JP2008158988A - Information processor and control method therefor, program, and computer-readable storage medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To simplify the operation by an operator and improve the work efficiency, when setting a plurality of OCR (optical character recognition) target areas (fields) for image data of read business forms, and displaying results of the recognition processing of information in the fields. <P>SOLUTION: A scanner 109 for reading business forms as image data is provided, and in a CPU 101, a plurality of fields are set according to the kinds of the business forms read by the scanner 109, recognition processing (OCR) is performed to the information in the fields set for the image data of the business forms and a result of the OCR for each field is transited and displayed in each display area set in the display screen of the display 105. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an information processing apparatus and its control method for recognizing information in a set field for image data of a form, a program for causing a computer to execute the control method, and the program stored therein The present invention relates to a computer-readable storage medium.

  2. Description of the Related Art Conventionally, an information processing apparatus having a so-called OCR (Optical Character Recognition) function that reads a form on a recording medium such as paper as image data and recognizes information such as characters and symbols included in the read image data has been proposed. ing.

  In each existing company's OCR software, various confirmation correction screens for the recognition processing result are prepared, and some of them are excellent in usability. Many of these display one or more processing target areas and their recognition results side by side, and as a result of visual confirmation, after correcting a portion that requires correction, the next processing target is operated by key or mouse operation. The operation is performed in the procedure of proceeding to the area. However, these methods have a drawback that even if there is almost no erroneous recognition, a key or mouse operation is required and the efficiency is not so high.

  Therefore, in order to eliminate this drawback, for example, Patent Document 1 and Patent Document 2 below propose an effective correction method and confirmation method for the recognition processing result.

  In Patent Document 1, only a portion of a manuscript (form) on which necessary data to be input is displayed is displayed in the vicinity of a designated position of a fixed format to which the data is to be input, and a necessary portion of the form to be input is displayed on the screen. While seeing above, a technique is disclosed in which data can be input from a keyboard at a designated position in a fixed format next to it.

  Patent Document 2 discloses a technique that displays a form image and a list of items of a plurality of OCR target areas, and further displays a recognition result on the same screen. At this time, in Patent Document 2, error information and the like are also displayed in the item list, and it is difficult for the operator to overlook a recognition error.

JP-A-2-238575 JP-A-11-353411

  However, in Patent Document 1 described above, since the necessary part of the form is not displayed unless the designated position of the standard format is designated with the keyboard, the operator's operation is performed when performing the procedure of confirming and correcting all items displayed. There is a problem that becomes complicated.

  Also, in Patent Document 2 described above, when there are a plurality of OCR target areas, there is no change in displaying a recognition result by an operator's operation and confirming and selecting a correction target item. There is a problem that the operation of the operator becomes complicated. Furthermore, when the number of recognition errors is small with respect to the number of OCR target areas, there is a problem that the possibility of overlooking a recognition error increases.

  That is, in the conventional information processing apparatus, when a plurality of OCR target areas (fields) are set for the read form image data and the recognition processing result of the information in the field is displayed, an operation by the operator is performed. There is a problem that it becomes complicated and it is difficult to improve the working efficiency.

  The present invention has been made in view of the above-described problems. When a plurality of OCR target areas (fields) are set for image data of a read form and a result of recognition processing of information in the field is displayed. Another object of the present invention is to simplify the operation by the operator and improve the working efficiency.

  An information processing apparatus according to the present invention includes a field setting unit that sets a plurality of fields according to the type of a form read as image data, and a field in the field set by the field setting unit for the image data. Information recognition means for performing information recognition processing; display means for displaying a recognition processing result by the information recognition means for each field; and a plurality of display areas for displaying the recognition processing results for each field. Display control means for performing display control by transitioning to.

  According to the control method of the information processing apparatus of the present invention, a field setting step for setting a plurality of fields according to the type of form read as image data, and the field setting step for the image data are set. An information recognition step for recognizing information in a field, and when displaying the recognition processing result by the information recognition step for each field for each display area, the recognition processing result for each field is And a display control step for performing display control by transitioning to each display area.

  A program according to the present invention is a program for causing a computer to execute a control method of an information processing apparatus including a display unit having a plurality of display areas, and a plurality of programs according to the type of form read as image data. A field setting step for setting a field; an information recognition step for recognizing information in the field set in the field setting step for the image data; and for each display area for each field When displaying the recognition processing result in the information recognition step, the computer executes a display control step for performing control to display the recognition processing result for each field by transitioning to each display area. .

  The computer-readable storage medium of the present invention stores the program.

