JP2018166014A - Face detection device and face detection method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent, when detecting a face from an image including a person, erroneously detection of an object other than the person as the face of a living body.SOLUTION: A face detection device 1 comprises: an image input part 3 that receives input of temporally continuous picked-up images including a person H; a face area detection part 4 that detects one or more face areas in the picked-up images; a vital information extraction part 8 that extracts vital information including an index indicating a living state of the faces picked up in the face areas on the basis of image data on the face areas; and a vital determination part 9 that determines whether or not the faces in the face areas are in the living state on the basis of the vital information. The face area detection part 4 recognizes, of the one or more face areas, the face area corresponding to the face determined to be in the living state by the vital determination part 9, as a face area based on a living body.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a face detection device, a face detection system, and a face detection method for detecting a face from an image including a person.

  Conventionally, in fields such as photography using digital cameras and authentication, face detection technology that detects the position of a face from a photographed image has been used, and various processes can be performed based on the face detection results. It has become.

  For example, regarding camera shooting, a video camera with an automatic camera platform that can automatically move the camera direction and shoot a subject at a predetermined screen position by detecting the position of the face of the subject, By detecting the face of the subject included in the image and displaying a trimmed image obtained by cutting out the area including the detected face in a predetermined position on the image displayed on the display unit, the photographer can select the main subject. There is known an imaging apparatus that makes it possible to easily designate the image (see Patent Document 1 and Patent Document 2).

  In addition, for example, for authentication, a template having been prepared in advance is obtained as a correlation value while moving in the image, so that the region having the highest correlation value is detected as the face region of the person to be verified, and the detected verification target There is known a face matching apparatus that performs personal authentication by combining face matching based on a person's face image and face matching based on a human face temperature distribution (see Patent Document 3).

JP-A-8-294038 JP2013-150265A JP 2005-115460 A

  By the way, in the related art as described in Patent Document 1-2, when acquiring (capturing) an image as a face detection target, an object having characteristics similar to a human face around the subject (for example, If there is a photograph of a face affixed to the wall behind the subject or the face of a doll placed on the subject's side, the object may be erroneously detected as a human face.

  On the other hand, as in the prior art described in Patent Document 3, whether or not an object having a form similar to a human face is a person's face is determined by a dedicated sensor or the like. However, there is a possibility that the apparatus configuration becomes complicated and the apparatus cost increases.

  The present invention has been devised in view of the problems of the prior art, and prevents a false detection of an object other than a person as a biological face when detecting a face from an image including a person. A main object is to provide a face detection device, a face detection system, and a face detection method.

  The face detection device of the present invention is a face detection device that detects a face from an image including a person, and includes an image input unit to which a temporally continuous captured image including the person is input, and one or more in the captured image A face area detection unit that detects a face area of the face, a vital information extraction unit that extracts vital information including an index indicating a living state of a face imaged in the face area based on image data relating to the face area, A vital determination unit that determines whether or not the face in the face region is alive based on the vital information, and the facial region detection unit includes the vital determination among the one or more facial regions. A face area corresponding to the face determined to be alive by a part is recognized as a face area based on a living body.

  According to the present invention, when a face is detected from an image including a person, it is possible to prevent an object other than the person from being erroneously detected as a biological face.

Functional block diagram of the face detection apparatus according to the first embodiment Explanatory drawing which shows the 1st example of the face detection target by the face area detection part which concerns on 1st Embodiment. Explanatory drawing which shows the 2nd example of the face detection object by the face area detection part which concerns on 1st Embodiment. Explanatory drawing of the vital information extraction process by the vital information extraction part which concerns on 1st Embodiment The flowchart which shows the flow of the process by the face detection apparatus which concerns on 1st Embodiment. Overall configuration diagram of a face detection system according to a second embodiment Functional block diagram of a face detection system according to the second embodiment The flowchart which shows the flow of the process by the face detection apparatus which concerns on 2nd Embodiment.

