JP2019008580A - Registration information confirming method and registration information confirming server - Google Patents

Abstract

To provide a registered information confirming method capable of extracting an image of an identification card with high probability compared to past one and reading character information in the identification card, for an imaging environment such as a color of a base where the identification card is placed at time of imaging or illumination for the identification card.SOLUTION: A registration information confirming method includes acquiring either one of an edge or a ruled line by performing, as a first processing, either one of an edge detection processing for detecting an edge of an image of an identification card from a captured image obtained by imaging the identification card or a ruled line detection processing for detecting a ruled line printed on the identification card, or as a second processing when detection by the first processing cannot be performed; correcting the captured image by the detected edge or the ruled line; and recognizing a character in an image of the identification card of the corrected captured image and reading the character information obtained.SELECTED DRAWING: Figure 5

Description

  The present invention relates to a registration information confirmation method and a registration information confirmation server.

In recent years, when contracting for opening a bank account or the like, only personal information is transmitted from a terminal or a portable terminal through a communication information network such as the Internet, and the processing time required for the contract is shortened.
For example, in order to confirm whether or not the personal information to be transmitted is information corresponding to the person who is making a contract, image information of an identification card such as a license is transmitted. Then, the identity of the contractor is confirmed from the image information of the transmitted identification card (for example, Patent Document 1). In addition, the character information of the identification card for identification is read from the image information by OCR (Optical Character Recognition / Reader), and the process of extracting the information for identification in the identification card is performed. (For example, refer to Patent Document 2).

JP 2002-358420 A Japanese Patent Laying-Open No. 2015-045910

As described above, when an image from an identification card is extracted from image information and a region for character recognition is detected, the outline of the identification card is generally determined by edge detection. Then, based on the detected edge, image correction processing such as trapezoid correction is performed, and the image of the identification card is corrected to a shape that can be read by OCR.
However, when the image of the identification card is taken, the edge of the identification card may not be detected depending on the color of the background on which the identification card is placed or the lighting state of the identification card. In this case, since the image of the identification card cannot be extracted, the area read by the OCR of the identification card cannot be extracted, and the character information cannot be read.

  The present invention has been made in view of such circumstances, and corresponds to an imaging environment such as a color of a background on which an identification card is arranged at the time of imaging, or illumination with respect to the identification card, and is based on a captured image captured. An object of the present invention is to provide a registration information confirmation method and a registration information confirmation server that can extract an image of an identification card with higher probability than before and can read character information in the identification card. .

  The present invention has been made to solve the above-described problems, and the registration information confirmation method according to the present invention includes an edge detection process for detecting an edge of an image of the identification card from a captured image obtained by imaging the identification card, or One of the ruled line detection processes for detecting the ruled line printed on the identification card is performed as the first process, and when the detection by the first process cannot be performed, the other is performed as the second process, and the edge or the ruled line is detected. A process of acquiring any one of the following: a process of correcting the captured image by the detected edge or ruled line; and character recognition in the image of the identification card of the corrected captured image; And a process of reading information.

  In the registered information confirmation method of the present invention, when the image of the identification card and the image of the seal imprint are each captured as the same frame in the captured image and the ruled line is acquired, the imaging is corrected based on the ruled line. The method further includes a step of extracting an image of the seal image taken together with the identification card from an image.

  The registered information confirmation server of the present invention performs an edge detection process for detecting an edge of an image of the identification card or a ruled line detection process for detecting a ruled line printed on the identification card from a captured image obtained by imaging the identification card. If either one is performed as the first process and detection by the first process cannot be performed, the other is performed as the second process, and either the edge or the ruled line is obtained, and the detected edge or ruled line is acquired. Thus, the captured image is corrected, character recognition is performed on the image of the identification card of the corrected captured image, and character information is read.

  According to this invention, it corresponds to the imaging environment such as the color of the background on which the identification card is arranged at the time of imaging or the illumination to the identification card, and the identification is performed with a higher probability than the conventional one from the captured image. The image of the book can be extracted, and the character information in the identification card can be read.