  According to the present invention, when a plurality of OCR target areas (fields) are set for the read form image data and the recognition processing result of the information in the field is displayed, the operation by the operator is simplified, Efficiency can be improved.

  The best mode for carrying out the present invention will be described below in detail with reference to the accompanying drawings.

FIG. 1 is a schematic configuration diagram of an information processing apparatus 100 according to an embodiment of the present invention.
As shown in FIG. 1, the information processing apparatus 100 includes a CPU 101, a RAM 102, a ROM 103, an external storage unit 104, a display 105, a keyboard 106, a speaker 107, a pointing device 108, and a scanner 109, which are connected via a system bus 110. Are connected to each other.

  The CPU 101 controls the operation of the information processing apparatus 100 in an integrated manner, and controls each component (102 to 109) of the information processing apparatus 100 via the bus 110.

  The RAM 102 functions as a main memory, work area, and the like for the CPU 101. When executing the processing, the CPU 101 loads a necessary program from the ROM 103 to the RAM 102 and executes the program to implement various operations.

  The ROM 103 stores a basic input / output system (BIOS) and an operating system program (OS), which are control programs for the CPU 101, and programs necessary for the CPU 101 to execute the processes shown in FIGS. Yes.

  The external storage unit 104 includes image data read by the scanner 109, information related to field settings to be described later, information related to recognition processing results of information in the fields, and information on the probability value 104a to be described later. Various types of information are stored.

  The display 105 functions as a display unit that displays various images, various information, and the like based on control by the CPU 101.

  The keyboard 106 and the pointing device 108 function as input means (operation means) for inputting various instructions from the operator to the CPU 101.

  The speaker 107 functions as sound generating means for generating sound based on control by the CPU 101.

  The scanner 109 functions as a reading unit that reads a form or the like as image data based on control by the CPU 101.

Next, a control method of the information processing apparatus 100 configured as shown in FIG. 1 will be described.
FIG. 2 is a flowchart showing a control method of the information processing apparatus 100 according to the embodiment of the present invention.

  First, in step S201, the CPU 101 performs pre-processing. The pre-processing in step S201 will be described in detail with reference to FIG.

  In the pre-processing in step S201, first, in step S301 in FIG. 3, the CPU 101 causes the scanner 109 to read the set form. Here, it is assumed that the scanner 109 reads a plurality of set forms as image data, and the image data read by the scanner 109 is stored in the external storage unit 104 under the control of the CPU 101.

  Subsequently, in step S302, the CPU 101 sets a form identification code for each type of form read by the scanner 109 in step S301. At this time, the CPU 101 stores the set form identification code in association with the image data stored in the external storage unit 104. As a method for setting the form identification code in step S302, for example, a number is assigned to the form in advance, and the number is recognized from the image data of the form (OCR) to form a form identification code. And a method of analyzing the layout of the image data of the form and setting a form identification code for each type of layout.

  Subsequently, in step S303, the CPU 101 sets a plurality of OCR target areas (hereinafter referred to as “fields”) according to the form identification code (that is, the form type) set in step S302. (Field setting means) to acquire the position coordinates of each field. In this embodiment, in this step S303, for example, a field is set using a template corresponding to the form identification code stored in the external storage unit 104. The field setting in step S303 may be performed based on information designated by the operator for each type of form from the input means, for example.

11 and 12 are schematic diagrams illustrating an example of a form.
11 shows that a plurality of fields shown in 11-1 to 11-N are set. In the form shown in FIG. 12, 5 shown in 12-1 to 12-5. Shows that two fields are set. In step S303, the position coordinates of each field set according to the form type are acquired.

  Subsequently, in step S304, the CPU 101 first performs information recognition processing (OCR) in the field set in step S303 for the image data of the form read in step S301 (information recognition unit). At this time, the information to be recognized includes not only characters but also symbols such as a check entered in check boxes indicated by fields 11-8 to 11-N in FIG. Next, the CPU 101 calculates the probability value of the recognition processing result for the image data of the field for each field (first calculation unit). The CPU 101 stores the calculated probability value (probability value) 104a for each field in the external storage unit 104 in association with the image data of the form. Here, when calculating the probability value 104a, for example, feature points in the image data of the set field are extracted, and are calculated based on the coincidence point and the difference with the information related to the recognition processing result. The calculated value is expressed as a percentage or a score.

  Subsequently, in step S <b> 305, the CPU 101 determines whether reading of all the forms set in the scanner 109 has been completed. As a result of the determination, if there is a form that has not yet been read, the process returns to step S301. On the other hand, as a result of the determination in step S305, if all the forms have been read, the process in step S201 is terminated.