  A first invention made to solve the above-described problem is a face detection device that detects a face from an image including a person, and an image input unit to which a captured image including the person is input in time. Extracting vital information including a face area detection unit that detects one or more face areas in the captured image, and an index indicating an alive state of the face imaged in the face area based on image data related to the face area A vital information extraction unit that determines whether the face in the face region is alive based on the vital information, and the face region detection unit includes the one or more face information detection units. Of the face areas, the face area corresponding to the face determined to be alive by the vital determination unit is recognized as a face area based on a living body.

  According to the face detection device according to the first aspect of the present invention, the face area corresponding to the face determined to be alive among the one or more face areas included in the captured image is set as the face area based on the living body. Since the recognition configuration is adopted, when a face is detected from an image including a person, it is possible to prevent an object other than the person from being erroneously detected as a biological face.

  Further, in the second invention, in the first invention, the vital information extraction unit estimates a pulse stay in the face imaged in the face area based on image data relating to the face area, and estimates the estimated value. It is characterized by extracting a pulse stay as the vital information.

  According to the face detection device according to the second aspect of the present invention, since it is determined based on the pulse whether the face in the face area is alive or not, the face area based on the living body can be determined with a simple configuration. It becomes possible to recognize.

  In a third aspect of the present invention, in the first or second aspect of the present invention, the display device further includes a display unit that displays the captured image, and the face region detection unit is configured to display the captured image displayed on the display unit. In the one or more face areas, image processing is performed to allow a user to identify a face area based on the living body and another face area.

  According to the face detection device according to the third aspect of the invention, the user can easily recognize the face area based on the living body, and as a result, the user can perform a desired operation on the face area based on the living body. Can be executed.

  According to a fourth aspect of the present invention, in any one of the first to third aspects of the present invention, the apparatus further comprises a face matching unit that matches face feature amounts in the face region with pre-registered face information. The unit performs the matching only on the face determined to be alive by the vital determination unit.

  According to the face detection device of the fourth aspect of the present invention, since face matching is performed only on a face (image) based on a living body, matching is performed on a face that is not based on a living body. It is possible to prevent the occurrence of erroneous authentication.

  According to a fifth aspect of the present invention, in any one of the first to third aspects of the present invention, the apparatus further comprises a face collation unit that collates face feature amounts in the face area with pre-registered face information. The unit makes the result of the collation invalid or inconsistent with respect to the face determined not to be alive by the vital determination unit.

  According to the face detection device of the fifth aspect of the invention, the verification result regarding the face (image) that is not based on the living body is made invalid or inconsistent, so that erroneous authentication based on the matching result for the face that is not based on the living body is generated. It becomes possible to prevent.

  The sixth invention includes the face detection device according to any one of the first to fifth inventions, and a camera that inputs the captured image to the face detection device. It is a face detection system.

  According to the face detection system of the sixth aspect of the present invention, the face area corresponding to the face determined to be alive among the one or more face areas included in the captured image is set as the face area based on the living body. Since the recognition configuration is adopted, when a face is detected from an image including a person, it is possible to prevent an object other than the person from being erroneously detected as a biological face.

  According to a seventh aspect of the present invention, there is provided a face detection method for detecting a face from a captured image including a person, an image input step in which a temporally continuous captured image including the person is input, and 1 in the captured image A face area detecting step for detecting the face area, and a vital information extracting step for extracting vital information including an index indicating a state in which the face imaged in the face area is alive based on image data relating to the face area; And a vital determination step for determining whether or not the face in the face area is alive based on the vital information, wherein the face area detection step includes the one or more of the one or more face areas. Recognizing a face area corresponding to the face determined to be alive in the vital determination step as a face area based on a living body

  According to the face detection method according to the seventh aspect of the present invention, the face area corresponding to the face determined to be alive among the one or more face areas included in the captured image is set as the face area based on the living body. Since the recognition configuration is adopted, when a face is detected from an image including a person, it is possible to prevent an object other than the person from being erroneously detected as a biological face.

