly reads a large amount of documents (forms) as image data from an image input device such as a scanner or a copying machine. Alternatively, the document may be read from the image input device, written in the storage device as a file, and read from this file. The character recognizing unit 40 cuts out individual character images for each recognition area set in the item setting storage unit 25 from the image data for each sheet obtained by the image input unit 30, and normalizes the size. The feature amount of the normalized character image is extracted, the feature amount is compared with the recognition dictionary, and a certain number of candidate characters are obtained in order of the degree of certainty as the certainty of the recognition. Are registered in the result storage means 45 as a recognition result. still,
A method for determining the certainty of each character is disclosed in
883.

[0009] As shown in FIG.
It consists of a form header, a representative value table, and a candidate character table.
The form header has one entry for one form, and the one entry has the following items. (A) Number When a form is input and character recognition of the form is started, it is counted up and set here. (B) Order When the candidate character string of each recognized form is corrected, the order indicates which form to correct from, and is set by the correction order determination means 70. (C) Pointer to image data This is a pointer to a file that stores the image input by the image input unit 30, and is displayed as original information when correcting the character recognition unit 40 and the character recognition result. (D) Pointer to representative value table This is a pointer to a representative value table that holds information such as representative values related to recognition items in a form, and the representative values are set by the representative value calculation unit 50.

The representative value table has an entry having the following items for each recognition item in one form. (A) Representative value 1 This is the minimum value of the certainty factor of each character in the character string in this recognition item. (B) Representative value 2 This is the average value of the certainty factor of each character in the character string in this recognition item. (C) Number of characters This is the number of characters in the character string in this recognition item. It is set by the character recognition means 40. (D) Pointer to candidate character This is a pointer to a candidate character representing the recognition result of the image area of the recognition item, and is created when the character recognition unit 40 registers the recognized candidate character. The candidate character table holds, for each character image in this region, the candidate character (character code) of the recognition result and its certainty, from the one with the highest certainty to the tenth. This candidate character table is stored in the character recognition unit 40.
Is set by

The representative value calculating means 50 calculates the representative value of each recognition item for each form as follows, and registers it in the result storage means 45 (see FIG. 3). (A) The minimum value of the certainty factor (probability) of the first candidate character of each character in the recognition item. The smallest certainty factor among all the characters existing in one item is set as a representative value. This representative value indicates that the lower the confidence, the less reliable the recognition result, and the higher the confidence, the more reliable the recognition result. For example,
Referring to FIG. 2, for the recognition items A to F in the form, the minimum value of the degree of certainty of the recognition candidate character for each included character is set as the representative value. In this example, six characters are recognized for the recognition item A, and looking at the certainty of each of those characters, the certainty 20 of the fourth character is the minimum value. Therefore, the representative value of the recognition item A is set to 20. (B) The average value of the credibility (probability) of the first candidate character of each character in the recognition item. An average value of the certainty factors of all the characters in one item. For example, referring to FIG. 3, for the recognition items A to F in the form, the average value of the degrees of certainty of the recognition candidate characters for each of the included characters is used as the representative value. In this example, six characters are recognized for the recognition item A, and the average of the certainty factors of those characters is 71. Therefore, the representative value of the recognition item A is set to 71. The priority order instructing means 60 indicates a priority order as to which of the recognition items in the form is important. In this case, the item names, area positions, etc. of the recognition items registered in the item setting storage unit 25 are displayed, the user gives an instruction, and the order is registered in the item setting storage unit 20. For example, there are usually several recognition items (for example, a form ID, an amount column, a name, a phonetic note, a remarks column, etc.) in a form,
The required recognition accuracy is different. Report ID
For example, important items such as an item serving as a keyword at the time of search and an amount column, etc., require high recognition accuracy, but items such as a remarks column do not require high recognition accuracy. Therefore, the user is required to specify the order in which each recognition item should be corrected.

When the representative values are sorted by the correction order determining means 70, the priorities coincide with the priorities of the sort keys for determining which form to recognize based on the recognition result. For example, when there are five recognition items A, B, C, D, and E, and their priorities are 4, 2, 3, 1, and 5, a primary key: D, a secondary key: B, Tertiary key: C,
The representative value of each form is sorted by five keys as a quaternary key A and a tertiary key: E. Also, the priority order indicating means 60
May be configured to operate together with the item setting means 20. The correction order determining means 70 regards the priority specified by the priority indicating means 60 as a sorting priority key, and determines a representative value of the recognition item (for example, a representative value 1 indicating the minimum value).
, Or any of the representative values 2 indicating the average value). This sort result is stored in the item “order” of the form header of the result storage unit 45.

