JP7787779B2 - Form recognition processing system, form recognition processing method, and form recognition processing program - Google Patents

Description

The present invention relates to a form recognition processing system, a form recognition processing method, and a form recognition processing program.

Patent Document 1 describes an automated teller machine installed in financial institutions and other institutions. This automated teller machine performs character recognition of the contents of payment slips, invoices, etc., and performs payment transactions for taxes, utility bills, etc.

Patent Document 2 describes a device that recognizes characters written on paper sheets. The video coding system in Patent Document 2 includes multiple recognition units. A second recognition unit performs character recognition on sorting information on paper sheets that could not be recognized by the first recognition unit using a different algorithm than the first recognition unit.

Japanese Patent Application Laid-Open No. 2018-197996 JP 2010-009410 A

Text indicating the payer's name, payment amount, etc. is printed on forms handled by automated teller machines. Printing errors can cause the text to be blurred or misaligned. If the automated teller machine encounters an error indicating it cannot recognize the characters, it cannot process the form. Therefore, no incorrect processing will be performed on the form. However, if it recognizes characters that differ from what is printed, for example, misrecognizing the number "8" as "9" or misrecognizing "￥8200" as "￥820," there is a risk that incorrect processing will be performed that differs from the true content of the form.

With the technology in Patent Document 2, if a first recognition unit is unable to recognize a character, a second recognition unit performs character recognition on top of it, thereby increasing the recognition rate (recognition success rate). However, if a character is misrecognized, the second recognition unit does not perform processing, because recognition has "successfully" been performed even though the content is incorrect. Therefore, the technology in Patent Document 2 cannot solve the above problem.

The object of the present invention is to provide a form recognition processing system, a form recognition processing method, and a form recognition processing program that make it easier to detect misrecognition of characters written on forms.

The form recognition processing system according to the present invention is characterized in that it performs recognition processing on forms that have multiple character areas, which are areas in which the same characters are written, and includes an image acquisition unit that acquires an image of the form, and a character recognition unit that recognizes character information from the image using preset recognition conditions, wherein the character recognition unit recognizes character information from the first character area using a first recognition condition as the recognition condition, and recognizes character information from the second character area using a second recognition condition as the recognition condition that is different from the first recognition condition.

The form recognition processing method according to the present invention is characterized in that it is a form recognition processing method in which a computer performs recognition processing on a form having a first character area and a second character area as character areas, which are areas in which the same characters are written, and includes an image acquisition step for acquiring an image of the form, and a character recognition step for recognizing character information in the first character area under first recognition conditions and recognizing character information in the second character area under second recognition conditions different from the first recognition conditions.

The form recognition processing program according to the present invention is characterized in that, when executed by a computer, it performs recognition processing on a form having a first character area and a second character area, which are character areas in which the same characters are written. The program causes the computer to realize an image acquisition function that acquires an image of the form, and a character recognition function that recognizes character information in the first character area under first recognition conditions and recognizes character information in the second character area under second recognition conditions that are different from the first recognition conditions.

The same character string may be written in multiple places on a document. For example, a document may have a payment notice, a payment slip, and a receipt, each of which lists the payer's name and the amount. The inventors focused on this point and conducted extensive research, leading to the invention of this invention. This configuration is configured to perform character recognition processing under different recognition conditions on multiple character areas containing the same character. This makes it possible to prevent the recognition results for each character area from being the same, even if erroneous recognition of character information occurs. Therefore, for example, it is easier to detect erroneous recognition of character information written in a character area compared to a configuration in which character recognition processing is performed under the same recognition conditions on multiple character areas.

The present invention preferably further includes a matching unit that matches the character information recognized by the character recognition unit, and a processing unit that processes the form when the matching unit determines that the character information recognized from the first character area matches the character information recognized from the second character area.

With this configuration, by comparing the character information, if a misrecognition of the character information occurs, it becomes easier to detect the misrecognition of the character information written in the character area.

In the present invention, it is preferable that the second recognition conditions differ from the first recognition conditions in the character recognition area of the character region.