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

(First embodiment)
FIG. 1 is a functional block diagram of the face detection apparatus 1 according to the first embodiment of the present invention. FIGS. 2 and 3 are diagrams illustrating first and second examples of face detection targets by the face area detection unit 4, respectively. FIG. 4 is an explanatory diagram of vital information extraction processing by the vital information extraction unit 8.

  As shown in FIG. 1, the face detection device 1 includes an imaging unit 2 that captures at least a face of a person as a subject, an image input unit 3 that receives a video signal from the imaging unit 2, and one or more of these captured images. Focus control for controlling the operation of a focus mechanism (not shown) including an optical system for inputting image light to the imaging unit 2 based on a detection result of the face region detection unit 4 for detecting the face region A display unit 6 for displaying a captured image input to the image input unit 3 and a face detection result by the face area detection unit 4; and an image storage unit 7 for storing the captured image.

  Furthermore, the face detection device 1 is configured to prevent an object other than a person from being erroneously detected as a biological face, based on image data related to the face area detected by the face area detection unit 4. A vital information extraction unit 8 that extracts vital information and a vital determination unit 9 that determines whether or not the face in the face area is alive based on the vital information are provided. Here, the vital information includes at least an index indicating the living state of the face imaged in the face area.

  The imaging unit 2 inputs an image signal obtained by converting the light of the formed image into an electric signal by forming an image of light from a subject obtained through the optical system on an image sensor (CCD, CMOS, etc.) (not shown). Output to part 3. The imaging unit 2 can perform known signal processing for noise suppression, contour enhancement, and the like. As a result, temporally continuous captured images (frame image data) are sequentially input to the image input unit 3.

  The face area detection unit 4 detects and tracks a face area by executing face detection processing based on a known pattern recognition method (for example, matching with a template prepared in advance) for each captured image, and the face area Face detection information (coordinates of detected face area, pixel values, etc.) is acquired. The face detection information acquired by the face area detection unit 4 is sent to the focus control unit 5, the display unit 6, the vital information extraction unit 8, and the like together with the captured image data. For the face detection processing by the face area detection unit 4, a known statistical learning method using face feature values may be used.

  Further, as will be described in detail later, the face detection device 1 can execute an operation mode (hereinafter referred to as a vital detection mode) that detects only the face of a living body by user selection. Then, when the face determined not to be alive by the vital determination unit 9 exists in the captured image, the face area detection unit 4 excludes those faces from the detection target.

  For example, as shown in FIG. 2, a person 11 and a poster (an object having a form similar to a person's face) 12 including a person 11 and a person's face photograph affixed to a wall behind the subject exist in the captured image P. In this case, the face area detection unit 4 detects only the face area 13 of the person 11 based on the living body, and excludes the face areas 14 and 15 based on the face photograph in the poster 12 that is not based on the living body from detection targets.

  Further, for example, as shown in FIG. 3, when a captured image P includes a person 21 and a plurality of (here, four) dolls 22 (mannequins) for costume display, The area detection unit 4 can detect only the face area 24 of the person 21 based on the living body, and can exclude the face areas 25-28 of the plurality of dolls 22 that are not based on the living body from detection targets.

  Here, the face areas 13-15 and 24-28 are indicated by rectangles, but the face area detected by the face area detecting unit 4 can be variously changed. It is possible to set a face area having an outline as an outer edge.

  The focus control unit 5 acquires the face detection information from the face region detection unit 4 and executes a known autofocus process for controlling the operation of the focus mechanism using the position of the face region in the captured image as a reference (focus point). Is possible. In particular, when the above-described vital detection mode is executed, the face detection information from the face area detection unit 4 includes only information based on the face of the living body. Even when there is an object having a similar shape to the face (face that is not based on the living body), the face of the person can be properly focused.