In this sorting, when the same value exists in the representative value (representative value 1 or representative value 2), the following processing is performed. (A) The order is determined based on the representative value of the next priority recognition item. The representative value at this time may be the same or different. (B) The order is determined based on the other representative values for the recognition items having the same value, in descending order. First, when sorting is performed using the representative value 1, sorting is performed using the representative value 2. (C) If the representative value 1 (minimum value) and the representative value 2 (average value) are the same, the data is sorted by another criterion as follows. -Order of input documents (forms) This is the order of documents read from the image input device. This is because it is highly likely that the order of the documents is arranged in chronological order (such as date).・ Number of characters in recognition item In this case, since it is highly likely that it depends on the contents of the document to be recognized, the user can set whether to give priority to the one with a large number of characters or the one with a small number of characters. I do.

The status display means 80 causes a display device such as a display to display the status of work on a form currently being processed at the time of correction work for determining candidate characters as a result of character recognition. For example, as shown in FIG. 6, for a certain recognition item, the following items are displayed using numerical values and graphs,
Give users information about where they are currently modifying. (A) A graph showing the transition status indicating how the representative value of this recognition item has changed in the entire form. (B) The number of sheets from the beginning of the form currently being corrected is displayed as a numerical value or a position on a graph. (C) The value of the representative value for this recognition item of the form is displayed as a numerical value and a graph. (D) The number of forms having the same representative value is displayed numerically. By making such a display, the current correction process
It is possible to grasp how much of the whole is processed, what is being processed, and how much should be corrected thereafter. Such a display may be always displayed, or may be displayed only when specified by a menu or the like. As a result of sorting by the correction order determining means 70, as shown in FIG. 7, the representative values (confidence) of the recognition items are low, that is, the recognition items are arranged in descending order of the probability of containing a misrecognized character. The correction work concentrates on the beginning, and as the representative value increases, the load of the correction work decreases, and eventually there is no need to make any correction. The user works while drawing the curve as shown in FIG. 7 in the head and knowing which part of the whole curve is being corrected by knowing the representative value of the currently-recognized recognition result. Can be. Thereafter, when the recognition result that does not need to be corrected at all continues to some extent (for the α sheets displayed in the shadow of FIG. 7), the user determines that the remaining recognition result has no erroneous conversion, and ends the correction work halfway. can do.

In such a configuration, the character recognition device of the embodiment operates as follows. First, the processing control means 10
Calls the item setting means 20 to allow the user to specify where the recognition item of the form for character recognition is.
The item setting means 20 reads the form template with an image input device such as a scanner, displays the form on a display device such as a display, and allows the user to specify the area with a mouse or the like. Each recognition item is registered in the item setting storage unit 25. Next, the control means 10
Is called successively with the image input means 30 and the character recognition means for each form, and is repeated until there are no more forms. The image input unit 30 directly reads a document (form) as image data from an image input device such as a scanner or a copying machine,
Alternatively, the document may be read from the image input device, written in the storage device as a file, and read from this file. When one form is read, the character recognizing means 40 is called for the form, and character recognition processing is performed on the image area of the recognition item on the form. From each image data, an individual character image is cut out for each recognition area set in the item setting storage unit 25, the size is normalized, and the feature amount of the normalized character image is extracted. The feature amount is compared with the recognition dictionary, a certain number of candidate characters are obtained in the order of the certainty as the certainty of the recognition, and the candidate characters and the certainty are registered in the result storage unit 45 as the recognition result. . When registering in the result storage means 45, the input order number of the form (the form number is counted up when the recognition processing is performed), a pointer to the file of the image data of the form, and the recognition item in the form Creates a report header consisting of pointers to the representative value tables. In the representative value table, the number of characters of a character string in each recognition item and a pointer to a candidate character table are created. In the candidate character table, for each character image in the image character string in this area, the candidate character (character code) of the recognition result and its certainty are registered from the one with the highest certainty to the tenth place. .

