Facial recognition terminal, facial recognition system, and facial recognition method

Abstract

To provide a face authentication terminal, a face authentication system, and a face authentication method that can reduce the possibility that the reliability of face authentication will decrease.SOLUTION: A face authentication system includes a face authentication terminal including a thermal sensor and a camera, and an authentication server. The face authentication terminal generates a first biometric private key from a face image of a person captured at a first timing when the person is detected by at least one of the camera and the thermal sensor. The face authentication terminal generates a second biometric private key from a face image of the person captured at a second timing different from the first timing, generates a biometric public key based on the second biometric private key, transmits the biometric public key to the authentication server, and requests registration of the biometric public key. The authentication server verifies whether the authentication is to be successful using the first biometric private key, and the biometric public key transmitted to the authentication server, and completes registration of the biometric public key if the authentication is verified to be successful.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a face recognition terminal, a face recognition system, and a face recognition method. [Background technology]

[0002] Authentication technology using biometric information is utilized in various fields. For example, Patent Document 1 discloses a biometric authentication system that encrypts biometric information and performs authentication using the encrypted biometric information as an authentication technology using biometric information. Patent Document 2 discloses an authentication system that performs authentication using a possession. In this authentication system, when an encryption key for authentication request is input to a possession, the encryption key and the public key are combined, and encrypted information is calculated from biometric information and variation information, and is sent to a verification unit as presented information. In the verification unit, the encrypted information is decoded using the encryption key and the public key for authentication, and the information is collated. In the verification unit, it is determined whether the decoded biometric information matches the registered biometric information, and authentication is completed. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-158681 A [Patent Document 2] JP 2002-149611 A Summary of the Invention [Problem to be solved by the invention]

[0004] The inventors of the present application are considering a face recognition system (face recognition terminal) that uses the well-known PBI (Public Biometrics Infrastructure). Since PBI is well-known, to briefly explain, it is a personal authentication infrastructure that uses biometric information embedded with a private key to perform one-way conversion to generate a PBI template (also called a "public template") that is difficult to restore to the original biometric information, and uses the PBI template to realize authentication, signing, and encryption.

[0005] In this face authentication system, a camera of a face authentication terminal captures an image of a user's face (face information), data indicating facial features extracted (generated) based on the face image (hereinafter referred to as "facial feature information") is acquired, and authentication is performed using the facial feature information like a private key. Note that in this specification, the facial feature information is used like a private key, and therefore is also referred to as a "biometric private key" for convenience.

[0006] In this face recognition system, at the time of registration, the face recognition terminal generates (extracts) facial feature information (biometric private key) based on a facial image captured by a camera of the user to be registered, creates a private key and a public key using existing encryption technology, embeds the private key in the facial feature information (biometric private key) and performs one-way conversion to generate information (PBI template) and the public key, which are then registered in the authentication server. For convenience, the PBI template and public key may also be referred to as the "biometric public key" or "PBI public key." After registration, the biometric private key and biometric public key are discarded from the face recognition terminal.

[0007] In this face authentication system, during authentication, the face authentication terminal captures a face image of the user to be authenticated using a camera, generates a biometric private key based on the face image, and the authentication server performs authentication using the biometric private key and the registered biometric public key. After authentication, the biometric private key (facial feature information) is discarded from the face authentication terminal. Note that the face authentication terminal may also perform authentication.

[0008] In this face authentication system (face authentication terminal), authentication is performed using a biometric public key generated based on a face image captured at the timing of registration and a biometric private key generated based on a face image captured at the timing of authentication. If the face image captured at the timing of registration and the face image captured at the timing of authentication match perfectly, authentication will be successful without any problems. However, the face image captured at the timing of registration and the face image captured at the timing of authentication do not match perfectly because there are fluctuations in position, posture, external light, facial expression, etc. that change due to the difference in the timing of imaging. Even if such fluctuations exist, if authentication is not successful using the biometric private key and the biometric public key, the reliability of authentication will be reduced.

[0009] The present invention has been made to solve the above problems. That is, an object of the present invention is to provide a face recognition terminal, a face recognition system, and a face recognition method that can reduce the possibility that the reliability of face recognition will decrease. [Means for solving the problem]

[0010] In order to solve the above problems, the face recognition terminal of the present invention is a face recognition terminal having a sensor including a camera, and the face recognition terminal is configured to generate a first biometric private key from a first face image, which is one of two face images acquired by capturing an image of the person's face with the camera at a first timing when a person is detected by the sensor and at a second timing different from the first timing, generate a second biometric private key from a second face image, which is the other of the two face images, and verify whether the authentication is successful by performing authentication using the first biometric private key and the biometric public key before registering the biometric public key in an internal or external key database, and complete the registration of the biometric public key in the key database if it is verified that the authentication is successful.

[0011] The face authentication system of the present invention includes a face authentication terminal having a sensor including a camera, and an authentication device, and is configured to be capable of transmitting and receiving information between the face authentication terminal and the authentication device, wherein the face authentication terminal is configured to generate a first biometric private key from a first face image, which is one of two face images acquired by capturing an image of the person's face with the camera at a first timing when the person is detected by the sensor and at a second timing different from the first timing, generate a second biometric private key from a second face image, which is the other of the two face images, generate a biometric public key based on the second biometric private key, and transmit the biometric public key to the authentication device to request the authentication device to register the biometric public key; The authentication device is configured to verify whether the authentication is successful by performing authentication using the first biometric private key and the biometric public key received from the face recognition terminal, and to complete registration of the biometric public key if it is verified that the authentication is successful.

[0012] The face recognition method of the present invention is a face recognition method using a face recognition terminal having a sensor including a camera, wherein the face recognition terminal generates a first biometric private key from a first face image which is one of two face images acquired by capturing an image of the person's face with the camera at a first timing when a person is detected by the sensor and at a second timing different from the first timing, generates a second biometric private key from a second face image which is the other of the two face images, generates a biometric public key based on the second biometric private key, and before registering the biometric public key in an internal or external key database, verifies whether authentication is successful using the first biometric private key and the biometric public key, and if it is verified that authentication is successful, completes the registration of the biometric public key in the key database. Effect of the Invention

[0013] According to the present invention, it is possible to reduce the possibility that the reliability of face authentication will decrease. [Brief description of the drawings]

[0014] [Figure 1] FIG. 1 is a system configuration diagram of an example of a face recognition system including a face recognition terminal according to a first embodiment of the present invention. [Diagram 2] FIG. 2 is a front view for explaining a configuration example of a face authentication terminal. [Figure 3A] FIG. 3A is a diagram for explaining an outline of the operation of the face authentication system. [Figure 3B] FIG. 3B is a diagram for explaining an outline of the operation of the face authentication system. [Figure 3C] FIG. 3C is a diagram for explaining an outline of the operation of the face authentication system. [Figure 3D] FIG. 3D is a diagram for explaining an outline of the operation of the face authentication system. [Figure 4] FIG. 4 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal according to the first embodiment. [Diagram 5] FIG. 5 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal according to the first embodiment. [Figure 6] FIG. 6 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal according to the first embodiment. [Figure 7] FIG. 7 is a diagram for explaining an example of the configuration of a face recognition terminal according to the second embodiment of the present invention. [Figure 8] FIG. 8 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal according to the second embodiment. [Figure 9] FIG. 9 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal according to the second embodiment. [Figure 10] FIG. 10 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal according to the third embodiment. [Figure 11] FIG. 11 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal according to the third embodiment. [Figure 12]FIG. 12 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal according to the fifth embodiment. [Figure 13A] FIG. 13A is a diagram for explaining a modified example of the face authentication system. [Figure 13B] FIG. 13B is a diagram for explaining a modified example of the face authentication system. [Figure 13C] FIG. 13C is a diagram for explaining a modified example of the face authentication system. [Figure 13D] FIG. 13D is a diagram for explaining a modified example of the face authentication system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, each embodiment of the present invention will be described with reference to the drawings. In addition, in all the drawings of the embodiments, the same or corresponding parts may be denoted by the same reference numerals. <<First embodiment>> <Configuration> Fig. 1 is a schematic diagram showing a configuration example of a face authentication system according to a first embodiment of the present invention. As shown in Fig. 1, the face authentication system includes a face authentication terminal 100 and an authentication server 200. The face authentication terminal 100 and the authentication server 200 are connected to each other via a network so that they can communicate with each other. For convenience, the authentication server 200 may also be referred to as an "authentication device."

[0016] 1, the face authentication terminal 100 includes a thermal sensor 110, a camera 120, a display 130, a CPU board 140, a memory 150, and a wireless LAN 160. These are connected to each other via a bus (not shown) so as to be able to transmit and receive information to and from each other.

[0017] Thermal sensor 110 is a sensor for measuring temperature, for example an infrared temperature sensor that detects the temperature of an object (person (user)) based on the amount of infrared energy emitted by the object to be measured.

[0018] The camera 120 captures an image of the face of a user present within an imaging range in front of the face authentication terminal 100, and acquires an image of the user's face.

[0019] The display 130 is a display device capable of displaying an image. In this example, the display 130 is a touch panel display that functions as both a display device and an input device.

[0020] The CPU board 140 is a board on which a CPU, a ROM, etc. are mounted. The CPU loads a program stored in the ROM into the memory 150. The CPU executes the program loaded into the memory 150 to realize various functions.

[0021] The memory 150 is, for example, a storage medium from which data can be read and written (for example, a volatile RAM from which data can be read and written). As described above, various programs executed by the CPU are loaded into the memory 150, and data used when the CPU executes the various programs is temporarily stored.

[0022] The wireless LAN 160 is a wireless LAN interface for connecting the face recognition terminal 100 to a network.

[0023] Fig. 2 is a front view for explaining a configuration example of the face authentication terminal 100. As shown in Fig. 2, the above-mentioned thermal sensor 110, the lens of the camera 120, and the display screen of the display 130 are arranged on the front side of the face authentication terminal 100.

[0024] The thermal sensor 110 is disposed at the upper end of the front surface of the face authentication terminal 100. The thermal sensor 110 receives infrared rays emitted by a measurement target object (e.g., a user) that exists in front of the face authentication terminal 100, and detects the temperature of the object (person).

[0025] The camera 120 is provided in the face authentication terminal 100 such that the lens of the camera 120 is disposed to the left of the thermal sensor 110 at the top end of the front side of the face authentication terminal 100. The camera 120 captures an image of a person's face present within the imaging range of the camera 120 in front of the face authentication terminal 100, thereby acquiring a captured image of the person's face (face image).

[0026] The display 130 is capable of displaying an image by dividing the screen into an area R1 and an area R2.

[0027] The authentication server 200 is composed of a computer (server, information processing device) including a CPU, ROM, RAM, an interface I / F, and a non-volatile storage device (HDD) that can read and write data. The CPU realizes various functions by executing programs stored in the ROM. The authentication server 200 may be composed of multiple information processing devices, and may be a virtual information processing device rather than a physical information processing device.

[0028] The authentication server 200 stores (memorizes, retains) in a storage device (HDD) a key database in which public keys and PBI templates (also referred to as "biometric public keys" or "PBI public keys") are associated with user information (e.g., a user ID and password for identifying a user).

[0029] <Summary> An outline of the operation of the face authentication system will be described. As shown in FIG. 3A, the face authentication terminal 100 captures the face of the user Us1 by the camera 120 at the first timing when a person is detected by at least one of the camera 120 and the thermal sensor 110, thereby acquiring a face image 1 which is a captured image of the face of the user Us1 at the first timing. In this example, this first timing is the timing when a person is detected by the camera 120 and the thermal sensor 110. In this case, the face authentication terminal 100 detects the face area of ​​the user Us1 from the captured image of the camera 120 (detects the face), for example, and confirms that the captured subject whose face area is detected is a human by the heat detected by the thermal sensor 110, and then detects the human.

[0030] In addition, the face authentication terminal 100 may determine, for example, the timing when the facial area of ​​user Us1 is detected from an image captured by the camera 120 as the first timing, or the timing when the thermal sensor 110 detects the heat of user Us1 (i.e., detects a person) as the first timing.

[0031] The face recognition terminal 100 generates (extracts) a biometric private key 1 (facial feature information 1) from a face image 1 using a known algorithm. The techniques disclosed in JP 2013-123142 A and Japanese Patent No. 6216567 A can be applied to the method of generating this biometric private key 1. The face recognition terminal 100 stores the biometric private key 1.

[0032] Then, as shown in FIG. 3B, the face authentication terminal 100 captures an image of the face of the user Us1 using the camera 120 at a second timing that is after the first timing, thereby acquiring face image 2, which is an image of the face of the user Us1 at the second timing.

[0033] The face recognition terminal 100 extracts (generates) a biometric private key 2 (facial feature information 2) from a face image 2, generates a private key and a public key using existing encryption technology, and generates a PBI template (sometimes also referred to as a "public template") based on the biometric private key 2 and the private key. Technologies disclosed in JP 2013-123142 A and JP 2019-161405 A and the like can be applied to create the PBI template.

[0034] 3C, the face authentication terminal 100 transmits the biometric public key (PBI template and public key) to the authentication server 200, requests the authentication server 200 to register the biometric public key, and discards the biometric public key from the face authentication terminal 100. Note that "discarding the biometric public key (information)" includes not leaving the information in the face authentication terminal 100 by erasing or overwriting the information, and not providing the information to other devices, etc.

[0035] Next, as shown in Fig. 3D, the authentication server 200 performs authentication using the biometric private key 1 stored in the face authentication terminal 100 and the biometric public key being requested to be registered to the authentication server 200. This authentication is performed, for example, by challenge-response authentication. That is, the authentication server 200 transmits a PBI template and a challenge code to the face authentication terminal 100. The face authentication terminal 100 restores (generates) a private key from the biometric private key 1 and the PBI template, signs (encrypts) the challenge code with the private key, and transmits it to the authentication server 200.

[0036] The authentication server 200 decrypts the encrypted challenge code with the public key included in the biometric public key, and compares whether the decrypted challenge code matches the challenge code previously sent. If they match, the authentication server 200 determines that the authentication is successful, and if they do not match, the authentication is unsuccessful.

[0037] If the authentication is successful, the face authentication terminal 100 discards the biometric private key 1, and the authentication server 200 completes the registration of the biometric public key. If the authentication is not successful, the face authentication terminal 100 discards the biometric private key 1, and the authentication server 200 does not register the biometric public key.

[0038] After the registration of the biometric public key is completed, when authenticating user Us1 in the face authentication system, the face authentication terminal 100 generates a biometric private key from a face image of the user Us1 for each authentication, and performs authentication using the generated biometric private key and the biometric public key registered in the authentication server 200. The biometric private key generated for each authentication is discarded from the face authentication terminal 100 when the authentication is completed.

[0039] In this face authentication system, authentication is successful using a biometric public key generated from a user's face image 2 captured at a second timing different from the first timing, and a biometric private key 1 generated from a user's face image 1 captured at the first timing, and after it is confirmed that the reliability of authentication using the biometric public key being requested for registration is high, registration of the biometric public key being requested for registration is completed. This allows the face authentication system to improve the reliability of subsequent face authentication of user Us1.

[0040] The above is an overview of how the facial recognition system works.

[0041] <Specific operation> The specific operation of the face authentication system will be described below. Fig. 4 is a flowchart showing the process flow executed by the CPU of the face authentication terminal 100. The CPU of the face authentication terminal 100 starts the process from step 400 and proceeds to step 405, where it displays the standby screen GM1 on the display 130. The standby screen GM1 includes a frame for aligning the image capture position of the face in area R1, and includes an arbitrary image (for example, an image of content such as an advertisement (including a video)) in area R2.

[0042] The CPU then proceeds to step 410 and determines whether the thermal sensor 110 has detected the user's heat (e.g., heat within a predetermined temperature range appropriate for determining that the user is human) and whether the camera 120 has detected (recognized) the user's face.

[0043] If both the user's heat and the user's face have not been detected, the CPU determines “NO” in step 410 and returns to step 405 .

[0044] On the other hand, if both the user's heat and the user's face are detected, the CPU judges “YES” in step 410 and executes the processes of steps 415 to 430 described below in order, and then proceeds to step 435.

[0045] Step 415: The CPU displays the detection screen GM2 on the display 130. The detection screen GM2 includes a frame for aligning the image capturing position of the face and a face image of the user reflected within the frame in the region R1, and includes an arbitrary image (for example, an image of content such as an advertisement (including a video)) in the region R2.

[0046] Step 420: The CPU uses the camera 120 to capture an image of the user's face, thereby acquiring a facial image of the user.

[0047] Step 425: The CPU converts the face image into PBI, stores (A) in memory 150, and discards the face image. That is, the CPU generates (extracts) a biometric private key (facial feature information) from the face image, stores the biometric private key in memory 150, and discards the face image. For ease of explanation, the biometric private key created in the processing of step 425 is referred to as (A).

[0048] Step 430: The CPU displays a registration authentication selection screen GM3 on the display 130. The registration authentication selection screen GM3 includes information indicating a heat detection result (e.g., temperature) in an area R1, and includes an ID input field and a new registration button, which is a button configured with an image, in an area R2.

[0049] When the CPU proceeds to step 435, it determines whether or not a new registration instruction has been issued to the face authentication terminal 100 by the user touching the new registration button.

[0050] If a new registration instruction has been given, the CPU determines "YES" in step 435 and proceeds to step 440 to execute the registration process shown in FIG. 5 described below, and then proceeds to step 495 to temporarily end this processing flow.

[0051] If there is no instruction for new registration, the CPU determines "NO" in step 435 and proceeds to step 445 to determine whether an ID (user ID) has been entered in the ID entry field.

[0052] If an ID is entered in the ID input field, the CPU judges "YES" in step 445 and proceeds to step 450 to execute the authentication process shown in FIG. 6 described below, and then proceeds to step 495 to temporarily end this processing flow.

[0053] If no ID has been entered in the ID entry field, the CPU determines “NO” in step 445 and returns to step 435 .

[0054] Fig. 5 is a flowchart showing the processing flow of the above-mentioned registration process executed by the CPU of the face authentication terminal 100. When the CPU proceeds to step 440 in Fig. 4, it starts the processing from step 500 in Fig. 5, proceeds to step 505, and displays the input authentication screen GM4 on the display 130. The input authentication screen GM4 includes a frame for aligning the QR code (registered trademark) in area R1, and includes an ID input field and a PW input field in area R2.

[0055] Thereafter, the CPU proceeds to step 510 and determines whether or not either "input of ID and password" or "detection of QR code" has been performed.

[0056] If neither “input of ID and password” nor “detection of QR code” has been performed, the CPU determines “NO” in step 510 and returns to step 505 .

[0057] If either “input of ID and password” or “detection of QR code” is performed, the CPU judges “YES” in step 510 and proceeds to step 515 to determine whether the user information (user ID and password) is registered in the key database of authentication server 200.

[0058] If the user information is registered in the key database of the authentication server 200, the CPU judges "YES" in step 515 and executes the processes of steps 520 to 535 described below in order, and then proceeds to step 540.

[0059] Step 520: The CPU displays a face photographing instruction screen GM5 on the display 130. The face photographing instruction screen GM5 includes an alignment frame and a face image of the user reflected within the alignment frame in an area R1, and includes instructions for the user to appropriately photograph the face (capture the face image) in an area R2.

[0060] Step 525: The CPU captures an image of the user's face using the camera 120, thereby acquiring a facial image of the user.

[0061] Step 530: The CPU converts the face image into a PBI and requests the authentication server 200 to register it. That is, the CPU extracts (generates) a biometric private key (facial feature information) from the face image acquired in step 525, generates a private key and a public key using existing encryption technology, and generates a PBI template from the biometric private key (facial feature information) and the private key. The CPU transmits the generated PBI template and public key (i.e., the biometric public key) to the authentication server 200 and requests registration of the biometric public key. After that, the CPU discards the biometric public key. For ease of explanation, the biometric public key created in this process is referred to as (B).

[0062] Step 535: The CPU requests the authentication server 200 to compare the biometric private key ((A)) stored in the memory 150 in step 425 with the biometric public key ((B)) transmitted to the authentication server 200. When the comparison is requested, the authentication server 200 performs authentication using the biometric private key ((A)) and the biometric public key ((B)), and transmits the authentication result (either success or failure) to the face authentication terminal 100. If the comparison result is OK (the authentication result is successful), the authentication server 200 registers (stores) the biometric public key ((B)) in the key database in association with the user ID and password. This completes the registration of the biometric public key ((B)).

[0063] When the CPU proceeds to step 540, it determines whether the received comparison result is OK or not.

[0064] If the matching result is OK, the CPU determines "YES" in step 540 and proceeds to step 545, where it displays a registration completion screen GM6 on the display 130. The registration completion screen GM6 includes "OK" in area R1, and includes a message indicating that registration has been completed in area R2. The CPU discards the biometric private key ((A)) by deleting the biometric private key ((A)) from the memory 150. Thereafter, the CPU proceeds to step 595, where it temporarily ends this processing flow.

[0065] If the comparison result is NG, the CPU determines "NO" in step 540 and proceeds to step 550, where it displays the registration retry screen GM7 on the display 130. The registration retry screen GM7 includes "NG" in area R1, and includes a message in area R2 indicating that registration has failed and requesting retry from the beginning of registration. The CPU discards the biometric private key ((A)) by deleting it from the memory 150. When retrying registration, the user starts over from heat detection and face detection (processing is performed from step 405). After that, the CPU proceeds to step 595 and ends this processing flow for the time being.

[0066] If the user information is not registered in the key database in step 515, the CPU determines "NO" in step 515 and proceeds to step 555 to display a registration confirmation request screen GM8 on the display 130. The registration confirmation request screen GM8 includes a message in area R2 requesting the user to confirm the registration. After that, the CPU proceeds to step 595 to temporarily end this processing flow.

[0067] Fig. 6 is a flowchart showing the process flow of the above-mentioned authentication process executed by the CPU of the face authentication terminal 100. When the CPU proceeds to step 450 in Fig. 4, it starts the process from step 600 in Fig. 6 and proceeds to step 605, where it checks whether the user information is registered in the key database of the authentication server 200 and whether a biometric public key corresponding to the user information (hereinafter referred to as a "registered biometric public key") exists in the key database of the authentication server 200.

[0068] If the user information is registered in the key database and the registered biometric public key corresponding to the user information exists in the key database, the CPU judges "YES" in step 605 and proceeds to step 610, where it requests the authentication server 200 to compare the biometric private key ((A)) stored in the memory 150 in step 425 with the registered biometric public key.

[0069] When a matching is requested, the authentication server 200 performs authentication using the biometric private key ((A))) and the registered biometric public key, and transmits the authentication result (either success or failure) to the face authentication terminal 100.

[0070] When the CPU proceeds to step 615, it determines whether or not the authentication is successful based on the authentication result. That is, if the authentication result is successful, the CPU determines that the authentication is successful, and if the authentication result is unsuccessful, the CPU determines that the authentication is unsuccessful.

[0071] If the authentication is successful, the CPU determines "YES" in step 615 and proceeds to step 620, where it displays an authentication success screen GM9 on the display 130. The authentication success screen GM9 includes "OK" in area R1, and includes a message indicating that the authentication is successful in area R2. The CPU discards the biometric private key ((A)) by deleting the biometric private key ((A)) from the memory 150. Thereafter, the CPU proceeds to step 695 and temporarily ends this processing flow.

[0072] If the authentication fails, the CPU determines "NO" in step 615 and proceeds to step 625, where it displays an authentication success screen GM10 on the display 130. The authentication success screen GM10 includes "NG" in area R1, and includes a message indicating that the authentication failed in area R2. The CPU discards the biometric private key ((A)) by deleting the biometric private key ((A)) from the memory 150. After that, the CPU proceeds to step 695 and temporarily ends this processing flow.

[0073] In the processing of step 605 described above, if at least one of the “user information” and the “biometric public key corresponding to the user information” is not registered in the key database, the CPU judges “NO” in step 605 and proceeds to step 625, executes the processing of step 625 described above, and then proceeds to step 695 to temporarily end this processing flow.

[0074] <Effects> As described above, the face recognition terminal 100 according to the first embodiment of the present invention and the face recognition system including the same can reduce the possibility that the reliability of face recognition will decrease.

[0075] <<Second embodiment>> A face authentication terminal 100 according to a second embodiment of the present invention will be described. The face authentication terminal 100 according to the second embodiment is different from the face authentication system of the first embodiment only in that the authentication server 200 is omitted from the face authentication system of the first embodiment, and the functions of the authentication server 200 are provided in the face authentication terminal 100.

[0076] The following description will focus on these differences.

[0077] FIG. 7 is a diagram for explaining a configuration example of a face authentication terminal 100 according to the second embodiment. As shown in FIG. 7, the face authentication terminal 100 includes a storage device 700. The storage device 700 is a non-volatile storage medium capable of reading and writing data. The storage device 700 includes (holds (stores)) a key database 710. This key database 710 is similar to the key database stored in the storage device of the authentication server 200 in the first embodiment. That is, the key database 710 stores a public key and a PBI template (biometric public key) in association with user information (for example, a user ID and password for identifying a user).

[0078] <Specific operation> The specific operation of the face recognition terminal 100 according to the second embodiment will be described below. The CPU of the face recognition terminal 100 executes the process flow shown in the flowchart of Fig. 4, the process flow shown in the flowchart of Fig. 8, and the process flow shown in the flowchart of Fig. 9. Note that the process flow of Fig. 4 has already been described, so a description thereof will be omitted.

[0079] Fig. 8 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal 100. The processing flow in Fig. 8 differs from the processing flow in Fig. 5 only in that steps 530 to 540 are replaced with steps 810 to 840. Therefore, the following description will focus on the different processing, and other descriptions will be omitted.

[0080] When the CPU proceeds to step 810, it converts the face image into a PBI. That is, the CPU extracts (generates) a biometric private key (facial feature information) from the face image acquired in step 525, generates a private key and a public key using existing encryption technology, and generates a PBI template from the biometric private key (facial feature information) and the private key. For ease of explanation, the public key and PBI template (biometric public key) created in this process are referred to as (B).

[0081] After that, the CPU proceeds to step 820 and compares the biometric private key ((A)) and the biometric public key ((B)) stored in the memory 150 in step 425 of Fig. 4. That is, the CPU performs authentication using the biometric private key ((A)) and the biometric public key ((B)), and determines whether authentication is possible.

[0082] The CPU then proceeds to step 830 and determines whether the comparison result is OK (authentication result is successful). If the comparison result is OK, the CPU determines "YES" in step 830 and proceeds to step 840, where it registers (stores) the biometric public key ((B)) in the key database 710 in association with the user ID and password, and discards the biometric private key ((A)). This completes the registration of the biometric public key ((B)). The CPU then proceeds to step 545.

[0083] On the other hand, if the comparison result is NG, the CPU determines "NO" in step 830 and proceeds to step 550. Note that even in this case, the CPU discards the biometric private key ((A)).

[0084] Fig. 9 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal 100. The processing flow in Fig. 9 differs from the processing flow in Fig. 6 only in that steps 605 to 615 in Fig. 6 are replaced with steps 910 to 930. Therefore, the following description will focus on the different processing, and other descriptions will be omitted.

[0085] When the CPU proceeds to step 910, it confirms whether or not the user information is registered in the key database 710 and whether or not a biometric public key corresponding to the user information (registered biometric public key) exists in the key database 710.

[0086] If the user information is registered in the key database 710 and a registered biometric public key corresponding to the user information exists in the key database 710, the CPU judges "YES" in step 910 and proceeds to step 920, where it compares the biometric private key ((A)) stored in the memory 150 in step 425 of FIG. 4 with the registered biometric public key.

[0087] When the CPU proceeds to step 930, it determines whether or not the authentication is successful. If the authentication is successful, the CPU determines "YES" in step 930 and proceeds to step 620. If the authentication is unsuccessful, the CPU determines "NO" in step 930 and proceeds to step 625.

[0088] In addition, in the processing of the above-mentioned step 910, if at least one of the “user information” and the “biometric public key corresponding to the user information” is not registered in the key database 710, the CPU judges “NO” in step 910 and proceeds to step 625.

[0089] <Effects> As described above, the face recognition terminal 100 according to the second embodiment of the present invention can reduce the possibility of a decrease in the reliability of face recognition, similar to the first embodiment.

[0090] <<Third embodiment>> A face authentication system including a face authentication terminal 100 according to a third embodiment of the present invention will be described. This face authentication system differs from the face authentication system of the first embodiment only in the following points. In the first embodiment, the authentication in the registration process and the authentication process is performed by the authentication server 200, but in the third embodiment, it is performed by the face authentication terminal 100.

[0091] The following description will focus on these differences.

[0092] <Specific operation> The specific operation of the face recognition terminal 100 according to the third embodiment will be described below. The CPU of the face recognition terminal 100 executes the process flow shown in the flowchart of Fig. 4, the process flow shown in the flowchart of Fig. 10, and the process flow shown in the flowchart of Fig. 11. Note that the process flow of Fig. 4 has already been described, so its description will be omitted.

[0093] Fig. 10 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal 100. The processing flow in Fig. 10 differs from the processing flow in Fig. 5 only in that steps 530 to 540 are replaced by steps 1010 to 1040. Therefore, the following description will focus on the different processing, and other descriptions will be omitted.

[0094] When the CPU proceeds to step 1010, it converts the facial image into a PBI. That is, the CPU extracts (generates) a biometric private key (facial feature information) from the facial image acquired in step 525, generates a private key and a public key using existing encryption technology, and generates a PBI template from the biometric private key (facial feature information) and the private key. That is, the CPU generates a PBI template and a public key (biometric public key). For ease of explanation, the biometric public key created in this process is referred to as (B).

[0095] After that, the CPU proceeds to step 1020 and compares the biometric private key ((A)) and the biometric public key ((B)) stored in the memory 150 in step 425 of Fig. 4. That is, the CPU performs authentication using the biometric private key ((A)) and the biometric public key ((B)).

[0096] The CPU proceeds to step 1030 and determines whether the collation result is OK (the authentication result is successful).

[0097] If the comparison result is OK, the CPU judges "YES" in step 1030 and proceeds to step 1040, where it transmits the biometric public key ((B)) to the authentication server 200 in association with the user ID and password, and discards the biometric private key (A). The authentication server 200 registers (stores) the biometric public key ((B)) in the key database in association with the user ID and password. This completes the registration of the biometric public key ((B)). The CPU then proceeds to step 545.

[0098] If the comparison result is NG, the CPU determines "NO" in step 1030 and proceeds to step 550. In this case, the CPU discards the biometric private key ((A)) and the biometric public key ((B)).

[0099] Fig. 11 is a flowchart showing a processing flow executed by the CPU of the face recognition terminal 100. The processing flow in Fig. 11 differs from the processing flow in Fig. 6 only in that steps 610 to 615 in Fig. 6 are replaced with steps 1110 to 1130. Therefore, the following description will focus on the different processing, and other descriptions will be omitted.

[0100] When the CPU proceeds to step 1110, it acquires from the authentication server 200 a registered biometric public key corresponding to the user information (the user ID input in step 445 of FIG. 4).

[0101] When the CPU proceeds to step 1120, the CPU compares the biometric private key ((A)) stored in the memory 150 in step 425 of FIG. 4 with the registered biometric public key.

[0102] When the CPU proceeds to step 1130, it determines whether or not the authentication is successful. If the authentication is successful, the CPU determines "YES" in step 1130 and proceeds to step 620. If the authentication is unsuccessful, the CPU determines "NO" in step 1130 and proceeds to step 625.