Due to paper misalignment during printing, characters in multiple character areas may be printed with the same misalignment from the standard position. In such cases, if the character recognition areas in the character areas are the same, there is a possibility that the same misrecognition will occur for the characters in the multiple character areas. For example, "￥8200" will be misrecognized as "￥820" in all of the multiple character areas. With this configuration, character recognition processing is performed for the multiple character areas using different recognition areas. This prevents the same misrecognition from occurring in multiple character areas, making it easier to detect misrecognition of character information.

The present invention preferably further comprises a setting unit capable of setting the recognition conditions, and a notification unit that notifies when the same recognition conditions are set for two of the character regions.

With this configuration, when setting recognition conditions, a notification is issued if the same recognition conditions are set for two character regions. This prevents the same recognition conditions from being inadvertently set for two character regions. This makes it easier to detect erroneous recognition of character information.

The present invention preferably further includes a setting unit capable of setting the recognition conditions, and the setting unit prohibits the same recognition conditions from being set for two of the character regions.

With this configuration, when setting recognition conditions, it is not possible to set the same recognition conditions for two character regions. This prevents the same recognition conditions from being set for two character regions. This makes it easier to detect erroneous recognition of character information.

The present invention preferably further comprises a setting unit capable of setting the recognition conditions, and a notification unit that notifies when the same recognition conditions are set for all the character regions.

With this configuration, a notification is issued when the same recognition conditions are set for all character areas. This prevents the same recognition conditions from being set for all character areas. This makes it easier to detect erroneous recognition of character information.

The present invention preferably further includes a setting unit capable of setting the recognition conditions, and the setting unit prohibits the same recognition conditions from being set for all of the character regions.

This configuration makes it impossible to set the same recognition conditions for all character regions. This prevents the same recognition conditions from being set for all character regions. This makes it easier to detect erroneous recognition of character information.

The present invention further includes an identification unit that identifies the character area from a sample image showing the contents of the form, and the setting unit sets the recognition conditions for the character area identified by the identification unit.

This configuration is preferable because it allows for proper identification of character areas.

FIG. 1 is a diagram illustrating an overview of a form recognition processing system. FIG. 10 is a diagram illustrating an example of a form. FIG. 2 is a functional block diagram showing the configuration of a document recognition processing device and a management device. FIG. 2 is a cross-sectional view showing the configuration of a document recognition processing device. 10 is a flowchart showing a processing procedure performed by the management device. FIG. 10 is a diagram illustrating an example of setting a recognition condition. FIG. 10 is a diagram illustrating an example of a setting result of a recognition condition. 10 is a flowchart showing a processing procedure performed by the document recognition processing device. FIG. 10 is a diagram illustrating an example of a process for recognizing character information. FIG. 10 is a diagram showing an example of a result of matching character information. FIG. 10 is a diagram illustrating another example of the recognition process of character information in another embodiment. FIG. 10 is a diagram illustrating another example of the recognition process of character information in another embodiment. FIG. 10 is a diagram illustrating another example of the recognition process of character information in another embodiment.

The form recognition processing system will be described below with reference to the accompanying drawings. The form recognition processing system is a system used for character recognition processing of forms. As shown in Figure 1, the form recognition processing system 1 includes a form recognition processing device 2 and a management device 3.

The document recognition processing device 2 is a device for accepting payments of taxes, utility bills, etc. from payers, and is installed in public facilities, financial institutions, etc. The document recognition processing device 2 performs character recognition processing on the accepted document 4 and executes processing such as payment based on the recognized characters.

Form 4 is created by printing individual information such as the recipient's name, amount, and date on paper with standard characters and borders. If the paper is misaligned or tilted when printing the individual information, the individual information may be printed out of place. The same character may be printed multiple times on Form 4. In the illustrated example, the character "890" is printed in three places as the payment amount. If the above-mentioned printing misalignment occurs, the three "890" characters will be printed in the same direction, for example, shifted to the right on the paper. If the "0" on the far right is located outside the target area for character recognition processing, the result of the character recognition processing for the printed "890" will be "89".

Here, if the recognition conditions for the character recognition process for the character "890" in all three places are the same, there is a possibility that the result of the character recognition process will be "89" in all three places. In that case, even if the form recognition processing device 2 is configured to compare the results of the character recognition process in all three places with each other, the three results will all match, "89," and the form recognition processing device 2 will not be able to detect the abnormality. This could result in the payment process being executed with the incorrect recognition result of "89."