When the input of the document (form) subjected to the character recognition is completed, the control means 10 first calls the representative value calculation means 50 in order to correct the recognition result. The representative value calculation means 50 calculates the representative value of each recognition item for each form registered in the result storage means 45 as follows, and additionally registers it in the result storage means 45. (A) The minimum value of the certainty factor of the first candidate character of each character in the recognition item. (B) The average value of the degrees of certainty of the first candidate character of each character in the recognition item. Next, the control means 10 calls the priority order indicating means 60. The priority order indicating means 60 displays the item names, area positions, and the like of the recognition items registered in the item setting storage means 25, and which of the items is important and which of the items is given priority. The user is instructed on the priority order of the correction, and the order is additionally registered in the item setting storage unit 20. Further, the priority order indicating means 60 may be configured to operate together with the item setting means 20. Next, the control unit 10 calls the correction order determination unit 70 in order to determine the order in which the correction of the recognition result should be performed efficiently. The correction order determination unit 70 regards the priority order of the recognition items stored in the item setting storage unit 25 as a sorting priority key, and sorts the recognition items in ascending order of the representative value of the recognition items.

This sort result is stored in the item “order” of the form header in the result storage means 45. In this sorting, when the same value exists as the representative value, one of the following processes is performed. (A) The order is determined based on the representative value of the next priority recognition item. (B) The order is determined based on the other representative values for the recognition items having the same value, in descending order. (C) If none of the above is used, the order is determined using another standard such as the order of the input document (form) or the number of characters of the recognition item. After such preparation, the control unit 10 calls the status display unit 80 to indicate the work status at the time of the correction work in which the user determines the candidate character as a result of the character recognition.
The status display by this call may be always displayed, or may be displayed only when specified by a menu or the like. The work status at this time displays the following contents for a certain recognition item on a display device such as a display using numerical values and graphs, and provides the user with information on which part is currently being corrected. (A) How the representative value of the item changes over the entire form (graph) (B) Number of sheets from the beginning of the form currently being corrected (numerical value and position on the graph) (C) This item of the form (Numerical value and graph) (D) Number of forms having the same representative value (numerical value) With the above configuration, a large number of documents created in a standard format like a form (Form)
In the work of correcting candidate characters after character recognition,
Since the user can understand how much processing amount is being processed, how much processing has been performed, and how much remains, the recognition result that does not need to be corrected at all has continued to some extent It is possible to determine whether the rest should be corrected and to end the operation halfway.

Since the user determines this termination, the criterion can be freely changed, so that the system can be operated flexibly. For example, it is possible to check strictly for important items, and to discontinue correction work for non-important items as soon as possible. Therefore,
When the number of documents (forms) is small, the effect of reducing the labor is increased, as well as the effect of improving the correction operation to obtain a high-quality recognition result in a shorter correction operation time in the case of a large amount of documents.

(2) Processing Flow FIG. 8 is a flowchart for explaining the processing flow of the character recognition device of this embodiment. The form template is read by an image input device such as a scanner, and is displayed on a display device such as a display.
The user is caused to specify where the recognition item area of the form for character recognition is located (step S100). The designated area is registered in the item setting storage unit 25 for each recognition item. One document (form) is directly read as image data from an image input device such as a scanner or a copying machine (step S110). Alternatively, the document may be read from the image input device, written as a file in the storage device, and read from the file as one image data. From one piece of image data, individual character images are cut out for each recognition area set in the item setting storage unit 25,
The size is normalized, the feature amount of the normalized character image is extracted, and the feature amount is compared with the recognition dictionary,
A certain number of candidate characters are obtained in ascending order of certainty as the probability of recognition, and the candidate characters and their certainty are registered in the result storage unit 45 as recognition results (step S12).
0). It is checked whether or not the input of the document (form) subjected to character recognition has been completed (step S130), and if not, the process returns to step S110 to read the next document (form). For each form registered in the result storage means 45, the representative value of each recognition item is calculated as follows, and additionally registered in the result storage means 45 (step S).
140). (A) The minimum value of the certainty factor of the first candidate character of each character in the recognition item. (B) The average value of the degrees of certainty of the first candidate character of each character in the recognition item. The item names, area positions, and the like of the recognition items registered in the item setting storage means 25 are displayed to determine which items are important and which items need to be corrected with priority. The user is instructed on the priority order, and the order is additionally registered in the item setting storage unit 20 (step S15).
0). The order in which the correction of the recognition result is performed and the correction can be performed efficiently is determined, and the order of the form to be corrected is stored in the item “order” of the form header of the result storage unit 45 (step S160). In this case, the priority of the recognition items stored in the item setting storage unit 25 is regarded as a sorting priority key, and the items are sorted in ascending order of the representative value of the recognition items.

