Personal authentication system, personal authentication method, and program

Abstract

A self-authentication system has a camera (260) and an information processing apparatus (200) that performs self-authentication based on a photographed image of a subject taken by the camera (260). The information processing apparatus (200) includes a first processing section (510) that determines a motion of a face of a subject based on first photographed images (251) of the subject, which are continuously taken by the camera (260) while a direction of the face is changed from a front direction to a direction different from the front direction, and performs face authentication of the subject based on the first photographed images (251) and an enrolled image (256), and a second processing section (520) that performs face authentication of the subject based on the enrolled image (256) and a second photographed image (252) of the subject taken by the camera (260).

Description

Technical Field

[0001] This invention relates to a personal authentication system, a personal authentication method, and a procedure. Background Technology

[0002] Japanese Patent Application Publication No. 2022-62533 (Patent Document 1) discloses an NC control panel with functions for facial recognition and body temperature management of the operator.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2022-62533 Summary of the Invention

[0006] The problem the invention aims to solve

[0007] As disclosed in Patent Document 1 above, facial recognition is used in various scenarios to verify that the subject is the person in question (personal verification). In this case, more accurate personal verification of the subject is required.

[0008] For example, in machine tool maintenance scenarios, facial recognition is performed on the operator performing the maintenance, thereby verifying the operator's identity. Accurate operator identity verification is required to ensure that machine tool maintenance is performed by individuals with appropriate knowledge and skills.

[0009] The purpose of this invention is to provide a self-authentication system, self-authentication method, and procedure that can more accurately authenticate the identity of the subject.

[0010] Solution for solving the problem

[0011] The personal authentication system according to the present invention includes: a camera for photographing a subject; and an information processing device for authenticating the subject's identity based on photographic images of the subject captured by the camera. The information processing device includes: a first processing unit that determines facial movement of the subject based on first photographic images of the subject continuously captured by the camera, in which the orientation of the face changes from a frontal view to a direction different from a frontal view, and performs facial authentication of the subject based on the first photographic images and a pre-registered registration image of the subject; and a second processing unit that performs facial authentication of the subject based on the registration image and a second photographic image of the subject captured by the camera.

[0012] The self-authentication method according to the present invention is a self-authentication method that verifies the identity of the subject based on photographic images of the subject. The self-authentication method includes the following steps: obtaining a first photographic image by continuously photographing the subject whose facial orientation changes from a frontal view to a direction different from a frontal view; determining the movement of the subject's face based on the first photographic image, and performing facial authentication of the subject based on the first photographic image and a pre-registered registration image of the subject; obtaining a second photographic image by photographing the subject; and performing facial authentication of the subject based on the second photographic image and the registration image.

[0013] The program according to the present invention is a program of an information processing device that performs authentication of a subject based on a photographic image of the subject. The program causes the information processing device to perform the following steps: determining facial movement of the subject based on a first photographic image of the subject in which the orientation of the face changes from a frontal view to a direction different from a frontal view; and performing facial authentication of the subject based on the first photographic image and a pre-registered registration image of the subject; and performing facial authentication of the subject based on a second photographic image of the subject and the registration image.

[0014] Invention Effects

[0015] According to the present invention, a self-authentication system, self-authentication method, and procedure can be provided that can more accurately authenticate that the subject is the self. Attached Figure Description

[0016] Figure 1 This diagram schematically illustrates the relationship between the personal authentication system and the machine tool in an embodiment of the present invention.

[0017] Figure 2 This is a functional block diagram showing the operator's PC and facial recognition server during impersonation detection.

[0018] Figure 3 This is a diagram showing the display unit during impersonation detection.

[0019] Figure 4 This is a functional block diagram showing the operator's PC and facial recognition server during the personal verification process.

[0020] Figure 5 This is a diagram showing the display when the user confirms their confirmation.

[0021] Figure 6 This is a flowchart illustrating the steps of impersonation detection.

[0022] Figure 7 This is a flowchart showing the steps I confirmed. Detailed Implementation

[0023] Embodiments of the present invention will be described with reference to the accompanying drawings. Furthermore, in the drawings referred to below, the same or equivalent components are labeled with the same reference numerals.