In this embodiment, the form recognition processing device 2 is configured to perform character recognition processing on multiple character areas containing the same character under different recognition conditions. As a result, even if the recognition result from one character area is "89," if the recognition conditions for other character areas are set relatively broadly and the recognition result from those areas is "890," the form recognition processing device 2 may be able to discover the abnormality. In this way, the form recognition processing system 1 of this embodiment has an advantage in dealing with printing misalignment.

The management device 3 is a device for presetting the recognition conditions R used in the character recognition process in the form recognition processing device 2. The management device 3 sets the recognition conditions R so that the recognition conditions R for character areas containing the same character are different from each other.

[Report]
An example of Form 4 is shown in Figure 2. As described above, Form 4 includes pre-printed standard characters and frames such as "Payment Notice" and "Due Date," as well as individually printed characters such as the due date "February 28, 2018" and the payment amount "890" (hereinafter referred to as "character string 9").

In this embodiment, an area in which the same characters are written is referred to as a "character area" and is assigned the reference number "41." In the illustrated example, the form 4 has three character areas 41 in which the same characters "890" are written: a left-side character area 41a on the left side, a central character area 41b in the center, and a right-side character area 41c on the right side.

As shown in Figure 2, the document 4 has a frame 42, a stamp area 43 where a receipt stamp is to be stamped, and a separation line 44.

Figure 2 shows the state in which the character string 9 is in its normal position (the correct position when there is no printing misalignment). In the illustrated example, the character string 9 is located inside the frame line 42. Due to the printing misalignment described above, the character string 9 may be written shifted up, down, left, or right from its normal position. If the misalignment is significant, part of the character string 9 may be located outside the frame line 42. In this sense, the character area 41 is not limited to the inside of the frame line 42, and may extend outside it.

[Management device]
The management device 3 is, for example, a personal computer, and includes a CPU and a memory (not shown). Programs stored in the memory are executed to realize the functions of the respective functional units described below.

As shown in FIG. 3, the management device 3 includes an image acquisition unit 31, an identification unit 32, a setting unit 33, a notification unit 34, a memory unit 35, a communication unit 36, and a display unit 37. The management device 3 may be located remotely from the form recognition processing device 2, or may be located in the same building as the form recognition processing device 2. In this embodiment, the management device 3 is located at a manufacturer (manufacturing company) or a dealer (sales and maintenance company).

The image acquisition unit 31 acquires a sample image 5a. The sample image 5a may be acquired, for example, from a camera or document scanner, or may be acquired from another device via wired or wireless communication.

The identification unit 32 identifies the character area 41 from the sample image 5a. The identification of the character area 41 may be performed based on a manual operation received by the management device 3, or may be performed automatically without manual operation using a technique such as image processing, or a combination of these techniques may be used.

The setting unit 33 sets the recognition condition R for the character area 41. The recognition condition R is the recognition condition used in the character recognition process of the form 4. In this embodiment, the recognition condition R is the character recognition area in the character area 41. The recognition condition R may be set based on a manual operation received by the management device 3, or it may be set automatically without a manual operation.

In this embodiment, the setting unit 33 sets a left-side recognition condition Ra for the left-side character region 41a. The setting unit 33 also sets a center recognition condition Rb for the center character region 41b. The setting unit 33 sets a right-side recognition condition Rc for the right-side character region 41c. However, if the form 4 has four or more character regions 41, the setting unit 33 may set four or more recognition conditions R.

The notification unit 34 displays a message on the display unit 37. Alternatively, the notification unit 34 may send a message, or issue a notification by sound or light. In this embodiment, the notification unit 34 is configured to issue a notification when the same recognition condition R is set for two character areas 41. The notification unit 34 may also be configured to issue a notification when the same recognition condition R is set for all character areas 41.

The storage unit 35 stores sample data 6. In this embodiment, the storage unit 35 is a storage device such as an HDD, ROM, or non-volatile memory. The sample data 6 includes a sample image 5a, position information for a character region 41 associated with the sample image 5a, and a recognition condition R.

The communication unit 36 can communicate with the communication unit 29 of the document recognition processing device 2 via an information communication network such as the Internet.

The display unit 37 is a device capable of displaying text information, such as a liquid crystal display.

The management device 3 may also be equipped with an input device (e.g., a keyboard or mouse) that accepts manual operation.

[Form recognition processing device]
As shown in Figures 3 and 4, the document recognition processing device 2 includes an input unit 21, a display unit 22, a conveying mechanism 23, an imaging device 24, a control unit 25, a cash deposit/withdrawal unit 26, a storage unit 27, a discharge unit 28, and a communication unit 29.

The input unit 21 is a device that accepts the insertion of the document 4 from the payer.

The display unit 22 displays information to the user and accepts operations and inputs from the user. In this embodiment, it is a touch-panel LCD monitor.

As shown in FIG. 4, the transport mechanism 23 includes a belt 23a, multiple rollers 23b, a cutter 23c, a stamp unit 23d, and a motor (not shown) that drives the belt 23a and rollers 23b. The transport mechanism 23 is connected to the intake unit 21. Forms 4 taken in by the intake unit 21 are transported one by one by the transport mechanism 23.

When payment of the amount due on the document 4 is completed, the stamping unit 23d stamps a receipt in the stamping area 43 on the document 4. The document 4 is returned upstream by the conveying mechanism 23, and the cutter 23c separates the receipt from the document 4.

The forms 4 from which the receipts have been separated are transported to the storage unit 27 and stored. The discharge unit 28 discharges rejected forms 4 and receipts.

The imaging device 24 captures an image of the form 4 positioned on the transport mechanism 23. The imaging device 24 is, for example, a camera or a document scanner.

[Control Unit]
The control unit 25 is a CPU (Central Processing Unit) that controls the entire document recognition processing device 2. The control unit 25 includes an image acquisition unit 25a, a character recognition unit 25b, a matching unit 25c, a notification unit 25d, a processing unit 25e, and a storage unit 25f. The functions of the above-mentioned functional units are realized by executing a program stored in a memory (not shown).

The image acquisition unit 25a acquires the image 4a of the form 4 captured by the imaging device 24. In other words, the control unit 25 has an image acquisition function. The image 4a may be acquired, for example, from a document scanner, or from another device via wired or wireless communication.

The character recognition unit 25b recognizes character information from the image 4a. Specifically, the character recognition unit 25b recognizes character information in the left character area 41a under left recognition conditions Ra, recognizes character information in the central character area 41b under central recognition conditions Rb that are different from the left recognition conditions Ra, and recognizes character information in the right character area 41c under right recognition conditions Rc. In other words, the control unit 25 has a character recognition function.

The character recognition unit 25b recognizes character information from the image 4a using an OCR (Optical Character Reader).

The matching unit 25c matches the character information recognized by the character recognition unit 25b. The processing unit 25e processes the form 4 when the matched character information matches.

The notification unit 25d notifies the user.

The storage unit 25f stores the character recognition results in association with the image 4a. The storage unit 25f is composed of, for example, a HDD, ROM, or non-volatile memory.

The deposit/withdrawal unit 26 accepts bills and coins inserted by users and dispenses change to the users.

The communication unit 29 can communicate with the communication unit 36 of the management device 3 via an information communication network such as the Internet.

[Processing of Management Device]
The processing procedure of the management device 3 will be described. FIG. 5 is a flowchart showing the processing procedure of the management device 3. The image acquisition unit 31 acquires a sample image 5a (step S101), and the identification unit 32 identifies a character area 41 from the sample image 5a (step S102). The identification unit 32 identifies the positions of the left character area 41a, the center character area 41b, and the right character area 41c from the sample image 5a. Position information of the character area 41 within the entire form 4 is stored in the sample data 6.

The setting unit 33 sets the recognition condition R for each of the multiple character regions 41 (step S103). Details of setting the recognition condition R will be described later.

When the same recognition condition R is set for at least two character regions 41 (step S104; Yes), the notification unit 34 notifies the user of this fact (step S105), thereby prompting the user to modify the recognition condition R. Specifically, the notification unit 34 displays on the display unit 37 that the recognition condition R for multiple character regions 41 is the same.

If the recognition conditions R are modified so that the recognition conditions R for all character regions 41 are different (Step S104; No), the management device 3 generates sample data 6 (Step S106). The set recognition conditions R are stored in the memory unit 35 as part of the sample data 6. The communication unit 36 transmits the sample data 6 to the form recognition processing device 2 (Step S107), and the process ends.

[About setting recognition conditions]
6 and 7 show an example of the setting of the recognition condition R in the management device 3. As shown in Fig. 6, in this embodiment, the character string 9 is not printed in the character area 41 of the sample image 5a. However, the present invention is not limited to this, and the character string 9 may be printed in the character area 41 of the sample image 5a.

As shown in Figures 6 and 7, recognition condition R is the relative position of the character recognition area based on frame lines 42a, 42b, and 42c. The left-right direction is the X-axis direction (right is +), and the up-down direction is the Y-axis direction (up is +). Recognition condition R is represented by a rectangle with the straight line connecting first coordinate #1 and second coordinate #2 as its diagonal. First coordinate #1 is the coordinate of the upper left corner of the rectangle. Second coordinate #2 is the coordinate of the lower left corner of the rectangle. First coordinate #1 represents a relative position with the coordinate of the upper left corner of frame lines 42a, 42b, and 42c as the origin. Second coordinate #2 represents a relative position with the coordinate of the lower right corner of frame lines 42a, 42b, and 42c as the origin.

As shown in FIG. 6, the left-side recognition condition Ra is expressed by the positions of the first coordinate #1 and the second coordinate #2 with respect to the frame line 42a. The center recognition condition Rb is expressed by the positions of the first coordinate #1 and the second coordinate #2 with respect to the frame line 42b. The right-side recognition condition Rc is expressed by the positions of the first coordinate #1 and the second coordinate #2 with respect to the frame line 42c.

Figure 7 shows an example of the setting results for recognition condition R. Figure 7(a) shows the recognition condition R of Figure 6(a). The values of X1, Y1, X2, and Y2 are expressed in pixels, for example. In Figure 6(a), the left-side recognition condition Ra, the center recognition condition Rb, and the right-side recognition condition Rc are set to match the frame lines 42a, 42b, and 42c. Therefore, as shown in Figure 7(a), the left-side recognition condition Ra, the center recognition condition Rb, and the right-side recognition condition Rc have first coordinate #1 (X1, Y1) and second coordinate #2 (X2, Y2) all set to "±0." In this example, the left-side recognition condition Ra, the center recognition condition Rb, and the right-side recognition condition Rc are identical.

Figure 7(b) shows the recognition condition R of Figure 6(b). In Figure 6(b), the center recognition condition Rb is set to match the frame line 42b. The left-side recognition condition Ra and the right-side recognition condition Rc are set not to match the frame line 42a and the frame line 42c. Specifically, as shown in Figure 7(b), the center recognition condition Rb is set so that the first coordinate #1 (X1, Y1) and the second coordinate #2 (X2, Y2) are all "±0".

The first coordinate #1 (X1, Y1) of the left-side recognition condition Ra is biased in the -X and +Y directions from the upper left corner of the frame line 42a. Therefore, the first coordinate #1 (X1, Y1) of the left-side recognition condition Ra is expressed as (-10, +20). Furthermore, the second coordinate #2 (X2, Y2) of the left-side recognition condition Ra is biased in the +X direction from the lower right corner of the frame line 42a. Therefore, the second coordinate #2 (X2, Y2) of the left-side recognition condition Ra is expressed as (+10, ±0).

The first coordinate #1 (X1, Y1) of the right-side recognition condition Rc coincides with the upper left corner of the frame line 42c. Therefore, the first coordinate #1 (X1, Y1) of the right-side recognition condition Rc is expressed as (±0, ±0). Furthermore, the second coordinate #2 (X2, Y2) of the right-side recognition condition Rc is biased in the +X direction from the lower right corner of the frame line 42c. Therefore, the second coordinate #2 (X2, Y2) of the right-side recognition condition Rc is expressed as (+20, ±0).

In the examples of Figures 6(b) and 7(b), the left-side recognition condition Ra, the center recognition condition Rb, and the right-side recognition condition Rc are different from each other.

[Processing by the document recognition processing device]
Next, a description will be given of the processing procedure of the form recognition processing device 2. Fig. 8 is a flowchart showing the processing procedure of the form recognition processing device 2. The communication unit 29 acquires sample data 6 from the management device 3 and stores it in the memory unit 25f. When the import unit 21 imports the form 4 (step S201), the imaging device 24 images the form 4.

The process includes an image acquisition step (step S202) in which the image acquisition unit 25a acquires an image 4a of the form 4. The image 4a is compared with a sample image 5a, and the recognition condition R associated with the sample image 5a is called up. For example, a template matching method is used to compare the image 4a with the sample image 5a. Note that if it is determined that there is no sample image 5a that matches the image 4a, the form 4 is rejected. The rejected form 4 is discharged from the discharge unit 28.

The character recognition unit 25b reads preset recognition conditions R from the acquired image 4a and sample data 6 (step S203). The character recognition unit 25b recognizes character information from the image 4a using the preset recognition conditions R (step S204). Specifically, the character recognition step includes recognizing character information in the left character area 41a using left recognition conditions Ra, recognizing character information in the central character area 41b using central recognition conditions Rb that are different from the left recognition conditions Ra, and recognizing character information in the right character area 41c using right recognition conditions Rc.

In step S204, the character recognition unit 25b may recognize the character information of the entire document 4 in addition to recognizing the character information in the character area 41. Furthermore, the recognition process for the character information in the left character area 41a and the recognition process for the character information in the central character area 41b may be performed simultaneously or sequentially.

The matching unit 25c checks whether the character information recognized by the character recognition unit 25b matches (step S205). Specifically, the matching unit 25c checks whether the character information recognized from the left character area 41a matches the character information recognized from the central character area 41b, and the character information recognized from the right character area 41c (matching step). This is not a limitation, and the matching unit 25c may simply match character information written in at least multiple character areas 41. For example, the matching unit 25c may only match the character information recognized from the left character area 41a with the character information recognized from the central character area 41b. Details of character information matching will be described later.

When the matching unit 25c determines that the character information matches (step S206; Yes), the processing unit 25e processes the document 4 (step S207). Specifically, the processing unit 25e determines the payment amount and starts paying the payment amount. When payment of the payment amount on the document 4 is completed, the stamping unit 23d stamps a receipt stamp in the stamping area 43 on the document 4.

The stamped form 4 is returned upstream by the transport mechanism 23, and the cutter 23c separates the receipt from the form 4. The form 4 from which the receipt has been separated is transported to the storage unit 27 and stored. The discharge unit 28 discharges the receipt.

If it is determined that the text information does not match (step S206; No), the notification unit 25d issues a notification (step S208). In this embodiment, the notification unit 25d displays a message on the display unit 22. For example, the display unit 22 displays a message such as "Please pay this document at the counter." However, the notification unit 25d may also send a message to the counter clerk via wired or wireless communication, or may notify the counter clerk by sound or light. In this case, the processing unit 25e ejects the document 4 from the ejection unit 28 without processing the document 4.

The character recognition results are stored in the memory unit 25f as form data 7. The communication unit 29 may also be configured to transmit the form data 7 to the management device 3.

[About character information recognition processing]
9 shows an example of the character information recognition process performed by the document recognition processing device 2. In the illustrated example, the characters "8200 yen" indicating the payment amount are printed with their right ends extending outside the frame lines 42a, 42b, and 42c.

Figure 9 (a) shows a case where the left-side recognition condition Ra, the center recognition condition Rb, and the right-side recognition condition Rc are the same. Specifically, the left-side recognition condition Ra, the center recognition condition Rb, and the right-side recognition condition Rc set the character recognition area at a position that coincides with the frame lines 42a, 42b, and 42c.

Figure 9 (b) shows a case where the left-side recognition condition Ra, the center recognition condition Rb, and the right-side recognition condition Rc are different. Specifically, the center recognition condition Rb sets the recognition area at a position that overlaps with the frame line 42b. The left-side recognition condition Ra and the right-side recognition condition Rc are set at positions offset in the X-axis and Y-axis directions with respect to the frame lines 42a and 42c.