  Through the processes in steps S301 to S305, the probability value 104a based on the result of the information recognition process in the field set according to the type of the read form is stored in the memory (external storage unit 104). Pre-processing in step S201 is performed.

  When the preliminary process in step S201 is completed, the CPU 101 performs a result display process in step S202 in FIG. The result display process in step S202 will be described in detail with reference to FIG.

  In the result display process of step S202, first, in step S401 of FIG. 4, the CPU 101 calculates the average value of the probability values 104a for each type of form from the probability values 104a stored in the external storage unit 104 ( (Second calculation means) performs a result alignment process for aligning the forms in descending order from the form with the highest average value. Detailed processing in step S401 will be described later with reference to FIG.

  Subsequently, in step S402, the CPU 101 sets and prepares a plurality of display areas for displaying the recognition processing results for each field (hereinafter referred to as “OCR results”) on the display 105 as display means. . Here, in this embodiment, as shown in 81 to 85 in FIG. 8 described later, five display areas are prepared.

  Subsequently, in step S403, the CPU 101 performs a setting to display the OCR result for each field in order from the form with the higher average value of the probability values 104a arranged in the result arrangement process in step S401. Specifically, in step S403, first, a form that has been read in the pre-processing in step S201 and that has not been subjected to the processing in step S405 described later is the highest average value of the probability values 104a. Set. Then, the number of fields of the form is set and the initial value of the number of fields to be displayed is set to zero.

  Subsequently, in step S404, the CPU 101 increases the number of fields to be displayed by 1 (+1).

  Subsequently, in step S405, the CPU 101 performs a screen transition control process in which the OCR result for each field in the form set in step S403 is displayed by transitioning to the five display areas prepared in step S402 (display control unit). ). Detailed processing in step S405 will be described later with reference to FIG.

  Subsequently, in step S406, the CPU 101 determines whether or not the OCR results of all fields of the form have been displayed. If it is determined that there is a field that has not been displayed yet, the process returns to step S404.

  On the other hand, as a result of the determination in step S406, when the display of the OCR results for all fields is completed, in step S407, the CPU 101 determines whether or not the OCR results for all the forms have been displayed. To do. If there is a form that has not been displayed as a result of this determination, the process returns to step S403. On the other hand, as a result of the determination in step S407, when the display of the OCR results for all the forms is completed, the processing in step S202 is terminated.

  As a result of the processing in steps S401 to S407, the result display processing in step S202 is performed in which the OCR results for each field obtained in step S201 are automatically displayed in the five display areas set in the display 105. The

Next, detailed processing of the result alignment processing in step S401 in FIG. 4 will be described.
FIG. 5 is a flowchart showing detailed processing of the result alignment processing in step S401 of FIG.

  In the result alignment process in step S401, first, in step S501 in FIG. 5, the CPU 101 substitutes the first read form identification code into “CurrentCode” indicating the current form identification code.

  Subsequently, in step S502, the CPU 101 determines whether or not “CurrentCode” is equal to (matches) the read form identification code. As a result of this determination, if “CurrentCode” is equal to (matches) the read form identification code, the process proceeds to step S503. If the form identification code is read first, the substitution process is performed in step S501, and therefore, it is determined that they are equal (match) in step S502.

  In step S503, the CPU 101 calculates an average value of the probability values 104a of each field in the read form type. If the average value of the probability value 104a of each field in the same form type has been calculated before, in step S503, the total average value is calculated in consideration of these.

  On the other hand, if it is determined in step S502 that “CurrentCode” is different from the read form identification code (when it is determined that the form is different from the current form), then in step S504, the CPU 101 It is determined whether or not the type of form that appears for the first time.

  If it is determined that the type of the form appears for the first time in step S504, then in step S505, the CPU 101 calculates the average value of the probability values 104a of the fields in the read form type.

  On the other hand, if it is determined in step S504 that the form does not appear for the first time (when it is determined that there is the same type as the form read in the past), then in step S506, the CPU 101 reads the form. The average value of the field likelihood values 104a in the form type is calculated from the field likelihood values 104a in the form and a form that has previously appeared of the same type as the form.

  When the process of step S505 or step S506 is completed, in step S507, the CPU 101 assigns the read form identification code to “CurrentCode”.

  When the process of step S503 or step S507 is completed, in step S508, the CPU 101 reads the next form identification code.