In this sorting, when the same value exists as the representative value, one of the following processes is performed. (A) The order is determined based on the representative value of the next priority recognition item. (B) The order is determined based on the other representative values for the recognition items having the same value, in descending order. (C) If none of the above is used, the order is determined using another criterion such as the order of the input document (form) or the number of characters of the recognition item. After making such preparations, the user performs a correction operation to determine candidate characters as a result of character recognition (step S).
170). In the confirmation operation, the result storage means 45 is modified by selecting from lower candidate characters or newly inputting by the user, replacing the candidate character with the first candidate character. At this time, in order to indicate the work status, the user designates the work status with a menu or the like, and causes the display device such as a display to display the work status for a certain recognition item as follows. Such a work situation may be always displayed when the correction work is started. (A) How the representative value of the item changes over the entire form (graph) (B) Number of sheets from the beginning of the form currently being corrected (numerical value and position on the graph) (C) This item of the form (D) Number of forms having the same representative value (numerical value) When the correction work is completed, the first candidate character for each recognition item in the result storage unit 45 is character recognition. The result of the processing.

<Example by Computer> Further, the present invention is not limited to only the above-described embodiment. For example, the character recognition device of FIG. 1 can be realized by the configuration of a computer device as shown in FIG. 9 includes an input device 1, an output device 2, a CPU (Central Processing Unit) 3, a memory 4, a storage device 5, a medium drive device 6, and a network connection device 7. Are connected to each other. The input device 1 includes a keyboard, a mouse, a touch panel, a scanner, and the like, and is used to input text and image information. The output device 2 outputs various output information, information input from the input device 1, and the like, and is a display device or a printer device. The CPU 3 operates various programs. The memory 4 holds the program itself, and also holds information temporarily created when the program is executed by the CPU 3. The storage device 5
The item setting storage unit 25, the result storage unit 45, the dictionary for character recognition, the read image data, the program, and the temporary information when the program is executed are stored in the character recognition apparatus of the present invention. The medium drive device 6 loads a recording medium storing programs, data, and the like and reads them,
It is used for storing in the memory 4 or the storage device 5.
Further, it may be used for directly inputting / outputting data or executing a program.

As a recording medium, a semiconductor medium (for example, ROM, IC memory card, etc.), an optical medium (for example, ROM,
DVD, MO, MD, CD-R, etc.) and magnetic media (for example, magnetic tape, flexible disk, etc.). Each function of the character recognition apparatus shown in FIG. 1 is programmed and written in advance on a recording medium such as a CD-ROM.
By installing these programs in a computer equipped with a medium drive device 6 such as a ROM drive, and storing these programs in the memory 4 or the storage device 5 of each computer device, and executing them, A similar function can be realized. Further, not only the functions of the above-described embodiments are realized by executing the loaded program, but also the operating system or the like performs part or all of the actual processing based on the instructions of the program, and the processing performs The case where the functions of the above-described embodiments are realized is also included. Further, when the program for realizing the above-described embodiment is a semiconductor recording medium such as a ROM, the program is directly loaded into the memory 4 and executed not from the medium driving device 6.
Further, a program for realizing the functions of the above-described embodiment is loaded into the memory provided on the function expansion board or the function expansion unit, and the CPU or the like provided on the function expansion board or the function expansion unit is actually executed based on the instructions of the program. And a part of the entire process is performed, and the function of the above-described embodiment is realized by the process.

<Operation in Network Environment of the Present Invention> FIG. 10 shows a configuration of an embodiment in which the present invention is connected to a network and operated. In this case, the user terminal 110 and the server 120 are configured by the general-purpose computer devices shown in FIG. 9 and include the network connection devices 7 for connecting to the network 9. Also, this network 9 is a terminal 1 of these users.
This is a transmission line for connecting the server 10 and the server 120, and is generally realized by a cable, and TCP / IP is used as a communication protocol. However, the transmission path is not limited to the cable, and may use a wireless LAN or a broadcast wave as long as the communication protocol between them is the same. The server 120 stores a character recognition program for realizing the functions of the present invention in a storage device such as a magnetic disk. On the user terminal 110, the server 1
The character recognition program is received from the terminal 20, an image is input, the terminal 110 executes the received character recognition program, and outputs the execution result. This has the advantage that the latest character recognition program can always be used, and the recognition dictionary can be unique to the user. In addition, the server 11 sends the terminal 11
0 can be connected via the network 9 and distributed in a form such as download. Further, the program for realizing the functions of the present invention may be provided by distributing it by broadcast waves.