It is a conceptual diagram which shows the structural example of the registration information confirmation system by the 1st Embodiment of this invention. It is a figure explaining the imaging process in the imaging application provided from a registration information confirmation server. It is a block diagram which shows the structural example of the registration information confirmation server by the 1st Embodiment of this invention. It is a figure explaining the detection process of the edge and outer frame line of the identification card from the captured image by the registration information confirmation server by the 1st Embodiment of this invention. It is a flowchart which shows the operation example of the registration information confirmation system by the 1st Embodiment of this invention. It is a conceptual diagram which shows the structural example of the registration information confirmation server by the 2nd Embodiment of this invention. It is a figure explaining the imaging process in the imaging application provided from a registration information confirmation server. It is a flowchart which shows the operation example of the registration information confirmation system by the 2nd Embodiment of this invention.

<First Embodiment>
Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a conceptual diagram showing a configuration example of a registration information confirmation system according to the first embodiment of the present invention. In FIG. 1, the registration information confirmation system includes a terminal 11 and a mobile terminal 12 owned by a user 1, a registration information confirmation server 21 and a database 22 provided in the registration information confirmation center 2. The registration information management server 31 of the facility 3 stores the registration information transmitted from the registration information confirmation server 21. The registration information is imaged data (image data) of the imaged identity card. The identification card is, for example, a driver's license such as a car, an insurance card, a passport (a page showing information such as a photograph), a pension book, and the like. In the present embodiment, a driver's license (hereinafter simply referred to as “license”) is used as an identification card.

The terminal 11 is a personal computer, for example, and can access the registered information confirmation server 21 through an information communication network such as the Internet.
The mobile terminal 12 is, for example, a smartphone having a camera function, and can access the registered information confirmation server 21 through an information communication network such as the Internet.

  In response to a download request from the mobile terminal 12, the registration information confirmation server 21 transmits to the mobile terminal 12 an application program that is displayed on the screen when the template frame is captured. The template frame is a frame displayed on the display screen when taking an image of an identification card, and is provided as an identification card frame. In addition, the user may download the application program from the Apple Store (registered trademark) or the web store of Google Inc.

  FIG. 2 is a diagram illustrating an imaging process in an imaging application provided from the registration information confirmation server. As shown in FIG. 2A, when the imaging application captures an image of an identification card on the display screen 12A of the mobile terminal 12, the identification card frame F1 is displayed as the template frame.

  In the ID card frame F1, the frame size is set for each type of ID card. Further, the identification frame F1 will be described later when a license image is arranged inside and the outer periphery of the arranged license image (hereinafter referred to as a license image) is captured in a size that overlaps in plan view. The size and resolution of the character image obtained by the OCR processing are set to a size that can be analyzed in the character recognition processing (character analysis). Also, for example, a preset error range is set for the degree of overlap in planar view between the identification frame F1 and the outer periphery of the license image in plan view.

  Further, as shown in FIG. 2B, the user can fit the outer periphery of the license image 100 into the identification card frame F1, and the outer periphery of the license image 100 can overlap the identification card frame F1. The license image 100 is captured by the portable terminal 12. Thereby, the license image 100 within the identification card frame F1 is captured in the frame. More specifically, the license is placed at a position where the license image 100 fits in the identification frame F <b> 1, and imaging is performed by the mobile terminal 12. In FIG. 2B, an edge 150 is an outline of the license image 100, that is, an edge portion of the license image 100. The outer frame line 200 is a kind of ruled line (for example, 157, 158, 159, 161, 162, 163, 164) printed on the surface of the license, and is a column in which information for identification is described. This is a ruled line located at the outermost position printed as an outer frame in the ruled line forming the frame.

FIG. 3 is a block diagram showing a configuration example of the registration information confirmation server according to the first embodiment of the present invention. The registration information confirmation server 21 includes an image acquisition unit 211, an edge acquisition processing unit 212, a ruled line acquisition processing unit 213, an image correction processing unit 214, an OCR processing unit 215, and a storage unit 216.
The image acquisition unit 211 inputs a captured image (captured image corresponding to the display screen 12 </ b> A illustrated in FIG. 2B) transmitted from the external device, for example, from the mobile terminal 12, and writes and stores it in the storage unit 216. Let

The edge acquisition processing unit 212 reads a captured image (hereinafter also referred to as “captured data”) from the storage unit 216, and detects an edge of the image of the identification portion (the edge 150 in FIG. 2B) from the captured image. I do.
Here, for example, the edge acquisition processing unit 212 obtains a gradient of change in luminance (pixel value) in the captured image, calculates the strength of the edge, and predicts the local direction of the edge from the direction of the gradient. Then, the edge acquisition processing unit 212 searches for a locally local maximum in the predicted local direction, compares the location with a preset threshold value, and detects an edge.