[0103] <Effects> As described above, the face recognition terminal 100 according to the third embodiment of the present invention can reduce the possibility of a decrease in the reliability of face recognition, similar to the first embodiment.

[0104] <<Fourth embodiment>> A face authentication system including a face authentication terminal 100 according to a fourth embodiment of the present invention will be described. This face authentication system differs from the face authentication system of the first embodiment only in the following points. In the first embodiment, authentication in the authentication process is performed by the authentication server 200, but in the fourth embodiment, it is performed by the face authentication terminal 100.

[0105] The following description will focus on these differences.

[0106] <Specific operation> A specific operation of the face authentication terminal 100 according to the fourth embodiment will be described. The CPU of the face authentication terminal 100 executes the process flow shown in the flowchart of Fig. 4, the process flow shown in the flowchart of Fig. 5, and the process flow shown in the flowchart of Fig. 11. Note that these process flows have already been described, so description thereof will be omitted.

[0107] <Effects> As described above, the face recognition terminal 100 according to the fourth embodiment of the present invention can reduce the possibility of a decrease in the reliability of face recognition, similar to the first embodiment.

[0108] <<Fifth embodiment>> A face authentication system including a face authentication terminal 100 according to a fifth embodiment of the present invention will be described. This face authentication system differs from the face authentication system of the first embodiment only in the following points. This face authentication system executes the process flow shown in the flowchart of FIG. 12 instead of the process flow shown in the flowchart of FIG.

[0109] The following explanation will focus on these differences.

[0110] The process flow in Fig. 12 differs from the process flow in Fig. 5 only in that step 520 in Fig. 5 has been moved to immediately after step 500, step 1210 has been added between step 520 and step 505, and step 525 and step 530 have been replaced with step 1220 and step 1230. Therefore, the following description will focus on the different processes and omit other descriptions.

[0111] The CPU of the face authentication terminal 100 starts the process from step 500 in FIG. 12, proceeds to step 520, and displays the face photographing instruction screen GM5 on the display 130. After that, the CPU proceeds to step 1210, and acquires the user's face image by capturing an image of the user's face using the camera 120. Furthermore, the CPU starts the process of converting the face image into a PBI. That is, the CPU starts the process of extracting (generating) a biometric private key (facial feature information) from the acquired face image, generating a private key and a public key (biometric public key) using an existing encryption technology, and generating a PBI template from the biometric private key (facial feature information) and the private key. For convenience of explanation, the biometric public key is designated as (B). After that, the CPU proceeds to step 505.

[0112] After executing the process of step 505, if the CPU judges "YES" in each of steps 510 and 515, the process proceeds to step 1220 and judges whether or not a biometric public key (B) has been generated at the present time.

[0113] If the biometric public key ((B)) has not been generated at this time, the CPU judges "NO" in step 1220 and returns to step 1220 again. If the biometric public key ((B)) has been generated at this time, the CPU judges "YES" in step 1220 and proceeds to step 1230. When the CPU proceeds to step 1230, it requests the authentication server 200 to register the biometric public key ((B)) and proceeds to step 535.

[0114] <Effects> As described above, the face authentication terminal 100 according to the fifth embodiment of the present invention can reduce the possibility of the reliability of face authentication decreasing, similar to the first embodiment. Furthermore, the face authentication terminal 100 according to the fifth embodiment makes the user input user information during the time-consuming process of converting a face image into a PBI, thereby preventing the user from being aware of the time required for the PBI process, thereby reducing the possibility that the user will feel annoyed by the time required for the process of converting a face image into a PBI. Note that the features of the fifth embodiment may be applied to the second to fourth embodiments.

[0115] <<Modifications>> The present invention is not limited to the above-described embodiments, and various modifications can be adopted within the scope of the present invention. Furthermore, the above-described embodiments can be combined with each other without departing from the scope of the present invention.

[0116] For example, in the first embodiment, the face authentication system may operate as described below (note that the features of this modified example described below may be applied to the second to fourth embodiments). That is, as shown in Fig. 13A, the face authentication terminal 100 captures an image of the face of the user Us1 by the camera 120 at the first timing when the user Us1 is detected by at least one of the camera 120 and the thermal sensor 110, thereby acquiring a face image 1 which is an image of the face of the user Us1 at the first timing. The face authentication terminal 100 generates (extracts) a biometric private key 1 (facial feature information 1) from the face image 1.

[0117] 13B, the face authentication terminal 100 generates a private key and a public key by an existing encryption technology, and generates a PBI template based on the biometric private key 1 and the private key. The face authentication terminal 100 transmits the biometric public key (PBI template and public key) to the authentication server 200. After that, the face authentication terminal 100 discards the biometric private key 1 and the biometric public key (PBI template and public key).

[0118] 13C, the face authentication terminal 100 captures an image of the face of the user Us1 by the camera 120 at a second timing after the first timing, thereby acquiring a face image 2 that is a captured image of the face of the user Us1 at the second timing. The face authentication terminal 100 extracts (generates) a biometric private key 2 (facial feature information 2) from the face image 2, and requests the authentication server 200 to register the biometric public key transmitted in the previous process.

[0119] As shown in FIG. 13D, the authentication server 200 performs authentication using the biometric private key 2 and the biometric public key that is being requested to be registered to the authentication server 200.

[0120] If the authentication is successful, the face authentication terminal 100 discards the biometric private key 2, and the authentication server 200 completes the registration of the biometric public key. If the authentication is not successful, the face authentication terminal 100 discards the biometric private key 2, and the authentication server 200 does not register the biometric public key.

[0121] For example, in each of the above-described embodiments, the configuration example of the face authentication terminal 100 is just an example, and a human sensor such as an ultrasonic sensor, a sound sensor, or a touch sensor may be used instead of the thermal sensor 110. Furthermore, in each of the above-described embodiments, the thermal sensor 110 may be omitted.

[0122] For example, in each of the above embodiments, the face recognition terminal 100 automatically captures the user's face with the camera 120 when a person is detected, but it may also be configured to display an instruction button to instruct the user to capture a face image for verification, and acquire the face image for verification by capturing an image of the user's face when the instruction button is operated.

[0123] For example, in each of the above embodiments, authentication may be performed using each of multiple biometric private keys generated based on multiple facial images captured at two or more times and the biometric public key, and if all authentication results are successful, the biometric public key may be registered.

[0124] The present invention can also have the following configuration.