[0024] Figure 1 This diagram schematically illustrates the relationship between the personal authentication system and the machine tool in an embodiment of the present invention. (Refer to...) Figure 1 The operator performing maintenance on machine tool 600 carries an operator PC 200. When operator authentication is completed, the operator can communicate maintenance information related to various states of machine tool 600 between the operator PC 200 and the machine tool 600's control panel 610. In this embodiment, the application of the operator authentication system, method, and program of this invention to the operator performing maintenance on machine tool 600 (corresponding to the subject of this invention) will be described.

[0025] The personal authentication system 100 in this embodiment includes an operator PC 200, a camera 260, a personal authentication management server 300, and a face comparison server 400. The operator PC 200 (camera 260), the personal authentication management server 300, and the face comparison server 400 communicate with each other via a network such as a wireless LAN.

[0026] The operator PC 200 corresponds to the information processing device in this invention. The various structural elements of the operator PC 200 are implemented through hardware and software. The hardware includes an arithmetic logic unit (ALU) such as a CPU (Central Processing Unit) and various computer processors, storage devices such as memory and storage devices, and wired or wireless communication lines connecting them. The software is stored in the storage devices and is used to supply processing commands to the ALU. The computer program may also consist of device drivers, an operating system, various application programs located at their upper levels, or libraries that provide common functions to these programs.

[0027] The operator PC 200 performs an authentication of the operator's identity (personal authentication) based on photographic images of the operator captured by the camera 260.

[0028] The main functions of the Operator PC 200 are impersonation detection and operator identity verification. Impersonation detection detects impersonations using photographs. Operator identity verification uses facial recognition to confirm the operator's identity. After completing the impersonation detection and operator identity verification steps, the Operator PC 200 ultimately verifies the operator's identity.

[0029] The operator PC 200 is a portable computer that the operator can carry. The operator PC 200 has a display unit 210 and an operation unit 220. The display unit 210 is composed of a liquid crystal display, an organic EL display, or other display devices. The display unit 210 can display photographic images of the operator captured by the camera 260, etc. The operation unit 220 handles various operations performed by the operator.

[0030] The camera 260 is configured to capture images of the operator. The camera 260 is installed on the operator's PC 200. The camera 260 is configured to capture images of the operator's face while operating the operation unit 220 of the operator's PC 200. Furthermore, in this invention, the camera may also be installed separately from the information processing device.

[0031] The Personal Authentication Management Server 300 is set up by the administrator of the Personal Authentication System 100. For example, the Personal Authentication Management Server 300 is set up in the office building of the manufacturer of the machine tool 600.

[0032] The main function of the self-authentication management server 300 is to manage information related to the self-authentication of operators. The self-authentication management server 300 registers the operator's facial photo, or verifies the operator's facial photo before and after registration, or monitors the calculation of the self-authentication reliability during the self-authentication process, or stores various information accompanying the operator's self-authentication in the database.

[0033] More specifically, the self-authentication management server 300 stores the registration images 256 of the operators. The registration images 256 are images registered in the database of the self-authentication management server 300 by the administrator of the self-authentication system 100 using facial photographs provided by the operators. The self-authentication management server 300 stores multiple registration images 256 corresponding to one operator. These multiple registration images 256 may include registration images showing the operator's face facing forward. The multiple registration images 256 may also include registration images showing the operator's face facing a different direction than forward.

[0034] The user authentication management server 300 sends the registered image 256 of the operator stored in the database to the face comparison server 400. The face comparison server 400 extracts facial feature values ​​from the registered image 256, quantifying features such as the position of the eyes, the shape of the nose, and the size of the mouth. The face comparison server 400 stores the facial feature values ​​of the operator extracted from the registered image 256.

[0035] Threshold information is also stored in the personal authentication management server 300. The threshold information includes a threshold t for the angle of the face used in impersonation detection, and a first threshold Ta and a second threshold Tb for personal reliability used in impersonation detection and personal verification, respectively.

[0036] The operator operates the operation unit 220, thereby the operator PC 200 receives the operator's user ID and password. If the received password matches the password registered in the user ID, the operator PC 200 sends the user ID to the personal authentication management server 300. The personal authentication management server 300 then sends the personal information 561 corresponding to the user ID to the operator PC 200. The personal information 561 includes at least the aforementioned threshold information.

[0037] Figure 2 This is a functional block diagram showing the operator's PC and facial recognition server during impersonation detection. Figure 3 This is a diagram showing the display unit during impersonation detection.

[0038] Reference Figures 1 to 3 The operator PC 200 has a first processing unit 510. The first processing unit 510 performs processing for impersonation detection.