  The vital information extraction unit 8 performs vital information extraction processing that extracts the staying of the living body as vital information without making contact with the extraction target (person). More specifically, the vital information extraction unit 8 relates to each pixel constituting the face area detected by the face area detection unit 4 in the temporally continuous captured image, for example, the pixel value (0-255) of each component of RGB. (Gradation) is calculated, and time-series data of the representative value (here, the average value of each pixel) is generated as a pulse signal. In this case, time-series data can be generated based on the pixel value of only the green component (G) that has a particularly large fluctuation due to pulsation.

  Further, the generated time-series data of the pixel value (average value) is, for example, as shown in FIG. 4A, a slight fluctuation (for example, one gradation of the pixel value) based on a change in hemoglobin concentration in blood. With less variation). Therefore, the vital information extraction unit 8 performs a known filter process (for example, a process using a bandpass filter in which a predetermined pass band is set) on the time series data based on the pixel value as necessary. Thus, as shown in FIG. 4B, the pulse wave from which the noise component has been removed can be extracted as vital information. The vital information extraction unit 8 can also calculate the pulse rate from the time between two or more adjacent peaks (or zero points) in the pulse wave, and use them as vital information. The vital information extracted by the vital information extraction unit 8 is sent to the vital determination unit 9. Furthermore, the vital information extraction unit 8 can also use the spectrum acquired by frequency analysis (fast Fourier transform) of time-series data as shown in FIG. 4A as vital information.

  The vital determination unit 9 determines whether or not the face in the face region is alive based on the information of the pulse wave (see FIG. 4B) as vital information extracted by the vital information extraction unit 8. can do. Here, the vital determination unit 9 performs a matching process between the pulse wave extracted by the vital information extraction unit 8 and a reference waveform of the pulse wave prepared in advance to determine whether or not the pulse stay has been detected (that is, , Whether or not the detected face is alive). Alternatively, the vital determination unit 9 may determine whether or not the face is alive depending on whether or not an appropriate pulse rate is detected by the vital information extraction unit 8. As another method, the vital determination unit 9 may determine whether or not the face is alive based on the spectrum as vital information by the vital information extraction unit 8.

  The face detection apparatus 1 as described above can be realized as a video camera used for photographing a person or the like, for example. In that case, in the face detection device 1, captured images are sequentially input to the image input unit 3 after the device is started up and displayed on the display unit 6, and the user operates a shutter button (recording start button). The captured images are sequentially stored in the image storage unit 7.

  Although details are not shown, for example, the face detection device 1 is a CPU (Central Processing Unit) that performs overall processing related to imaging, control of peripheral devices, and the like based on a predetermined control program, and image data captured from an image sensor. Known hardware configuration including a RAM (Random Access Memory) that temporarily stores, a DSP (Digital Signal Processor) that executes predetermined image processing on image data, a driver for an image sensor, an LCD, a memory card, and the like At least a part of the functions of the respective units of the face detection apparatus 1 shown in FIG. 1 can be realized by the CPU executing a predetermined control program related to the present invention. Note that at least part of the functions of the face detection apparatus 1 may be replaced by processing using other known hardware.

  FIG. 5 is a flowchart showing the flow of processing by the face detection apparatus 1 according to the first embodiment. In the face detection device 1, imaging is started upon activation, and captured images (frame images) are sequentially input from the imaging unit 2 to the image input unit 3 (ST101). Therefore, when the user of the face detection device 1 has selected an operation mode for performing face detection (hereinafter referred to as face detection mode) (ST102: Yes), the face area detection unit 4 executes face detection processing. (ST103).

  Subsequently, in the face detection device 1, it is determined whether or not a face area is detected by the face detection process in step ST103 (ST104). If the face area is detected (Yes), the user further detects vitals. It is determined whether or not a mode is selected (ST105).