The ruled line acquisition processing unit 213 reads the captured image from the storage unit 216, and in the captured image, from the ruled line that forms the frame of the column on which the identification information is printed that is printed on the surface of the identification card. An outer frame line (outer frame line 200 in FIG. 2B) which is the outermost ruled line is detected.
Here, the ruled line acquisition processing unit 213 extracts, for example, a line segment from the image and extracts a ruled line based on a ruled line extraction rule set in advance. In other words, the ruled line acquisition processing unit 213 determines whether or not the extracted line segment width or line segment length is a ruled line in the ruled line extraction rule, and determines the outermost ruled line obtained as a determination result. The ruled line located at is detected as an outer frame line.

The image correction processing unit 214 uses either the edge 150 acquired by the edge acquisition processing unit 212 or the outer frame line 200 acquired by the ruled line acquisition processing unit 213, and uses the trapezoid correction, the aspect ratio correction, and the lens aberration of the captured image. Image correction processing such as correction is performed. Here, instead of the outer frame line, any ruled line may be used as long as it can perform image correction processing such as trapezoidal correction, aspect ratio correction, and lens aberration correction of the captured image.
The OCR processing unit 215 performs character recognition at a predetermined position (previously designated area) of the license image 100 in the corrected captured image, and extracts text data as character information from each position.

FIG. 4 is a diagram for explaining the detection processing of the edge and outer frame line of the identification card from the captured image by the registration information confirmation server according to the first embodiment of the present invention.
In FIG. 4, an edge 150 of the license image 100 indicates an outer peripheral portion of the license image 100, and a difference in height between the background and the license at the time of imaging, that is, the thickness of the license or the color of the background. It is formed as a difference from the color of the outer periphery of the license, that is, a difference in brightness. For this reason, when the image is captured at an angle at which it is difficult to shadow when the license is captured, or when the background color does not have a luminance difference from the color of the outer periphery of the license, an edge exceeding the above threshold cannot be detected, and the edge 150 Is not detected.
On the other hand, the ruled line extraction has higher detection accuracy than the edge extraction described above, but the ruled line cannot be extracted due to the reflection of the illumination light on the surface or the like depending on the state of the illumination light when imaging the license and the imaging angle. The outer frame line 200 cannot be detected based on the ruled line extraction rule.

The OCR processing unit 215 captures each character image in a predetermined area of the license of the license image 100 by using an optical character reading function. The predetermined area is an area in which character data of items such as an address, a name, an expiration date, and a date of birth in the license is described. As shown in FIG. 4, the OCR processing unit 215 designates a reading position in the license image 100 for each item in advance. The reading position (area) is any one of the predetermined areas or a combination thereof. This designation can also be performed by the operator operating from the input unit of the registration information confirmation server 21.
In addition, the OCR processing unit 215 relatively detects the reading position in the license image 100 described above with reference to the edge 150 or the outer frame line 200.

  Next, registration information confirmation performed by the registration information confirmation server according to the first embodiment of the present invention will be described with reference to FIGS. 1, 2, 3, 4, and 5. FIG. 5 is a flowchart showing an operation example of the registration information confirmation system according to the first embodiment of the present invention. In the following, description will be given by taking as an example confirmation of license registration information, which is a confirmation document for confirming personal information when the user registers his / her personal information in order to open a bank account.

Step S1:
The user accesses the registration information confirmation server 21 via the information communication network by the terminal 11 and refers to a web page for performing registration processing on the display screen of the terminal 11.
The registration information confirmation server 21 transmits to the mobile terminal 12 a display for downloading an application program for displaying the template frame shown in FIG.

Then, the user clicks a button for instructing download on the registration screen displayed on the mobile terminal 12. Thereby, the mobile terminal 12 downloads the application program from the registration information confirmation server 21. When the mobile terminal 12 downloads the application program, the mobile terminal 12 displays a button for executing the application on the web page of the display screen. Here, the user may download the application program from the Apple Store (registered trademark) or the web store of Google Inc.
Then, the user causes the mobile terminal 12 to execute an application program.

