JP7552050B2 - OCR image acquisition system and OCR image acquisition method - Google Patents

Description

The present invention relates to an image acquisition system for OCR and an image acquisition method for OCR.

In recent years, various application procedures, such as opening a bank account, have come to be carried out electronically by using image data captured by a user terminal such as a mobile phone or smartphone of an identification document, such as a driver's license, an individual number card, or an individual number notification card, and text character information obtained by subjecting the image data to character recognition processing (OCR (Optical Character Recognition) processing).
2. Description of the Related Art As a technique for performing OCR processing on document image data captured by an imaging device of a user terminal, for example, there is a device described in Japanese Patent Laid-Open No. 2003-233996.

In the technology disclosed in Patent Document 1, for example, an identification card is successively photographed, and OCR processing is performed on the document image data of each identification card, to obtain character information such as letters and numbers of items to be read that are included in the identification card and are required for a contract.
Then, the acquired text information for each item is used to fill in the fields of the input form required for the application procedure, thereby generating an application form suited to the user.

Patent No. 6364051

In the above-mentioned OCR processing, for example, each of a plurality of document image data obtained by capturing an image of a document to be recognized is subjected to OCR processing, the number of document image data for which the same recognition result is obtained is counted, and text characters obtained from a predetermined set number or more of document image data are output as the recognition result of the character recognition processing in the OCR processing.
Therefore, in order to perform the OCR process, it is necessary to transmit a plurality of document image data from the user terminal to the application reception server that performs the OCR process.

However, depending on the form (imaging state) of each image in the transmitted document image data, character recognition may not be possible and the above recognition result may not be obtained, so the image may need to be re-captured and the multiple document image data may need to be re-sent from the user terminal to the application reception server.
For example, if a user takes an image and sends it as document image data, because the image quality is such that OCR processing cannot be performed, for example, because the entire identification card is not captured or the image is too small, the above recognition result cannot be obtained in OCR processing.
As a result, the traffic in the communication network between the user terminal and the application reception server increases due to the large volume of data being transmitted multiple times.

Furthermore, due to the problem of the quality of the document image data described above, the document image data is repeatedly transmitted multiple times, which increases the number of times OCR processing is performed, and increases the load of OCR processing on the application reception server.
The above-mentioned increase in communication network traffic and the increased load on the application reception server cause delays in the processing of application procedures, which in turn increases the time required to process applications over the Internet, resulting in a decrease in user satisfaction with application processing via the Internet.

The present invention has been made in consideration of the above circumstances, and aims to provide an OCR image acquisition system and an OCR image acquisition method that suppress the transmission of document image data that cannot be processed by character recognition to a server that performs OCR processing, and reduce the load caused by OCR processing on the server.

The present invention has been made to solve the above-mentioned problems, and an image acquisition system for OCR of the present invention is an image acquisition system for OCR that acquires a document image of a document that is a target of character recognition processing, and transmits the acquired document image to a server that performs OCR processing, and is a group of modules included in an image acquisition application that is downloaded when performing the acquisition process of the document image for the character recognition processing and operates using a web browser as a platform, the group of modules being a document image capture module that causes an imaging device to capture an image of the document and generate the document image, an image form determination module that determines whether the document image has been captured in an image form corresponding to a predetermined determination rule, and a module that determines whether the document image has been captured in an image form corresponding to a predetermined determination rule, and and a document image selection module that selects a document image that satisfies the above conditions as the document image to be transmitted to the server, and a judgment rule table contained in the downloaded image acquisition application is provided for each identification card, and making the judgment includes referring to a judgment rule table corresponding to the identification card identified from the document image and determining whether the document image data has a form that corresponds to the judgment rule, and the judgment rules in the judgment rule table include image form specifications for each type of identification card, and are specifications for the form of the outermost image area of a document image that allows for a higher accuracy in determining whether character recognition processing of a character image in a document image is possible compared to other image areas in the document image .

