JP2010218039A - System and method for authenticating face - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a face authentication system capable of surely performing an authentication while hardly impairing the convenience of the authentication using a moving image. <P>SOLUTION: A face authentication system includes: a detection part 111 for detecting an authentication candidate; an image pickup part 112 for picking up the image of the detected authentication candidate, and for generating moving image data; a feature extraction part 122 for generating feature information by extracting the features of the face of the authentication candidate based on the moving image data; an authentication part 123 for performing face authentication based on the feature information; and a guidance part 113 for guiding the authentication candidate to turn his or her face to the direction of the image pickup means in a prescribed time or more when the feature of the face of the authentication candidate can not be extracted by the feature extraction means. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a face authentication system and a face authentication method.

  A face authentication system that uses a moving image (video) has a feature that it allows a certain amount of movement of the person to be authenticated and changes in facial expressions, and is more difficult to impersonate than a face authentication system that uses still images.

  However, if the person to be authenticated does not turn his face to the camera, the authentication cannot be performed both in the case of using a moving image and in the case of using a still image.

  As a conventional method of directing the face of the person to be authenticated to the camera, there is a method of giving a physical action that induces reflex behavior (see, for example, Patent Document 1).

JP-A-2005-94710

  The method described in Patent Literature 1 expects the face to face the direction of the camera as a result of the action of the person to be authenticated reflexively with respect to the physical action, and can perform face authentication. Although it has a possibility of increasing the probability, it does not ensure face authentication. In other words, with this method, it is not expected to continuously face the camera for the time required for authentication.

  On the other hand, in order to reliably perform face authentication, requesting the authentication target person to take a predetermined posture with respect to the authentication target deteriorates the convenience of authentication using moving images. Is.

  Therefore, an object of the present invention is to provide a face authentication system that can reliably perform face authentication without substantially impairing the convenience of the person to be authenticated.

  A face authentication system according to an aspect of the present invention includes a detection unit that detects a person to be authenticated, an image pickup unit that captures an image of the person to be detected detected by the detection unit and generates moving image data, and the moving image data The feature extraction means for extracting the feature of the face of the person to be authenticated based on the above and generating feature information, the authentication means for performing authentication based on the feature information, and the feature of the face of the person to be authenticated by the feature extraction means And a guiding unit that guides the person to be authenticated to face the face toward the image capturing unit for a predetermined time or longer when extraction is not possible.

  According to the present invention, when the feature of the face of the person to be authenticated cannot be extracted, the face is guided to face the imaging means for a predetermined time or more, and when the feature can be extracted , No action is required on the subject of authentication. For this reason, face authentication can be reliably performed without substantially impairing the convenience of the person to be authenticated.

It is a block diagram which shows schematic structure of the authentication system which concerns on the 1st Embodiment of this invention. It is a block diagram which shows schematic structure of the authentication system which concerns on the 2nd Embodiment of this invention. It is a flowchart for demonstrating operation | movement of the authentication system of FIG.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

  FIG. 1 is a block diagram showing a schematic configuration of a face authentication system according to the first embodiment of the present invention.

  The illustrated face authentication system includes an authentication device 11, an authentication server 12, and a storage device 13.

  The authentication device 11 includes a detection unit 111, an imaging unit 112, and a guidance unit 113.

  The authentication server 12 includes a control unit 121, a feature extraction unit 122, and an authentication unit 123.

  Furthermore, the storage unit 13 includes an authentication data storage unit 131.

  The authentication device 11 is disposed near an authentication target device such as a locking device, or a part or all of the authentication device 11 is incorporated in the authentication target device.

  The detection unit 111 may be a sensor that detects that there is a person who enters an area assumed to be entered by a person (authentication target person) who operates the authentication target device. Alternatively, the sensor may be a sensor incorporated in a portion (a switch or the like) that is first touched when the authentication target person operates the authentication target device. When detecting the presence of the authentication target person, the detection unit 111 notifies the authentication server 12 that the authentication target person has been detected.