  Subsequently, in step S509, the CPU 101 determines whether or not the average value of the probability values 104a of all the forms has been calculated. As a result of the determination, if there is a form for which the calculation of the average value of the probability values 104a has not been completed, the process returns to step S502. On the other hand, if the average value of the probability values 104a of all the forms is calculated as a result of the determination in step S509, subsequently, in step S510, the CPU 101 descends in descending order from the type of form having a high average value of the probability values 104a. Line up the forms.

  Through the processing of the above steps S501 to S510, the average value of the probability value 104a is calculated for each type of form from the probability value 104a stored in the external storage unit 104, and the form having the higher average value is calculated. As a result of the arrangement in step S401, the forms are arranged in descending order.

Next, detailed processing of the screen transition control processing in step S405 of FIG. 4 will be described.
FIG. 6 is a flowchart showing detailed processing of the screen transition control processing in step S405 of FIG.

  In the screen transition control process of step S405, first, in step S601 of FIG. 6, the CPU 101 performs a result substitution process that substitutes and displays the OCR results of each field in the five display areas set on the display 105. Here, the detailed process of the result substitution process in step S601 will be described with reference to FIGS.

  FIG. 7 is a flowchart showing detailed processing of the result substitution processing in step S601 of FIG. 8 to 10 are schematic diagrams showing display screens on the display 105 when displaying the OCR results of each field in the set five display areas.

  In the result substitution process in step S601, first, in step S701 in FIG. 7, the CPU 101 determines whether or not the number of fields for displaying the OCR result is one. As a result of this determination, when the number of fields for displaying the OCR result is 1 (when displaying the first field), subsequently, in step S702, the CPU 101 displays the third display area of the display 105 in the third display area. The OCR result in the first field and the original image in the field are substituted and displayed.

Here, the process of step S702 will be described with reference to FIG.
FIG. 8 shows a display screen of the OCR result on the display 105. On the display screen, a form image 80 based on the image data read in step S301 is displayed and the five display areas 81 set in step S402 are displayed. ˜85, an OK button 86 and a correction button 87. In the example shown in FIG. 8, it is assumed that the fields shown in 8-1 to 8-6 are set in step S303. Each display area 81-85 is provided with original image display areas 81a-85a for displaying the image data of the form in each field and OCR result display areas 81b-85b for displaying the OCR result in each field. It has been. In this embodiment, when the correction button 87 is pressed by the operator, the OCR result stopped and displayed in the third display area 83 (OCR result display area 83b) can be corrected.

  In step S702 described above, the OCR result in the first field 8-1 is displayed in the OCR result display area 83b in the third display area 83 shown in FIG. 8, and the original image in the field 8-1 is displayed as the original image. It is displayed in the area 83a.

  If it is determined in step S701 in FIG. 7 that the number of fields for displaying the OCR result is not 1, then in step S703, the CPU 101 determines whether the number of fields for displaying the OCR result is two. Judging. If the number of fields for displaying the OCR result is 2 as a result of this determination, then in step S704, the CPU 101 displays the second in the OCR result display area 84b of the fourth display area 84 shown in FIG. The OCR result in the field 8-2 is displayed, and the original image in the field 8-2 is displayed in the original image display area 84a.

  If it is determined in step S703 in FIG. 7 that the number of fields for displaying the OCR result is not two, then in step S705, the CPU 101 determines whether the number of fields for displaying the OCR result is three. Judging. If the number of fields for displaying the OCR result is three as a result of this determination, then in step S706, the CPU 101 displays the third in the OCR result display area 85b of the fifth display area 85 shown in FIG. The OCR result in the field 8-3 is displayed, and the original image in the field 8-3 is displayed in the original image display area 85a.

  If it is determined in step S705 in FIG. 7 that the number of fields for displaying the OCR result is not 3, the screen transition start state is followed, and then in step S707, the CPU 101 determines the field for displaying the OCR result. It is determined whether or not the number is 4.

  If the number of fields for displaying the OCR result is four as a result of the determination in step S707, the following processing in steps S708 to S711 is performed simultaneously to obtain the display screen state shown in FIG.

  In step S708, the CPU 101 performs control to display the OCR result and the original image displayed in the third display area 83 in FIG. 8 in the second display area 82 shown in FIG. In step S709, the CPU 101 performs control to display the OCR result and the original image displayed in the fourth display area 84 in FIG. 8 in the third display area 83 shown in FIG. In step S710, the CPU 101 performs control to display the OCR result and the original image displayed in the fifth display area 85 in FIG. 8 in the fourth display area 84 shown in FIG. In step S711, the CPU 101 performs control to display the OCR result and the original image in the fourth field 8-4 in the fifth display area 85 in FIG.