The OCR image acquisition system of the present invention is characterized in that the judgment rule is a provision for the shape of a specified image area that allows a judgment as to whether character recognition processing of a character image in a document image is possible or not to be performed with a higher degree of accuracy than other image areas in the document image.

The OCR image acquisition system of the present invention is characterized in that the image morphology determination module determines the document type of the document image and transmits it to the server together with the document image.

The OCR image acquisition system of the present invention is characterized in that the judgment rules are set for each of the document types in accordance with the characteristic forms of the documents of each type.

The OCR image acquisition method of the present invention is an OCR image acquisition method for acquiring a document image of a document to be subjected to character recognition processing, and transmitting the acquired document image to a server that performs OCR processing, and the method includes the steps of: a document image acquisition module, an image form determination module, and a document image selection module, which are included in an image acquisition application that is downloaded when performing the document image acquisition processing for performing the character recognition processing and operates using a web browser as a platform; a document image acquisition step in which the document image acquisition module causes an imaging device to capture a document and generate the document image; an image form determination step in which the image form determination module determines whether the document image has been captured in an image form corresponding to a predetermined determination rule; and a document image selection module. and a document image selection process in which the downloaded image acquisition application module selects a document image that satisfies the form in the determination as the document image to be transmitted to the server, a determination rule table contained in the downloaded image acquisition application is provided for each identification card, and the image form determination process includes referencing a determination rule table corresponding to the identification card identified from the document image and determining whether or not the document image data has a form that corresponds to the determination rule, and the determination rules in the determination rule table include image form specifications for each type of identification card, and are specifications for the form of the outermost image area of the document image that allow for a determination of whether or not character recognition processing of a character image in the document image is possible with a higher accuracy than other image areas in the document image .

This invention provides an OCR image acquisition system and an OCR image acquisition method that suppress the transmission of document image data that cannot be processed by character recognition to a server that performs OCR processing, and that reduces the load caused by OCR processing on the server.

1 is a conceptual diagram showing an example of the configuration of an image acquisition system for OCR according to an embodiment of the present invention. 11 is a diagram for explaining generation of an application input form based on document image data obtained by the OCR image acquisition system of this embodiment. FIG. 10 is a flowchart showing an example of the operation of a process for acquiring document image data of an identification card by the OCR image acquisition system of the present embodiment.

When various application procedures such as opening a bank account are carried out over the Internet, the OCR image acquisition system of the present invention captures images of identification documents such as driver's licenses, My Number cards, and My Number notification cards in response to user operations.
The OCR image acquisition system of the present invention then selects document image data suitable for OCR processing from the document image data, which is image data of the identification card, and transmits the selected document image data to the application reception server that accepts the application. This prevents the user terminal of the user from transmitting document images in a format unsuitable for OCR processing to the application reception server, thereby reducing traffic on the communication network and reducing the load of pre-processing that the application reception server performs before OCR processing.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Fig. 1 is a conceptual diagram showing an example of the configuration of an OCR image acquisition system according to an embodiment of the present invention. In Fig. 1, a user terminal 100 and an application reception server 200 are connected by a communication network 300 including the Internet.
The user terminal 100 is a terminal such as a smartphone owned by a user. The application reception server 200 is a server that receives applications for, for example, opening a bank account, joining a sports club, and the like.
The user terminal 100 includes an OCR image acquisition system 1 , a web browser (World Wide Web) 2 , and a display unit 3 .

The OCR image acquisition system 1 in this embodiment is formed by an image acquisition application that operates on a platform of a web browser provided in the user terminal 100 owned by the user. That is, the image acquisition application is launched on the web browser, and is deployed as a plurality of modules (module group) on the memory of the user terminal 100, thereby realizing the functions of the OCR image acquisition system 1. In addition, the image acquisition application program is downloaded from the application reception server 200 to each user terminal 100 every time a user performs an application process using the user terminal 100 (every time a need arises to perform character recognition processing), written and stored in the memory unit of the user terminal 100, and erased from the memory unit after the application process is completed.
The OCR image acquisition system 1 includes a data input/output module 11 , an imaging control module 12 , an image form determination module 13 , a document image selection module 14 , and a determination rule table 15 .