  The imaging unit 112 functions as an imaging unit, and may be a CCD camera, for example. The imaging unit 112 images a predetermined area defined for the authentication target device. This predetermined area is defined as an area assumed to exist when the face of the person to be authenticated attempts to operate the device to be authenticated. Imaging data from the imaging unit 112 is sent to the authentication server 12.

  The guiding unit 113 may include, for example, a display and a speaker. In accordance with an instruction from the authentication server 12, the guiding unit 113 guides the authentication target person by display or sound so that the image of the authentication target person's face is captured by the imaging unit 112.

  The control unit 121 operates according to the control program and controls the entire authentication system. The control program may be stored in the storage device 13. Alternatively, the control program may be stored in a storage device 13 (not shown) built in the authentication server 12. Alternatively, it may be recorded on a recording medium such as a magnetic disk or an optical disk and read by a reading device (not shown) provided in the authentication server 12.

  The control unit 121 causes the imaging data from the imaging unit 112 of the authentication device 11 to be sent to the feature extraction unit 122 in response to the detection notification from the detection unit 111. In addition, the control unit 121 issues a guidance instruction to the guidance unit 113 of the authentication device 11 in response to the feature extraction failure notification from the feature extraction unit 122.

  The feature extraction unit 122 extracts the facial features of the person to be authenticated based on the imaging data from the authentication device 11 and sends the feature information to the authentication unit 123. If the facial features of the person to be authenticated cannot be extracted within a predetermined time, the control unit 121 is notified accordingly.

  The authentication unit 123 performs authentication based on the feature information from the feature extraction unit 122 and the authentication data stored in the authentication data storage unit 131 of the storage device 13. The authentication result is notified to the control unit 121 and sent from the control unit 121 to the authentication target device.

  The authentication data storage unit 131 stores in advance the facial features of one or more registrants as authentication data.

  Next, the operation of the face authentication system in FIG. 1 will be described.

  The detection unit 111 functions as a detection unit, and when detecting the person to be authenticated, notifies the authentication server 12 to that effect.

  The control unit 121 of the authentication server 12 receives the notification of the authentication target person detection from the detection unit 111 of the authentication device 11 and causes the feature extraction unit 122 to capture the image data from the imaging unit 112 of the authentication device 11. In this case, the imaging unit 112 may continuously capture a predetermined area, or may capture an image of the predetermined area in response to an instruction from the control unit 121.

  The feature extraction unit 122 functions as a feature extraction unit under the control of the control unit 121. That is, the feature extraction unit 122 attempts to extract the feature of the face of the person to be authenticated based on the imaging data sequentially transmitted from the imaging unit 112 of the authentication device 11. For example, the feature extraction unit 122 attempts to extract the feature of the face of the person to be authenticated using image frames (a predetermined number of image frames) obtained within a predetermined time. When the feature extraction is successful, the control unit 121 is notified to that effect, and the obtained feature information is passed to the authentication unit 123. On the other hand, if feature extraction has failed, the control unit 121 is notified to that effect.

  The authentication unit 123 functions as an authentication unit under the control of the control device 121. That is, when receiving the feature information from the feature extraction unit 122, the authentication unit 123 collates with authentication data stored in the authentication data storage unit 131 of the storage device 13. If the authentication data stored in the authentication data storage unit 131 includes authentication data that matches the feature information from the feature extraction unit 122 or is determined to match with a predetermined probability, the authentication unit 123 authenticates the authentication data. It judges that it is possible and notifies the control part 121 to that effect. If such authentication data does not exist, the authentication unit 123 determines that authentication is not possible, and notifies the control unit 121 accordingly.

  The control unit 121 sends the authentication result from the authentication unit 123 to the authentication target device. The authentication target device enables or disables the input operation of the authentication target person based on the authentication result from the control unit 121.

  When the feature extraction unit 122 notifies the control unit 121 that the feature cannot be extracted, the control unit 121 issues a guidance instruction to the guidance unit 113 of the authentication device 11.