  If it is determined in step S707 in FIG. 7 that the number of fields for displaying the OCR result is not four, in step S712, the CPU 101 determines whether the number of fields for displaying the OCR result is five or more. Determine whether.

  As a result of the determination in step S712, if the number of fields for displaying the OCR result is five or more, the following processes in steps S713 to S718 are simultaneously performed to obtain the display screen state shown in FIG.

  In step S713, the CPU 101 performs control to delete the OCR result and the original image displayed in the first display area 81. At this time, if nothing is displayed in the first display area 81, the process of step S713 is not performed. In step S714, the CPU 101 performs control to display the OCR result and the original image displayed in the second display area 82 in FIG. 9 in the first display area 81 shown in FIG. In step S715, the CPU 101 performs control to display the OCR result and the original image displayed in the third display area 83 in FIG. 9 in the second display area 82 shown in FIG. In step S716, the CPU 101 performs control to display the OCR result and the original image displayed in the fourth display area 84 in FIG. 9 in the third display area 83 shown in FIG. In step S717, the CPU 101 performs control to display the OCR result and the original image displayed in the fifth display area 85 in FIG. 9 in the fourth display area 84 shown in FIG. In step S718, the CPU 101 displays the OCR result and the original image in the fifth and subsequent fields (the fifth field 8-5 in the example shown in FIG. 10) in the fifth display area 85 in FIG. Control the display.

  If the processing in step S702, S704, S706, S711, or S718 is completed, or if it is determined in step S712 that the number of fields for displaying the OCR result is less than 5, the processing in step S601 is terminated.

  Through the processes in steps S701 to S718, the result substitution process in step S601 is performed in which the OCR results of each field are substituted and displayed in the five display areas 81 to 85 set on the display 105.

  In FIG. 6, when the process of step S601 is completed, subsequently, in step S602, the CPU 101 externally stores the likelihood value 104a in the OCR result of the field (newly displayed field) set by the process of step S404. It is extracted from the unit 104, and it is determined whether or not the extracted probability value is larger than the determination value 1 (first determination means). Here, the determination value 1 is a value at which it can be determined that the OCR result is correct.

  As a result of the determination in step S602, when the probability value is larger than the determination value 1, subsequently, in step S603, the CPU 101 performs control so as not to sound a beep sound emitted from the speaker 107.

  Subsequently, in step S604, the CPU 101 determines whether or not the probability value larger than the determination value 1 continues five times or more (whether or not the field of the probability value larger than the determination value 1 continues five or more times). To do. Note that in step S604 of the present embodiment, the probability value larger than the determination value 1 may be five times or more, for example, two times, three times, four times, or other times. As a result of the determination in step S604, if the probability value larger than determination value 1 does not continue five times or more, the process returns to step S601.

  On the other hand, as a result of the determination in step S604, if the probability value larger than the determination value 1 continues five times or more, subsequently, in step S605, the CPU 101 determines the screen transition speed (each display area 81 to 81). It is determined whether or not the transition display speed at 85 is less than a certain speed. If the result of this determination is that the screen transition speed is not less than a certain speed, the process returns to step S601.

  On the other hand, if the result of determination in step S605 is that the screen transition speed is less than a certain speed, then in step S606, the CPU 101 transitions to each display area 81 to 85 such as the OCR result in the field. Display control is performed to increase the display speed to the constant speed. When the process of step S606 ends, the process returns to step S601.

  As a result of the determination in step S602, if the probability value is equal to or smaller than the determination value 1, subsequently, in step S607, the CPU 101 performs control to make a beep sound from the speaker 107.

  Subsequently, in step S608, the CPU 101 performs setting to return the screen transition speed to the default.

  Subsequently, in step S609, the CPU 101 determines whether or not the probability value 104a in the OCR result of the field (newly displayed field) set by the process in step S404 is larger than the determination value 2. Here, the determination value 2 is a value smaller than the determination value 1, and is a value at which it can be determined that the OCR result is probably correct.

  As a result of the determination in step S609, if the probability value is larger than the determination value 2, subsequently, in step S610, the CPU 101 determines that the OCR result of the field is the third display area 83 (OCR result display area 83b). ) Is displayed.

  As a result of the determination in step S610, when the OCR result of the field is displayed in the third display area 83 (OCR result display area 83b), subsequently, in step S611, the CPU 101 displays the current transition display. Is controlled to stop for 0.5 seconds.

  When the process of step S611 is completed, in step S613, the CPU 101 determines whether there is a correction request from the operator. Whether or not a correction request can be made in step S613 is determined based on whether or not the correction button 87 has been pressed by the operator. If there is no correction request from the operator as a result of this determination, the process returns to step S601.

  On the other hand, as a result of the determination in step S613, if there is a correction request from the operator, subsequently, in step S614, the CPU 101 stops the screen transition process. Subsequently, in step S615, the CPU 101 permits correction of the OCR result from the operator via the keyboard 106 or the like, and restarts the screen transition process when the OK button 86 is pressed by the operator. Thereafter, the process returns to step S601.

  On the other hand, as a result of the determination in step S610, when the OCR result of the field is not displayed in the third display area 83 (OCR result display area 83b), the process in the field moves to step S601, When the OCR result of the field is displayed in the third display area 83 (OCR result display area 83b), the CPU 101 performs control to stop the transition display for 0.5 seconds (S612). When it is determined in step S610 that the OCR result of the field is not displayed in the third display area 83 (OCR result display area 83b), the OCR result of the field is displayed in the third display area 83 (OCR Information indicating that the transition display is controlled to stop for 0.5 seconds when displayed in the result display area 83b) is stored in, for example, the RAM 102 and held until the CPU 101 performs stop control for 0.5 seconds based on the information. Is done. And if the process of step S612 is performed, the process of step S613-S615 mentioned above will be performed as needed, and it will return to step S601.

  As a result of the determination in step S609, if the probability value is equal to or less than the determination value 2, subsequently, in step S616, the CPU 101 determines the field (newly displayed field) set by the process in step S404. It is determined whether or not the probability value 104a in the OCR result is larger than the determination value 3 (second determination means). Here, the determination value 3 is a value smaller than the determination value 2, and is a value at which it can be determined whether or not the OCR result is an error.

  As a result of the determination in step S616, when the probability value is larger than the determination value 3, the OCR result is at a level at which it can be determined that an error is probably caused. In this case, in step S617, the CPU 101 determines whether or not the OCR result of the field is displayed in the third display area 83 (OCR result display area 83b).

  As a result of the determination in step S617, when the OCR result of the field is displayed in the third display area 83 (OCR result display area 83b), subsequently, in step S618, the CPU 101 displays the current transition display. Is controlled to stop for 1.0 second.

  When the process of step S618 ends, in step S620, the CPU 101 determines whether there is a correction request from the operator. Whether or not the correction request can be made in step S620 is determined based on whether or not the correction button 87 has been pressed by the operator. If there is no correction request from the operator as a result of this determination, the process returns to step S601.

  On the other hand, as a result of the determination in step S620, if there is a correction request from the operator, then in step S621, the CPU 101 stops the screen transition process. Subsequently, in step S622, the CPU 101 permits correction of the OCR result from the operator via the keyboard 106 or the like, and restarts the screen transition process when the OK button 86 is pressed by the operator. Thereafter, the process returns to step S601.

  On the other hand, as a result of the determination in step S617, if the OCR result of the field is not displayed in the third display area 83 (OCR result display area 83b), the process in the field moves to step S601, When the OCR result of the field is displayed in the third display area 83 (OCR result display area 83b), the CPU 101 performs control to stop the transition display for 1.0 second (S619). When it is determined in step S617 that the OCR result of the field is not displayed in the third display area 83 (OCR result display area 83b), the OCR result of the field is displayed in the third display area 83 (OCR Information indicating that the transition display is controlled to stop for 1.0 second when displayed in the result display area 83b) is stored in, for example, the RAM 102 and held until the CPU 101 performs stop control for 1.0 second based on the information. Is done. And if the process of step S619 is performed, the process of step S620-S622 mentioned above will be performed as needed, and it will return to step S601.

  As a result of the determination in step S616, when the probability value is equal to or smaller than the determination value 3, the OCR result is determined to be an error. In this case, in step S623, the CPU 101 performs control to add a color to the background of the display area of the field, that is, to change and display the background color of the display area. For example, in the example of FIG. 8, since the OCR result in the third field 8-3 displayed in the fifth display area 85 is equal to or less than the determination value 3, the fifth display area 85 (original image display area) The background of 85a) is changed to color 88. In the example of FIG. 8, “173” handwritten in the field 8-3 is processed as the OCR result “773”, and this is displayed in the OCR result display area 85 a. In the present embodiment, as shown in FIG. 8, the background color of the original image display area 85a is changed. For example, the background color of the OCR result display area 85a may be changed. Alternatively, the background colors of both the original image display area and the OCR result display area may be changed. In this way, by changing the background color, it is possible to notify the operator that the OCR result is an error.