  When the vital detection mode is selected in step ST105 (Yes), the vital information extraction unit 8 extracts vital information (here, a pulse stay) from each of the face areas detected in step ST103 (ST106). Subsequently, the vital determination unit 9 determines the validity of the vital information extracted in step ST106 (ST107). In the present embodiment, the vital information determination unit 9 validates the vital information when it is determined that the face in the face area is alive based on the pulse wave information extracted from the face area (ST107: Yes). On the other hand, if it is determined that the face in the face area is not alive (that is, the face detected in step ST103 is derived from an object having a form similar to a human face), vital information Is invalid (ST107: No).

  When it is determined in step ST107 that the vital information is valid (Yes), the focus control unit 5 performs an autofocus process based on the position of the face area detected in step ST103 (ST108). Further, the face detection result based on step ST104 (for example, refer to the frame surrounding the face shown as face area 13 in FIG. 2) is displayed on display unit 6 together with the captured image (ST109). Thereby, the user can easily recognize the face area based on the living body, and as a result, the user can perform a desired operation (for example, the user touches the face area) on the face area based on the living body. It is possible to execute autofocus on the face area.

  On the other hand, if it is determined in step ST107 that the vital information is invalid (No) during execution of the vital detection mode, steps ST108 and ST109 are not executed. Thereby, it can avoid performing focus control on the basis of the face area which is not based on a living body.

  The operations in the above-described steps ST101 to ST109 are repeatedly executed until there is a processing stop request based on a user operation (for example, a power-off operation or a shooting completion operation) (ST110: Yes). If the user has not selected execution of the face detection mode (ST102: No), the processes of steps ST103 to ST109 are omitted. Further, when the user does not select the vital detection mode (ST105: No), steps ST106 and ST107 are not executed, and the position of the face area (including the face area not based on the living body) detected in step ST103. As a reference, the autofocus process is executed (ST108). Further, the captured image after the focus control in step ST108 is executed is stored in the image storage unit 7 when the user performs an operation of pressing the shutter button (recording start button) separately.

(Second Embodiment)
FIG. 6 is an overall configuration diagram of the face detection system 100 according to the second embodiment of the present invention, and FIG. 7 is a functional block diagram of the face detection system 100. In FIG. 6 and FIG. 7, the same code | symbol is attached | subjected about the component similar to the above-mentioned 1st Embodiment. In the second embodiment, matters not particularly mentioned below are the same as those in the above-described first embodiment.

  As shown in FIG. 6, the face detection system 100 includes a camera 31 that captures at least a face of a person H as a subject, and a face detection device 1 that detects a face from a captured image obtained by capturing with the camera 31. In the present embodiment, the face detection device 1 not only performs face detection, but also functions as a face authentication device that performs face authentication based on the result of the face detection, whereby the face detection system 100 can perform face authentication. It can function as a system. In the face detection system 100, the camera 31 and the face detection apparatus 1 are connected to be communicable with each other via a network 32 such as the Internet or a LAN (Local Area Network). However, the configuration is not limited to this, and the camera 31 and the face detection device 1 may be directly connected to each other via a known communication cable so as to communicate with each other.

  The camera 31 is a video camera having a known configuration. As shown in FIG. 7, the light from the subject obtained through the zoom lens is imaged on an image sensor (CCD, CMOS, etc.) (not shown), and the camera 31 is connected. An imaging unit 2 is provided that outputs a video signal obtained by converting light of the imaged image into an electrical signal to the face detection device 1. Although only one camera 31 is shown in FIG. 6, the face detection system 100 may be configured with a plurality of similar cameras.

  In addition to the image input unit 3, the face region detection unit 4, the display unit 6, the vital information extraction unit 8, and the vital determination unit 9, the face detection device 1 has the same functions as those in the first embodiment described above. A feature amount extraction unit 41 that extracts a feature amount of a face in the face area detected by the face region detection unit 4 and face information of a plurality of persons in which the extracted feature amounts are registered in advance (hereinafter, registered face information). Based on the face matching result by the face matching unit 42 and the registered information storage unit 43 for storing the registered face information used for the matching. And an authentication control unit 44 for executing predetermined post-authentication processing.