  The guide unit 113 functions as a guide unit in accordance with instructions from the control unit 121. That is, the guide unit 113 guides the person to be authenticated by display and / or voice so that the face of the person to be authenticated faces the image pickup unit 112. At this time, the face of the person to be authenticated is guided to the imaging unit 112 for a predetermined time or longer so that the authentication can be surely performed. For example, ““ Finished. Please keep on watching the camera until you hear the signal "". Note that the predetermined time is a time during which at least one feature extraction can be attempted (a time required to obtain a predetermined number of image frames and execute the feature extraction operation). The predetermined time is a time during which feature extraction can be attempted a plurality of times if possible.

  The feature extraction unit 122 repeats the feature extraction operation even after notifying the control unit 121 that the feature cannot be extracted. Accordingly, there is a possibility that facial features can be extracted before the person to be authenticated turns his face to the camera in response to guidance by the guidance unit 113.

  If the feature extraction unit 122 succeeds in feature extraction as a result of guidance by the guidance unit 113 or before that, the control unit 121 is notified of this and feature information is sent to the authentication unit 123. As described above, the authentication unit 123 performs an authentication process based on the feature information.

  In response to the notification of the successful feature extraction from the feature extraction unit 122, the control unit 121 instructs the guidance unit 113 to end guidance. In response to the instruction to terminate the guidance, the guidance unit 113 functions as a completion notification unit. For example, the guiding unit 113 sends a message such as “finished”. Thereafter, depending on the authentication result, the operation of the device to be authenticated is enabled or disabled.

  As described above, according to the present embodiment, authentication is normally performed without causing the person to be authenticated to take a special attitude, so that the convenience of the authentication system using moving images is hardly impaired. On the other hand, if facial feature extraction cannot be performed within a predetermined time, the face is directed to the imaging unit 112 for a predetermined time or longer (for example, by specifying the end time) required for feature extraction. Authentication can be performed reliably.

  In the above embodiment, the authentication server 11 notifies the authentication server 12 that the authentication target person has been detected. However, if the authentication apparatus 11 detects the authentication target person, the authentication server 21 captures the captured image data. You may make it send to.

  In the above embodiment, it has been described that the authentication server 12 includes the control unit 121, the feature extraction unit 122, and the authentication unit 123. However, when the computer executes the control program, the control unit 121 and the feature extraction unit 122 are executed. The authentication unit 123 may be operated.

  Next, an authentication system according to the second embodiment of the present invention will be described with reference to FIG.

  The authentication system in FIG. 2 requires an authentication server 21 that operates under program control, a storage device 22 that stores programs and information necessary for the operation of the authentication server 21, an authentication device 23, and authentication information of the person performing the operation. And an authentication target device 24 such as an entrance / exit management device. The authentication server 21, the authentication device 23, and the authentication target device 24 are connected via a wireless or wired network 25.

  In FIG. 2, one authentication device 23 and one authentication target device 24 are shown, but a plurality of these devices may exist. Usually, the authentication device 23 and the authentication target device 24 correspond one-to-one, but a plurality of authentication devices 23 (a plurality of cameras 234) may be provided for one authentication target device 24. In any case, each of the authentication target devices 24 is associated with at least one authentication device 23, and each authentication device 23 is configured so that the associated authentication target device 24 and the face of the person who operates the device are reflected on the camera. Be placed.

  The authentication server 21 includes a communication control unit 211, a video analysis unit 212, a face recognition execution unit 213, an authentication management unit 214, and an authentication guidance control unit 215.

  The communication control unit 211 receives video data (imaging data) from the authentication device 23, transmits an authentication guidance instruction and authentication completion notification to the authentication device 23, receives an authentication request from the authentication target device 24, and authenticates. An authentication guidance instruction to the target device 24 and transmission of an authentication completion notification are realized.