[0125] [1] A face recognition terminal having a sensor including a camera, The face recognition terminal includes: generating a first biometric private key from a first face image, which is one of two face images acquired by capturing images of the face of the person with the camera at a first timing when the person is detected by the sensor and at a second timing different from the first timing; generating a second biometric private key from a second face image, which is the other of the two face images; and generating a biometric public key based on the second biometric private key; Before registering the biometric public key in an internal or external key database, the first biometric private key and the biometric public key are used to verify whether authentication is successful, and if it is verified that the authentication is successful, the registration of the biometric public key in the key database is completed. Facial recognition device.

[0126] [2] In the face recognition terminal according to [1], The key database is external; The face authentication terminal is configured to be capable of transmitting and receiving information to and from an authentication device including the key database, and is configured to register the biometric public key in the key database included in the authentication device; The face recognition terminal includes: transmitting the biometric public key to the authentication device to request the authentication device to register the biometric public key in the key database, and having the authentication device perform authentication using the first biometric private key and the biometric public key received from the face authentication terminal, thereby verifying whether the authentication is successful; It was configured as follows: Facial recognition device.

[0127] [3] In the face recognition terminal according to [1], The key database is internal; The face recognition terminal further includes a storage device in which the key database is stored. Facial recognition device.

[0128] [4] In the face recognition terminal according to [1], the sensor includes a sensor other than the camera, The face recognition terminal includes: a timing when the person is detected by at least one of the other sensor and the camera is defined as the first timing; It was configured as follows: Facial recognition device.

[0129] [5] In the face recognition terminal according to [1], The face recognition terminal includes: acquiring the first face image by capturing an image of the face of the person at the first timing; acquiring the second face image by capturing an image of the face of the person at the second timing that is later than the first timing; It was configured as follows: Facial recognition device.

[0130] [6] In the face recognition terminal according to [5], The face recognition terminal has a display device capable of displaying an image, the face authentication terminal displays a face photographing instruction screen including information instructing to photograph a face on the display device, and photographs the face of the person at the second timing; It was configured as follows: Facial recognition device.

[0131] According to the face recognition terminal of [6], a first face image is captured by a camera at a first timing detected by a human detection sensor without the user being aware that it is for authentication purposes, and a second face image is captured by the camera with the user being aware that it is for authentication purposes. This allows the face recognition device in [6] to improve the chances of acquiring two face images for verification that have greater fluctuations, such as different facial expressions. By verifying that authentication is successful based on the two face images for verification that have greater fluctuations, and registering the biometric public key, the reliability of subsequent authentication is improved.

[0132] [7] [6] In a face recognition terminal according to the present invention, The face recognition terminal includes: After capturing an image of the face of the person at the second timing, a process of generating the second biometric private key from the second face image is started, and a screen for prompting the person to input user information is displayed on the display device during the period from the start of the process to the completion of generation of the second biometric private key. It was configured as follows: Facial recognition device.

[0133] [8] In the face recognition terminal according to [2], The face recognition terminal includes: acquiring the first face image by capturing an image of the face of the person at the first timing; The second face image is acquired by capturing an image of the face of the person at the second timing that is later than the first timing, The face recognition terminal includes: storing the first biometric private key generated from the first face image captured at the first timing; After transmitting the biometric public key to the authentication device, discard the second biometric private key and the biometric public key; configured to discard the first biometric private key after authentication by the authentication device is performed; Facial recognition device. According to the face recognition terminal of [8], by discarding the first biometric private key, the second biometric private key, and the biometric public key, it is possible to prevent information required for authentication from being illegally obtained by others.

[0134] [9] In the face recognition terminal according to [1], The face recognition terminal includes a display device that displays an image, The face recognition terminal includes: displaying a screen corresponding to the verification result on the display device; It was configured as follows: Facial recognition device.

[0135]

[10] In the face recognition terminal according to [4], The other sensor is a thermal sensor that detects heat of the person. Facial recognition device.

[0136]

[11] In the face recognition terminal according to [1], The face recognition terminal includes: When performing face authentication after completing registration of the biometric public key, a biometric private key for authentication is generated from a face image for authentication obtained by capturing an image of the face of the person by the camera at a timing when the person is detected by the sensor, and Obtaining the registered biometric public key from the key database; performing authentication using the biometric private key and the registered biometric public key; After the authentication is performed, discard the biometric private key for authentication. It was configured as follows: Facial recognition device.

[0137]

[12] In the face recognition terminal according to [2], The face recognition terminal includes: When performing face authentication after completing registration of the biometric public key, a biometric private key for authentication is generated from a face image for authentication obtained by capturing an image of the face of the person by the camera at a timing when the person is detected by the sensor, and causing the authentication device to perform authentication using the biometric private key and the registered biometric public key; After the authentication is performed by the authentication device, the biometric private key for authentication is discarded. It was configured as follows: Facial recognition device.

[0138] According to the face recognition terminals of

[11] and

[12] , by discarding the biometric private key used for authentication, it is possible to prevent information required for authentication from being illegally obtained by others.

[0139]

[13] In the face recognition terminal according to [1], The face recognition terminal includes: capturing an image of the face of the person at the first timing and the second timing to obtain the first face image and the second face image in which the facial expressions of the person appearing in the images are different from each other; It was configured as follows: Facial recognition device.

[0140]

[14] In the face recognition terminal according to [1], The face recognition terminal includes: acquiring the second face image by capturing an image of the face of the person at the first timing; acquiring the first face image by capturing an image of the face of the person at the second timing that is later than the first timing; It was configured as follows: Facial recognition device.

[0141]

[15] A face recognition terminal having a sensor including a camera; An authentication device; having A face authentication system configured so that the face authentication terminal and the authentication device can transmit and receive information to each other, The face recognition terminal includes: the authentication device is configured to generate a first biometric private key from a first face image, which is one of two face images acquired by capturing an image of the face of the person with the camera at a first timing when the person is detected by the sensor and at a second timing different from the first timing, generate a second biometric private key from a second face image, which is the other of the two face images, generate a biometric public key based on the second biometric private key, and transmit the biometric public key to the authentication device to request the authentication device to register the biometric public key; The authentication device is configured to verify whether the authentication is successful by performing authentication using the first biometric private key and the biometric public key received from the face authentication terminal, and complete registration of the biometric public key when it is verified that the authentication is successful. Facial recognition system.