Step S2:
When the application is executed, the mobile terminal 12 switches itself to the imaging mode and displays the template frame of FIG. 2A on the display screen.
In the template frame, as shown in FIG. 2B, the user adjusts the arrangement of the license so that the outer periphery of the license image 100 overlaps the identification frame F1, and also captures the mobile terminal 12. Adjustments such as zooming in and out of the position and imaging range are performed.

The user captures the license image 100 with the portable terminal 12 so that the license image 100 that is the identification card fits in the identification card frame F1 in the template frame. Thereby, the mobile terminal 12 transmits the captured image data (captured image) to the registration information confirmation server 21.
The image acquisition unit 211 inputs imaging data supplied from the mobile terminal 12 and writes and stores it in the storage unit 216.

Step S3:
The ruled line acquisition processing unit 213 reads the imaging data from the storage unit 216, performs ruled line extraction image processing on the imaging data, and extracts the outer frame line 200 in the license image 100.

Step S4:
Then, the ruled line acquisition processing unit 213 determines whether or not the outer frame line 200 can be detected and acquired from the ruled lines extracted based on the rule for extracting the ruled lines, and the license written in the storage unit 216 in advance is set. It is determined by the shape and aspect ratio of the outer frame line.
At this time, if the outer frame line 200 can be acquired, the ruled line acquisition processing unit 213 outputs the outer frame line information of the outer frame line 200 to the image correction processing unit 214, and the process proceeds to step S5. On the other hand, when the outer frame line 200 cannot be acquired, the ruled line acquisition processing unit 213 outputs information indicating that the outer frame line 200 cannot be extracted to the image correction processing unit 214, and the process is performed in step S15. Proceed to

Step S5:
The image correction processing unit 214 performs image correction such as trapezoidal correction, aspect ratio correction, and lens aberration correction on the imaging data (image data) based on the information of the outer frame line 200 supplied from the ruled line acquisition processing unit 213. , OCR makes it possible to recognize characters.

Step S6:
The OCR processing unit 215 performs OCR processing of imaging data transmitted from the mobile terminal 12 using an optical character reader (not shown).
The registration information confirmation server 21 extracts character images, which are character image data in each of the preset areas, as shown in FIG. 4 from the image data obtained by OCR processing from the image data.
The OCR processing unit 215 performs character recognition of the character image and obtains text data corresponding to the character image.

Step S7:
Then, the user can use personal information such as the user's name, address, and telephone number on the web page for registering the display screen displayed on the terminal 11 using the input device (eg, keyboard) of the terminal 11. Enter.

Step S8:
The user inputs necessary personal information to the web page on the display screen of the terminal 11, and then clicks an execution button that requests execution of registration processing on the web page.
Thereby, the terminal 11 transmits the personal information described in the web page to the registered information confirmation server 21 via the information communication network.

And the registration information confirmation server 21 will give an application number with respect to this personal information, if personal information is input. The registration information confirmation server 21 writes and stores the personal information and the assigned application number as a set in the database 22.
Further, the registration information confirmation server 21 transmits the assigned application number to the terminal 11.

Step S9:
The registration information confirmation server 21 displays personal information on the web page on the display screen of the mobile terminal 12 and prompts the user to confirm the registration contents.

Step S10:
When the registration information (screen content) displayed on the web page of the display screen of the mobile terminal 12 is correct, the user clicks a button indicating approval on the web page, for example. On the other hand, when the registration information is to be corrected, for example, a button indicating cancellation on the web page is clicked.
If the approval button is clicked (YES), the mobile terminal 12 proceeds to step S11. If the cancel button is clicked (NO), the mobile terminal 12 ends the process.

Step S11:
The mobile terminal 12 transmits a response signal that acknowledges that the personal information is correct and that registration is performed to the registration information confirmation server 21.
And the portable terminal 12 complete | finishes execution of an application program, and returns to the normal mode in which the application is not performed.

Step S12:
The registration information confirmation server 21 writes and stores the imaging data (license image 100) of the registration information in the database 22 in association with the personal information.