[0024]

As described above, according to the present invention,
Even when a large number of originals (forms) are input, it is possible to efficiently correct the character recognition result.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of a character recognition device according to an embodiment of the present invention.

FIG. 2 is a diagram for explaining a data structure of an item setting storage unit.

FIG. 3 is a diagram for explaining a data structure of a result storage unit.

FIG. 4 is a diagram for explaining a method of calculating a representative value (minimum value).

FIG. 5 is a diagram for explaining a method of calculating a representative value (average value).

FIG. 6 is a diagram showing an example of a screen displayed by the status display means.

FIG. 7 is a diagram for explaining a work load situation when a situation is displayed.

FIG. 8 is a flowchart for explaining processing of the character recognition device of the embodiment.

FIG. 9 is a diagram illustrating a hardware configuration when the character recognition device of the present invention is implemented by a computer.

FIG. 10 is a diagram showing a configuration of a mode in which the present invention is operated on a network.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Input device 2 Output device 3 CPU 4 Memory 5 Storage device 6 Medium drive device 7 Network connection device 8 Bus 9 Network 10 Control means 20 Item setting means 25 Item setting storage means 30 Image input means 40 Character recognition means 45 Result storage means 50 Representative value calculating means 60 priority order indicating means 70 correction order determining means 80 status display means 110 terminal 120 server

Claims (11)

[Claims] 1. A character recognition apparatus for obtaining information on the recognition result and certainty of characters in each of the recognition items in each of the forms of an image in which a plurality of forms including one or more recognition items are input as image data, Representative value calculating means for obtaining a representative value of each recognition item in each form from information on the likelihood of the recognition result, and priority order indicating means for indicating a priority for correcting the recognition result of each recognition item in the form Determining a correction order for correcting a recognition result based on the representative value of each recognition item obtained by the representative value calculating means in accordance with the priority specified by the priority specifying means. Means for correcting a recognition result. 2. The recognition result correcting apparatus according to claim 1, wherein the correction order determining means sets a priority of the recognition item designated by the priority designating means as a priority of the sort key, and a representative value of the recognition item. Wherein the order of forms to be corrected is determined by sorting the forms. 3. The recognition result correcting apparatus according to claim 2, wherein when there are a plurality of representative values having the same value, the correction order determining means recognizes the next priority of the form having the same representative value. By sorting by the representative value of the item,
A recognition result correcting apparatus, wherein the order of a form to be corrected is determined. 4. The recognition result correcting apparatus according to claim 2, wherein, when there are a plurality of representative values having the same value, the correction order determining unit determines, for a form having the same representative value, another form having the same representative value. A recognition result correcting apparatus, wherein the order of a form to be corrected is determined by sorting by a representative value. 5. The recognition result correcting apparatus according to claim 1, wherein said representative value calculation means includes a minimum value of certainty information of each character in said recognition item and / or A recognition result correction device, wherein an average value is calculated as a representative value. 6. A recognition result correcting apparatus according to claim 1, wherein a transition between a representative value of a recognition item to be corrected and a form currently being corrected is displayed. 1. A recognition result correcting apparatus comprising: 7. A character recognition method for obtaining information on a recognition result and certainty of a character in each recognition item in each form of an image in which a plurality of forms including one or more recognition items is input as image data, From the information on the likelihood of the recognition result, a representative value of each recognition item in each form is obtained, a priority order for correcting the recognition result of each recognition item in the form is designated, and the designated priority is sorted by a sort key. And determining the order of the form to be corrected by sorting the representative values of the recognition items. 8. The recognition result correcting method according to claim 7, wherein when sorting by a representative value, when there are a plurality of representative values of the same value, a form having the same representative value is recognized in the next priority order. A method of correcting a recognition result, wherein the order of a form to be corrected is determined by sorting by a representative value of an item. 9. The recognition result correcting apparatus according to claim 7, wherein when sorting by a representative value, when there are a plurality of representative values of the same value, a form having the same representative value is replaced with another one of the recognition items. A method of correcting a recognition result, wherein the order of a form to be corrected is determined by sorting by a representative value. 10. The method of correcting a recognition result according to claim 7, wherein a relation between a transition of a representative value of a recognition item to be corrected and a form currently being corrected is displayed. And displaying a current correction state. 11. A computer-readable recording medium having recorded thereon a program for realizing the function of the recognition result correcting apparatus according to claim 1. Description: