JP6910236B2 - Personal information registration system and personal information registration method - Google Patents

Description

The present invention relates to a personal information registration system and a personal information registration method.

The use of biometric authentication technology is expanding as a safe and convenient personal authentication means to replace the combination of ID and password. In financial services, the use of biometric authentication for opening an account from a mobile terminal, inquiring a balance, transferring an account, and authenticating a person when using an ATM is being realized. When using a biometric authentication service in a bank service, the cost of registering biometric information becomes a problem. The user needs to go to the counter once at the time of opening the account or after opening the account and register the biometric information separately. Therefore, if registration procedures can be performed at home without going to the counter, convenience is expected to improve and the number of users is expected to increase.

As a technique for opening an account without visiting a store, there is Japanese Patent Application Laid-Open No. 2017-004115 (Patent Document 1). In Patent Document 1, "On the user terminal, when the registration start icon is touched (S2: YES), the option of personal information to be registered is displayed on the screen (S3). The option is selected, and the option is displayed. When the specification completion icon is touched (S4: YES), the registration start request and the information of the option selected by the user are sent to the registration server (S5). When the registration start notification is received from the registration server (S4: YES) S6: YES), the control of the camera unit, the microphone unit, and the fingerprint sensor is started according to the instruction of the registration server (S7). This control is performed by the MDM control. Therefore, the image from the camera unit is started by the MDM control of the registration server. , The voice from the microphone unit is transmitted from the user terminal to the registration server (S8). "(See summary).

JP-A-2017-004115

However, in the technique described in Patent Document 1, since it is not verified whether the biometric information such as the fingerprint and the image of the official certificate belong to the same person, the registered biometric information is the account holder himself / herself. It may not be a thing.

Therefore, one aspect of the present invention is to carry out personal information registration that can guarantee personality with high accuracy even from a remote location.

In order to solve the above problems, one aspect of the present invention adopts the following configuration. It is a personal information registration system for registering the first biometric information of a person to be registered, and has a processor and a storage device. The storage device holds a biometric authentication template for storing biometric information, and the processor , The information of the document including the second biometric information of the person to be registered, which is different from the first biometric information and is image information, is acquired, and the first biometric information and the second biological body photographed by the imaging device are acquired. The acquired second biometric information is the second biometric information of the person to be registered, based on the degree of similarity between the information and the acquired second biometric information and the second biometric information contained in the document. When it is determined that the difference between the generation time of the acquired first biometric information and the photographing time of the acquired second biometric information is within a predetermined value, the acquired first biometric information is referred to as described above. Personal information registration system stored in the biometric authentication template.

According to one aspect of the present invention, personal information registration capable of ensuring personality with high accuracy can be performed even from a remote location.

Issues, configurations and effects other than those described above will be clarified by the description of the following embodiments.

It is a block diagram which shows the structural example of the personal information registration system in Example 1. FIG. It is a block diagram which shows the configuration example of the user terminal in Example 1. FIG. It is a block diagram which shows the configuration example of the business server in Example 1. FIG. It is a block diagram which shows the configuration example of the registration / authentication server in Example 1. FIG. It is a flowchart which shows an example of personal information registration processing in Example 1. FIG. It is a flowchart which shows an example of personal information registration processing in Example 2. FIG. It is a sequence diagram which shows an example of personal information registration processing in Example 1. FIG. It is a sequence diagram which shows an example of personal information registration processing in Example 2. FIG. It is a sequence diagram which shows an example of the personal information registration process in Example 3. It is a flowchart which shows an example of the authentication process in Example 1. FIG. This is an example of the account information table in the first embodiment. This is an example of the authentication template in the first embodiment. It is explanatory drawing which shows an example of the method of determining whether the 1st biological information and the 2nd biological information belong to the same person in Example 1. It is explanatory drawing which shows another example of the method of determining whether the 1st biological information and the 2nd biological information belong to the same person in Example 1. It is explanatory drawing which shows the relationship between the 1st biological information and the 2nd biological information in Example 1. FIG. It is an example of the power spectrum in Example 1. It is explanatory drawing which shows an example of the Local Binary Pattern (LBP) used for the forgery determination in Example 1. FIG. It is explanatory drawing which shows an example of the outline of the forgery determination process in Example 1. FIG. It is a flowchart which shows an example of the forgery determination processing in Example 1. FIG.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. It should be noted that the present embodiment is merely an example for realizing the present invention and does not limit the technical scope of the present invention. The same reference numerals are given to common configurations in each figure.

FIG. 1 is a block diagram showing a configuration example of a personal information registration system. The personal information registration system includes, for example, a user terminal 10, a business server 20, a registration / authentication server 30, a window system 50, and an ATM 60, which are connected to each other by a network 40. An example in which the personal information registration system is used to open a new bank account will be described below. With the personal information registration system of the present embodiment, a person who wishes to open an account can register personal information and open a new bank account without visiting a bank.

The user terminal 10 is a terminal owned by a person who wishes to open a bank account, and is, for example, a smartphone, a personal computer, a tablet terminal, or the like. The user terminal 10 is, for example, a computer for safely registering various personal information at the time of opening an account.

The business server 20 is installed in a bank, for example, and performs account opening reception, personal information registration, account information management, and the like. The registration / authentication server 30 holds, for example, information for authenticating the account holder (for example, biometric information), and the information is used when the account holder uses the window system 50 or the ATM (Automatic Teller Machine) 60. Perform identity verification (biometric authentication) using. The window system 50 is a computer installed at a bank window, and executes, for example, deposits and withdrawals of deposits.