The data input/output module 11 transmits and receives data to and from the application reception server 200 via the web browser 2 .
The imaging control module 12 displays an imaging guide frame on the display unit 3, and has the user perform an imaging operation with the identification card contained within this imaging guide frame, thereby acquiring document image data which is an image of the document.
Here, the imaging control module 12 drives an imaging device (not shown) installed in the user terminal 100 to take continuous images of the identification card at a predetermined period, thereby acquiring multiple (e.g., 15) pieces of text image data (which may also be frame images of a video).
For example, if the identification card is a driver's license or a My Number card, document image data of the front and back is obtained, and if the identification card is a My Number notification card, document image data of the front is obtained.

The image form determination module 13 determines whether the form of a document object image, which is an image portion of a document in the document image data, corresponds to a predetermined determination rule that has been set in advance. In this embodiment, the determination rule is set as a regulation for the form of a predetermined image area (an outermost frame to be described later) of the document object image, which allows a determination of whether character recognition processing of a character image in the document image data is possible or not with a higher accuracy than other image areas in the document object image of the document image data.
Here, the predetermined judgment rules are included as judgment rule table 15 in the downloaded image acquisition application program, and include at least whether the shape of the outermost frame of the document object image (the shape of the outline of the document when viewed in a plane) is a rectangle (with four vertices), whether the lines of the outermost frame of the document object image (e.g., line segments near a character image) are detected, whether the inner angles of the rectangle that is the outline of the document object image are within a predetermined angle range (determination of the degree of shape deformation such as a trapezoid), whether the lines of the outermost frame of the document object image (e.g., line segments near a character image) are curved (distorted), and whether the area ratio of the document object image shown in the document image data is a predetermined ratio or more (determination of the size of the document object image), etc.
In addition, the specified judgment rules may also include whether the hue in the outermost frame of the document object image is within a predetermined hue range, whether the saturation is within a predetermined saturation range, and whether the brightness is within a predetermined brightness range.

That is, if the document object image is not rectangular, it is outside the imaging guide frame, and information for acquiring the document image when performing OCR processing is missing. If the contour line is not detected, it means that the range of the document object image cannot be extracted, and therefore keystone correction or the like cannot be performed on the document image. The inner corners of the rectangle are imaged obliquely and deformed into a trapezoidal shape, and if they are outside the specified angle, it indicates that even if keystone correction is performed, the character image will not be of a quality sufficient for OCR processing. If the contour line is curved, the character image is also distorted, and it indicates that the image is not imaged with a quality that allows OCR processing. If the area ratio is less than the specified ratio, it indicates that the document image is not imaged with a size that allows character recognition in OCR processing.
In addition, when the hue in the outermost frame of the document object image is not within a predetermined hue range, when the saturation is not within a predetermined saturation range, and when the brightness is not within a predetermined brightness range, each of these cases indicates that the document object image has not been captured as a character image with sufficient clarity to perform OCR processing.

The document image selection module 14 checks the judgment results of the image form judgment module 13 for each captured document image data, selects document image data that meets the judgment rules, and deletes other document image data.
Then, the document image selection module 14 transmits the selected document image data to the application reception server 200 via the data input/output module 11 and the web browser 2 .

Before performing OCR processing on each piece of document image data supplied from the user terminal 100, the application reception server 200 performs preprocessing such as keystone correction of the shape of the document object image, size adjustment, and rotation.
Then, the application reception server 200 determines whether the document object image after the preprocessing is an image of a driver's license, a My Number card, or a My Number notification card.
For example, if the application reception server 200 determines that the document object image in the document image data is an image of a driver's license, it compares the template image of the driver's license with the document object image, extracts character images of the items required for the application form, and performs OCR processing (character recognition processing) to obtain the character images.

The character image here is information obtained by performing OCR processing on the document object image, and includes an image showing an item and an image of characters showing the data for the item. The image showing an item is an image of a character string of a name printed outside the margin of an item such as name or address. The image showing the data for an item is an image of personal data printed inside the margin, for example, an image of a character string (including numbers, symbols, etc.).

Then, the application reception server 200 performs OCR processing on each of the document object images after preprocessing, and if the document image of each item is converted into the same text character in three or more sentence image data, the text character is regarded as the result of the conversion of the character image into text.
Here, in this embodiment, only document image data that is determined to be capable of OCR processing is transmitted, and therefore when determining text characters as the conversion result, it is possible to reduce the number of document images converted into the same text characters compared to the conventional method. For example, by reducing the number from three or more in the conventional method to two or more, it is possible to reduce the load on the OCR processing of the application reception server 200.

The data input/output module 11 of the user terminal 100 writes data for the items required for the application, which has been converted from the character image of the document image data to text characters by OCR processing in the application reception server 200, into the designated fields of the application input form (display area 501 and display area 502 in Figure 2 (c) described below).
At this time, the application reception server 200 performs a compositing process to paste the document object image 510 into the input form, but during this compositing process, the sensitive information portion 510B in the document object image 510 (image of the identification document) is made invisible (for example, by blacking out or whitening out the portion, or erasing the text image, hereinafter referred to as masking).

FIG. 2 is a diagram for explaining the generation of an application input form based on document image data obtained by the OCR image acquisition system of this embodiment.
Figure 2 (a) is an example of an image that the imaging control module 12 displays on the display screen 3S of the display unit 3 when the image acquisition application is downloaded from the application reception server 200 and launched on a web browser to prompt the user to capture an image of an identification card.
2A, a display area 501 is an area where the document image data of an identification card is OCR-processed to display the character string of the user's name, and a display area 502 is an area where the document image data of an identification card is OCR-processed to display the character string of the user's address.
Moreover, a button 503 is a button that is displayed so that the user can press (touch) when taking an image of the identification card.

Fig. 2B is an example of an image in which the imaging control module 12 performs imaging processing of an identification card, which is displayed on the display screen 3S of the display unit 3 when the user presses the button 503 in Fig. 2A. The imaging control module 12 displays an imaging guide frame 504 on the display screen 3S of the display unit 3. The user holds the user terminal 100 over a position where the document object image 600 of the identification card is contained within the imaging guide frame 504, to capture an image of the identification card.
The button 507 is a shutter button for causing the imaging device of the user terminal 100 to capture an image of the identification card. When the button 507 (shutter button) is pressed (touched), the imaging control module 12 acquires a predetermined number of pieces of text image data.

2C is an example of an image of an input form generated by the application reception server 200 after the document image data has been subjected to OCR processing. When the input form is supplied from the application reception server 200, the imaging control module 12 displays the input form of FIG. 2C on the display screen 3S of the display unit 3.
2B, a display area 501 is an area where the document image data of the identification card is OCR-processed and the character string of the user's name is displayed. The character string of the user's name is displayed in the display area 501 after being converted from a character image showing the user's name to text characters by the OCR processing of the document image data.

The display area 502 is an area where the document image data of the identification card is OCR processed and the character string of the user's address is displayed. The character string of the user's address is displayed in the display area 502 after being converted from a character image showing the user's address into text characters by the OCR processing of the document image data.
The document object image is an image of a document object extracted from a document image and corrected in a preprocessing, and is pasted (combined) into the input format for display. The portion 510B of the document object image containing sensitive information is masked, for example, by filling it in black or leaving it white.

With the above-mentioned configuration, according to this embodiment, the OCR image acquisition system captures document image data using an imaging device mounted on the user terminal 100, determines whether each of the document object images in the captured multiple document image data is captured in a form that allows character recognition, and transmits only the document image data captured in a form that allows character recognition to the application reception server 200. This reduces the occurrence of erroneous capture of document image data that is not included in the imaging guide frame 504, the occurrence of an inappropriate imaging angle when imaging an identification card, the occurrence of document image data that is not character-recognizable by OCR processing due to a small size of the document object image, or the occurrence of re-imaging an identification card and re-transmitting the document image data when OCR processing cannot be performed, making it possible to suppress unnecessary increases in traffic on the communication network 300 and reducing the communication load on the communication network 300.

In addition, according to this embodiment, by supplying document image data captured in a format that allows character recognition, the application reception server 200 does not need to perform preprocessing and OCR processing on document image data of a quality that does not allow character recognition as in the past, thereby reducing the load on the application reception server 200 in OCR processing.

In addition, according to this embodiment, the image acquisition application on the web browser is deployed and operates in each module in the OCR image acquisition system 1, and performs part of the pre-processing in the OCR process on behalf of the application. This makes it possible to execute the document object image form determination process performed by the image form determination module 13 without transmitting data necessary for the determination between the application reception server 200 and the application reception server 200. This eliminates the need to transmit and receive data between the application reception server 200 and the web browser 2, and shortens the time it takes for the document image selection module 14 to select document image data and send it to the application reception server 200. This shortens the time from obtaining document image data to OCR processing, and allows the process to be executed in real time from when the user captures an image of his/her identification card to when the image of the input form in FIG. 2(c) is obtained.

In addition, according to this embodiment, an application that acquires document image data that can be recognized by OCR processing is downloaded from the application reception server 200 for each application process and executed on the web browser of the user terminal 100. Therefore, compared to applications that run on the OS platform, which require the user to take the trouble of upgrading, the latest version of the document acquisition application can always be easily provided from the application reception server 200.

3 is a flowchart showing an example of the operation of the process of acquiring document image data of an identification card by the OCR image acquisition system of this embodiment. In the following description, the acquisition of document image data of a driver's license when opening a bank account will be described as an example.
Step S101: A user uses a smartphone as a user terminal 100 to access a bank's application reception server 200 via the Internet in a communication network 300 in order to open a bank account.

Step S102: The user presses (touches) the button for downloading the image capture application on the page for explaining how to open an account displayed by the application reception server 200.
As a result, the web browser 2 downloads the image capture application, and writes and stores the image capture application program in a storage unit (not shown) of the user terminal 100 .

Step S103: The user starts an image acquisition application to acquire document image data to be sent to the application reception server 200.
At this time, the web browser 2 loads an image acquisition application on the memory, and generates a data input/output module 11, an imaging control module 12, an image form determination module 13, a document image selection module 14, and a determination rule table.
Then, the imaging control module 12 displays a screen prompting the user to take an image of the driver's license, as shown in FIG. 2A, on the display screen 3S of the display unit 3 in the user terminal 100.

Step S104: The user presses the button 503 in FIG. 2A to capture an image of the driver's license.
Thus, when the imaging control module 12 detects that the button 503 has been pressed, it displays an image of the identification card obtained by imaging processing shown in FIG. 2B on the display screen 3S of the display unit 3.

The user adjusts the imaging position of the license so that the document object image 600 of the license is contained within the imaging guide frame 504 on the display screen 3S of the display unit 3, i.e., so that the entire outer periphery of the license fits within the imaging guide frame 504.
Then, the user confirms that the document object image is enclosed within the imaging guide frame 504 and presses the button 507 .
When the imaging control module 12 detects that the button 507 has been pressed, it captures a plurality of images, for example, 15 images of a document at a predetermined cycle using the imaging device.

Step S 105 : The image form determination module 13 determines whether or not the form of the document object image of the document image data satisfies each determination rule in the determination rule table 15 .
If the form of the document object image of the document image data does not deviate from the provisions of the determination rules, the image form determination module 13 adds a flag indicating suitability to the document image data.
On the other hand, if the form of the document object image of the document image data does not comply with the determination rules, the image form determination module 13 adds a flag indicating inappropriateness to the document image data.