  The feature quantity extraction unit 41 obtains face detection information from the face area detected by the face area detection unit 4 by a known technique, thereby obtaining a face shape in the face area, a relative position of eyes, nose, mouth, and the like. A feature point based on the color of the face (skin) or the like is detected, and a feature amount representing the feature is extracted. Here, the face area detected by the face area detection unit 4 preferably includes a face image in front of the person H.

  The face matching unit 42 performs matching processing between the feature amount extracted by the feature amount extraction unit 41 and registered face information (registered feature amount) as face matching processing. As a result of the matching process, when it is determined that the extracted feature amount matches any of the registered face information, the face matching unit 42 sends a notification that the authentication has been accepted to the authentication control unit 44. To do. On the other hand, if it is determined that the extracted feature amount does not match any of the registered face information, the face collation unit 42 sends a notification that the authentication is rejected to the authentication control unit 44.

  In addition, when the vital detection mode is selected by the user of the face detection system 100, the face collation unit 42 determines by the vital determination unit 9 (determines whether the face in the face area is alive). ) Result. And the face collation part 42 can make only the face determined by the vital judgment part 9 to be based on a living body (that is, in a living state) as a target for matching (matching process). Alternatively, even if the extracted feature value matches any of the registered face information as a result of the matching process, the face matching unit 42 does not use the vital determination unit 9 based on the living body for the face from which the feature value is extracted. If it is determined that there is no match, the collation result can be invalid or mismatch.

  With this configuration, when the vital detection mode is selected, the face matching unit 42 has an object having a form similar to a human face (for example, a doll's face, a person's face photograph not based on a living body, It is possible to prevent false authentication of a mask made to resemble a human face.

  Upon receiving a notification from the face matching unit 42 that the authentication has been accepted, the authentication control unit 44 executes preset post-authentication processing. Such post-authentication processing is not particularly limited, but includes, for example, unlocking the door in the security area, outputting information by image or sound on the display unit 6, and permitting operation on the electronic device. On the other hand, when the authentication control unit 44 receives a notification that the authentication is rejected from the face matching unit 42, the authentication control unit 44 records information regarding the authentication rejection without executing the post-authentication process.

  The face detection apparatus 1 according to the second embodiment described above can be configured from an information processing apparatus such as a PC (Personal Computer), for example. Although details are not shown, the face detection device 1 is a CPU (Central Processing Unit) that performs various information processing and control of peripheral devices based on a predetermined control program, a RAM that functions as a work area of the CPU ( Random Access Memory), ROM (Read Only Memory) for storing control programs executed by the CPU and data, network interface for executing communication processing via the network, monitor (image output device), speaker, input device, HDD ( Hard disk drive), etc., and at least part of the functions of each part of the face detection apparatus 1 shown in FIG. 7 can be realized by the CPU executing a predetermined control program. is there. Note that at least part of the functions of the face detection apparatus 1 may be replaced by processing using other known hardware.

  FIG. 8 is a flowchart showing the flow of processing by the face detection apparatus 1 according to the second embodiment. In face detection system 100, imaging by camera 31 is started upon activation, and step ST201 similar to step ST101 in FIG. 5 is executed. Subsequently, in the face detection apparatus 1, steps ST202 to ST206 similar to steps ST103 to ST107 in FIG. 5 are executed.

  Next, when the user (administrator) of the face detection system 100 has selected an operation mode for performing face authentication (ST207: Yes), the face matching unit 42 performs face matching processing using facial feature values. Is executed (ST208). Subsequently, when receiving a notification from the face matching unit 42 that the authentication has been accepted (ST209: Yes), the authentication control unit 44 executes a prescribed post-authentication process (ST210).

  When it is determined in step ST206 that the vital information is invalid (the detected face is not based on a living body) (ST206: No), the authentication control unit 44 performs predetermined abnormality occurrence processing (for example, face Notification to the administrator of the detection system 100, recording of a captured image when an abnormality occurs, etc.) are performed (ST211).