Step S13:
The registration information confirmation server 21 transmits the imaging data and the personal information to the registration information management server 31 of the contract facility 3 after the registration of the registration information is completed.
Then, the registration information management server 31 writes and accumulates the registration information transmitted from the registration information confirmation server 21 in a database (not shown).

Step S14:
If the information input is not correctly performed in step S7, the registration information confirmation server 21 transmits re-registration information indicating that the process is restarted from the input of the personal information in step S7 to the portable terminal 12, and performs the process. finish.
In addition, when neither the ruled line acquisition nor the edge acquisition can be performed, the registration information confirmation server 21 gives re-imaging information to the portable terminal 12 indicating that the processing is started again from the imaging of the license (identification card) in step S2. To send.

Step S15:
The edge acquisition processing unit 212 reads the imaging data from the storage unit 216, performs image processing for ruled line extraction on the imaging data, and extracts the edge 150 in the license image 100.

Step S16:
Then, the edge acquisition processing unit 212 determines whether or not the edge 150 can be detected and acquired from the edges extracted based on the rule of edge extraction, and the edge of the license set in advance in the storage unit 216. Judgment is made based on the shape and aspect ratio.
At this time, if the edge 150 can be acquired, the edge acquisition processing unit 212 outputs the edge information of the edge 150 to the image correction processing unit 214, and the process proceeds to step S17. On the other hand, if the edge 150 cannot be acquired, the ruled line acquisition processing unit 213 outputs information indicating that the edge 150 cannot be extracted to the image correction processing unit 214, and advances the processing to step S14.

Step S17:
The image correction processing unit 214 performs image correction such as trapezoidal correction, aspect ratio correction, and lens aberration correction on the imaging data based on the information of the edge 150 supplied from the edge acquisition processing unit 212, and character recognition is performed by OCR. Make it possible.

  As described above, the present embodiment has a configuration in which both edge extraction and ruled line extraction processing can be performed from the license image 100 in the imaging data of the license (identification certificate). When either one of 150 and the outer frame line 200 cannot be acquired, the other is acquired. Therefore, according to the present embodiment, when character recognition of a character image described in a predetermined column of the license image 100 is performed by OCR processing, OCR is performed by at least one of the edge 150 and the outer frame line 200. A form capable of recognizing a character image can be realized, and the possibility of performing image correction such as trapezoidal correction, aspect ratio correction, and lens aberration correction can be improved as compared with the related art.

In other words, each of the edge acquisition and ruled line acquisition is different depending on the brightness difference due to the step and the printed line segment image, so depending on the captured environment, either one may be easily detected, When it is difficult to detect the other, it is possible to increase the probability that information used for correcting the shape of the license image necessary for image correction can be acquired as compared with the related art.
As a result, it is possible to reduce the frequency of requesting the user to re-image the certificate compared to the conventional configuration in which only one of the edge and the ruled line is acquired, and the personal information registration work It is possible to reduce the troublesomeness of re-imaging and improve usability (ease of use).

<Second Embodiment>
Embodiments of the present invention will be described below with reference to the drawings. FIG. 6 is a conceptual diagram showing a configuration example of a registration information confirmation system according to the second embodiment of the present invention. In FIG. 6, the registration information confirmation server 21A includes an image acquisition unit 211, an edge acquisition processing unit 212, a ruled line acquisition processing unit 213, an image correction processing unit 214, an OCR processing unit 215, a storage unit 216, and an imprint acquisition unit 217. It has. The difference from the first embodiment is that it includes an imprint acquisition unit 217 that acquires an imprint image (imprint image).

  When the imprint flag is set, the seal impression acquisition unit 217 performs processing for extracting and acquiring a seal image stamped by the user from the image data captured by the user. Here, when it is necessary to acquire an imprint image from the image data, the registration information confirmation server 21A sets the imprint flag added to the image data (for example, “1”), and the imprint image from the image data. When it is not necessary to acquire the image, the imprint flag added to the imaging data is set to a reset state (for example, “0”).