FIG. 2 is a block diagram showing a configuration example of the user terminal 10. The user terminal 10 includes, for example, an input device 11, a display device 12, a CPU (Central Processing Unit) 13, a photographing device 14, a memory 15, an auxiliary storage device 16, a GPS (Global Positioning System) device 17, a communication interface 18, and an IC. It is composed of a computer having a chip reader 19.

The input device 11 is a device that receives an input such as an instruction by a user, and is, for example, a keyboard, a mouse, a touch panel, or the like. For example, the user can use the input device 11 to select a process to be executed from a plurality of boxes (buttons) displayed on the display device 12. The display device 12 is a device that outputs information such as various characters and images to the user in a format that can be visually recognized by the user, and is, for example, an image display device such as a liquid crystal display, a printer, or the like. The input device 11 and the display device 12 may be integrated.

The photographing device 14 photographs a subject such as a face, a finger (fingerprint), a palm (palm print), and a public certificate such as a driver's license or an Individual Number Card. Specifically, the photographing device 14 is, for example, a camera attached to the user terminal 10.

The CPU 13 includes a processor and executes a program stored in the memory 15. The memory 15 includes a ROM which is a non-volatile storage element and a RAM which is a volatile storage element. The ROM stores an invariant program (for example, BIOS) and the like. The RAM is a high-speed and volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores a program executed by the CPU 13 and data used when the program is executed.

The auxiliary storage device 16 is, for example, a large-capacity and non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD), and stores a program executed by the CPU 13 and data used when executing the program. .. That is, the program is read from the auxiliary storage device 16, loaded into the memory 15, and executed by the CPU 13.

The program executed by the CPU 13 is provided to the user terminal 10 via removable media (CD-ROM, flash memory, etc.) or a network, and is stored in the non-volatile auxiliary storage device 16 which is a non-temporary storage medium. .. Therefore, the user terminal 10 may have an interface for reading data from removable media.

The auxiliary storage device 16 holds the account opening application 161. For example, the CPU 13 functions as an account opening unit by operating according to the account opening application 161 which is a program loaded in the memory 15. The same applies to the relationship between the CPU and the program held by the business server 20 and the registration / authentication server 30, which will be described later. Although not shown, the auxiliary storage device 16 also stores an OS (Operating System) and a communication program for communicating with another device via the communication interface 18.

The GPS device 17 positions the current position of the user terminal 10. The communication interface 18 is a network interface device that controls communication with other devices according to a predetermined protocol. Further, the communication interface 18 includes, for example, a serial interface such as USB. The IC chip reader 19 is, for example, an IC chip reader such as NFC, and reads information (for example, address, name, age, gender, face image information, etc.) described in a public certificate.

FIG. 3 is a block diagram showing a configuration example of the business server 20. The business server 20 is composed of, for example, a computer having an input device 21, a display device 22, a CPU 23, a memory 25, an auxiliary storage device 26, and a communication interface 28. The input device 21, the display device 22, the CPU 23, the memory 25, the auxiliary storage device 26, and the communication interface 28 are the same as the input device 11, the display device 12, the CPU 13, the memory 15, the auxiliary storage device 16, and the communication interface 18, respectively. The description of is omitted.

The auxiliary storage device 26 holds, for example, an account opening program 261, a face verification program 262, an address verification program 263, a time verification program 264, and a deposit business execution program 267. In addition, the auxiliary storage device 26 holds, for example, an account information table 265 and a biometric authentication template 266.

The account opening program 261 is, for example, in response to an account opening request from the user terminal 10, an instruction to present a public certificate, an operation instruction such as taking a picture of a user's face or biometric information, and various personal information registrations associated with opening an account. Perform the necessary processing for opening an account. The face verification program 262 verifies, for example, whether or not the face information obtained from the official certificate matches the face image taken by the photographing device 14 of the user terminal 10.

The address verification program 263 includes, for example, address information obtained by character recognition of an image from a public certificate or by reading an IC chip of a public certificate, and an address determined by the GPS device 17 of the user terminal 10. And, are verified whether they match or are within a predetermined distance. Verification by the address verification program 263 can improve the accuracy of identity verification.

The time verification program 264 determines, for example, that the shooting times of a plurality of biometric information are simultaneously or within a certain time, and that the shooting time of the official certificate and the shooting time of the biometric information are simultaneously or within a certain time. Verify. The deposit business execution program 267 accepts and executes deposits and withdrawals.

The account information table 265 stores the account number and the personal information of the account opener in association with each other. The biometric authentication template 266 holds, for example, the information that identifies the account number, the information that identifies the account holder, and the biometric information of the account holder in association with each other. The biometric information held by the biometric authentication template 266 is preferably biometric information converted by a one-way function or the like.

FIG. 4 is a block diagram showing a configuration example of the registration / authentication server 30. The registration / authentication server 30 is composed of, for example, a computer having a CPU 33, a memory 35, an auxiliary storage device 36, and a communication interface 38. The same description as for each of the CPU 13, the memory 15, the auxiliary storage device 16, and the communication interface 18 will be omitted for each of the CPU 33, the memory 35, the auxiliary storage device 36, and the communication interface 38. The registration / authentication server 30 may further have an input device and a display device.

The auxiliary storage device 36 holds a spoofing detection program 361 and a biometric signature verification program 362. In addition, the auxiliary storage device 36 holds the biometric authentication template 363. The pretending detection program 361 determines whether or not the photographed image of the public certificate transmitted from the user terminal 10 is obtained by photographing the public certificate itself. Specifically, for example, the spoofing detection program 361 determines whether or not the captured image is a printed matter of the official certificate or an image obtained by capturing the official certificate displayed on the display.