[0039] The first processing unit 510 determines the movement of the operator's face based on the first photographic image 251 continuously captured by the camera 260, in which the orientation of the operator's face changes from the front to a direction different from the front, and performs facial authentication of the operator based on the first photographic image 251 and the pre-registered registration image 256 of the operator.

[0040] More specifically, the first processing unit 510 includes a display control unit 531. The display control unit 531 controls the display unit 210. During spoofing detection, the display control unit 531 controls the display unit 210 to display a first display screen 210A.

[0041] like Figure 3 As shown, the first display screen 210A has a first instruction image unit 216A. The first instruction image unit 216A displays instructions to the operator during impersonation detection. The first instruction image unit 216A includes a first annotation column 218A and a first illustration column 217A. The first annotation column 218A displays an instruction to the operator via annotation to change the orientation of their face from the front to a direction different from the front. The first annotation column 218A displays an annotation such as "Please slowly turn to the right in the following direction (please hold for a few seconds)". The first illustration column 217A displays an illustration to the operator to change the orientation of their face from the front to a direction different from the front. The first illustration column 217A displays an illustration and an arrow indicating the operator's face to the right.

[0042] Furthermore, in the first indicator image unit 216A, any one of the directions (left, right, up, down) is randomly indicated as a direction different from the front view. The direction indicated by the first indicator image unit 216A that is different from the front view is not particularly limited; for example, it could be a direction tilted relative to the up, down, left, or right directions.

[0043] The first display screen 210A also includes a notice section 212. The notice section 212 displays precautions for operators when posing as inspectors. For example, the notice section 212 displays precautions such as "Please remove the following items: mask, sunglasses, safety goggles," "Please avoid strong lighting (including backlighting)," and "Do not cover your eyes or mouth."

[0044] like Figure 2 As shown, the first processing unit 510 also includes a camera control unit 532. The camera control unit 532 controls the camera 260. During impersonation detection, the camera control unit 532 controls the camera 260 to continuously capture images of the worker whose facial orientation changes from a frontal view to a different orientation. The camera control unit 532's shooting interval is, for example, 500 ms / frame. Through the capturing by the camera 260, a first photographic image 251 of the worker whose facial orientation changes from a frontal view to a different orientation is obtained.

[0045] The operator PC 200 also has a transmitting unit 230. The transmitting unit 230 transmits the first photographic image 251 to the face comparison server 400 via a network.

[0046] like Figure 3 As shown, the first display screen 210A also includes a first photographic image unit 211A. The first photographic image unit 211A continuously displays the first photographic image 251 captured by the camera 260.

[0047] like Figure 1 and Figure 2 As shown, the face comparison server 400 is set up by a cloud service provider. The main functions of the face comparison server 400 are to calculate the angle of the operator's face based on the photographic image, and to calculate the reliability of the individual by comparing the facial feature quantities extracted from the photographic image with the facial feature quantities extracted from the registration image.

[0048] The face comparison server 400 has an angle calculation unit 410. The angle calculation unit 410 acquires a first photographic image 251 from the operator's PC 200 during impersonation detection. The angle calculation unit 410 calculates the angle of the operator's face in the first photographic image 251 (0° as a reference for the face facing forward, and the angle of the face facing a direction different from the face facing forward).

[0049] For example, the angle calculation unit 410 calculates the angle of the worker's face in the first photographic image 251 by recognizing the facial contour and feature points such as eyebrows, eyes, nose and mouth, and verifying the changes in the position of the feature points relative to the recognized contour.

[0050] The face comparison server 400 also has a reliability calculation unit 420 and a feature storage unit 430. The feature storage unit 430 stores the facial feature data of the operator extracted from the registered image 256 from the self-authentication management server 300.

[0051] During impersonation detection, the reliability calculation unit 420 acquires a first photographic image 251 from the operator's PC 200 and reads the operator's facial feature data from the feature data storage unit 430. The reliability calculation unit 420 calculates the reliability (personality reliability) that the operator's face in the first photographic image 251 is the same as the operator in the registration image 256 by comparing the facial feature data extracted from the first photographic image 251 (which faces a direction different from the front) with the facial feature data read from the feature data storage unit 430. When the personality reliability is 1, the probability that the operator in the first photographic image 251 is the same as the operator in the registration image 256 is the highest; when the personality reliability is 0, the probability that the operator in the first photographic image 251 is the same as the operator in the registration image 256 is the lowest.