  The video analysis unit 212 functions as a feature extraction unit. That is, the video analysis unit 212 analyzes the video data from the authentication device 23, identifies the person located in the place where the authentication target device 24 that has issued the authentication request is most easily operated as the authentication target person, and sees the face. If so, the feature of the face is extracted and the feature information is notified to the authentication management unit 214. On the other hand, if the face of the person to be identified is not visible in the transmitted video data and the facial features cannot be extracted, the video analysis unit 212 notifies the authentication management unit 214 that authentication is impossible, and then The video data is monitored, and when the face of the person to be authenticated is seen, the facial feature is extracted and the feature information is notified to the authentication management unit 214. When video data from a plurality of authentication devices 23 exists, the video analysis unit 212 selects video data that best reflects the face of the person to be authenticated. In this case, the authentication management unit 214 is also notified of information for identifying the authentication device 23 that is the transmission source of the selected video data (selected authentication device identification information).

  The face recognition execution unit 213 functions as an authentication unit. That is, the face recognition execution unit 213 performs face recognition using the feature information from the video analysis unit 212 received via the authentication management unit 214 and the face recognition data stored in the storage unit 22, and performs authentication. It is determined whether or not the target person is a registered person.

  The authentication management unit 214 receives an authentication request from the authentication target device 24 via the communication control unit 211. Upon receiving the authentication request, the authentication management unit 214 notifies the video analysis unit 212 of information for identifying the authentication target device 24 that has issued the authentication request, and one or more authentication devices 23 corresponding to the authentication target device 24. Analyzing video data from. Thereafter, if there is a notification that authentication is impossible from the video analysis unit 212, the authentication management unit 214 instructs the authentication guidance control unit 215 to execute authentication guidance. When the selective authentication device identification information is sent from the video analysis unit 212, the authentication management unit 214 also sends the information to the authentication guidance control unit 215. Also, when feature information is sent from the video analysis unit 212, the authentication management unit 214 sends the feature information to the face recognition execution unit 213 and instructs execution of face recognition.

  The authentication guidance control unit 215 creates authentication guidance instructions and authentication completion notifications corresponding to the authentication device 23 and the authentication target device 24, respectively, and transmits them through the authentication management unit 214 and the communication control unit 211. The authentication guidance instruction and the authentication completion notification are created based on the authentication guidance data stored in the storage device 22. When there are a plurality of authentication devices 23 corresponding to the authentication target device 24 that has issued the authentication request, an authentication guidance instruction and an authentication completion notification are transmitted to the plurality of authentication devices 23.

  The storage device 22 includes a face recognition data storage unit 221 and an authentication guidance data storage unit 222.

  The face recognition data storage unit 221 stores in advance feature information of a person's face that needs to be authenticated.

  The authentication guidance data storage unit 222 is an authentication guidance method according to voice information and display information for authentication guidance executed by the speaker 235 and the display device 236 of the authentication device 23, functions of the user interface unit 243 of the authentication target device 24, and the like. Information for is stored in advance.

  The authentication device 23 includes a communication control unit 231, a video transmission control unit 232, a guidance execution unit 233, a camera 234, a speaker 235, and a display 236.

  The communication control unit 231 transmits video data to the authentication server 21 and receives an authentication guidance instruction and an authentication completion notification from the authentication server 21.

  The video transmission control unit 232 controls the camera 234 to image the authentication target device 24 and the authentication target person, and sends the video data to the authentication server 21 via the communication control unit 231.

  The guidance execution unit 233 functions as a guidance unit and a completion notification unit together with the speaker 235 and the display 236. The guidance execution unit 233 causes the speaker 235 to output sound in accordance with the authentication guidance instruction from the authentication server 21 and the authentication completion notification, and displays a message or the like on the display 236.

  The camera 234 functions as an imaging unit. That is, the camera 234 images the authentication target device 24 and the authentication target person, and outputs video data.

  The speaker 235 outputs a sound corresponding to the authentication guidance instruction and the authentication completion notification under the control of the guidance execution unit 233.

  The display device 236 performs display according to the authentication guidance instruction and the authentication completion notification under the control of the guidance execution unit 233.

  The authentication target device 24 includes a communication control unit 241, an authentication information control unit 242, a user interface unit 243, and a device control unit 244.

  The communication control unit 241 transmits an authentication request to the authentication server 21 and receives an authentication guidance instruction and an authentication completion notification from the authentication server 21.