The biometric signature verification program 362 performs authentication processing and signature verification processing using, for example, the biometric information input by the account holder when using the window system 50 or ATM 60 and the biometric information held by the biometric authentication template 363. The biometric authentication template 363 holds, for example, the information that identifies the account number, the information that identifies the account holder, and the biometric information of the account holder in association with each other. The biometric information held by the biometric authentication template 363 is preferably biometric information converted by a one-way function or the like.

In the present embodiment, the information used by the user terminal 10, the business server 20, and the registration / authentication server 30 may be represented by any data structure regardless of the data structure. For example, a properly selected data structure from a table, list, database or queue can store the information.

The user terminal 10, the business server 20, and the registration / authentication server 30 are each a computer system composed of physically one computer or a plurality of logically or physically configured computers. Yes, it may run on the same computer in separate threads, or it may run on virtual computers built on multiple physical computer resources. Further, for example, the business server 20 and the registration / authentication server 30 may be configured by one computer.

FIG. 5 is a flowchart showing an example of the personal information registration process. In the following, taking the opening of a new bank account as an example, the personal information registration system confirms the identity verification documents (public certificate) of the person who wishes to open an account and the biometric information that certifies the identity of the person at the time of registration. Prove.

First, in step S501, the user terminal 10 activates the account opening application 161 and the account opening application 161 transmits, for example, an account opening request to the business server 20 according to a user's instruction. In step S502, when the account opening application 161 receives the public certificate information transmission request from the account opening program 261 of the business server 20, the account opening application 161 selects a method of presenting the public certificate for identity verification according to the user's instruction.

The official certificate is, for example, a document in which personal information such as the address, name, and age of the person who wishes to open an account, and information such as the first biometric information are described. For example, a driver's license and a driver's license and My number card etc. Further, an IC chip or the like that holds such information may be embedded in the public certificate. The first biometric information is biometric information that can identify an individual, such as a face image. Hereinafter, an example in which the first biological information is a face image will be described. The method of presenting the public certificate that can be selected in step S502 includes, for example, IC chip reading and image capture.

When IC chip reading is selected as the method of presenting the official certificate (S502: IC chip reading), in step S505, the IC chip reading device 19 follows the user's operation to address, name, age, and gender in the IC chip. , And the information such as the first biometric information (face image) is read, the account opening application 161 transmits the information to the business server 20, and the process proceeds to step S506.

When image capture is selected as the method of presenting the official certificate (S502: image capture), in step S503, the imaging device 14 (general-purpose camera) mounted on the user terminal 10 is subjected to the official certificate according to the user's operation. The account opening application 161 transmits the photographed official certificate image to the business server 20 and the registration / authentication server 30. The official certificate image needs to include information such as the address, name, age, and first biological information (for example, face image) of the person who wishes to open an account. The account opening application 161 may directly send the public certificate image to the registration / authentication server 30, or request the business server 20 to send the public certificate image to the registration / authentication server 30. May be good.

Next, in step S504, the forgery detection program 361 is whether the received official certificate image is an image duplicated by printing or the like or an image displayed on the display (that is, a genuine public certificate image). Make a forgery judgment about (whether the image is a photograph of the certificate itself). The specific method of forgery determination will be described later.

When the pretending detection program 361 determines that the official certificate is a forgery (S504: Yes), the determination result indicating that the account cannot be opened is determined via the business server 20 or directly by the user terminal 10. And ends the personal information registration process. When the pretending detection program 361 determines that the official certificate is not a forgery (S504: No), the process proceeds to step S506.

Even if the predecessor detection program 361 cannot recognize information such as the address, name, age, and first biometric information (for example, face image) of the person who wishes to open an account in the official certificate image, the account The determination result indicating that the opening cannot be performed may be transmitted to the user terminal 10 via the business server 20 or directly to end the personal information registration process.

In step S506, the photographing device 14 of the user terminal 10 photographs the first biometric information (face image) according to the user's instruction, and the account opening application 161 transmits the image of the first biometric information to the business server 20. .. The first biometric information (face image) captured in step S506 is an image of the user's own face directly captured (that is, not a printed face image, a face image displayed on a display, or the like).

Next, in step S507, the user terminal 10 acquires the second biometric information used for biometric authentication according to the instruction of the user. The second biometric information is biometric information that can identify an individual and is different from the first biometric information. For example, as the second biological information, an image of a palm vein, a fingerprint, a palm print, a voice, or the like is used. The second biometric information acquired in step S507 is information directly acquired from the user himself / herself (that is, an image obtained by directly photographing the palm vein of the user himself / herself or sound data obtained by directly recording the voice of the user himself / herself).

The process of step S507 may be performed not immediately after step S506, but immediately before step S510 in the case of "Yes" in step S508 described later.

In step S508, the face verification program 262 matches the first biometric information acquired in step S507 with the first biometric information acquired in step S503 or step S506 (for example, the similarity is predetermined). (More than the value) is verified using, for example, a face recognition algorithm. That is, the face verification program 262 verifies whether the first biometric information acquired in step S507 belongs to the person who wishes to open an account.

When image capture is selected in step S502, the face verification program 262 may extract the first biometric information (face image) from the official certificate image by using, for example, a face recognition algorithm or the like. Then, the first biometric information (face image) may be extracted by extracting a predetermined area of the official certificate image.

In step S510, when the face verification program 262 determines that the two first biometric information do not match (S508: No), the determination result indicating that the account cannot be opened is determined via the business server 20 by the user terminal. It is transmitted to 10 and the personal information registration process is completed.

When the face verification program 262 determines that the two first biometric information match (S508: Yes), in step S509, the account opening application 161 transfers the second biometric information acquired in step S507 to the business server 20. The account opening program 261 transmits and transmits the first biometric information acquired in step S506 and the second biometric information acquired in step S507 in association with each other to the registration / authentication server 30.

In each of the above-mentioned processes, when the account opening application 161 transmits information to an external device such as a business server 20, the information is described in, for example, "Japanese Patent Laid-Open No. 2013-123142". After the direction is changed, the converted information may be transmitted to the business server 20. As a result, the risk of information leakage can be reduced.

Subsequently, in step S510, the biometric signature verification program 362 checks for duplication with the already registered account information. The biometric signature verification program 362 checks for duplication, specifically, for example, whether the biometric information received from the business server 20 in step S509 has not been registered in the biometric authentication template 363. In addition, as a technology for performing biometric authentication processing, fingerprint, finger vein, and palm authentication methods, which are known technologies (for example, Seiichiro Hanga, et al., "Biometrics Textbook-From Principles to Programming," Corona, June 8, 2012 , Etc.) can be adopted.

If it is determined in step S510 that there is duplication (S510: there is duplication), the biometric signature verification program 362 transmits a determination result indicating that the account cannot be opened to the user terminal 10 via the business server 20 or directly. Then, the personal information registration process is completed. If it is determined in step S510 that there is no duplication (S510: no duplication), the business server 20 opens a new account in step S511.

Specifically, in step S511, for example, the account opening program 261 extracts the personal information described in the public certificate by an algorithm such as character recognition. The account opening program 261 issues a unique ID to the account opener when the same individual as the extracted personal information is not in the account information table 265. When the same individual as the extracted personal information exists in the account information table 265, the account opening program 261 identifies the ID of the individual. In addition, the account opening program 261 issues a unique account number and a unique connection key.

The account opening program 261 stores a record associated with a light emitting or specified ID, an account number, personal information described in a public certificate, and the connection key in the account information table 265, and the connection is performed. Notify the registration / authentication server 30 of the key. In addition, the account opening program 261 stores a record in which the key, the first biometric information, and the second biometric information are associated with each other in the biometric authentication template 266. Further, the biometric signature verification program 362 stores a record in which the connection key notified from the business server 20, the first biometric information, and the second biometric information are associated with each other in the biometric authentication template 363. After step S511 is executed, the personal information registration process ends. The business server 20 does not have to hold the biometric authentication template 266. In this case, the account opening program 261 does not perform the record addition process to the biometric authentication template 266 in step S511.

In step S510, not only the duplication check by the biometric signature verification program 362, but also the personal information acquired from the public certificate by the account opening program 261 of the business server 20, the information registered in the account information table 265, and the information registered in the account information table 265. Duplicate checking may be further performed. The biometric signature verification program 362 may determine that there is duplication only when all of the personal information is duplicated, or when predetermined personal information is duplicated (for example, when the combination of name and age is duplicated). Etc.), it may be determined that there is duplication.

FIG. 11A is an example of the account information table 265. The account information table 265 stores the opened account information. The account information table 265 includes, for example, an ID column 110, an account number column 111, a name column 112, an address column 113, a gender column 114, a date of birth column 115, a concatenation key column 116, and the like.

FIG. 11B is an example of the biometric authentication template 266. In addition, the biometric authentication template 266 stores the biometric information associated with the account information. The biometric authentication template 266 has a concatenation key column 117, a first authentication template column 118 based on the first biometric information, and a second authentication template column 119 based on the second biometric information. The authentication template stored in the biometric authentication template 266 is converted into, for example, a technique (for example, one-way conversion) described in "Japanese Patent Laid-Open No. 2013-123142" or the like, and is not restored to the original biometric information. Is desirable.

As described above, the account information and the authentication template information are associated with each other by the value stored in the concatenated key column 116 and the value stored in the concatenated key column 117. The configuration of the biometric authentication template 363 is the same as the configuration of the biometric authentication template 266 of FIG. 11B. Since the account information table 265, the biometric authentication template 266, and the biometric authentication template 363 have the above-described configurations, it is possible to reliably check duplicate accounts when opening a new account.

FIG. 7 is a sequence diagram showing an example of the personal information registration process described with reference to FIG. In the example of FIG. 7, imaging is selected in step S502, it is determined in step S504 that the certificate image is not a forgery, in step S508 it is determined that the biometric information matches, and in step S510 it is determined that there is no account duplication. ing. As described in FIG. 7, the process of step S506 and the process of extracting the face image in the official certificate image in step S508 may be performed in parallel.

In the personal information registration process described above, if the first biometric information acquired in step S506 and the second biometric information acquired in step S507 are not the same person, an account is opened. It is desirable that the personal information registration process is completed. Specifically, for example, after step S507 and before step S510, the first biometric information acquired in step S506 and the second biometric information acquired in step S507 by the business server 20. It is desirable that the same person check process for checking whether they belong to the same person is executed.

FIG. 12 is an explanatory diagram showing an example of a method of determining whether the first biological information acquired in step S506 and the second biological information acquired in step S507 belong to the same person. .. In the example of FIG. 12, it is assumed that a face image is used as the first biological information and an image of the palm vein is used as the second biological information.

The subject 1200 is the face of a person who wishes to open an account. Subject 1202 is the palm of a person who wishes to open an account. In steps S506 and S507, one of the first biometric information or the second biometric information is simultaneously or continuously obtained by the in-camera of the photographing device 14 of the user terminal 10 and the other by the out-camera of the photographing device 14 of the user terminal 10. Shoot within a certain period of time by switching.

In the same person check process, the time verification program 264 compares the shooting times of images included as meta information in the first biometric information and the second biometric information, and the difference between the shooting times is less than or equal to a predetermined value. In some cases (the predetermined value may be 0), it is determined that the first biometric information and the second biometric information belong to the same person, and if not, it is determined that they do not belong to the same person. .. Further, in the time verification program 264, the difference in shooting time is equal to or less than a predetermined value, and the identifier of the user terminal 10 included as meta information in the first biometric information and the second biometric information image information is the same. In some cases, it may be determined that the first biometric information and the second biometric information belong to the same person, and if not, it may be determined that they do not belong to the same person.

FIG. 13 is an explanatory diagram showing another example of a method of determining whether the first biological information acquired in step S506 and the second biological information acquired in step S507 belong to the same person. be. In step S506 and step S507, the photographing device 14 mounted on the user terminal 10 continuously photographs the subject 1200 to the subject 1202. Specifically, for example, in moving image shooting, the subject 1200 is first shot, then the neck, shoulders, and arms of the person who wishes to open an account are continuously shot, and finally the subject 1202 is shot. As described above, it is desirable that a part of the body of the person who wishes to open an account is always shown in the moving image from the shooting of the subject 1200 to the shooting of the subject 1202.

In the same person check process, the account opening program 261 executes, for example, object tracking using an optical flow or the like for the video, so that the first biometric information and the second biometric information included in the video are recorded. And can be determined whether they belong to the same person. Specifically, for example, the account opening program 261 estimates the mapping of corresponding points between continuous images by using a feature amount such as SHIFT or SURF, which is one of the image features. At this time, it is expected that the estimation mapping result (generally expressed by the affine transformation matrix) of the continuous region of the same object is almost the same during the moving image shooting. When the area is long, the account opening program 261 divides the area into two or more partial areas and repeats the continuity estimation of each adjacent pair to estimate a series of continuous areas such as one arm.

In the personal information registration system of this embodiment, the first biometric information and the second biometric information are of the same person by performing the same person check process by the method described with reference to FIGS. 12 and 13. This can be determined with high accuracy, and by extension, it is possible to prevent the registration of personal information by impersonation.

FIG. 14 is an explanatory diagram showing the relationship between the first biological information and the second biological information acquired in this embodiment. The public certificate 140 is, for example, a public certificate such as a driver's license or an Individual Number Card. Image 141 is, for example, a face image extracted in step S508. Image 142 is the first biological information taken in step S506. The second biological information (subject 1202) and the first biological information (subject 1200) photographed by the user terminal 10 are linked and registered in the business server 20 and the registration / authentication server 30. Further, by the match determination in step S508, the second biometric information to be registered and the public certificate information can be linked and registered in the business server 20.

FIG. 10 is a flowchart showing an example of the authentication process. An example of authentication processing when an account holder who visits a bank counter withdraws cash from the account will be described. In the example of FIG. 10, it is assumed that the business server 20 does not hold the biometric authentication template 266.

In step S1001, the window system 50 transmits a cash withdrawal request to the business server 20. In step S1002, the deposit business execution program 267 transmits an identity verification method selection request to the window system 50. As the identity verification method, for example, there are a biometric authentication method using biometric information, a seal stamp verification method for collating with a registered seal stamp, and the like. In the example of FIG. 10, it is assumed that the biometric authentication method is selected.

In step S1003, the window system 50 notifies the business server 20 that the biometric authentication method has been selected as the identity verification method. In step S1004, the deposit business execution program 267 requests the window system 50 to input the account number and the second biometric information.

In step S1005, the window system 50 transmits the ID information input from the user and the second biometric information to the business server 20. If the second biometric information stored in the biometric authentication template 363 has undergone conversion such as one-way conversion, the window system 50 performs the conversion on the second biometric information. , Send to the business server 20.

In step S1006, the deposit business execution program 267 acquires the concatenated key corresponding to the received account number from the account information table 265, and transmits the acquired concatenated key and the second biometric information to the registration / authentication server 30. do. If the received account number is not included in the account information table 265, the deposit business execution program 267 notifies the window system 50 of an error.

In step S1007, the biometric signature verification program 362 acquires the second biometric information corresponding to the concatenation key from the biometric authentication template 363, and the received second biometric information and the second biometric information acquired from the biometric authentication template 363. The information is compared and the authentication process is executed. In step S1008, the biometric signature verification program 362 notifies the business server 20 of the authentication result, and in step S1009, the deposit business execution program 267 notifies the window system 50 of the authentication result. If the authentication is successful, the deposit business execution program 267 permits the withdrawal of cash, and the cash is paid out at the window system 50.

Hereinafter, a specific example of the forgery determination in step S504 will be described. FIG. 16 is an explanatory diagram showing an example of a Local Binary Pattern (LBP) used for forgery determination, which is a texture feature extraction operator used in various image classification tasks.

The LBP is obtained by binary coding the gradient of brightness with neighboring pixels and creating a histogram, and is generally used as an extraction operator of texture features. In (A), an example of the brightness value of the pixel group 1601 including the attention pixel 1602 and the 3x3 neighboring pixels of the attention pixel 1602 is shown.

In (B), the magnitude comparison result of the brightness value of each of the adjacent pixels and the brightness value of the attention pixel 1602 is indicated by the binarized pixel value. By binarization, for example, the pixel value of the adjacent pixel having a brightness value equal to or higher than the brightness value of the attention pixel 1602 becomes "1", and the pixel value of the adjacent pixel having a brightness value less than the brightness value of the attention pixel 1602 becomes "1". It becomes 0 ". Specifically, since the brightness value "123" of the pixel in the upper left corner is smaller than the brightness value "125" of the pixel of interest 1602, "0" is obtained as a result of binarization. In this way, the eight adjacent pixels binarize all of them.

In (C), the binarized pixel value is converted into one integer value. An integer value is obtained by using the adjacent 8 pixels as a binary code. In the example of (C), 2 ^ 6 + 2 ^ 4 + 2 ^ 2 = 84 is obtained by binary coding with the left adjacent pixel of the pixel of interest as the base point. In this way, by calculating the code value with all the pixels of the official certificate image as the pixel of interest, a histogram of the binary code value having a class of 0 to 255 can be obtained.

FIG. 18 is a flowchart showing an example of the forgery determination process of step S504 using the Local Binary Pattern (LBP). Further, FIG. 17 is an explanatory diagram showing an example of an outline of the forgery determination process described with reference to FIG.

First, in step S1801, the pretending detection program 361 calculates an LBP histogram from the official certificate image taken by the photographing device 14 by, for example, the method shown in FIG. Next, in step S1802, the spoofing detection program 361 performs wavelet transform on the official certificate image to enhance the image in order to emphasize the noise pattern in the image. In step S1803, the spoofing detection program 361 calculates an LBP histogram for the official certificate image after wavelet transform.

In step S1804, the spoofing detection program 361 compresses (reduces) the official certificate image and the wavelet-transformed image at a constant ratio. In step S1805, the spoofing detection program 361 calculates an LBP histogram from each of the compressed public certificate image and the compressed wavelet-transformed image. For example, in consideration of block noise, the compression ratio of the LBP neighborhood image region to a pixel size of 3x3 is used.

In step S1806, the spoofing detection program 361 includes an LBP histogram of the original image obtained in step S1801, an LBP histogram of the wavelet-transformed image obtained in step S1803, and a compressed original image obtained in step S1805. The LBP histogram of the above and the LBP histogram of the compressed wavelet-transformed image are connected as feature quantities, for example, as a vector of one row.

In step S1807, whether or not the spoofing detection program 361 has forged an image of a public certificate using concatenated features by, for example, a method such as a linear SVM (Support Vector Machine). Is determined (step S1807). It is assumed that the feature amount in which the LBP histogram for the forged official certificate is concatenated and the feature amount in which the LBP histogram for the genuine official certificate are concatenated are learned in advance.

Subsequently, another example of the forgery determination process in step S504 will be described. The completion detection program 361 executes the following calculation. When the image is x (m, n) (m is the vertical component of the image, n is the horizontal component of the image, m ∈ [1, M], n ∈ [1, N]), the difference image in the horizontal direction is , Expressed by the following formula.

When the image x (m, n) 1-dimensional Fourier transform of the (horizontal) and X (m, l), power spectrum _p m for each m (n) is expressed by the following equation.

However, D _h (m, l) is _{a one-dimensional Fourier transform of d h} (m, l), and l ∈ [1, N]. Spoofing detection program 361, m = 1, ···, for _M, calculates the average power spectrum _P h of _{p m (l) (l)} .

FIG. 15 is an example of a power spectrum. The upper graph _{represents Ph} (l) and the lower graph shows the difference from the moving average. In order to use the peak as the feature quantity, spoofing detection program 361 _calculates the difference value from the moving average of _{P h (l) (MA (} P h (l))). Further, the completion detection program 361 does not use the difference value as a feature amount as it is, but uses the number of peaks exceeding a plurality of predetermined threshold values as the feature amount.

Note that δ is a delta function, a is the number of features, and v (i) is the i-th threshold value. The forgery detection program 361 is characterized in that the average power spectrum _Pv (l) for the vertical component is calculated in the same manner as the horizontal component, the feature vector VecV is defined, and VecH and VecV are concatenated. As a quantity vector, forgery determination is executed by a method such as SUV. It is assumed that the feature vector for the forged official certificate and the feature vector for the genuine official certificate have been learned in advance.

Subsequently, another example of the forgery determination process in step S504 will be described. Assuming that the image is x (m, n) (m ∈ [1, M], n ∈ [1, N]), the one-dimensional horizontal difference signal is expressed by the following equation.

_{The prescription detection program 361 calculates the average B h of the image luminance difference d h} (m, n) for the block boundary portion using the following mathematical formula in order to express the block noise.

Then, spoofing detection program 361, an average A _h of the signal strength of the blocks inside the image is calculated using the following formula.

Finally, the spoofing detection program 361 calculates the zero-crossing (ZC) rate of the difference signal. The ZC rate indicates the number of times the value of the difference image d (m, n) changes (n ∈ [1, N-1]) from positive to negative or negative to positive (that is, across 0). First, zero-crossing (ZC) is defined by the following mathematical formula.

Subsequently, the completion detection program 361 calculates the ZC rate using the following mathematical formula.

Through the above processing, the completion detection program 361 _{calculated three indexes {B h} , A _h , Z _h } for the horizontal component. _{The completion detection program 361 calculates three indexes {B v} , _Av , Z _v } for the vertical component in the same manner as for the horizontal component. The forgery detection program 361 executes a forgery determination by a method such as SUV using a feature amount vector in which these features are combined. It is assumed that the feature vector for the forged official certificate and the feature vector for the genuine official certificate have been learned in advance.

The personal information registration system of this embodiment can determine with high accuracy whether the official certificate is genuine or not by these forgery determination processes described above, and thus prevent personal information registration by pretending to be done. be able to. Since these forgery determination processes described above can be performed on an image captured by a general-purpose camera or the like, not only the first biometric information acquired in step S507 but also the first biometric information acquired in step S507 and the first biometric information acquired in step S508 are acquired. It may also be executed for the second biometric information.

The personal information registration system of this embodiment determines whether or not personal information can be registered based on the comparison result between the first biometric information extracted from the official certificate and the first biometric information directly acquired. Furthermore, by verifying whether the first biometric information and the second biometric information belong to the same person, the registration of the second biometric authentication can be safely performed, that is, the identity, even from a remote location. It can be carried out with high accuracy.

Differences from the first embodiment will be described. FIG. 6 is a flowchart showing another example of the personal information registration process. Hereinafter, the differences from FIG. 5 will be described. In step S601 following step S507, the account opening application 161 acquires the current position of the user terminal 10 from the GPS device 17 of the user terminal 10 and transmits it to the business server 20. After that, the process proceeds to step S508.

When it is determined in step S508 that the two biometric information match (step S508: Yes), in step S602, the address verification program 263 determines the address of the official certificate and the current address of the user terminal 10 received in step S601. Whether the position matches (specifically, for example, whether the distance between the address of the official certificate and the current position of the user terminal 10 is within a predetermined value (the predetermined value may be 0)). judge. In the determination in step S602, for example, a geocoding technique for converting address information into location information may be used.

When image shooting is selected in step S502, the address verification program 263 uses, for example, character recognition or the like, or extracts a predetermined area of the public certificate image to obtain a public certificate. The address described in may be extracted.

When the address verification program 263 determines that the address of the public certificate and the current position of the user terminal 10 do not match (S602: No), the determination result indicating that the account cannot be opened is determined via the business server 20. Alternatively, it is directly transmitted to the user terminal 10 to end the personal information registration process. When the address verification program 263 determines that the address of the public certificate and the current position of the user terminal 10 match (S602: No), the process proceeds to step S509.

FIG. 8 is a sequence diagram showing an example of the personal information registration process described with reference to FIG. In the example of FIG. 8, imaging is selected in step S502, the certificate image is determined not to be a forgery in step S504, biometric information is determined to match in step S508, and no account duplication is determined in step S510. , In step S602, it is determined that the address of the official certificate and the position information by GPS match.

The personal information registration system of this embodiment further uses the comparison result of the address extracted from the public certificate and the current position of the user terminal 10 to determine whether or not the personal information can be registered. Registration can be suppressed.

Differences from the first embodiment will be described. In the personal information registration system of this embodiment, the subject of some steps in the personal information registration process is different from that of the first embodiment. FIG. 9 is a sequence diagram showing another example of the personal information registration process. In the example of FIG. 9, imaging is selected in step S502, the certificate image is determined not to be counterfeit in step S504, biometric information is determined to match in step S508, and no account duplication is determined in step S510. ing.

Differences from the sequence diagram of FIG. 7 will be described. In the example of FIG. 7, the process of step S504, the process of step S508, and the process of associating the first biometric information and the second biometric information in step S509, which were performed by the business server 20, are performed by the user terminal in the example of FIG. 10 is running.

In the personal information registration system of this embodiment, the number of times of exchanging biometric information, personal information, etc. with external devices such as the business server 20 and the registration / authentication server 30 is reduced by executing the above-mentioned processing by the user terminal 10. The risk of information leakage can be reduced.

The present invention is not limited to the above-described examples, and includes various modifications. For example, the above-described embodiment has been described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the described configurations. It is also possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. Further, it is possible to add / delete / replace a part of the configuration of each embodiment with another configuration.

Further, each of the above configurations, functions, processing units, processing means and the like may be realized by hardware by designing a part or all of them by, for example, an integrated circuit. Further, each of the above configurations, functions, and the like may be realized by software by the processor interpreting and executing a program that realizes each function. Information such as programs, tables, and files that realize each function can be stored in a memory, a hard disk, a recording device such as an SSD (Solid State Drive), or a recording medium such as an IC card, an SD card, or a DVD.

In addition, the control lines and information lines indicate those that are considered necessary for explanation, and do not necessarily indicate all the control lines and information lines in the product. In practice, it can be considered that almost all configurations are interconnected.

10 user terminal, 13 CPU, 15 memory, 16 auxiliary storage device, 20 business server, 23 CPU, 25 memory, 26 auxiliary storage device, 30 registration / authentication server, 33 CPU, 35 memory, 36 auxiliary storage device, 161 account opening Application, 261 account opening program, 262 face verification program, 263 address verification program, 264 time verification program, 265 account information table, 266 biometrics template, 361 spoofing detection program, 362 biometric signature verification program, 363 biometrics template

Claims (12)

It is a personal information registration system that registers the first biometric information of the person to be registered.
It has a processor and a storage device,
The storage device holds a biometric authentication template for storing biometric information.
The processor
Accepting a designation of the different from the first biological information and the second biometric information of the registration target user is image information, acquisition method information documents that contain,
When the reading of the IC chip is specified as the method of acquiring the information of the document, the second biometric information is acquired from the IC chip included in the document.
When image capture is specified as the method for acquiring the information of the document, the second biometric information is acquired from the image of the document captured by the imaging device, and the LBP (Local Horizontal Pattern) of each pixel of the image of the document is obtained. , The forgery determination process of the document is executed based on at least one of the average power spectrum of each of the horizontal component and the vertical component of the image of the document and the zero-crossing rate of the difference signal.
When the reading of the IC chip is specified as the method of acquiring the information of the document, or when it is determined in the forgery determination process that the document is not forged, the first biometric information and the photographing apparatus have taken a picture. Obtain the second biometric information and
Determining a second biometric information which is the shooting based on the similarity between the second biometric information acquired from the document and the second biological information which is the shooting is the second biometric information of the person to be registered, and If the difference between the photographing time of the second biological information which is the imaging and generation time of the first biometric information the acquired is determined to be within a predetermined value, the first biometric information the acquired the biometric template Personal information registration system to store. The personal information registration system according to claim 1.
The acquired first biological information is image information photographed by the photographing apparatus.
The acquired first biological information and the photographed second biological information are included in one moving image photographed by the photographing apparatus.
The processor
The difference between the photographing time of the second biometric information captured is determined to be the second biometric information of the person to be registered, the acquired shooting time and the captured second biometric information of the first biological information Is within a predetermined value, and when it is determined that the acquired first biometric information and the photographed second biometric information are the same person by object tracking in the moving image, the acquired first biometric information is determined. A personal information registration system that stores biometric information in the biometric authentication template. The personal information registration system according to claim 1.
The information of the acquired document is the image information taken by the photographing device, and is
The processor
In the counterfeit determination process, each of the LBP (Local Binary Pattern) of each pixel of the image of the document, the LBP of each pixel of the image of the document compressed at a predetermined ratio, and the image obtained by wavelet-converting the image of the document. Obtained by taking a document in which the image information of the document is genuine based on at least one of the LBP of the pixels and the LBP of each pixel of the image obtained by compressing the wavelet-converted image at a predetermined ratio. image and Ru determine Teisu whether the document has not been forged by whether information, personal information registration system. The personal information registration system according to claim 1 .
The processor
In the counterfeit determination process, for each of the horizontal component and the vertical component of the image of the document, a difference value obtained by subtracting the average power spectrum from the moving average of the average power spectrum is calculated, and a comparison result between the difference value and a predetermined threshold value is calculated. based on, Ru determine Teisu whether the document has not been forged by whether the image information obtained by the image information is authentic documents taken of the documents, personal information registration system. The personal information registration system according to claim 1 .
The processor
In the forgery determination process, the average of the image luminance difference for the block boundary portion, the average of the signal strength of the image inside the block, and the zero-crossing rate of the difference signal for each of the horizontal component and the vertical component of the image of the document. If, on the basis of, Ru determine Teisu is whether or not forged the documents, personal information registration system. The personal information registration system according to claim 1.
Including terminals operated by the registered person
The information of the acquired documents includes the address information of the person to be registered.
The processor
Acquire the location information of the terminal and
It is determined that the photographed second biometric information is the second biometric information of the person to be registered, and the distance between the address indicated by the address information and the position indicated by the acquired location information is equal to or less than a predetermined value. A personal information registration system that stores the acquired first biometric information in the biometric authentication template when it is determined to be present. The personal information registration system is a method of registering the first biometric information of the person to be registered.
The personal information registration system
Accepting a designation of the different from the first biological information and the second biometric information of the registration target user is image information, acquisition method information documents that contain,
When the reading of the IC chip is specified as the method of acquiring the information of the document, the second biometric information is acquired from the IC chip included in the document.
When image capture is specified as the method for acquiring the information of the document, the second biometric information is acquired from the image of the document captured by the imaging device, and the LBP (Local Horizontal Pattern) of each pixel of the image of the document is obtained. , The forgery determination process of the document is executed based on at least one of the average power spectrum of each of the horizontal component and the vertical component of the image of the document and the zero-crossing rate of the difference signal.
When the reading of the IC chip is specified as the method of acquiring the information of the document, or when it is determined in the forgery determination process that the document is not forged, the first biometric information and the photographing apparatus have taken a picture. Obtain the second biometric information and
Determining a second biometric information which is the shooting based on the similarity between the second biometric information acquired from the document and the second biological information which is the shooting is the second biometric information of the person to be registered, and If the difference between the photographing time of the second biological information which is the imaging and generation time of the first biometric information the acquired is determined to be within a predetermined value, said first biometric information the acquired personal information registration system A method of storing in a biometric template that has. The method according to claim 7.
The acquired first biological information is image information photographed by the photographing apparatus.
The acquired first biological information and the photographed second biological information are included in one moving image photographed by the photographing apparatus.
The method is
The personal information registration system
The second biological information captured is determined to be the second biometric information of the person to be registered, the difference between the photographing time of the second biological information which is the imaging and generation time of the first biometric information the acquired When it is determined that the value is within a predetermined value, and it is determined that the acquired first biometric information and the photographed second biometric information are the same person by object tracking in the moving image, the acquired first biometric information is obtained. A method of storing information in the biometric template. The method according to claim 7.
The information of the acquired document is the image information taken by the photographing device, and is
The method is
The personal information registration system
In the counterfeit determination process, each of the LBP (Local Binary Pattern) of each pixel of the image of the document, the LBP of each pixel of the image obtained by compressing the document at a predetermined ratio, and the image obtained by wavelet-converting the image of the document. Obtained by taking a document in which the image information of the document is genuine based on at least one of the LBP of the pixels and the LBP of each pixel of the image obtained by compressing the wavelet-converted image at a predetermined ratio. said document by whether the image information is Ru determine Teisu or not forged, methods. The method according to claim 7 .
The method is
The personal information registration system
In the forgery determination process, for each of the horizontal component and the vertical component of the image of the document, a difference value obtained by subtracting the average power spectrum from the moving average of the average power spectrum is calculated, and the comparison result between the difference value and a predetermined threshold value is calculated. based on the image information of the document is Ru determine Teisu whether the document has not been forged by whether the image information obtained by the authentic document was taken, method. The method according to claim 7 .
The method is
The personal information registration system
In the forgery determination process, the average of the image luminance difference for the block boundary portion for each of the horizontal component and the vertical component of the image of the document, the average of the signal intensity of the image inside the block, and the zero-crossing rate of the difference signal. If, based on, whether the document has not been forged Ru determine Teisu method. The method according to claim 7.
The personal information registration system includes a terminal operated by the registration target person, and includes a terminal.
The information of the acquired documents includes the address information of the person to be registered.
The method is
The personal information registration system
Acquire the location information of the terminal and
The second biological information captured is determined to be the second biometric information of the person to be registered, the difference between the photographing time of the second biological information which is the imaging and generation time of the first biometric information the acquired When it is determined that the distance is within the predetermined value and the distance between the address indicated by the address information and the position indicated by the acquired position information is equal to or less than the predetermined value, the acquired first biometric information is referred to as described above. How to store in a biometric template.

Images