  FIG. 7 is a diagram illustrating an imaging process in an imaging application provided from the registration information confirmation server. As shown in FIG. 7A, the imaging application displays an identification card frame F1 and an imprint frame F2 on the display screen 12A of the mobile terminal 12 when capturing an identification card and an imprint image. The identification card frame F1 has the same configuration as that of the first embodiment. Thereby, each of the image of the identification card and the seal imprint image is included in the same frame, and is captured by one image data. The imprint acquisition unit 217 acquires an image extracted in the imprint frame F2 as an imprint image.

  Further, as shown in FIG. 7B, the user can fit the outer periphery of the license image 100 into the identification card frame F1, and the outer periphery of the license image 100 can overlap the identification card frame F1. The license image 100 is captured by the portable terminal 12. At this time, the user arranges the imprint image 101 so that the imprint image 101 fits in the imprint frame F2, and captures the imprint image 101 by the portable terminal 12 together with the license image 100 in the identification card frame F1. . Thereby, the license image 100 in the identification frame F1 and the seal image 101 in the seal frame F2 are captured in the same frame. More specifically, the imprint is imprinted on the paper, and the license image 100 is placed in a position where the license image 100 fits in the identification frame F1 in a state where the imprint image 101 is within the imprint frame F2. 12 performs imaging.

  FIG. 8 is a flowchart showing an operation example of the registration information confirmation system according to the second exemplary embodiment of the present invention. Only the processing different from the flowchart of FIG. 5 in the first embodiment will be described below. In the flowchart of FIG. 8, the processing different from the first flowchart is each of steps S1A, S4A, S5A, S5B, S12A, and S14A.

Step S1A:
The registration information confirmation server 21 transmits to the portable terminal 12 a display for downloading an application program for displaying the template frame shown in FIG. Here, the user may download the application program from the Apple Store (registered trademark) or the web store of Google Inc.

Step S4A:
The imprint acquisition unit 217 determines whether the imprint flag added to the imaging data is set or reset, that is, the presence or absence of the imprint image 101 to be acquired in the imaging data. At this time, if the seal impression acquisition unit 217 determines that the seal impression image 101 to be acquired exists in the imaging data, the process proceeds to step S14A. On the other hand, if the seal impression acquisition unit 217 determines that there is no seal impression image 101 to be acquired in the imaging data, the process proceeds to step S15.
That is, when there is no imprint image 101 in the imaging data, since only the OCR process needs to be performed, the acquisition of the outer frame line 200 has failed, so the step of acquiring the edge 150 used for the image process before the OCR process is performed. The process proceeds to S15. On the other hand, if the imprint data 101 includes the imprint image 101, it is necessary to extract the imprint image in addition to the OCR processing. However, if the ruled line cannot be acquired, the captured image does not have the accuracy of acquiring the imprint image 101. The process proceeds to step S14A.

Step S5A:
The imprint acquisition unit 217 determines whether the imprint flag added to the imaging data is set or reset, that is, the presence or absence of the imprint image 101 to be acquired in the imaging data. At this time, if the seal impression acquisition unit 217 determines that the seal impression image 101 to be acquired exists in the imaging data, the process proceeds to step S5B. On the other hand, if the seal impression acquisition unit 217 determines that there is no seal image 101 to be acquired in the imaging data, the process proceeds to step S6.
That is, when there is no imprint image 101 in the imaged data, only the OCR process needs to be performed, so there is no need to perform the imprint acquisition process, and the process proceeds to step S6. On the other hand, if there is an imprint image in the captured image data, it is necessary to extract the imprint image 101 in addition to the OCR process, and thus the process proceeds to step S5B in which a process for acquiring the imprint image 101 is performed.

Step S5B:
The imprint acquisition unit 217 extracts an image in the imprint frame F2 from the imaging data as the imprint image 101. At this time, the seal imprint acquisition unit 217 can acquire the seal imprint image 101 with the accuracy with which the ruled line can be acquired (the resolution of the image of the imaged data is sufficient).

Step S12A:
The registration information confirmation server 21 writes and stores image data of the registration information (the license image 100 and the seal image 101) in the database 22 in association with the personal information.