  The authentication information control unit 242 functions as a detection unit alone or together with the user interface unit 243. The authentication information control unit 242 detects that the user interface unit 243 has been operated or that a person has entered the operable area, creates an authentication request, and sends it to the authentication server 21 via the communication control unit 241. Further, the authentication information control unit 242 receives an authentication completion notification from the authentication server 21 via the communication control unit 241, thereby receiving authentication information of the operator or the operable area intruder. Further, the authentication information control unit 242 receives an authentication guidance instruction from the authentication server 21 via the communication control unit 241. In this case, the authentication information control unit 242 instructs the user interface unit 243 according to the authentication guidance instruction.

  The user interface unit 243 includes an input panel such as an operation panel for operating the authentication target device 24, a sensor that detects intrusion into the operable area, and an output function such as a display, a lamp, and a speaker that notify the device status and message. have. The functions provided differ depending on the type of the authentication target device 24.

  The device control unit 244 controls the range of functions realized by the operation of the user interface unit 243 based on the authentication information obtained by the authentication information control unit 242.

  Next, the operation of the authentication system of FIG. 1 will be described in detail with reference to FIG. 2 in addition to FIG.

  When there is an input operation (step S301), the user interface unit 243 of the authentication target device 24 detects it and makes an authentication request (step S302). The authentication request is made to the authentication server 21 via the communication control unit 241.

  The user interface unit 243 may detect that a person has entered the predetermined area instead of detecting the input operation. In this case, the predetermined area is determined so as to include an area having a high probability that a person who intends to operate the authentication target device 24 exists.

  After making the authentication request, the user interface unit 243 suspends execution of the input operation until the authentication is completed.

  In the authentication server 21, the authentication management unit 214 receives an authentication request from the authentication target device 24 via the communication control unit 211, and information for identifying the authentication target device 24 that has issued the authentication request to the video analysis unit 212. give.

  Based on the information for identifying the authentication target device 24 given from the authentication management unit 214, the video analysis unit 212 sends one or more authentication devices 23 associated with the authentication target device 24 that transmitted the authentication request to the authentication device 23. A request is made to transmit video data via the communication control unit 211 (step S303).

  In the authentication device 23, when the video transmission control unit 232 receives a video data request from the authentication server 21 via the communication control unit 231, the video transmission control unit 232 controls the camera 234 to capture the authentication target device 24 and its surroundings and create video data. To do. Then, the video transmission control unit 232 sends the created video data to the authentication server 21 via the communication control unit 231 (step S304). Video data is sent in real time.

  Note that the video data from the authentication device 23 may be sent to the authentication server 21 at all times instead of being sent only when necessary in response to a request from the authentication server 21 as described above. In this case, video data from the authentication device 23 associated with the authentication target device 24 that has issued the authentication request on the authentication server 21 side is selected.

  When the video analysis unit 212 receives the video data transmitted from the authentication device 23 via the communication control unit 211, the video analysis unit 212 performs video analysis. Then, a person who is located in a place where the authentication target device 24 that has issued the authentication request is most easily operated is detected as an authentication target person (step S305). Furthermore, the video analysis unit 212 attempts to extract the feature of the detected face of the person to be authenticated (step S306). At this time, when using video data from two or more authentication devices 23, the video that is most likely to show the face of the person to be authenticated is selected.

  In the case where the facial features cannot be extracted (NO in step S306), such as when the authentication target person bends in front of the authentication target device 24 and the face cannot be captured by the camera 234 (NO in step S306), the video analysis unit 212 does not authenticate. The authentication management unit 214 is notified of the possibility together with information for identifying the authentication device 23 that is the transmission source of the video data. Thereafter, the video analysis unit 212 monitors the video data (it repeatedly tries to extract facial features).

  Upon receiving the authentication impossible notification from the video analysis unit 212, the authentication management unit 214 instructs the authentication guidance control unit 215 to execute authentication guidance.