Step S106: The document image selection module 14 checks the flag added to the document image data, and determines whether or not the flag indicates suitability (corresponds to the determination rule).
At this time, if the flag is appropriate, the document image selection module 14 advances the process to step S107, whereas if the flag is inappropriate, the document image selection module 14 advances the process to step S110.

Step S107: The document image selection module S109 transmits the document image data selected by the document image selection module 14 as having a suitable flag to the application reception server 200 via the data input/output module 11.

Step S108: The document image selection module 14 determines whether the selection process has been completed for the document object images in all document image data captured by the imaging control module 12, i.e., all 15 sheets of document image data (selection process has been completed).
At this time, if the document image selection module 14 has completed the selection process for all document image data captured by the imaging control module 12, the document image selection module 14 advances the process to step S109.
On the other hand, if the document image selection module 14 has not yet completed the selection process for all document image data captured by the imaging control module 12, the document image selection module 14 advances the process to step S105 to perform the selection process for the next document image data.

Step S109: The application reception server 200 performs preprocessing on each of the document images supplied from the document image selection module 14 of the user terminal 100, and then performs OCR processing to convert character images of necessary items into text.
Then, the application reception server 200 enters character strings in the required item fields, synthesizes the preprocessed document object image, generates the input form shown in Figure 2 (c), and sends the generated input form to the user terminal 100.

Step S 110 : The data input/output module 11 receives the input form supplied from the application reception server 200 , and displays it on the display screen 3 S of the display unit 3 in the user terminal 100 .
This allows the user to check the input form displayed on the display screen 3S of the display unit 3, and use this input form to apply to the application reception server 200 for opening a bank account.
After the above-mentioned application process is completed, the data input/output module 11 erases the image acquisition application program from the memory unit of the user terminal 100 .

Step S111: The document image selection module S109 deletes the document image data whose flag has been determined to be inappropriate by the document image selection module 14, and does not transmit the document image data to the application reception server 200.

In the above-described embodiment, the application reception server 200 is configured to perform pre-processing of OCR processing on document image data supplied from the user terminal 100 in a form corresponding to the judgment rules, but this pre-processing of OCR processing may also be performed by the document image selection module, and the application reception server 200 may be configured to perform only OCR processing.

In addition, in this embodiment, type discrimination information such as a template (reference image) of the format for each type of identification card or a criterion for the reading process of the type of identification card may be included in the image acquisition application and downloaded, so that the type of identification card of the document object image in the document image data is determined based on the type discrimination information, and the document image data to which the information on the determined type of identification card is added is transmitted to the application reception server.

In this embodiment, a determination rule table included in the downloaded image acquisition application may be provided for each identification card, and the determination rule table corresponding to the identification card identified from the document image data may be referenced to determine whether the document image data is in a form corresponding to the determination rule. In this configuration, the determination rule includes, for each type of identification card, the definition of the image form such as the state of lines (faintness, distortion, etc.) in the part (area) where the determination of whether character recognition of the character image in the document object image is possible or not is higher than other parts, or where the determination can be made with the highest accuracy in the document, the angle of the inner corners of the rectangle in the column or the state of a symbolic mark (faintness, distortion, etc.), and the state of hue, saturation , and brightness.
In addition, in this embodiment, the outermost frame, the lines forming the column frame, or a symbolic mark are used as examples, but any image area may be used as long as the shape of the image area is known in advance, as this makes it easy to improve the accuracy of the judgment.

In addition, in this embodiment, if there is a large amount of document image data that the image morphology determination module 13 has determined to be inappropriate and the number of document image data that has been determined to be appropriate is not sufficient to cover the number of document image data used to determine the results of character recognition in the OCR process of the application reception server 200, a notification encouraging additional imaging processing may be displayed on the display screen 3S of the display unit 3.