Figure 10 shows an example of the character information matching process performed by the document recognition processing device 2. Figure 10(a) shows the character recognition and matching results of Figure 9(a). The characters printed on document 4 are "¥8200." Meanwhile, the characters recognized from the left character area 41a, center character area 41b, and right character area 41c are "¥820." The "0" character located outside the frame lines 42a, 42b, and 42c is not recognized. In this case, the matching unit 25c determines that the character information matches "¥820." Therefore, the processing unit 25e processes document 4 with the incorrect payment amount of "¥820" (an amount different from the amount printed on document 4).

Figure 10(b) shows the character recognition and matching results of Figure 9(b). The character information recognized from the left character area 41a and the right character area 41c is "￥8200." The character information recognized from the center character area 41b is "￥820." In this case, the matching unit 25c determines that the character information does not match. Therefore, it is possible to detect erroneous recognition of the character information, and the processing unit 25e can prevent the document 4 from being processed with an incorrect payment amount.

The "first recognition condition" and "second recognition condition" described in the claims are any two of the left-side recognition condition Ra, center recognition condition Rb, and right-side recognition condition Rc in the embodiment. The "first character area" and "second character area" described in the claims are two of the left-side character area 41a, center character area 41b, and right-side character area 41c in the embodiment that correspond to the "first recognition condition" and "second recognition condition." For example, if the center recognition condition Rb and the right-side recognition condition Rc correspond to the "first recognition condition" and "second recognition condition," then the center character area 41b and the right-side character area 41c correspond to the "first character area" and "second character area."

[Another embodiment]
(1) In the above example, the notification unit 34 is configured to issue a notification when the same recognition condition R is set for two (or all) character areas 41. Other means may be employed to avoid setting the same recognition condition R. For example, the setting unit 33 may be configured to prohibit the setting of the same recognition condition R for two (or all) character areas 41. When the recognition condition R is set based on a manual operation, the setting unit 33 may be configured to refuse to accept the operation or prohibit completion of the setting when it receives a manual operation to set the same recognition condition R for two (or all) character areas 41.

(2) The document recognition processing device 2 may be configured to issue a warning when there is a high possibility of misrecognition of characters. For example, as shown in FIG. 11, the warning unit 25d may be configured to issue a warning when the character recognition unit 25b performs character recognition and the margin a is smaller than the width b of one character that is the character width c. The warning unit 25d displays a message for the user on the display unit 22. Specifically, the warning unit 25d displays a message on the display unit 22 indicating that there is a possibility of misrecognition and that processing will be carried out at the counter. The warning unit 25d may send a message to the counter clerk via wired or wireless communication, or may issue a warning by sound or light emission.

The notification unit 25d may also be configured to issue an alert when the margin a in multiple character regions 41 is smaller than the width b of one character of the character width c. If the margin a in a single character region 41 is smaller than the width b of one character of the character width c, the notification unit 25d will not issue an alert. For example, the notification unit 25d issues an alert when the margin a in the left character region 41a and the center character region 41b is smaller than the width b of one character of the character width c. This makes it possible to issue an alert only when there is a high possibility of erroneous recognition of the form 4, compared to a configuration that issues an alert when the margin a in a single character region 41 is smaller than the width b of one character of the character width c. This makes it easier to detect erroneous recognition of the form 4 and reduces the frequency of alerts by the notification unit 25d.

(3) In the above example, the recognition conditions R differ in the relative position of the recognition range with respect to the frame line 42. The recognition conditions R may differ in other respects. For example, the recognition conditions R may differ in the character recognition method. For example, the character recognition method for one recognition condition R may be OCR using AI, and the character recognition method for another recognition condition R may be non-AI OCR.

(4) Recognition condition R is the character recognition area in character area 41, and center recognition condition Rb may be such that the size of the character recognition area in left character area 41a or right character area 41c is different. Recognition condition R may differ in the size of the character recognition area.

(5) As shown in FIG. 12, the recognition condition R may have a different form from the example described above in terms of the divisions for recognizing characters in the character area 41. In the illustrated example, the left-side recognition condition Ra recognizes the entire character information in the left-side character area 41a in one division. The center recognition condition Rb recognizes the character information in the center character area 41b in divisions one character at a time. The right-side recognition condition Rc recognizes the character information in the right-side character area 41c by dividing it into commas.