  Upon receiving the authentication guidance execution instruction from the authentication management unit 214, the authentication guidance control unit 215 authenticates the authentication target device 24 that has issued the authentication request and the authentication device 23 that is the transmission source of the selected video data. Create instructions. The creation of the authentication guidance instruction is performed based on the authentication guidance data stored in the storage device 22 so as to be compatible with the authentication target device 24 and the authentication device 23 that are the targets of the instruction. The created authentication guidance instruction is transmitted to the authentication target device 24 and the authentication device 23 via the authentication management unit 214 and the communication control unit 211 (step S307).

  In the authentication device 23, when an authentication guidance instruction is sent from the authentication server 21, the authentication guidance instruction received by the communication control unit 231 is delivered to the guidance execution unit 233. In accordance with the received authentication guidance instruction, the guidance execution unit 233 emits sound from the speaker 235 and displays a message or the like on the display 236 (step S308A).

  In the authentication target device 24, when an authentication guidance instruction is sent from the authentication server 21, the authentication guidance instruction received by the communication control unit 241 is delivered to the authentication information control unit 242. The authentication information control unit 242 performs voice output and message display from the user interface unit 243 in accordance with the received authentication guidance instruction (step S308B).

  For authentication guidance, for example, the authentication device 23 is installed on the clock, and the message “What is the picture coming out on the clock?” Or “Look here until the chime rings!” Etc. In any case, the face of the person to be authenticated is directed toward the camera 234, and the face orientation is maintained to some extent until a next signal is given. If the person to be authenticated is looking at the direction of the clock or sound while waiting for the next output, a face appears on the camera 234 (step S309).

  The authentication device 23 continues to transmit the video data from step S304, and the video data obtained by capturing the face of the person to be authenticated is sent to the authentication server 21 by the authentication guidance operation (step S310).

  In the authentication server 21, since the video analysis unit 212 includes the information of the face of the person to be authenticated in the monitored video data, the face feature of the person to be authenticated is successfully extracted (YES in step S306). . The video analysis unit 212 notifies the facial feature information to the authentication management unit 214.

  Upon obtaining the facial feature information, the authentication management unit 214 instructs the face recognition execution unit 213 to execute face recognition. The face recognition execution unit 213 executes face recognition based on the facial feature information passed from the authentication management unit 214 and the face recognition data stored in the face authentication data storage unit 221 of the storage device 22, and performs authentication. It is determined (authenticated) whether the person corresponds to the registered person (step S311).

  The authentication management unit 214 passes the authentication result to the authentication guidance control unit 215. At this time, predetermined information regarding a registered person included in the face authentication data may be added. By doing so, the operation restriction (function restriction) of the authentication target device 24 can be performed for each registrant.

  The authentication guidance control unit 215 creates an authentication completion notification based on the authentication result. Based on the authentication guidance data stored in the authentication guidance data storage unit 222, the authentication guidance control unit 215 is adapted to the authentication target device 24 that has issued the authentication request and the authentication device 23 that has transmitted the selected video data. Create an authentication completion notification. The created authentication completion notification is transmitted to the authentication target device 24 and the authentication device 23 via the authentication management unit 214 and the communication control unit 211 (step S312).

  When the guidance execution unit 233 of the authentication device 23 receives the authentication completion notification from the authentication server 21 via the communication control unit 231, in accordance with the received authentication completion notification, the guidance execution unit 233 notifies the speaker 235 or the display 236 of the authentication completion, The display is output (step S313). For example, the authentication completion notification may be displayed on the display 236 of the authentication device 23 on the clock by displaying a mark determined for each person to be authenticated or an image of the face of the person to be authenticated, or sounding a completion chime. Done. If authentication guidance has been performed, the voice or display corresponding to the authentication guidance is used. Thereby, from step S309, the person to be authenticated who has been waiting for something to come out can know that his / her authentication has been completed by listening to the display and voice. Even if the person to be authenticated does not understand the intention of the authentication, the authentication can be completed simply by waiting for something to be output in accordance with the display or voice of the authentication guide (step S314).