Step S14A:
If the information input is not correctly performed in step S7, the registration information confirmation server 21 transmits re-registration information indicating that the process is restarted from the input of the personal information in step S7 to the portable terminal 12, and performs the process. finish.
In addition, when neither the ruled line acquisition nor the edge acquisition can be performed, the registration information confirmation server 21 gives re-imaging information to the portable terminal 12 indicating that the processing is started again from the imaging of the license (identification card) in step S2. To send.
Further, the registration information confirmation server 21 indicates that if the ruled line cannot be acquired and the image data includes the seal image 101, the processing is restarted from the license (identification card) and seal image capturing in step S2. The re-imaging information is transmitted to the mobile terminal 12.

  According to the present embodiment, when only OCR processing is performed, as in the first embodiment, when character recognition of a character image described in a predetermined column of the license image 100 is performed by OCR processing, at least an edge Either 150 or the outer frame line 200 enables a character image to be recognized by OCR, and the possibility of performing image correction such as trapezoidal correction, aspect ratio correction, and lens aberration correction is conventionally known. It can be improved compared to That is, according to the present embodiment, when only OCR processing is performed, OCR processing can be performed as long as at least an edge can be acquired from captured image data, even if ruled line acquisition that guarantees the quality of acquiring a seal impression image cannot be performed. Therefore, even if the outer frame line 200 is not detected in the ruled line process, an error that the OCR process cannot be performed does not occur. Therefore, it is possible to reduce the troublesomeness of re-imaging in the registration process of personal information and improve usability. It becomes possible.

  In addition, according to the present embodiment, registration processing of an image of only an ID card or registration processing of an ID card image and an imprint image 101 can be respectively performed. It is determined whether or not the quality of the image of the captured data is such that an imprint image can be acquired, depending on whether or not the image can be acquired. For this reason, according to the present embodiment, when the ruled line cannot be acquired, the imprint image 101 is not acquired. Therefore, the quality of the imprint image 101 can be maintained at a certain accuracy.

  In each of the first embodiment and the second embodiment, the ruled line acquisition process is performed before the edge acquisition process, but the edge acquisition process may be performed before the ruled line acquisition process.

  Further, a program for realizing each function of the registration information confirmation server 21 in FIG. 3 or the registration information confirmation server 21A in FIG. 8 is recorded on a computer-readable recording medium, and the program recorded on the recording medium is recorded. By reading the information into a computer system and executing it, confirmation processing of registration information for each image of the identification card or seal may be performed. Here, the “computer system” includes an OS and hardware such as peripheral devices.

Further, the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used.
The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Furthermore, the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory in a computer system serving as a server or a client in that case, and a program that holds a program for a certain period of time are also included. The program may be a program for realizing a part of the functions described above, and may be a program capable of realizing the functions described above in combination with a program already recorded in a computer system.

  The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes design and the like within a scope not departing from the gist of the present invention.

DESCRIPTION OF SYMBOLS 1 ... User 2 ... Registration information confirmation center 3 ... Facility 11 ... Terminal 12 ... Mobile terminal 12A ... Display screen 21, 21A ... Registration information confirmation server 22 ... Database 31 ... Registration information management server 100 ... License image 101 ... Imprint image 150 ... Edge 200 ... Outer frame line F1 ... Identification card frame F2 ... Imprint frame

Claims (3)

One of the edge detection process for detecting the edge of the image of the identification card and the ruled line detection process for detecting the ruled line printed on the identification card is performed as the first process from the captured image obtained by capturing the identification card. When the detection by the first process cannot be performed, the other is performed as the second process, and the edge or the ruled line is acquired.
Correcting the captured image by the detected edge or ruled line;
And a step of performing character recognition in the image of the identification card of the corrected captured image and reading character information. In the captured image, each of the image of the identification card and the image of the seal imprint is captured as the same frame, and when the ruled line is acquired, the captured image is captured together with the identification card from the captured image corrected based on the ruled line. The registered information confirmation method according to claim 1, further comprising a step of extracting an image of the printed seal impression.   One of the edge detection process for detecting the edge of the image of the identification card and the ruled line detection process for detecting the ruled line printed on the identification card is performed as the first process from the captured image obtained by capturing the identification card. When the detection by the first process cannot be performed, the other is performed as the second process, either the edge or the ruled line is acquired, and the captured image is corrected by the detected edge or the ruled line. A registered information confirmation server that performs character recognition in the image of the identification card of the corrected captured image and reads character information.

Images