[0052] More specifically, the reliability calculation unit 420 extracts the operator's facial feature data from the first photographed image 251, performs facial comparison by comparing the operator's facial feature data with the facial feature data read from the feature data storage unit 430, and calculates the operator's reliability (corresponding to the consistency between the facial feature data extracted from the first photographed image 251 and the facial feature data read from the feature data storage unit 430). Facial comparison is not limited to this; for example, images can be directly compared, or comparison methods using machine learning or similar techniques can be applied. Alternatively, the operator's PC 200 can be equipped with the functions of the facial comparison server 400 without using a cloud-based facial comparison server 400.

[0053] The operator's PC 200 sends the angle of the operator's face and the individual's reliability calculated in the face comparison server 400. The operator PC 200 also has a receiving unit 240. The receiving unit 240 receives the angle of the operator's face and the individual's reliability from the face comparison server 400.

[0054] The operator PC 200 also has a storage unit 560. The storage unit 560 stores personal information 561 from the personal authentication management server 300. The storage unit 560 also stores a program for enabling the operator PC 200 to perform personal authentication for the operator.

[0055] The first processing unit 510 also includes a motion determination unit 533. The motion determination unit 533 acquires the angle of the operator's face from the face comparison server 400 and reads a threshold t for the facial angle from the storage unit 560. The motion determination unit 533 compares the angle of the operator's face from the face comparison server 400 with the threshold t, and determines that there is motion of the operator if the facial angle is above the threshold t. For example, the threshold t is 30°.

[0056] The first processing unit 510 also includes a first facial authentication determination unit 534. When the motion determination unit 533 determines that there is movement of the operator, the first facial authentication determination unit 534 obtains the identity reliability from the facial comparison server 400 and reads the first threshold Ta of identity reliability at the time of impersonation detection from the storage unit 560. The first facial authentication determination unit 534 compares the identity reliability from the facial comparison server 400 with the first threshold Ta of identity reliability at the time of impersonation detection, and if the identity reliability is above the first threshold Ta, confirms the operator's facial authentication.

[0057] The first facial authentication determination unit 534 confirms the operator's facial identity, thus completing the impersonation detection step and moving on to the personal confirmation step.

[0058] Figure 4 This is a functional block diagram showing the operator's PC and facial recognition server during the personal verification process. Figure 5 This is a diagram showing the display when the user confirms their confirmation.

[0059] Reference Figure 4 and Figure 5 The operator PC 200 has a second processing unit 520. The second processing unit 520 performs processing for the operator's personal confirmation.

[0060] The second processing unit 520 performs facial authentication of the operator based on the registered image 256 and the facial feature data extracted from the second photographic image 252 of the operator captured by the camera 260.

[0061] More specifically, the second processing unit 520 has a display control unit 531. The display control unit 531 controls the display unit 210 to display the second display screen 210B when the operator confirms.

[0062] like Figure 5As shown, the second display screen 210B has a second instruction image section 216B and a note annotation section 212. The second instruction image section 216B displays instructions to the operator when the operator confirms the information. The second instruction image section 216B includes a second note bar 218B and a second illustration bar 217B. The second note bar 218B displays instructions to the operator on how to turn their face back to a facing position. The second note bar 218B displays a note such as "Please slowly turn your face forward in the following direction (please move within eye level)". The second illustration bar 217B displays instructions to the operator on how to turn their face back to a facing position. The second illustration bar 217B displays an illustration of a face facing forward. The note annotation section 212 is the same as the note annotation section 212 in the first display screen 210A.

[0063] like Figure 4 As shown, the second processing unit 520 also includes a camera control unit 532. The camera control unit 532 controls the camera 260 to capture images of the operator upon the operator's confirmation. Through the capture by the camera 260, a second photographic image 252 of the operator facing forward is obtained.

[0064] The sending unit 230 sends the second photographic image 252 to the face comparison server 400 via the network.

[0065] like Figure 5 As shown, the second display screen 210B also has a second photographic image unit 211B. The second photographic image unit 211B displays a second photographic image 252 captured by the camera 260.

[0066] like Figure 4 As shown, the reliability calculation unit 420 acquires a second photographic image 252 from the operator's PC 200 upon operator self-verification and reads the facial feature data of the operator extracted from the registration image 256 from the feature data storage unit 430. The reliability calculation unit 420 calculates the reliability (self-verification reliability) that the face of the operator in the second photographic image 252 is the same as the face of the operator in the registration image 256 by comparing the facial feature data extracted from the second photographic image 252 with the facial feature data read from the feature data storage unit 430.