  Upon receiving the authentication completion notification from the authentication server 21, the authentication information control unit 242 of the authentication target device 24 instructs the device control unit 244 to validate or invalidate the input operation of the authentication target device 24. When the authentication completion notification includes predetermined information related to the registered person, the authentication information control unit 242 instructs the device control unit 244 to limit the function of the authentication target device 24 accordingly.

  In response to an instruction from the authentication information control unit 242, the device control unit 244 enables or disables the operation that has been suspended in steps S301 and S302. If the authentication target person is authenticated by the authentication server 21 as a registrant, the use of the authentication target device 24 is permitted within the permitted function range (step S316).

  As mentioned above, although this invention was demonstrated according to some embodiment, this invention is not limited to the said embodiment, A various change and deformation | transformation are possible without deviating from the scope of the present invention. It is. For example, in the second embodiment, the authentication device 23 and the authentication target device 24 are separate, but the authentication device 23 may be incorporated in the authentication target device 24.

DESCRIPTION OF SYMBOLS 11 Authentication apparatus 12 Authentication server 13 Storage apparatus 21 Authentication server 22 Storage apparatus 23 Authentication apparatus 24 Authentication object apparatus 25 Network 111 Detection part 112 Imaging part 113 Guidance part 121 Control part 122 Feature extraction part 123 Authentication part 131 Authentication data storage part 211 Communication Control unit 212 Video analysis unit 213 Face recognition execution unit 214 Authentication management unit 215 Authentication guidance control unit 221 Face recognition data storage unit 222 Authentication guidance data storage unit 231 Communication control unit 232 Video transmission control unit 233 Guidance execution unit 234 Camera 235 Speaker 236 Display 241 Communication control unit 242 Authentication information control unit 243 User interface unit 244 Device control unit

Claims (8)

A detecting means for detecting a person to be authenticated;
Imaging means for imaging the authentication subject detected by the detection means and generating moving image data;
Feature extraction means for extracting features of the face of the person to be authenticated based on the moving image data and generating feature information;
Authentication means for performing authentication based on the feature information;
Guidance means for guiding the authentication target person to turn the face toward the imaging means for a predetermined time or more when the feature extraction means cannot extract the facial feature of the authentication target person;
A face authentication system characterized by comprising:   2. The face authentication system according to claim 1, wherein the guidance unit includes a completion notification unit that notifies completion of feature extraction of the face of the person to be authenticated by the feature extraction unit or completion of authentication by the authentication unit. An authentication target device that operates based on an authentication result by the authentication unit;
An authentication device including the imaging means and the guidance means;
An authentication server including the feature extraction unit, the authentication unit, and the control unit;
The face authentication system according to claim 1, wherein the face recognition systems are interconnected via a network.   The face authentication system according to claim 1, further comprising a storage unit that stores authentication data used for authentication by the authentication unit. Detecting a person to be authenticated;
Imaging the detected person to be detected and generating moving image data;
Extracting facial features of the person to be authenticated based on the moving image data and generating feature information;
Authenticating based on the feature information;
Guiding the authentication target person to turn the face toward the imaging unit for a predetermined time or more when the feature extraction unit cannot extract the feature of the face of the authentication target person;
A face authentication method comprising:   Including notifying the authentication target person that the face is directed toward the imaging means for a predetermined time or more, and then notifying completion of facial feature extraction or authentication completion of the authentication target person, The face authentication method according to claim 5. Receiving a notification that the person to be authenticated has been detected, and obtaining moving image data obtained by imaging the person to be authenticated;
Extracting facial features of the person to be authenticated based on the moving image data and generating feature information;
Authenticating based on the feature information;
Instructing the guidance unit to direct the face of the person to be authenticated toward the image pickup means for a predetermined time or more when the feature extraction means cannot extract the feature of the face of the person to be authenticated. When,
A program that causes a computer to execute.   The guidance unit is instructed to notify the person to be authenticated that the face is directed toward the imaging unit for a predetermined time or more, and then notify the completion of feature extraction or authentication completion of the person to be authenticated. 8. The program according to claim 7, which causes a computer to execute the steps.

Images