  Subsequently, in step S624, the CPU 101 determines whether or not the OCR result of the field is displayed in the third display area 83 (OCR result display area 83b).

  If the result of determination in step S624 is that the OCR result for that field is displayed in the third display area 83 (OCR result display area 83b), then in step S625, the CPU 101 performs screen transition processing. Control to stop.

  When the process of step S625 ends, subsequently, in step S627, the CPU 101 determines whether or not the correction button 87 is pressed by the operator and there is a correction input of the OCR result via the keyboard 106 or the like. As a result of this determination, if there is no correction input, the screen transition process is resumed, and the process returns to step S601.

  On the other hand, if there is a correction input as a result of the determination in step S627, subsequently, in step S628, the CPU 101 permits the correction input and triggers that the OK button 86 is pressed by the operator. Then, the color 88 attached to the background of the display area of the OCR result in the field is removed, and the screen transition process is restarted. Thereafter, the process returns to step S601.

  On the other hand, as a result of the determination in step S624, if the OCR result of the field is not displayed in the third display area 83 (OCR result display area 83b), the process in the field moves to step S601, When the OCR result of the field is displayed in the third display area 83 (OCR result display area 83b), the CPU 101 performs control to stop the screen transition process (S626). When it is determined in step S624 that the OCR result of the field is not displayed in the third display area 83 (OCR result display area 83b), the OCR result of the field is displayed in the third display area 83 (OCR Information indicating that the screen transition process is controlled to be stopped when displayed in the result display area 83b) is stored in, for example, the RAM 102 and held until the CPU 101 performs stop control based on the information. And if the process of step S626 is performed, the process of step S627 and S628 mentioned above will be performed as needed, and it will return to step S601.

  The screen transition control process of step 405 that causes the plurality of display areas 81 to 85 set on the display screen of the display 105 to display the OCR results in a transitional manner through the processes of steps S601 to S628 described above. Made.

  According to the information processing apparatus 100 according to the present embodiment, when a plurality of fields are set for the read form image data and the OCR result of the information in the field is displayed on the display 105, the OCR for each field is displayed. Since the result is automatically displayed in transition in each of the display areas 81 to 85 set on the display screen of the display 105, an operation for selecting the OCR result of each field is not necessary, thereby simplifying the operation by the operator. It is possible to improve work efficiency.

  Further, according to the information processing apparatus 100 according to the present embodiment, for each type of form, the average value in the probability value 104a is calculated, and each display area is displayed in descending order from the OCR result relating to the form with the high average value. Since the transition display is performed from 81 to 85, it is possible to sequentially check the OCR result of a form with a high average value of the probability value 104a, so it is possible to further improve the work efficiency. It becomes.

  Further, according to the information processing apparatus 100 according to the present embodiment, when the probability value in the field is equal to or less than the determination value 1 (a value at which the OCR result can be determined to be correct), the information is notified from the speaker 107 with a beep sound. Since this is done (step S607), it is possible to reduce oversight of errors in the OCR result. In addition, it is not necessary to keep visual inspection.

  Further, according to the information processing apparatus 100 according to the present embodiment, when the probability value in the field is the determination value 3 or less (when the OCR result can be determined to be an error), the screen transition process is stopped. Since it did in this way (step S625, S626), the error of an OCR result can be corrected reliably, and it becomes possible to aim at the efficiency of the confirmation of the OCR result, and the correction work.

  Each unit of FIG. 1 constituting the information processing apparatus 100 according to the present embodiment and each step of FIG. 2 to FIG. 7 showing the control method of the information processing apparatus 100 are stored in a RAM or a ROM of a computer. It can be realized by running the program. This program and a computer-readable storage medium storing the program are included in the present invention.

  Specifically, the program is recorded in a storage medium such as a CD-ROM, or provided to a computer via various transmission media. As a storage medium for recording the program, a flexible disk, a hard disk, a magnetic tape, a magneto-optical disk, a nonvolatile memory card, and the like can be used in addition to the CD-ROM. On the other hand, as the transmission medium of the program, a communication medium in a computer network (LAN, WAN such as the Internet, wireless communication network, etc.) system for propagating and supplying program information as a carrier wave can be used. Moreover, examples of the communication medium at this time include a wired line such as an optical fiber, a wireless line, and the like.

  Moreover, not only the function of the information processing apparatus 100 according to the present embodiment is realized by executing a program supplied by the computer, but also an OS (operating system) or other application in which the program is running on the computer. When the functions of the information processing apparatus 100 according to the present embodiment are realized in cooperation with software, all or part of the processing of the supplied program is performed by a function expansion board or a function expansion unit of the computer. Such a program is also included in the present invention when the functions of the information processing apparatus 100 according to the present embodiment are realized.