(6) As shown in FIG. 13, the recognition condition R may be set based on the normal position (normally printed position) of the character string 9. In the illustrated example, the ranges d1, d2, d3, and d4 of the area based on the character string 9 in the left-side recognition condition Ra are different from the ranges e1, e2, e3, and e4 of the area based on the character string 9 in the center recognition condition Rb and the ranges f1, f2, f3, and f4 of the area based on the character string 9 in the right-side recognition condition Rc.

(7) The identification unit 32 may be provided in the document recognition processing device 2.

(8) In this embodiment, the recognition condition R is represented by a rectangle whose diagonal is a straight line connecting the first coordinate #1 (X1, Y1) and the second coordinate #2 (X2, Y2). This is not limited to this, and the character recognition area of the character area 41 can have any shape.

(9) In this embodiment, the text area 41 is an area in which the payment amount is written. However, the text area 41 may also be an area in which the payer, late fees, payment deadline, total payment amount, etc. are written.

As described above, the form recognition processing system, form recognition processing method, and form recognition processing program of the present invention are suitable for making it easier to detect misrecognition of forms.

1: Form recognition processing system 2: Form recognition processing device 3: Management device 4: Form 4a: Image 5a: Sample image 25a: Image acquisition unit 25b: Character recognition unit 25c: Collation unit 25e: Processing unit 32: Identification unit 33: Setting unit 34: Notification unit 41: Character area 41a: Left character area (first character area, second character area)
41b: Central character area (first character area, second character area)
41c: Right side character area (first character area, second character area)
R: Recognition condition Ra: Left side recognition condition (first recognition condition, second recognition condition)
Rb: Central recognition condition (first recognition condition, second recognition condition)
Rc: Right side recognition condition (first recognition condition, second recognition condition)

Claims (10)

A form recognition processing system that performs recognition processing on a form having a plurality of character areas in which the same characters are written,
an image acquisition unit that acquires an image of the form;
a character recognition unit that recognizes character information from the image using a predetermined recognition condition,
A document recognition processing system in which the character recognition unit recognizes character information from a first character area as the character area using a first recognition condition as the recognition condition, and recognizes character information from a second character area as the character area using a second recognition condition as the recognition condition that is different from the first recognition condition. a matching unit that matches the character information recognized by the character recognition unit;
The document recognition processing system according to claim 1, further comprising a processing unit that processes the document when the comparison unit determines that the character information recognized from the first character area matches the character information recognized from the second character area. The form recognition processing system of claim 1, wherein the second recognition conditions differ from the first recognition conditions in the character recognition area of the character region. a setting unit capable of setting the recognition conditions;
The document recognition processing system according to claim 1 , further comprising: a notification unit that notifies when the same recognition conditions are set for two of the character areas. further comprising a setting unit capable of setting the recognition conditions,
The form recognition processing system according to claim 1 , wherein the setting unit prohibits the same recognition condition from being set for two of the character regions. a setting unit capable of setting the recognition conditions;
The document recognition processing system according to claim 1 , further comprising: a notification unit that notifies when the same recognition conditions are set for all the character areas. further comprising a setting unit capable of setting the recognition conditions,
2. The form recognition processing system according to claim 1, wherein the setting unit prohibits the same recognition condition from being set for all the character regions. an identifying unit that identifies the character area from a sample image showing the content of the form;
The form recognition processing system according to claim 4 , wherein the setting unit sets the recognition conditions for the character area identified by the identifying unit. A form recognition processing method in which a computer performs recognition processing on a form having a first character area and a second character area as character areas in which the same character is written,
an image acquisition step of acquiring an image of the form;
A form recognition processing method including a character recognition step of recognizing character information in the first character region under first recognition conditions, and recognizing character information in the second character region under second recognition conditions different from the first recognition conditions. A form recognition processing program that, when executed by a computer, performs recognition processing on a form having a first character area and a second character area as character areas in which the same character is written,
an image acquisition function for acquiring an image of the form;
A document recognition processing program that causes a computer to realize a character recognition function that recognizes character information in the first character area under a first recognition condition, and recognizes character information in the second character area under a second recognition condition that is different from the first recognition condition.