  Steps ST201 to ST211 described above are repeatedly executed until all authentication processes are finally completed.

  As mentioned above, although this invention was demonstrated based on specific embodiment, these embodiment is an illustration to the last, Comprising: This invention is not limited by these embodiment. Note that the components of the face detection device, the face detection system, and the face detection method according to the present invention described in the above embodiments are not necessarily all required, and are appropriately selected as long as they do not depart from the scope of the present invention. Is possible.

  The face detection device, face detection system, and face detection method according to the present invention can prevent erroneous detection of an object other than a person as a biological face when detecting a face from an image including the person. The present invention is useful as a face detection device, a face detection system, a face detection method, and the like that detect a face from included images.

DESCRIPTION OF SYMBOLS 1 Face detection apparatus 2 Imaging part 3 Image input part 4 Face area detection part 5 Focus control part 6 Display part 7 Image memory | storage part 8 Vital information extraction part 9 Vital determination part 11, 21 Person 12 Poster 13-15 Face area 22 Doll 24 -28 Face region 31 Camera 32 Network 41 Feature extraction unit 42 Face collation unit 43 Registration information storage unit 44 Authentication control unit 100 Face detection system H Person P Captured image

Claims (11)

A face authentication device for performing face authentication,
An image input unit for inputting a captured image including a person;
A vital information extraction unit that extracts vital information in the face area of the person included in the captured image;
A vital determination unit that determines the effectiveness of the extracted vital information;
A face collation unit for collating the face of the person with face information registered in advance,
In response to user input, the vital determination unit selects whether or not to execute one or both of a process for determining the validity of the vital information and a process for the face matching unit to perform face matching. Face recognition device. The face authentication device according to claim 1,
A face authentication device in which both a process in which the vital determination unit determines the validity of the vital information and a process in which the face collation unit collates a face are executed by user input. The face authentication device according to claim 2,
A face authentication device that performs authentication of the person based on validity of the vital information determined by the vital determination unit and a result of face verification in the face verification unit. The face authentication device according to claim 2,
When the vital determination unit determines that the vital information is valid, the face verification unit verifies the face from which the vital information determined to be valid is extracted. The face authentication device according to claim 1,
The face authentication device in which the process of determining the validity of the vital information is not performed by the vital determination unit and the process of collating the face by the face matching unit is performed by user input. The face authentication device according to claim 5,
A face authentication device that performs authentication of the person based on a result of face matching in the face matching unit. The face authentication device according to claim 1,
The face authentication apparatus in which the vital determination unit performs a process of determining the validity of the vital information and the face collation unit does not perform a process of collating a face by user input. The face authentication device according to claim 3 or 6,
A face authentication apparatus, further comprising an authentication control unit that executes post-authentication processing set when the person is authenticated, and records information related to the rejection of the authentication when the authentication of the person is rejected. The face authentication device according to claim 1,
A face authentication device that executes a predetermined abnormality occurrence process when the vital determination unit determines that the vital information is invalid or when the face verification unit cannot match the face of the person. The face authentication device according to claim 1,
A face area detection unit for detecting the face area of the person from the captured image;
When the face area detection unit detects a plurality of face areas from the captured image, the vital information extraction unit extracts a plurality of vital information from the plurality of face areas, and the vital determination unit extracts the plurality of extracted A face authentication device that determines the validity of each of the vital information, and the face matching unit performs a face matching process only on the face area for which the vital information is determined to be valid. A face authentication method for performing face authentication,
A step of inputting a captured image including a person;
Extracting vital information in the face area of the person included in the captured image;
Determining the effectiveness of the extracted vital information;
Collating the person's face with pre-registered face information,
A face authentication method for selecting whether or not to execute one or both of the step of determining the validity of the vital information and the step of collating the face according to a user input.