[0067] The system sends the individual's reliability calculated in the face comparison server 400 to the operator's PC 200. The receiving unit 240 receives the individual's reliability from the face comparison server 400.

[0068] The second processing unit 520 also includes a second facial authentication determination unit 535. The second facial authentication determination unit 535 acquires the identity reliability from the facial comparison server 400 and reads a second threshold Tb of the identity reliability at the time of identity verification from the storage unit 560. The second facial authentication determination unit 535 compares the identity reliability from the facial comparison server 400 with the second threshold Tb of the identity reliability at the time of identity verification, and confirms the operator's facial authentication if the identity reliability is above the second threshold Tb.

[0069] The second threshold Tb for the reliability of the person during self-verification is larger than the first threshold Ta for the reliability of the person during impersonation detection. For example, the first threshold Ta is 0.5 and the second threshold Tb is 0.8.

[0070] The second facial recognition determination unit 535 confirms the operator's face, thus completing the self-confirmation step. The operator PC 200 then performs final authentication to verify that the operator is indeed the person in question. This enables communication of maintenance information for the machine tool 600 between the operator PC 200 and the machine tool 600's control panel 610.

[0071] Figure 6 This is a flowchart illustrating the steps involved in impersonation detection. (Refer to...) Figures 1 to 3 as well as Figure 6 The operator's PC 200 accepts the ID code and password (S101).

[0072] In this step, if the received password matches the password registered in the user ID, the operator PC200 sends the user ID to the personal authentication management server 300. The personal authentication management server 300 then sends the personal information 561 corresponding to the user ID to the operator PC 200.

[0073] Next, the operator PC 200 obtains the user's information 561 (S102). In this step, the storage unit 560 stores the user's information 561 from the user authentication management server 300.

[0074] Next, the operator PC 200 (display control unit 531) causes the display unit 210 to display the first display screen 210A. In this step, the operator receives the instruction displayed in the first instruction image unit 216A and changes the orientation of their face from front to a direction different from front.

[0075] Next, the operator PC 200 (camera control unit 532) captures images of the operator changing the orientation of their face from a frontal view to a different orientation. The operator PC 200 (transmission unit 230) then sends the first captured image 251 to the face comparison server 400 (S104).

[0076] The face comparison server 400 (angle calculation unit 410) calculates the angle of the operator's face in the first photographic image 251 from the operator's PC 200.

[0077] Next, the operator PC 200 (receiving unit 240) receives the facial angle calculated by the facial comparison server 400 (S105). Then, the operator PC 200 (motion determination unit 533) compares the facial angle of the operator calculated by the facial comparison server 400 with the threshold t of facial angle stored in the storage unit 560, and determines whether the facial angle is above the threshold t (S106).

[0078] If the angle of the face is determined to be less than the threshold t in step S106, return to step S104.

[0079] In step S106, if the angle of the face is determined to be above the threshold t, the face comparison server 400 (reliability calculation unit 420) calculates the reliability (personal reliability) that the face of the operator in the first photographic image 251 is the face of the operator in the registration image 256.

[0080] Next, the operator PC 200 (receiving unit 240) receives the identity reliability calculated by the face comparison server 400 (S107). Then, the operator PC 200 (first face authentication determination unit 534) compares the identity reliability calculated by the face comparison server 400 with the first threshold Ta of identity reliability during impersonation detection, and determines whether the identity reliability is above the first threshold Ta (S108).

[0081] If, in step S108, it is determined that the reliability of the individual is less than the first threshold Ta, the operator PC 200 determines whether a certain amount of time has elapsed since the start of the impersonation detection step (S109).

[0082] If it is determined in step S109 that a certain amount of time has not elapsed, the process returns to step S104. If it is determined in step S109 that a certain amount of time has elapsed, the process returns to step S103, and the operator PC 200 (display control unit 531) displays an unacceptable comment on the first display screen 210A.

[0083] If the reliability of the person is determined to be above the first threshold Ta in step S108, the impersonation detection step is completed.

[0084] Figure 7 This is a flowchart showing the steps I confirmed. (Refer to...) Figure 1 , Figures 4 to 5 as well as Figure 7The operator PC 200 (display control unit 531) causes the display unit 210 to display the second display screen 210B (S111). In this step, the operator accepts the instruction displayed in the second instruction image unit 216B and changes the orientation of their face from a direction different from the front to the front.