In addition, an image acquisition application program for realizing the functions of the OCR image acquisition system 1 in FIG. 1 may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed to perform a determination process as to whether or not the form of the document object image in the text image data corresponds to the determination rule. Note that the term "computer system" here includes hardware such as the OS and peripheral devices.

Furthermore, if the WWW system is used, the "computer system" also includes the home page providing environment (or display environment).
In addition, "computer-readable recording medium" refers to portable media such as flexible disks, optical magnetic disks, ROMs, and CD-ROMs, as well as storage devices such as hard disks built into computer systems. Furthermore, "computer-readable recording medium" also includes devices that dynamically hold a program for a short period of time, such as communication lines when transmitting a program via a network such as the Internet or a communication line such as a telephone line, and devices that hold a program for a certain period of time, such as volatile memory inside a computer system that serves as a server or client in such cases. Furthermore, the above program may be one that realizes part of the above-mentioned functions, or may be one that can realize the above-mentioned functions in combination with a program already recorded in the computer system.

The above describes an embodiment of the present invention in detail with reference to the drawings, but the specific configuration is not limited to this embodiment and includes designs that do not deviate from the gist of the present invention.

Reference Signs List 1 OCR image acquisition system 2 Web browser 3 Display unit 3S Display screen 11 Data input/output module 12 Imaging control module 13 Image form determination module 14 Document image selection module 15 Determination rule table 100 User terminal 200 Application reception server 300 Communication network

Claims (4)

An OCR image acquisition system that acquires a document image of a document to be subjected to character recognition processing, and transmits the acquired document image to a server that performs OCR processing,
a group of modules included in an image acquisition application that is downloaded when performing the document image acquisition process for performing the character recognition process and that operates using a web browser as a platform, the group of modules comprising:
a document image capturing module that captures an image of a document using an imaging device to generate the document image;
an image form determination module for determining whether the document image is captured in an image form corresponding to a predetermined determination rule;
a document image selection module that selects a document image that satisfies the form in the determination as the document image to be transmitted to the server;
a determination rule table included in the downloaded image acquisition application is provided for each identification card;
making the determination includes referring to a determination rule table corresponding to the identification card to be determined from the document image and determining whether or not the document image data is in a form corresponding to the determination rule;
The determination rules in the determination rule table include definitions of the form of an image for each type of identification document, and are definitions for the form of an outermost frame image area of a document image that allows a determination of whether character recognition processing of a character image in the document image is possible with a higher degree of accuracy than other image areas in the document image.
Image acquisition system for OCR. The image morphology determination module:
2. The OCR image acquisition system according to claim 1, further comprising: determining a type of the document of the document image and transmitting the determined type of the document together with the document image to the server. 3. The OCR image acquisition system according to claim 1 , wherein the determination rule is set for each of the document types in accordance with a characteristic form of the document of each of the document types. A method for acquiring an image for OCR, comprising: acquiring a document image of a document to be subjected to character recognition processing; and transmitting the acquired document image to a server that performs OCR processing,
A document image capturing module, an image form determination module, and a document image selection module are included in an image capture application that is downloaded when performing the document image capture process for performing the character recognition process and operates using a web browser as a platform,
a document image capturing step in which the document image capturing module causes an image capturing device to capture an image of a document and generate the document image;
an image form determination step in which the image form determination module determines whether the document image is captured in an image form corresponding to a predetermined determination rule;
a document image selection process in which the document image selection module selects a document image that satisfies the form in the determination as the document image to be transmitted to the server;
a determination rule table included in the downloaded image acquisition application is provided for each identification card;
The image form determination step includes referring to a determination rule table corresponding to the identification document to be determined from the document image and determining whether the document image data is in a form corresponding to the determination rule;
The determination rules in the determination rule table include definitions of the form of an image for each type of identification document, and are definitions for the form of an outermost frame image area of a document image that allows a determination of whether character recognition processing of a character image in the document image is possible with a higher degree of accuracy than other image areas in the document image.
Image acquisition method for OCR.

Images