[0142]

[16] A face authentication method using a face authentication terminal having a sensor including a camera, The face recognition terminal, a first biometric private key is generated from a first face image, which is one of two face images acquired by capturing an image of the face of the person with the camera at a first timing when the person is detected by the sensor and at a second timing different from the first timing; a second biometric private key is generated from a second face image, which is the other of the two face images; and a biometric public key is generated based on the second biometric private key. Before registering the biometric public key in an internal or external key database, authentication is performed using the first biometric private key and the biometric public key to verify whether the authentication is successful, and if it is verified that the authentication is successful, the registration of the biometric public key in the key database is completed. Face recognition method. [Explanation of symbols]

[0143] 100: face recognition terminal, 110: thermal sensor, 120: camera, 130: display, 140: CPU board, 150: memory, 160: wireless LAN, 200: authentication server

Claims

1. A face recognition terminal having a sensor including a camera, The face recognition terminal includes: generating a first biometric private key from a first face image which is one of two face images acquired by capturing images of the face of the person with the camera at a first timing when the person is detected by the sensor and at a second timing different from the first timing, generating a second biometric private key from a second face image which is the other of the two face images, and generating a biometric public key based on the second biometric private key; Before registering the biometric public key in an internal or external key database, the first biometric private key and the biometric public key are used to verify whether authentication is successful, and if it is verified that the authentication is successful, the registration of the biometric public key in the key database is completed. Facial recognition device.

2. The face recognition terminal according to claim 1, The key database is external; The face authentication terminal is configured to be capable of transmitting and receiving information to and from an authentication device including the key database, and is configured to register the biometric public key in the key database included in the authentication device; The face recognition terminal includes: transmitting the biometric public key to the authentication device to request the authentication device to register the biometric public key in the key database, and having the authentication device perform authentication using the first biometric private key and the biometric public key received from the face authentication terminal, thereby verifying whether the authentication is successful; It was configured as follows: Facial recognition device.

3. The face recognition terminal according to claim 1, The key database is internal; The face recognition terminal further includes a storage device in which the key database is stored. Facial recognition device.

4. The face recognition terminal according to claim 1, the sensor includes a sensor other than the camera, The face recognition terminal includes: a timing at which the person is detected by at least one of the other sensor and the camera is defined as the first timing; It was configured as follows: Facial recognition device.

5. The face recognition terminal according to claim 1, The face recognition terminal includes: acquiring the first face image by capturing an image of the face of the person at the first timing; acquiring the second face image by capturing an image of the face of the person at the second timing that is later than the first timing; It was configured as follows: Facial recognition device.

6. The face recognition terminal according to claim 5, The face recognition terminal has a display device capable of displaying an image, the face authentication terminal displays a face photographing instruction screen including information instructing to photograph a face on the display device, and photographs the face of the person at the second timing; It was configured as follows: Facial recognition device.

7. 7. The face recognition terminal according to claim 6, The face recognition terminal includes: After capturing an image of the face of the person at the second timing, a process of generating the second biometric private key from the second face image is started, and a screen for prompting the person to input user information is displayed on the display device during the period from the start of the process to the completion of generation of the second biometric private key. It was configured as follows: Facial recognition device.

8. 3. The face recognition terminal according to claim 2, The face recognition terminal includes: acquiring the first face image by capturing an image of the face of the person at the first timing; The second face image is acquired by capturing an image of the face of the person at the second timing that is later than the first timing, The face recognition terminal includes: storing the first biometric private key generated from the first face image captured at the first timing; After transmitting the biometric public key to the authentication device, discarding the second biometric private key and the biometric public key; The authentication device is configured to discard the first biometric private key after authentication is performed by the authentication device. Facial recognition device.

9. The face recognition terminal according to claim 1, The face recognition terminal includes a display device that displays an image, The face recognition terminal includes: displaying a screen corresponding to the verification result on the display device; It was configured as follows: Facial recognition device.

10. The face recognition terminal according to claim 4, The other sensor is a thermal sensor that detects heat of the person. Facial recognition device.

11. The face recognition terminal according to claim 1, The face recognition terminal includes: When performing face authentication after completing registration of the biometric public key, a biometric private key for authentication is generated from a face image for authentication obtained by capturing an image of the face of the person by the camera at a timing when the person is detected by the sensor, and Obtaining the registered biometric public key from the key database; performing authentication using the biometric private key and the registered biometric public key; After the authentication is performed, discard the biometric private key for authentication. It was configured as follows: Facial recognition device.

12. 3. The face recognition terminal according to claim 2, The face recognition terminal includes: When performing face authentication after completing registration of the biometric public key, a biometric private key for authentication is generated from a face image for authentication obtained by capturing an image of the face of the person by the camera at a timing when the person is detected by the sensor, and causing the authentication device to perform authentication using the biometric private key and the registered biometric public key; After the authentication is performed by the authentication device, the biometric private key for authentication is discarded. It was configured as follows: Facial recognition device.

13. The face recognition terminal according to claim 1, The face recognition terminal includes: capturing an image of the face of the person at the first timing and the second timing to obtain the first face image and the second face image in which the facial expressions of the person appearing in the images are different from each other; It was configured as follows: Facial recognition device.

14. A face recognition terminal having a sensor including a camera; An authentication device; having A face authentication system configured so that the face authentication terminal and the authentication device can transmit and receive information to each other, The face recognition terminal includes: the authentication device is configured to generate a first biometric private key from a first face image, which is one of two face images acquired by capturing an image of the face of the person with the camera at a first timing when the person is detected by the sensor and at a second timing different from the first timing, generate a second biometric private key from a second face image, which is the other of the two face images, generate a biometric public key based on the second biometric private key, and transmit the biometric public key to the authentication device to request the authentication device to register the biometric public key; The authentication device includes: The method is configured to verify whether the authentication is successful by performing authentication using the first biometric private key and the biometric public key received from the face authentication terminal, and complete registration of the biometric public key when it is verified that the authentication is successful. Facial recognition system.

15. A face authentication method using a face authentication terminal having a sensor including a camera, The face recognition terminal, a first biometric private key is generated from a first face image which is one of two face images acquired by capturing an image of the face of the person with the camera at a first timing when the person is detected by the sensor and at a second timing different from the first timing, a second biometric private key is generated from a second face image which is the other of the two face images, and a biometric public key is generated based on the second biometric private key; and before registering the biometric public key in an internal or external key database, using the first biometric private key and the biometric public key, verify whether or not authentication is successful, and if it is verified that authentication is successful, complete the registration of the biometric public key in the key database. Face recognition method.

Images