[0085] Next, the operator PC 200 (camera control unit 532) takes a picture of the operator. The operator PC 200 (transmission unit 230) sends the obtained second photographic image 252 to the face comparison server 400 (S112).

[0086] The face comparison server 400 (reliability calculation unit 420) calculates the reliability (personal reliability) that the face of the operator in the second photographic image 252 is the same as the face of the operator in the registration image 256.

[0087] Next, the operator PC 200 (receiving unit 240) receives the identity reliability calculated by the face comparison server 400 (S113). Then, the operator PC 200 (second face authentication determination unit 535) compares the identity reliability calculated by the face comparison server 400 with the second threshold Tb of identity reliability at the time of identity verification, and determines whether the identity reliability is above the second threshold Tb (S114).

[0088] If, in step S114, it is determined that the individual's reliability is less than the second threshold Tb, the operator PC 200 determines whether a certain amount of time has elapsed since the start of the step confirmed by the individual (S115).

[0089] If it is determined in step S115 that a certain amount of time has not elapsed, the process returns to step S112. If it is determined in step S115 that a certain amount of time has elapsed, the process returns to step S111, and the operator PC 200 (display control unit 531) displays an unacceptable comment on the second display screen 210B.

[0090] If, in step S114, the user's reliability is determined to be above the second threshold Tb, the user's confirmation step is completed. The operator PC 200 ultimately verifies the user's own authentication.

[0091] Furthermore, the order of the steps for impersonation detection and the steps for personal confirmation described above can also be reversed.

[0092] In summary, the above description outlines the structure of the self-authentication system, self-authentication method, and program in the embodiments of the present invention.

[0093] The self-authentication system 100 in this embodiment includes: a camera 260 for capturing images of an operator as the subject; and an operator PC 200 as an information processing device that performs authentication of the operator's identity based on photographic images of the operator captured by the camera 260. The operator PC 200 includes: a first processing unit 510 that determines the movement of the operator's face based on first photographic images 251 continuously captured by the camera 260, showing the operator's face orientation changing from a frontal view to a different direction, and performs facial authentication of the operator based on the first photographic images 251 and a pre-registered registration image 256 of the operator; and a second processing unit 520 that performs facial authentication of the operator based on the registration image 256 and a second photographic image 252 of the operator captured by the camera 260.

[0094] Furthermore, the self-authentication method in this embodiment is a self-authentication method that verifies the operator's identity based on photographic images of the operator as the subject. The self-authentication method includes the following steps: step (S104), obtaining a first photographic image 251 by continuously photographing the operator changing the orientation of their face from a frontal view to a different direction; steps (S106, S108), determining the movement of the operator's face based on the first photographic image 251, and performing facial authentication of the operator based on the first photographic image 251 and a pre-registered registration image 256 of the operator; step (S112), obtaining a second photographic image 252 by photographing the operator; and step (S114), performing facial authentication of the operator based on the second photographic image 252 and the registration image 256.

[0095] Furthermore, the program in this embodiment executes a program on the operator PC 200, an information processing device, to authenticate the operator's identity based on a photographic image of the operator as the subject. The program causes the operator PC 200 to perform the following steps: steps (S106, S108), determining the movement of the operator's face based on a first photographic image 251 of the operator whose facial orientation changes from a frontal view to a different direction, and performing facial authentication of the operator based on the first photographic image 251 and a pre-registered registration image 256 of the operator; and step (S114), performing facial authentication of the operator based on a second photographic image 252 of the operator and the registration image 256.

[0096] Programs can also be recorded on computer-readable storage media. Computer-readable storage media can also be non-transitory computer-readable storage media.

[0097] Based on this structure, by determining the movement of the operator's face based on a first photographic image 251 showing the operator changing their facial orientation from a frontal view to a different direction, it can be confirmed that the operator in the first photographic image 251 is not impersonating someone else using a photograph. During this impersonation detection, facial authentication of the operator is performed based on the first photographic image 251 and a pre-registered registration image 256 of the operator, thus confirming that it is not someone else who performed the aforementioned facial movement change. Furthermore, facial authentication of the operator is performed based on a second photographic image 252 showing the operator facing forward and the registration image 256, thus confirming that the operator is indeed the person in question. Through these methods, accurate identification of the operator's identity can be performed.