1 is a schematic configuration diagram of an information processing apparatus according to an embodiment of the present invention. It is a flowchart which shows the control method of the information processing apparatus which concerns on embodiment of this invention. It is a flowchart which shows the detailed process of the pre-process in step S201 of FIG. It is a flowchart which shows the detailed process of the result display process in step S202 of FIG. It is a flowchart which shows the detailed process of the result alignment process in FIG.4 S401. It is a flowchart which shows the detailed process of the screen transition control process in FIG.4 S405. It is a flowchart which shows the detailed process of the result substitution process in step S601 of FIG. It is a schematic diagram which shows the display screen of a display at the time of displaying the recognition process result (OCR result) of each field in the set five display area. It is a schematic diagram which shows the display screen of a display at the time of displaying the recognition process result (OCR result) of each field in the set five display area. It is a schematic diagram which shows the display screen of the display at the time of displaying the recognition process result (OCR result) of each field in the set five display area. It is a schematic diagram which shows an example of a form. It is a schematic diagram which shows an example of a form.

Explanation of symbols

100 Information processing apparatus 101 CPU
102 RAM
103 ROM
104 External storage unit 104a Probability value 105 Display 106 Keyboard 107 Speaker 108 Pointing device 109 Scanner 110 System bus 80 Form image 8-1 to 8-6, 11-1 to 11-N, 12-1 to 12-5 Field 81 -85 Display area 81a-85a Original image display area 81b-85b OCR result display area 86 OK button 87 Correction button

Claims (11)

Field setting means for setting a plurality of fields according to the type of form read as image data,
Information recognition means for recognizing information in the field set by the field setting means for the image data;
Display means comprising a plurality of display areas for displaying recognition processing results by the information recognition means for each field;
An information processing apparatus comprising: a display control unit configured to control to display the recognition processing result for each field by transitioning to each display area. A first calculating unit that calculates a probability value of the recognition processing result of the field for the image data in the field set by the field setting unit;
2. The display control unit controls transition display for each display area of the recognition processing result in the field according to the probability value calculated by the first calculation unit. The information processing apparatus described in 1.   The information processing apparatus according to claim 2, wherein the display control unit controls a speed of transition display for each of the display areas in accordance with the probability value. For each type of form, further comprising second calculation means for calculating an average value of the probability values calculated by the first calculation means;
3. The display control unit according to claim 2, wherein the display control unit sequentially performs a transition display on each of the display areas from the recognition processing result relating to the form having a high average value calculated by the second calculation unit. 3. The information processing apparatus according to 3. Based on the probability value calculated by the first calculation means, further comprising first determination means for determining whether or not the recognition processing result of the field is correct;
When a predetermined number of fields determined to be correct by the first determination means continue, the display control means increases the speed of the transition display for each display area of the recognition processing result in the field to a certain speed. The information processing apparatus according to claim 2, wherein the information processing apparatus is an information processing apparatus.   6. The apparatus according to claim 5, further comprising voice generating means for generating and notifying a voice when displaying the recognition processing result of the field that is not determined to be correct by the first determining means on the display means. The information processing apparatus described in 1. Based on the probability value calculated by the first calculation means, further comprising second determination means for determining whether or not the recognition processing result of the field is an error;
When the display control means displays the recognition processing result of the field determined to be an error by the second determination means on the display means, the display control means stops in any one of the display areas. The information processing apparatus according to any one of claims 2 to 6, wherein the information processing apparatus displays the display area while changing the color of the background of the display area stopped and displayed.   The information processing apparatus according to claim 1, wherein the image data in the field is displayed in the display area together with the recognition processing result for each field. A method for controlling an information processing apparatus including a display unit having a plurality of display areas,
A field setting step for setting a plurality of fields according to the type of form read as image data,
An information recognition step for recognizing information in the field set in the field setting step for the image data;
Display control for controlling each display area to display the recognition process result for each field by transitioning to each display area when displaying the recognition process result by the information recognition step for each field. And a method for controlling the information processing apparatus. A program for causing a computer to execute a control method of an information processing apparatus including a display unit having a plurality of display areas,
A field setting step for setting a plurality of fields according to the type of form read as image data,
An information recognition step for recognizing information in the field set in the field setting step for the image data;
Display control for controlling each display area to display the recognition process result for each field by transitioning to each display area when displaying the recognition process result by the information recognition step for each field. A program that causes a computer to execute steps and.   A computer-readable storage medium storing the program according to claim 10.

Images