[0098] Furthermore, the second threshold Tb used in facial authentication for identity verification is greater than the first threshold Ta used in facial authentication for impersonation detection. Based on this structure, a lower first threshold Ta is used in facial authentication using a first photographic image 251 facing a direction different from the front during impersonation detection, while a higher second threshold Tb is used in facial authentication using a second photographic image 252 for identity verification, thereby enabling more accurate identity verification.

[0099] Furthermore, during impersonation detection, the first processing unit 510 displays the direction in which the operator changes the orientation of their face on the display unit 210. With this structure, the operator is prompted to change the orientation of their face by the display on the display unit 210, thereby enabling the impersonation detection process to proceed smoothly.

[0100] Furthermore, this embodiment describes the application of the personal authentication system, method, and program of the present invention to the personal authentication of an operator performing maintenance on machine tool 600, but the present invention is not limited thereto. The present invention can be applied, for example, to personal authentication accompanying the unlocking of various doors, or to personal authentication accompanying the unlocking of computer access, etc.

[0101] The embodiments disclosed herein should be considered illustrative rather than restrictive in all respects. The scope of the invention is set forth not by the foregoing description but by the claims, and is intended to include all modifications within the meaning and scope equivalent to the claims.

[0102] Explanation of reference numerals in the attached figures

[0103] 100: Personal authentication system; 200: Operator PC; 210: Display unit; 210A: First display screen; 210B: Second display screen; 211A: First photographic image unit; 211B: Second photographic image unit; 212: Note annotation unit; 216A: First instruction image unit; 216B: Second instruction image unit; 217A: First illustration column; 217B: Second illustration column; 218A: First annotation column; 218B: Second annotation column; 220: Operation unit; 230: Transmitting unit; 240: Receiving unit; 251: First photographic image; 252: Second photographic image; 256: Registration Image recording; 260: Camera; 300: Personal authentication management server; 400: Face comparison server; 410: Angle calculation unit; 420: Reliability calculation unit; 430: Feature storage unit; 510: First processing unit; 520: Second processing unit; 531: Display control unit; 532: Camera control unit; 533: Motion determination unit; 534: First face authentication determination unit; 535: Second face authentication determination unit; 560: Storage unit; 561: Personal information; 600: Machine tool; 610: Operation panel; 620: Recording medium; Ta: First threshold; Tb: Second threshold; t: Threshold.

Claims

1. A personal authentication system, comprising: A camera, which is used to photograph a subject; and An information processing device that performs authentication of the subject based on photographic images of the subject captured by the camera. in, The information processing device includes: The first processing unit determines the movement of the subject's face based on first photographic images of the subject continuously captured by the camera, in which the orientation of the face changes from a frontal view to a direction different from a frontal view, and performs facial authentication of the subject based on the first photographic images and pre-registered registration images of the subject; and The second processing unit performs facial authentication of the subject based on the registered image and a second photographic image of the subject captured by the camera.

2. The personal authentication system according to claim 1, wherein, If the reliability that the subject in the first photographed image is the same person as the subject in the registered image is above a first threshold, the first processing unit confirms the subject's facial authentication. If the reliability that the subject in the second photographed image is the same person as the subject in the registered image is greater than a second threshold that is greater than the first threshold, the second processing unit confirms the subject's facial authentication.

3. The personal authentication system according to claim 1 or 2, wherein, It also includes a display unit capable of displaying objects captured by the camera. The first processing unit causes the display unit to display the direction in which the subject's face changes orientation.

4. A method for verifying identity, which verifies the identity of the subject based on a photographic image of the subject, the method comprising the following steps: A first photographic image is obtained by continuously photographing a subject whose face orientation changes from frontal to a different direction. The movement of the subject's face is determined based on the first photographed image, and facial authentication of the subject is performed based on the first photographed image and the pre-registered image of the subject. A second photographic image is obtained by photographing the subject. as well as Facial authentication of the subject is performed based on the second photographic image and the registration image.

5. A program, which is a program for an information processing device, wherein, The information processing device performs authentication of the subject based on the photographic image of the subject. The program causes the information processing device to perform the following steps: The movement of the subject's face is determined based on a first photographic image of the subject whose face orientation changes from front to a direction different from front, and the subject's face is authenticated based on the first photographic image and a pre-registered image of the subject. as well as Facial authentication of the subject is performed based on a second photographic image of the subject and the registration image.

Images